CN113763311B - Image recognition method and device and automatic sorting robot - Google Patents

Abstract

The present disclosure provides an image recognition method. The method includes: acquiring a first image; obtaining the clarity of the first image; and when the clarity of the first image is greater than a blur threshold, determining that the first image is a clear image; wherein the blur threshold is determined based on the distribution of the clarity of M second images; wherein the M second images and the first image are images taken for the same scene. The present disclosure also provides an image recognition device, an automatic sorting robot, an electronic device, and a computer-readable storage medium.

Description

Image recognition method and device, and automatic sorting robot

Technical Field

The present disclosure relates to the field of image processing technology, and more specifically, to an image recognition method and device, an automatic sorting robot, an electronic device, and a computer-readable storage medium.

Background technique

When the automatic sorting robot is sorting goods, it needs to collect images through the camera of the automatic sorting robot to realize the visual recognition of the picked objects. In order to achieve accurate picking of objects, the coordinate system of the automatic sorting robot's mechanical arm and the coordinate system of the machine vision must be very accurate. However, in practice, the collected images are usually blurred due to interference from the picking robot and mechanical vibration.

Currently, the cleaning work of images obtained by object detection cameras is mostly done by direct manual screening, where the human eye identifies each photo one by one to see if it meets the standards. However, manual screening of photos consumes a lot of manpower, has high labor costs, and the work cannot be reused. Focusing on the high-brightness screen for a long time to screen images also causes damage to the health of personnel.

In academia, there is a method to determine whether an image is blurred by detecting the distribution of high-frequency and low-frequency components of an image after fast Fourier transformation. However, for a robot picking scene with a single scene and a high degree of image similarity, the image cannot effectively distinguish the difference between the distribution of high-frequency and low-frequency components after fast Fourier transformation, so it is not applicable.

Summary of the invention

In view of this, the embodiments of the present disclosure provide an image recognition method and device, an electronic device, a computer-readable storage medium, and an automatic sorting robot for automatically identifying images taken in the same scene with a high degree of similarity.

One aspect of an embodiment of the present disclosure provides an image recognition method. The method includes: acquiring a first image; obtaining the clarity of the first image; and when the clarity of the first image is greater than a blur threshold, determining that the first image is a clear image; wherein the blur threshold is determined based on the distribution of the clarity of M second images; wherein M is an integer greater than 1, and the M second images and the first image are images taken for the same scene.

According to an embodiment of the present disclosure, the method further includes: acquiring M second images; obtaining the clarity of each second image; and determining the blur threshold based on the distribution of the clarity of the M second images.

According to an embodiment of the present disclosure, determining the blur threshold based on the distribution of the clarity of the M second images includes: dividing the distribution of the clarity of the M second images into two different normally distributed clarity values as the blur threshold.

According to an embodiment of the present disclosure, determining the blur threshold based on the distribution of clarity of the M second images includes: generating a distribution histogram of the clarity of the M second images; performing gradient detection on the distribution histogram to determine the position of the trough; and using the clarity value corresponding to the position of the trough as the blur threshold.

According to an embodiment of the present disclosure, before acquiring the M second images, the method further includes taking the first image as a second image to expand the M second images.

According to an embodiment of the present disclosure, the clarity of the first image and each of the M second images is obtained in the following manner: performing Laplace transform on the image to obtain a pixel matrix corresponding to the image; calculating the variance of all elements constituting the pixel matrix; and using the variance as the clarity of the image.

According to an embodiment of the present disclosure, obtaining the clarity of each image further includes, before performing Laplace transform on the image, performing Gaussian filtering on the image, and/or converting the image into a grayscale image.

In another aspect of the embodiments of the present disclosure, an image recognition device is provided. The device includes an image acquisition module, a clarity acquisition module, and a first determination module. The image acquisition module is used to acquire a first image. The clarity acquisition module is used to obtain the clarity of the first image. The first determination module is used to determine that the first image is a clear image when the clarity of the first image is greater than a blur threshold; wherein the blur threshold is determined based on the distribution of the clarity of M second images; wherein M is an integer greater than 1, and the M second images and the first image are images taken for the same scene.

According to an embodiment of the present disclosure, the device further includes a second determination module. The image acquisition module is further used to acquire M second images. The clarity acquisition module is further used to obtain the clarity of each second image. The second determination module is used to determine the blur threshold based on the distribution of the clarity of the M second images.

