CN113408528B - Quality recognition method and device for commodity image, computing equipment and storage medium - Google Patents
Quality recognition method and device for commodity image, computing equipment and storage medium Download PDFInfo
- Publication number
- CN113408528B CN113408528B CN202110706314.3A CN202110706314A CN113408528B CN 113408528 B CN113408528 B CN 113408528B CN 202110706314 A CN202110706314 A CN 202110706314A CN 113408528 B CN113408528 B CN 113408528B
- Authority
- CN
- China
- Prior art keywords
- commodity
- visual experience
- image
- quality score
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Electronic shopping [e-shopping] utilising user interfaces specially adapted for shopping
- G06Q30/0643—Electronic shopping [e-shopping] utilising user interfaces specially adapted for shopping graphically representing goods, e.g. 3D product representation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a quality identification method, a quality identification device, computing equipment and a storage medium for commodity images. The method comprises the following steps: acquiring commodity images; inputting the commodity image into an image background recognition model, and obtaining a background quality score of the commodity image based on an output result of the image background recognition model; inputting the commodity image into a commodity position identification model, and obtaining a commodity position quality score of the commodity image based on an output result of the commodity position identification model; inputting the commodity image into a user visual experience identification model, and obtaining a visual experience quality score of the commodity image based on an output result of the user visual experience identification model; and obtaining a total quality score according to the background quality score, the commodity position quality score and the visual experience quality score. According to the method, the total quality score of the commodity image is automatically obtained from three dimensions of the image background, the commodity position and the user visual experience, the commodity image quality score accuracy is improved, and the commodity image quality score efficiency is improved.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method and apparatus for quality identification of commodity images, a computing device, and a storage medium.
Background
In the field of electronic commerce, merchandise images can display merchandise information to a user in an intuitive and quick manner. The quality of the merchandise image directly or indirectly affects the user's desire to view or purchase the merchandise. And thus the identification of commodity image quality is particularly important.
However, the inventors found in practice that the following drawbacks exist in the prior art: in the prior art, a manual identification mode is adopted when the quality of the commodity image is identified. However, the quality recognition efficiency of the commodity image is low and the recognition accuracy is low in this way.
Disclosure of Invention
The present invention has been made in view of the above problems, and provides a quality recognition method, apparatus, computing device, and storage medium for commodity images that overcomes or at least partially solves the above problems.
According to an aspect of the present invention, there is provided a quality recognition method of a commodity image, comprising:
acquiring commodity images;
inputting the commodity image into a pre-trained image background recognition model, and obtaining a background quality score of the commodity image based on an output result of the image background recognition model;
Inputting the commodity image into a pre-trained commodity position identification model, and obtaining a commodity position quality score of the commodity image based on an output result of the commodity position identification model;
inputting the commodity image into a pre-trained user visual experience recognition model, and obtaining a visual experience quality score of the commodity image based on an output result of the user visual experience recognition model;
and obtaining the total quality score of the commodity image according to the background quality score, the commodity position quality score and the visual experience quality score.
According to another aspect of the present invention, there is provided a quality recognition apparatus of a commodity image, comprising:
the acquisition module is used for acquiring commodity images;
the first execution module is used for inputting the commodity image into a pre-trained image background recognition model and obtaining a background quality score of the commodity image based on an output result of the image background recognition model;
a second execution module for inputting the commodity image into a pre-trained commodity position identification model and obtaining commodity position quality scores of the commodity image based on the output result of the commodity position identification model
The third execution module is used for inputting the commodity image into a pre-trained user visual experience recognition model and obtaining a visual experience quality score of the commodity image based on an output result of the user visual experience recognition model;
and the comprehensive module is used for obtaining the total quality score of the commodity image according to the background quality score, the commodity position quality score and the visual experience quality score by a user.
According to yet another aspect of the present invention, there is provided a computing device comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the quality identification method of the commodity image.
According to still another aspect of the present invention, there is provided a computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the quality recognition method of commodity images as described above.
According to the quality identification method, the quality identification device, the computing equipment and the storage medium of the commodity image, the commodity image is acquired; inputting the commodity image into an image background recognition model, and obtaining a background quality score of the commodity image based on an output result of the image background recognition model; inputting the commodity image into a commodity position identification model, and obtaining a commodity position quality score of the commodity image based on an output result of the commodity position identification model; inputting the commodity image into a user visual experience identification model, and obtaining a visual experience quality score of the commodity image based on an output result of the user visual experience identification model; and obtaining a total quality score according to the background quality score, the commodity position quality score and the visual experience quality score. According to the method, the total quality score of the commodity image is automatically obtained from three dimensions of the image background, the commodity position and the user visual experience, the commodity image quality score accuracy is improved, and the commodity image quality score efficiency is improved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a flow chart of a method for quality identification of merchandise images according to one embodiment of the present invention;
FIG. 2 is a schematic diagram of an image background recognition model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a Bottleneck_3x3 module according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a Bottleneck_5x5 module according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a commodity location identification model according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a CBL cell according to one embodiment of the present invention;
FIG. 7 is a schematic diagram of a Focus unit according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of an SPP unit according to an embodiment of the present invention;
FIG. 9 is a schematic diagram showing the structure of a CSP1_X unit according to an embodiment of the invention;
FIG. 10 is a schematic diagram of a Resunit assembly according to one embodiment of the present invention;
FIG. 11 is a schematic diagram showing the structure of a CSP2_X unit according to an embodiment of the invention;
FIG. 12 is a schematic diagram of a user visual experience recognition model according to one embodiment of the present invention;
fig. 13 is a schematic diagram showing a structure of a quality recognition apparatus for a commodity image according to an embodiment of the present invention;
FIG. 14 illustrates a schematic diagram of a computing device provided by one embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 is a flowchart of a quality recognition method of a commodity image according to an embodiment of the present invention. As shown in fig. 1, the method includes:
step S110, acquiring commodity images.
The commodity image is specifically an image for carrying out quality recognition subsequently, and the commodity image contains related information of commodities. For example, the merchandise image may be a merchandise display view in a shopping website, or the like. The present embodiment is not limited to the type, format, size, and the like of the acquired commodity image.
Unlike the prior art, the present embodiment does not manually identify the quality of the commodity image after the commodity image is acquired, but automatically obtains the quality score of the commodity image from three dimensions of the background of the commodity image, the position of the commodity in the commodity image, and the user visual experience of the commodity image through the subsequent steps S120-S150 based on the machine learning algorithm.
Step S120, inputting the commodity image into a pre-trained image background recognition model, and obtaining the background quality score of the commodity image based on the output result of the image background recognition model.
The image background adopted by the commodity image can directly influence the learning degree of the commodity characteristics of the user, thereby influencing the purchasing desire of the user. For example, when the image background of the commodity image is too cluttered, the relevant characteristics of the commodity cannot be highlighted, thereby reducing the purchasing desire of the user for the commodity. The quality of the commodity image is identified from the image background dimension of the commodity image, so that the background quality score of the commodity image is obtained.
Specifically, the embodiment previously constructs an image background recognition model, which is constructed based on a neural network algorithm. The specific structure of the image background recognition model is not limited in this embodiment. Alternatively, the specific structure of the image background recognition model may be as shown in fig. 2.
As can be seen from fig. 2, the image background recognition model includes a plurality of different structured bottleck modules (the plurality of different structured bottleck modules are a bottleck_3x3 module and a bottleck_5x5 module), an Input layer (Input layer), a Conv layer (convolution layer), a Concat layer (splice layer), an AvgPooling layer (average pooling layer), a flat layer (flattening layer), and a class_prediction layer (result output layer).
As shown in fig. 3, the bottleneck_3x3 module includes: input layer (Input layer), dw_3x3 layer (depth separable convolutional layer), conv layer (convolutional layer), BN layer (Batch Normalization batch normalization layer), maxPooling layer (max pooling layer), avgPooling layer (average pooling layer) and Add layer (Add operation). In the bottleneck_3x3 module, the gradient in the back propagation process can not disappear in the training process by adopting the DW_3x3 layer and the Conv_1x1 layer at the edge, so that the loss can be ensured to be continuously reduced, the convergence rate of the model is improved on one hand, and the training precision of the model is improved on the other hand. In addition, the Bottleneck_3x3 module comprises 3 DW_3x3 layers, so that the image background recognition model can effectively learn the background characteristics of commodity images, and the recognition accuracy of the image background recognition model is improved.
As shown in fig. 4, the bottleneck_5x5 module includes: input layer, dw_3x3 layer, conv layer, BN layer, avgPooling layer, dw_1x5 layer, dw_5x1 layer, dw_5x5 layer, and Add layer. Wherein, the Bottleneck_5x5 module has additional DW_1x5 layer, DW_5x1 layer and DW_5x5 layer compared with the Bottleneck_3x3 module. The DW_1x5 layer and the DW_5x1 layer can increase the extracted features through channel separation, and the feature receptive fields extracted by the DW_1x5 layer, the DW_5x1 layer, the DW_5x5 layer and the DW_3x3 layer are different, so that the background characteristics of commodity images can be learned from multiple dimensions, and the fitting degree and accuracy of an algorithm on complex problems and nonlinear problems are further increased.
In addition, the DW layer (comprising a DW_1x5 layer, a DW_5x1 layer, a DW_5x5 layer and a DW_3x3 layer) can also reduce the parameter quantity and the calculation quantity of the image background recognition model, save the calculation resources and improve the calculation efficiency; and the receptive field of the model can be increased, and the recognition accuracy of the model is improved.
Further, a sample commodity image required by a training image background recognition model is obtained. The sample merchandise image may be a merchandise image that includes various image backgrounds. Among other things, various image contexts may include: white background, black background, living scene background, solid color background, etc. And generating a background type label of the sample commodity image aiming at any acquired sample commodity image, inputting the sample commodity image and the corresponding background type label into a constructed image background recognition model, and outputting a trained image background recognition model when a preset loss condition is met.
After obtaining the trained image background recognition model, the image background recognition model is used to perform background recognition on the commodity image obtained in step S110. Specifically, the image background recognition model outputs a background classification result of the commodity image.
In an alternative embodiment, the background quality score matched with the background classification result output by the image background recognition model may be found in advance according to the mapping relation between different background classifications and different background quality scores, where the matched background quality score is the background quality score of the commodity image obtained in step S110. By adopting the mode, the background quality score of the commodity image can be obtained rapidly according to the output result of the image background recognition model.