According to an embodiment of the present disclosure, the second determination module includes a distribution histogram generation submodule, a gradient detection submodule, and a threshold determination submodule. The distribution histogram generation submodule is used to generate a distribution histogram of the clarity of the M second images. The gradient detection submodule is used to perform gradient detection on the distribution histogram to determine the position of the trough. The threshold determination submodule is used to use the clarity value corresponding to the position of the trough as the blur threshold.

According to an embodiment of the present disclosure, the clarity acquisition module is used to obtain the clarity of the first image and each of M second images in the following manner: performing Laplace transform on the image to obtain a pixel matrix corresponding to the image; calculating the variance of all elements constituting the pixel matrix; and using the variance as the clarity of the image.

According to an embodiment of the present disclosure, the clarity acquisition module is further used to perform Gaussian filtering on the image and/or convert the image into a grayscale image before performing Laplace transform on the image.

Another aspect of the embodiments of the present disclosure provides an automatic sorting robot. The automatic sorting robot includes a camera, a processor, and a sorting unit. The camera is used to capture a first image. The sorting unit is used to sort goods. The processor is used to: obtain the clarity of the first image: when the clarity of the first image is greater than a blur threshold, determine that the first image is a clear image, wherein the blur threshold is determined based on the distribution of the clarity of M second images, wherein M is an integer greater than 1, and the M second images and the first image are images taken for the same scene; and control the sorting unit to sort goods based on the first image determined to be a clear image.

According to an embodiment of the present disclosure, the processor is further used to determine that the first image is a blurred image when the clarity of the first image is less than or equal to a blur threshold, and control the camera to re-capture the first image.

Another aspect of the present disclosure provides an electronic device. The electronic device includes one or more processors and one or more memories. The one or more memories are used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

Another aspect of an embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method described above when executed.

Another aspect of an embodiment of the present disclosure provides a computer program, wherein the computer program includes computer executable instructions, and the instructions are used to implement the method described above when executed.

One or more of the above-mentioned embodiments have the following advantages or beneficial effects: according to the clarity distribution of a large number of images with a high degree of similarity taken in the same scene, a blur threshold for distinguishing whether an image is a clear image or a blurred image can be obtained, thereby effectively identifying whether the image is a clear image, providing an effective means for identifying whether an image is clear.

BRIEF DESCRIPTION OF THE DRAWINGS

The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

FIG1 schematically shows a structural block diagram of an automatic sorting robot according to an embodiment of the present disclosure;

FIG2 schematically shows a flow chart of an image recognition method according to an embodiment of the present disclosure;

FIG3 schematically shows a flow chart of an image recognition method according to another embodiment of the present disclosure;

FIG4 schematically shows a flow chart of determining a blur threshold in an image recognition method according to yet another embodiment of the present disclosure;

FIG5 schematically shows an application example of the image recognition method according to an embodiment of the present disclosure;

FIG6 schematically shows a block diagram of an image recognition device according to an embodiment of the present disclosure; and

FIG. 7 schematically shows a block diagram of an electronic device suitable for implementing the image recognition method according to an embodiment of the present disclosure.

Detailed ways

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "include", "comprising", etc. used herein indicate the existence of the features, steps, operations and/or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and/or A, B, C, etc.). In the case of using expressions such as "at least one of A, B, or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and/or A, B, C, etc.).

The embodiments of the present disclosure provide an image recognition method and device, an electronic device, a computer-readable storage medium, and an automatic sorting robot using the image recognition method for automatically identifying images that are taken in the same scene and have a high degree of similarity. In the image recognition method, a first image to be recognized is first acquired, and then the clarity of the first image is obtained. Next, when the clarity of the first image is greater than a blur threshold, the first image is determined to be a clear image. The blur threshold is determined based on the distribution of the clarity of M second images, wherein M is an integer greater than 1, and the M second images and the first image are images taken for the same scene.

The blur threshold may be a value of clarity that divides the distribution of the clarity of the M second images into two different distributions. That is, the blur threshold may effectively distinguish a normal clear image and a blurry image into two different distributions in the clarity dimension.

According to one embodiment of the present disclosure, when calculating the clarity of an image, the image can be subjected to Laplace Laplacian transformation, and the variance of the constituent elements in the pixel matrix obtained after the Laplacian transformation can be used as the clarity. The Laplacian operator can be used to measure the second-order derivative of an image, and can emphasize the area in the image where the density changes rapidly, that is, the boundary, so it can be used for boundary detection. In a normal clear image, the boundary is relatively clear, so the calculated variance will be relatively large; while in a blurred image, there is little boundary information contained, so the calculated variance will be relatively small. Therefore, based on the clarity distribution of a large number of images, a clarity value that can divide the overall distribution into two different distributions can be selected as a blur threshold. In this way, the clarity of images with a large degree of similarity in the same scene can be effectively judged.