In yet another alternative embodiment, the commodity image may be applied to different scenes, and the background quality scores corresponding to the background classifications may be different. For example, in the application scene of the digital product, the purchasing rate of the user corresponding to the commodity image with the pure white background is high through analyzing a large amount of data; in the food product application scene, the purchasing rate of the user corresponding to the commodity image with the color background is high. Based on this, in the embodiment, after obtaining the background classification result output by the image background recognition model, the application scene of the commodity image obtained in step S110 is further obtained. And then searching the matched background quality scores according to the background classification result and the application scene. The background quality score matched with the background classification result and the application scene is the background quality score of the commodity image obtained in step S110. By adopting the mode, the background quality score of the commodity image can be accurately obtained according to the output result of the image background recognition model.
Step S130, inputting the commodity image into a pre-trained commodity position identification model, and obtaining a commodity position quality score of the commodity image based on the output result of the commodity position identification model.
The position of the commodity in the commodity image occupied by the image also influences the perception of the commodity characteristics by the user, and then influences the purchasing desire of the user. For example, when a commodity is located at the boundary of a commodity image, the purchasing desire of the user or the like may be reduced. Based on this, the present step identifies the quality of the commodity image from the commodity position dimension of the commodity image, thereby obtaining the commodity position quality score of the commodity image.
Specifically, the present embodiment has previously built a commodity location identification model that is built based on a neural network algorithm. The specific structure of the commodity position identification model is not limited in this embodiment. Alternatively, the specific structure of the commodity location identification model is shown in fig. 5.
As can be seen from fig. 5, the commodity location identification model includes: CBL unit, focus unit, SPP unit, csp1_x unit, and csp2_x unit.
As shown in fig. 6, the CBL unit is a conv+bn+leak_relu structure, where Conv is a convolutional layer, BN is a normalized layer, and leak_relu is a leak_relu activation function. The structure can enhance the feature extraction effect of the model, thereby being beneficial to improving the prediction precision of the model.
As shown in fig. 7, the Focus unit may perform a slicing (Slice) operation on the input, thereby achieving channel separation. For example, after slicing an input image of original n×n×3, a feature map of n/2*n/2×12 is generated, so that feature extraction is increased, and prediction accuracy of a model is further improved. The Focus unit further performs tensor stitching through concat after slicing the input image, thereby expanding tensor dimension, and finally outputting data via CBL in the Focus unit.
As shown in fig. 8, the SPP unit includes a plurality of Maxpool layers, for example, the SPP unit may use a maximum pooling method of 1×1,3×3,5×5,7×7,9×9, 11×11, 13×13, and perform multi-scale fusion after feature extraction, so as to enhance robustness and accuracy of the network, reduce the number of parameters in the model, and improve the prediction speed of the model.
As shown in fig. 9, the csp1_x unit can downsample the feature map to increase the receptive field and enhance feature extraction for small target samples. The CSP1_X unit comprises X reset components, a concrete structure diagram of the reset components is shown in fig. 10, wherein ADD is tensor addition operation. The residual structure is used by the Resunit component, so that the model network hierarchy is deepened, the feature extraction effect is enhanced, and the overfitting can be restrained in the model training process. Further, the multi-scale and multi-dimensional feature fusion is carried out through Concat in the CSP1_X unit, so that the diversity of the features is enriched, and the prediction precision of the model is further improved.
As shown in fig. 11, the csp2_x unit can downsample the feature map to increase the receptive field. Moreover, the CSP2_X unit is different from the CSP1_X unit in that the CSP2_X unit replaces X Resunit components of the CSP1_X unit with 2X CBL units, the feature extraction effect is enhanced through the CBL units, and the multi-scale and multi-dimensional feature fusion is carried out through the Concat, so that the diversity of features is enriched, and the prediction precision of a model is further improved.
Further, as can be seen from fig. 5, the commodity location identification model includes three Output layers (Output 1, output2, and Output 3). The Output1 is configured to Output a commodity location category, where the commodity location category is specifically a subject category or a non-subject category. The subject category is a subject location where the merchandise occupies the merchandise image, while the non-subject category is a non-subject location where the merchandise occupies the merchandise image. Output2 is used for outputting commodity coordinate information, and the commodity coordinate information is specific coordinate information of a commodity in a commodity image. Output3 is used to Output coordinate probability information, which is specifically the prediction probability of the corresponding coordinate.
Further, a sample commodity image required for training the commodity position identification model is acquired. The sample merchandise image may be a merchandise image including various merchandise locations. And generating a commodity position label of the sample commodity image aiming at any acquired sample commodity image, inputting the sample commodity image and the corresponding commodity position label into a constructed commodity position identification model, and outputting a trained commodity position identification model when a preset loss condition is met.
After obtaining the trained commodity position identification model, the commodity position identification model is used to perform commodity position on the commodity image obtained in step S110. Specifically, the commodity position category, commodity coordinate information and coordinate probability information output by the commodity position identification model are obtained, and the commodity position quality score of the commodity image obtained in step S110 is obtained according to the commodity position category, the commodity coordinate information and/or the coordinate probability information. For example, the commodity location quality score of the commodity image may be derived from the commodity location category, the commodity coordinate information, and/or the mapping of the coordinate probability information to the quality score.
Step S140, inputting the commodity image into a pre-trained user visual experience recognition model, and obtaining a visual experience quality score of the commodity image based on an output result of the user visual experience recognition model.
The visual experience (e.g., aesthetic experience, etc.) of the merchandise image by the user may also affect the perception of the merchandise characteristics by the user, which in turn affects the purchasing desire of the user. For example, when the commodity composition is poor, the purchasing desire of the user or the like may be reduced. Based on this, the present step identifies the quality of the merchandise image from the user visual experience dimension, thereby obtaining a visual experience quality score for the merchandise image.
Specifically, the embodiment is pre-constructed with a user visual experience recognition model, which is constructed based on a neural network algorithm. The specific structure of the user visual experience recognition model is not limited in this embodiment. Alternatively, the specific structure of the user visual experience recognition model is shown in fig. 12.
As can be seen from fig. 12, the user visual experience recognition model includes: input layer, conv layer, flame layer, and two Output layers (Output 1 and Output 2). Output1 in the user visual experience identification model is used for outputting visual experience sub-scores, wherein the visual experience sub-scores are specifically user aesthetic experience scores; output2 in the user visual experience recognition model is used to Output a noise sub-score, specifically a noise score of the image.
In the process of training the user visual experience recognition model, in order to improve the recognition accuracy of the user visual experience recognition model, the embodiment further builds a twin model of the user visual experience recognition model besides the user visual experience recognition model. The twin model has the same structure as the user visual experience recognition model, but the training samples and model parameters of the twin model and the user visual experience recognition model are different in the training process.
And further acquiring sample data required for training the user visual experience recognition model and the twin model. Specifically, for any sample commodity image, inputting the sample commodity image and a visual experience quality scoring tag of the sample commodity image to a twin model, and inputting a noisy sample image after the sample commodity image is noisy and a visual experience quality scoring tag of the noisy sample image to a user visual experience identification model. In this embodiment, the specific noise adding method is not limited, and for example, random gaussian and/or random filtering noise processing may be performed on the sample commodity image. Also, in this embodiment, the visual quality of experience scoring tags include a user aesthetic experience scoring tag (where the user aesthetic experience scoring tag may be obtained by aesthetic indicators of composition, color, contrast, texture, etc.) and a noise sub-scoring tag.
And calculating a loss function according to the difference between the output result of the twin model and the output result of the user visual experience recognition model, and outputting the trained user visual experience recognition model when the preset loss condition is met. Specifically, the output results also include a visual experience sub-score and a noise sub-score. If the visual experience quality score output by the twin model is greater than or equal to the visual experience quality score output by the user visual experience identification model, not calculating a loss function; and if the visual experience quality score output by the twin model is smaller than the visual experience quality score output by the visual experience identification model, calculating a loss function. Judging whether the loss function meets a preset loss condition, and if so, outputting a current user visual experience identification model; and if the preset loss condition is not met, adjusting the model parameters of the user visual experience recognition model, and then performing the next training. And outputting the trained user visual experience recognition model until the preset loss condition is met. Optionally, in calculating the loss function, specifically, a first regression loss of the twin model is calculated according to a visual experience quality score output by the twin model, a second regression loss of the user visual experience identification model is calculated according to a visual experience quality score output by the user visual experience identification model, and finally the loss function is calculated according to the first regression loss and the second regression loss. For example, the difference between the first regression loss and the second regression loss may be taken as the loss function.
After the pre-trained user visual experience recognition model is obtained, inputting the commodity image into the pre-trained user visual experience recognition model, obtaining the visual experience sub-score and the noise sub-score of the output of the user visual experience recognition model, and obtaining the visual experience quality score of the commodity image according to the visual experience sub-score and the noise sub-score. For example, the visual experience quality score of the merchandise image may be based on the weighted sum of the visual experience sub-score and the noise sub-score.
Optionally, in order to ensure accuracy of quality scores of final commodity images, sample data adopted in training the image background recognition model, the commodity position recognition model and the user visual experience recognition model in the embodiment are the same.
In addition, the execution order of step S120, step S130, and step S140 is not limited in this embodiment. The steps S120, S130 and S140 may be sequentially performed in a corresponding order, or may be concurrently performed.
And step S150, obtaining the total quality score of the commodity image according to the background quality score, the commodity position quality score and the visual experience quality score.
Specifically, corresponding weight coefficients are respectively allocated to the background quality score, the commodity position quality score and the visual experience quality score, so that the total quality score of the commodity image is obtained according to the weighted summation result of the background quality score, the commodity position quality score and the visual experience quality score.
Therefore, the embodiment automatically obtains the total quality score of the commodity image from the background of the commodity image, the position of the commodity in the commodity image and the three dimensions of the user visual experience of the commodity image based on the machine learning algorithm, and improves the quality score accuracy of the commodity image and the quality score efficiency of the commodity image.
Fig. 13 is a schematic diagram showing a structure of a quality recognition apparatus for commodity images according to an embodiment of the present invention.
As shown in fig. 13, the quality recognition apparatus 1300 of a commodity image includes: the acquisition module 1310, the first execution module 1320, the second execution module 1330, the third execution module 1340, and the integration module 1350.