The image recognition method of the embodiment of the present disclosure can be applied to an automatic sorting robot, and can also be applied to any device or scene that requires automatic recognition of images with a high degree of similarity taken in the same scene, and the present disclosure is not limited to this.

FIG1 schematically shows a structural block diagram of an automatic sorting robot 100 according to an embodiment of the present disclosure.

As shown in FIG. 1 , the automatic sorting robot 100 may include a camera 110 , a processor 120 , and a sorting unit 130 .

The camera 110 is used to capture the first image and transmit the first image to the processor 120. The automatic sorting robot 100 generally has highly refined work content, and the image scenes captured are relatively simple and similar.

The sorting unit 130 may be, for example, a robot arm.

The processor 120 can execute the image recognition method according to the embodiment of the present disclosure to identify whether the first image is a clear image. When the first image is determined to be a clear image, the sorting unit 130 is controlled to sort the goods; or when the first image is determined not to be a clear image, the camera 110 is controlled to re-capture the first image. In this way, it is possible to effectively identify whether the image captured by the camera 110 is a normal clear image, thereby improving the efficiency of the automatic sorting robot 100 in sorting goods.

The processor 120 may execute the image recognition method according to the embodiment of the present disclosure. First, a first image is acquired. Then, the clarity of the first image is obtained by processing the first image. Then, when the clarity of the first image is greater than a blur threshold, the first image is determined to be a clear image; or, when the clarity of the first image is less than or equal to the blur threshold, the first image is determined to be a blur image. The blur threshold is determined based on the distribution of the clarity of the M second images. The M second images and the first image are images taken for the same scene. For example, the M second images are all images taken by the camera 110 during the cargo sorting process within a historical period.

FIG. 2 schematically shows a flow chart of an image recognition method 200 according to an embodiment of the present disclosure.

As shown in FIG. 2 , the image recognition method 200 may include operations S210 to S230 .

In operation S210, a first image is acquired. For example, the camera 110 captures the first image; or, for example, the first image is downloaded from a database or a cloud.

In operation S220, the definition of the first image is obtained.

In operation S230, when the clarity of the first image is greater than a blur threshold, the first image is determined to be a clear image; wherein the blur threshold is determined based on the distribution of the clarity of M second images; wherein the M second images and the first image are images taken for the same scene, and M is an integer greater than 1.

According to an embodiment of the present disclosure, before acquiring the M second images, the first image can be used as a second image to expand the M second images. For example, after the automatic sorting robot 100 acquires the first image through the camera 110, the first image can be updated to the M second images in real time, so that the clarity distribution of the image acquired by the camera can be counted in real time, and the blur threshold can be updated in real time.

The image clarity can be calculated using any algorithm such as Brenner gradient function, grayscale variance function, entropy function, etc.

According to an embodiment of the present disclosure, the variance of the image pixel matrix after Laplace transformation can be used as an indicator to measure the clarity of the image.

Specifically, the clarity of the first image and each of the M second images is obtained by: performing Laplace transform on the image to obtain a pixel matrix corresponding to the image; calculating the variance of all elements constituting the pixel matrix; and using the variance as the clarity of the image.

For example, the pixel value at any position (x, y) in the image can be expressed as a discrete function f(x, y). Through Laplacian transformation, the second-order derivative at the position (x, y) in the image can be obtained, as shown in formula (1):

For any position (x, y) in the image except for edge pixels, the second-order derivative value of the position can be obtained by transformation using formula (1). Thus, the pixel matrix corresponding to the image is obtained, wherein the pixel matrix may not contain the second-order derivative of the edge pixels of the image.

According to an embodiment of the present disclosure, before performing Laplace transform on the image according to equation (1), Gaussian filtering can be performed on the image, and/or the image can be converted into a grayscale image, which can reduce the amount of calculation for the image processing process.

According to the embodiments of the present disclosure, a blur threshold for distinguishing whether an image is a clear image or a blurred image can be obtained based on the clarity distribution of a large number of images with a high degree of similarity taken in the same scene. This can effectively identify whether the image is a clear image, providing an effective means for identifying whether an image is clear.