An acquisition module 1310 for acquiring an image of a commodity;
a first execution module 1320, configured to input the commodity image to a pre-trained image background recognition model, and obtain a background quality score of the commodity image based on an output result of the image background recognition model;
a second execution module 1330 for inputting the commodity image into a pre-trained commodity position identification model and obtaining a commodity position quality score of the commodity image based on the output result of the commodity position identification model
A third execution module 1340, configured to input the commodity image to a pre-trained user visual experience recognition model, and obtain a visual experience quality score of the commodity image based on an output result of the user visual experience recognition model;
and a synthesis module 1350, wherein the user obtains a total quality score of the commodity image according to the background quality score, the commodity location quality score, and the visual experience quality score.
In an alternative embodiment, the third execution module 1340 is further configured to: before inputting the commodity image into a pre-trained user visual experience recognition model, constructing a user visual experience recognition model and a twin model of the user visual experience recognition model;
for any sample commodity image, inputting the sample commodity image and a visual experience quality scoring label of the sample commodity image into the twin model, and inputting a noisy sample image after the sample commodity image is noisy and a visual experience quality scoring label of the noisy sample image into the user visual experience identification model;
calculating a loss function according to the difference between the output result of the twin model and the output result of the user visual experience identification model;
And when the preset loss condition is met, outputting the trained user visual experience recognition model.
In an alternative embodiment, the third execution module 1340 is further configured to: if the visual experience quality score output by the twin model is greater than or equal to the visual experience quality score output by the user visual experience identification model, not calculating the loss function;
and if the visual experience quality score output by the twin model is smaller than the visual experience quality score output by the user visual experience identification model, calculating the loss function.
In an alternative embodiment, the third execution module 1340 is further configured to: calculating a first regression loss of the twin model according to the visual experience quality score output by the twin model, and calculating a second regression loss of the user visual experience identification model according to the visual experience quality score output by the user visual experience identification model;
and calculating the loss function according to the first regression loss and the second regression loss.
In an alternative embodiment, the third execution module 1340 is further configured to: acquiring a visual experience sub-score and a noise sub-score of the output of the user visual experience identification model;
And obtaining the visual experience quality score of the commodity image according to the visual experience sub-score and the noise sub-score.
In an alternative embodiment, the image background recognition model includes: a plurality of different structured Bottleneck modules.
In an alternative embodiment, the second execution module 1330 is further configured to: acquiring commodity position category, commodity coordinate information and coordinate probability information output by the commodity position identification model;
and obtaining the commodity position quality score of the commodity image according to the commodity position category, the commodity coordinate information and/or the coordinate probability information.
The specific implementation process of each module in the apparatus may refer to the description of the corresponding part in the method embodiment shown in fig. 1, and this embodiment is not repeated herein.
Therefore, the embodiment automatically obtains the total quality score of the commodity image from the background of the commodity image, the position of the commodity in the commodity image and the three dimensions of the user visual experience of the commodity image based on the machine learning algorithm, and improves the quality score accuracy of the commodity image and the quality score efficiency of the commodity image.
An embodiment of the present invention provides a non-volatile computer storage medium storing at least one executable instruction that is capable of performing the quality recognition method of a commodity image in any of the above-described method embodiments.
The executable instructions may be particularly useful for causing a processor to:
acquiring commodity images;
inputting the commodity image into a pre-trained image background recognition model, and obtaining a background quality score of the commodity image based on an output result of the image background recognition model;
inputting the commodity image into a pre-trained commodity position identification model, and obtaining a commodity position quality score of the commodity image based on an output result of the commodity position identification model;
inputting the commodity image into a pre-trained user visual experience recognition model, and obtaining a visual experience quality score of the commodity image based on an output result of the user visual experience recognition model;
and obtaining the total quality score of the commodity image according to the background quality score, the commodity position quality score and the visual experience quality score.
In an alternative embodiment, the executable instructions may be specifically configured to cause a processor to:
prior to said inputting said merchandise image into a pre-trained user visual experience recognition model,
constructing a user visual experience recognition model and a twin model of the user visual experience recognition model;
for any sample commodity image, inputting the sample commodity image and a visual experience quality scoring label of the sample commodity image into the twin model, and inputting a noisy sample image after the sample commodity image is noisy and a visual experience quality scoring label of the noisy sample image into the user visual experience identification model;
calculating a loss function according to the difference between the output result of the twin model and the output result of the user visual experience identification model;
and when the preset loss condition is met, outputting the trained user visual experience recognition model.
In an alternative embodiment, the executable instructions may be specifically configured to cause a processor to:
if the visual experience quality score output by the twin model is greater than or equal to the visual experience quality score output by the user visual experience identification model, not calculating the loss function;
And if the visual experience quality score output by the twin model is smaller than the visual experience quality score output by the user visual experience identification model, calculating the loss function.
In an alternative embodiment, the executable instructions may be specifically configured to cause a processor to:
calculating a first regression loss of the twin model according to the visual experience quality score output by the twin model, and calculating a second regression loss of the user visual experience identification model according to the visual experience quality score output by the user visual experience identification model;
and calculating the loss function according to the first regression loss and the second regression loss.
In an alternative embodiment, the executable instructions may be specifically configured to cause a processor to:
acquiring a visual experience sub-score and a noise sub-score of the output of the user visual experience identification model;
and obtaining the visual experience quality score of the commodity image according to the visual experience sub-score and the noise sub-score.
In an alternative embodiment, the image background recognition model includes: a plurality of different structured Bottleneck modules.
In an alternative embodiment, the executable instructions may be specifically configured to cause a processor to:
acquiring commodity position category, commodity coordinate information and coordinate probability information output by the commodity position identification model;
and obtaining the commodity position quality score of the commodity image according to the commodity position category, the commodity coordinate information and/or the coordinate probability information.
Therefore, the embodiment automatically obtains the total quality score of the commodity image from the background of the commodity image, the position of the commodity in the commodity image and the three dimensions of the user visual experience of the commodity image based on the machine learning algorithm, and improves the quality score accuracy of the commodity image and the quality score efficiency of the commodity image.
FIG. 14 illustrates a schematic diagram of a computing device provided by one embodiment of the invention. The specific embodiments of the present invention are not limited to a particular implementation of a computing device.
As shown in fig. 14, the computing device may include: a processor 1402, a communication interface (Communications Interface) 1404, a memory 1406, and a communication bus 1408.
Wherein: processor 1402, communication interface 1404, and memory 1406 communicate with each other via a communication bus 1408. A communication interface 1404 for communicating with network elements of other devices, such as clients or other servers. The processor 1402 is configured to execute the program 1410, and may specifically perform relevant steps in the method embodiments described above.
In particular, program 1410 may include program code including computer operating instructions.
The processor 1402 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 1406 for storing a program 1410. Memory 1406 may comprise high-speed RAM memory or may also comprise non-volatile memory, such as at least one disk memory.
The program 1410 may be specifically configured to cause the processor 1402 to:
the executable instructions may be particularly useful for causing a processor to:
acquiring commodity images;
inputting the commodity image into a pre-trained image background recognition model, and obtaining a background quality score of the commodity image based on an output result of the image background recognition model;
inputting the commodity image into a pre-trained commodity position identification model, and obtaining a commodity position quality score of the commodity image based on an output result of the commodity position identification model;
Inputting the commodity image into a pre-trained user visual experience recognition model, and obtaining a visual experience quality score of the commodity image based on an output result of the user visual experience recognition model;
and obtaining the total quality score of the commodity image according to the background quality score, the commodity position quality score and the visual experience quality score.
In an alternative embodiment, program 1410 may be specifically configured to cause processor 1402 to:
before inputting the commodity image into a pre-trained user visual experience recognition model, constructing a user visual experience recognition model and a twin model of the user visual experience recognition model;
for any sample commodity image, inputting the sample commodity image and a visual experience quality scoring label of the sample commodity image into the twin model, and inputting a noisy sample image after the sample commodity image is noisy and a visual experience quality scoring label of the noisy sample image into the user visual experience identification model;
calculating a loss function according to the difference between the output result of the twin model and the output result of the user visual experience identification model;
And when the preset loss condition is met, outputting the trained user visual experience recognition model.
In an alternative embodiment, program 1410 may be specifically configured to cause processor 1402 to:
if the visual experience quality score output by the twin model is greater than or equal to the visual experience quality score output by the user visual experience identification model, not calculating the loss function;
and if the visual experience quality score output by the twin model is smaller than the visual experience quality score output by the user visual experience identification model, calculating the loss function.
In an alternative embodiment, program 1410 may be specifically configured to cause processor 1402 to:
calculating a first regression loss of the twin model according to the visual experience quality score output by the twin model, and calculating a second regression loss of the user visual experience identification model according to the visual experience quality score output by the user visual experience identification model;
and calculating the loss function according to the first regression loss and the second regression loss.
In an alternative embodiment, program 1410 may be specifically configured to cause processor 1402 to:
Acquiring a visual experience sub-score and a noise sub-score of the output of the user visual experience identification model;
and obtaining the visual experience quality score of the commodity image according to the visual experience sub-score and the noise sub-score.
In an alternative embodiment, the image background recognition model includes: a plurality of different structured Bottleneck modules.
In an alternative embodiment, program 1410 may be specifically configured to cause processor 1402 to:
acquiring commodity position category, commodity coordinate information and coordinate probability information output by the commodity position identification model;
and obtaining the commodity position quality score of the commodity image according to the commodity position category, the commodity coordinate information and/or the coordinate probability information.
Therefore, the embodiment automatically obtains the total quality score of the commodity image from the background of the commodity image, the position of the commodity in the commodity image and the three dimensions of the user visual experience of the commodity image based on the machine learning algorithm, and improves the quality score accuracy of the commodity image and the quality score efficiency of the commodity image.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components according to embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.
Claims (8)
1. A quality recognition method of a commodity image, comprising:
constructing a user visual experience recognition model and a twin model of the user visual experience recognition model; for any sample commodity image, inputting the sample commodity image and a visual experience quality scoring label of the sample commodity image into the twin model, and inputting a noisy sample image after the sample commodity image is noisy and a visual experience quality scoring label of the noisy sample image into the user visual experience identification model; calculating a loss function according to the difference between the output result of the twin model and the output result of the user visual experience identification model; when the preset loss condition is met, outputting a trained user visual experience recognition model; if the visual experience quality score output by the twin model is greater than or equal to the visual experience quality score output by the user visual experience identification model, not calculating the loss function; if the visual experience quality score output by the twin model is smaller than the visual experience quality score output by the user visual experience identification model, calculating the loss function;
Acquiring commodity images;
inputting the commodity image into a pre-trained image background recognition model, and obtaining a background quality score of the commodity image based on an output result of the image background recognition model;
inputting the commodity image into a pre-trained commodity position identification model, and obtaining a commodity position quality score of the commodity image based on an output result of the commodity position identification model;
inputting the commodity image into a pre-trained user visual experience recognition model, and obtaining a visual experience quality score of the commodity image based on an output result of the user visual experience recognition model;
and obtaining the total quality score of the commodity image according to the background quality score, the commodity position quality score and the visual experience quality score.