FIG3 schematically shows a flow chart of an image recognition method 300 according to another embodiment of the present disclosure.

As shown in FIG. 3 , in combination with FIG. 2 , the image recognition method 300 according to the embodiment of the present disclosure is based on the method 200 and further includes operations S340 to S360 , wherein the blur threshold is determined through operations S340 to S360 .

In operation S340 , M second images are acquired. For example, all images collected by the camera 110 within a historical period are acquired.

In operation S350, the definition of each second image is obtained. The calculation of the definition is referred to above and will not be repeated here.

In operation S360, a blur threshold is determined based on a distribution of the sharpness of the M second images.

Theoretically, both the blurred image and the clear image can be considered to be normally distributed with their respective clarity means as the center, so the clarity distribution of the M second images can be divided into two different normally distributed clarity values as blur thresholds.

FIG. 4 schematically shows a flow chart of determining a blur threshold in an image recognition method according to yet another embodiment of the present disclosure.

As shown in FIG. 4 , in combination with FIG. 3 , the image recognition method 400 according to the embodiment of the present disclosure is based on the method 300 , and operation S360 is further implemented as operations S461 to S463 .

In operation S461, a distribution histogram of the sharpness of the M second images is generated. The horizontal axis of the distribution histogram is the value of the sharpness of each image, for example, the sharpness is formed from the minimum to the maximum. The vertical axis is the frequency of occurrence or frequency of each value of the sharpness. In theory, the blurred image and the sharp image will follow a normal distribution with their respective sharpness means as the center, so that the distribution histogram will show a bimodal characteristic, that is, it has two peaks.

In operation S462, the distribution histogram is subjected to gradient detection to determine the position of the trough. The gradient of the trough approaches zero, the gradient on the left side of the trough is negative, and the gradient on the right side of the trough is positive, thereby determining the position of the trough.

In operation S463, the clarity value corresponding to the position of the trough is used as a blur threshold.

For example, if the horizontal axis is formed by the clarity from minimum to maximum, then the left side of the trough position in the distribution histogram is the clarity distribution of the blurred image, and the right side of the trough position is the clarity distribution of the normal clear image. Therefore, the blurred image and the normal clear image can be distinguished as two different distributions through the clarity corresponding to the trough position.

FIG. 5 schematically shows an application example 500 of the image recognition method according to an embodiment of the present disclosure.

As shown in FIG. 5 , the application example 500 may include steps S501 to S508 .

Step S501 , collecting images captured by the camera 110 when the automatic sorting robot 100 picks up an object.

Step S502: fix the pixel number of the image to be detected (ie, the first image in this article) to 742*742. The pixel number of the image is related to the camera and subsequent data processing, and 742*742 here is only an example.

Step S503: remove Gaussian noise of the image to be detected by using a processing method such as Gaussian filtering.

Step S504: convert the image to be detected into a grayscale image to reduce the amount of calculation for each image during the detection process.

Step S505: Perform Laplace transformation on the image to be detected to obtain a new pixel matrix, and calculate the variance of the pixel matrix, which is recorded as the clarity of the image.

Step S506, calculating the clarity of a large number of images (ie, M second images in this article) collected under the same scene, and generating a distribution histogram with a bimodal characteristic.

Step S507, perform gradient detection on the distribution histogram, determine the position of the trough, and set it as the blur threshold of the group of images. The gradient of the trough is close to zero, the gradient on the left side of the trough is negative, and the gradient on the right side of the trough is positive.

Step S508, the clarity of the image to be detected is judged. If the clarity of the image to be detected is greater than the blur threshold, it is judged as a clear qualified image, otherwise it is processed as a blurred image.

FIG. 6 schematically shows a block diagram of an image recognition device 600 according to an embodiment of the present disclosure.

As shown in FIG6 , the image recognition device 600 according to an embodiment of the present disclosure includes an image acquisition module 610, a clarity acquisition module 620, and a first determination module 630. According to another embodiment of the present disclosure, the image recognition device 600 may further include a second determination module 640. The device 600 may implement the image recognition method described with reference to FIGS. 2 to 5 . The device 600 may be disposed in the automatic sorting robot 100; for example, disposed in the processor 120; or partially disposed in the processor 120 and partially disposed in the camera 110.

The image acquisition module 610 is used to acquire a first image.

The clarity acquisition module 620 is used to obtain the clarity of the first image. According to one embodiment of the present disclosure, the clarity acquisition module 620 is used to obtain the clarity of each of the first image and the