2. The method of claim 1, wherein the calculating the loss function further comprises:
calculating a first regression loss of the twin model according to the visual experience quality score output by the twin model, and calculating a second regression loss of the user visual experience identification model according to the visual experience quality score output by the user visual experience identification model;
And calculating the loss function according to the first regression loss and the second regression loss.
3. The method of claim 1, wherein the obtaining a visual quality of experience score for the merchandise image based on the output of the user visual quality recognition model further comprises:
acquiring a visual experience sub-score and a noise sub-score of the output of the user visual experience identification model;
and obtaining the visual experience quality score of the commodity image according to the visual experience sub-score and the noise sub-score.
4. A method according to any of claims 1-3, wherein the image background recognition model comprises: a plurality of different structured Bottleneck modules.
5. A method according to any one of claims 1-3, wherein the obtaining a commodity location quality score for the commodity image based on the output of the commodity location identification model further comprises:
acquiring commodity position category, commodity coordinate information and coordinate probability information output by the commodity position identification model;
and obtaining the commodity position quality score of the commodity image according to the commodity position category, the commodity coordinate information and/or the coordinate probability information.
6. A quality recognition apparatus for a commodity image, comprising:
the acquisition module is used for acquiring commodity images;
the first execution module is used for inputting the commodity image into a pre-trained image background recognition model and obtaining a background quality score of the commodity image based on an output result of the image background recognition model;
the second execution module is used for inputting the commodity image into a pre-trained commodity position identification model and obtaining a commodity position quality score of the commodity image based on an output result of the commodity position identification model;
the third execution module is used for inputting the commodity image into a pre-trained user visual experience recognition model and obtaining a visual experience quality score of the commodity image based on an output result of the user visual experience recognition model;
the comprehensive module is used for enabling a user to obtain the total quality score of the commodity image according to the background quality score, the commodity position quality score and the visual experience quality score;
constructing a user visual experience recognition model and a twin model of the user visual experience recognition model; for any sample commodity image, inputting the sample commodity image and a visual experience quality scoring label of the sample commodity image into the twin model, and inputting a noisy sample image after the sample commodity image is noisy and a visual experience quality scoring label of the noisy sample image into the user visual experience identification model; calculating a loss function according to the difference between the output result of the twin model and the output result of the user visual experience identification model; when the preset loss condition is met, outputting a trained user visual experience recognition model; if the visual experience quality score output by the twin model is greater than or equal to the visual experience quality score output by the user visual experience identification model, not calculating the loss function; and if the visual experience quality score output by the twin model is smaller than the visual experience quality score output by the user visual experience identification model, calculating the loss function.
7. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to perform the operations corresponding to the quality recognition method for a commodity image according to any one of claims 1 to 5.
8. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the quality recognition method of a commodity image according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110706314.3A CN113408528B (en) | 2021-06-24 | 2021-06-24 | Quality recognition method and device for commodity image, computing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110706314.3A CN113408528B (en) | 2021-06-24 | 2021-06-24 | Quality recognition method and device for commodity image, computing equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113408528A CN113408528A (en) | 2021-09-17 |
| CN113408528B true CN113408528B (en) | 2024-02-23 |
Family
ID=77683047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110706314.3A Active CN113408528B (en) | 2021-06-24 | 2021-06-24 | Quality recognition method and device for commodity image, computing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408528B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115908774B (en) * | 2023-01-10 | 2023-05-09 | 佰聆数据股份有限公司 | Quality detection method and device for deformed materials based on machine vision |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101072370A (en) * | 2006-05-09 | 2007-11-14 | 罗燕海 | Control device for preventing unlicensed signal from getting to broadcasting television play device |
| CN101448174A (en) * | 2008-12-26 | 2009-06-03 | 深圳华为通信技术有限公司 | Image quality evaluation device and method thereof |
| CN102799669A (en) * | 2012-07-17 | 2012-11-28 | 杭州淘淘搜科技有限公司 | Automatic grading method for commodity image vision quality |
| JP2017138808A (en) * | 2016-02-03 | 2017-08-10 | キヤノン株式会社 | Information processing device and information processing method |
| CN108898591A (en) * | 2018-06-22 | 2018-11-27 | 北京小米移动软件有限公司 | Methods of marking and device, electronic equipment, the readable storage medium storing program for executing of picture quality |
| CN110189196A (en) * | 2019-05-16 | 2019-08-30 | 深圳远航股份有限公司 | A method of entrance figure sales field is built based on picture quality point |
| CN110659591A (en) * | 2019-09-07 | 2020-01-07 | 中国海洋大学 | SAR image change detection method based on twin network |
| GB201919015D0 (en) * | 2019-12-20 | 2020-02-05 | Reid Steven | Blood glucose monitor |
| CN111797258A (en) * | 2020-07-10 | 2020-10-20 | 携程计算机技术（上海）有限公司 | Image pushing method, system, equipment and storage medium based on aesthetic evaluation |
| CN112668342A (en) * | 2021-01-08 | 2021-04-16 | 中国科学院自动化研究所 | Remote supervision relation extraction noise reduction system based on twin network |
| CN112801179A (en) * | 2021-01-27 | 2021-05-14 | 北京理工大学 | Twin classifier certainty maximization method for cross-domain complex visual task |
| CN112818774A (en) * | 2021-01-20 | 2021-05-18 | 中国银联股份有限公司 | Living body detection method and device |
| CN112967210A (en) * | 2021-04-29 | 2021-06-15 | 福州大学 | Unmanned aerial vehicle image denoising method based on full convolution twin network |
-
2021
- 2021-06-24 CN CN202110706314.3A patent/CN113408528B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101072370A (en) * | 2006-05-09 | 2007-11-14 | 罗燕海 | Control device for preventing unlicensed signal from getting to broadcasting television play device |
| CN101448174A (en) * | 2008-12-26 | 2009-06-03 | 深圳华为通信技术有限公司 | Image quality evaluation device and method thereof |
| CN102799669A (en) * | 2012-07-17 | 2012-11-28 | 杭州淘淘搜科技有限公司 | Automatic grading method for commodity image vision quality |
| JP2017138808A (en) * | 2016-02-03 | 2017-08-10 | キヤノン株式会社 | Information processing device and information processing method |
| CN108898591A (en) * | 2018-06-22 | 2018-11-27 | 北京小米移动软件有限公司 | Methods of marking and device, electronic equipment, the readable storage medium storing program for executing of picture quality |
| CN110189196A (en) * | 2019-05-16 | 2019-08-30 | 深圳远航股份有限公司 | A method of entrance figure sales field is built based on picture quality point |
| CN110659591A (en) * | 2019-09-07 | 2020-01-07 | 中国海洋大学 | SAR image change detection method based on twin network |
| GB201919015D0 (en) * | 2019-12-20 | 2020-02-05 | Reid Steven | Blood glucose monitor |
| CN111797258A (en) * | 2020-07-10 | 2020-10-20 | 携程计算机技术（上海）有限公司 | Image pushing method, system, equipment and storage medium based on aesthetic evaluation |
| CN112668342A (en) * | 2021-01-08 | 2021-04-16 | 中国科学院自动化研究所 | Remote supervision relation extraction noise reduction system based on twin network |
| CN112818774A (en) * | 2021-01-20 | 2021-05-18 | 中国银联股份有限公司 | Living body detection method and device |
| CN112801179A (en) * | 2021-01-27 | 2021-05-14 | 北京理工大学 | Twin classifier certainty maximization method for cross-domain complex visual task |
| CN112967210A (en) * | 2021-04-29 | 2021-06-15 | 福州大学 | Unmanned aerial vehicle image denoising method based on full convolution twin network |
Non-Patent Citations (1)
| Title |
|---|
| 基于栈式降噪自编码神经网络的车牌字符识别;贾文其;李明;朱美强;王军;;计算机工程与设计(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113408528A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6843086B2 (en) | Image processing systems, methods for performing multi-label semantic edge detection in images, and non-temporary computer-readable storage media | |
| TWI746674B (en) | Type prediction method, device and electronic equipment for identifying objects in images | |
| US9349076B1 (en) | Template-based target object detection in an image | |
| CN106934397B (en) | Image processing method and device and electronic equipment | |
| JP2023073231A (en) | Method and device for image processing | |
| CN112927209B (en) | A CNN-based saliency detection system and method | |
| CN111680698A (en) | Image recognition method and device and training method and device of image recognition model | |
| CN111967464B (en) | Weak supervision target positioning method based on deep learning | |
| CN111860309A (en) | Face recognition method and system | |
| CN109086779B (en) | Attention target identification method based on convolutional neural network | |
| CN109859113B (en) | Model generation method, image enhancement method, device and computer-readable storage medium | |
| CN111401339B (en) | Method and device for identifying age of person in face image and electronic equipment | |
| CN110321943B (en) | CT image classification method, system and device based on semi-supervised deep learning | |
| CN111680755A (en) | Medical image recognition model construction method, medical image recognition device, medical image recognition medium and medical image recognition terminal | |
| CN114359819A (en) | Image processing method, apparatus, device, storage medium and computer program product | |
| CN111160114A (en) | Gesture recognition method, device, equipment and computer readable storage medium | |
| CN113077464A (en) | Medical image processing method, medical image identification method and device | |
| CN111027670B (en) | Feature map processing method and device, electronic equipment and storage medium | |
| CN112700462B (en) | Image segmentation method, device, electronic device and storage medium | |
| CN113408528B (en) | Quality recognition method and device for commodity image, computing equipment and storage medium | |
| CN120318754A (en) | A mask target detection method and system based on improved YOLOWorld world model | |
| CN111160368A (en) | Method, device and equipment for detecting target in image and storage medium | |
| CN111401415A (en) | Training method, device, equipment and storage medium of computer vision task model | |
| CN114841974A (en) | Nondestructive testing method and system for internal structure of fruit, electronic equipment and medium | |
| CN113343987B (en) | Text detection processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |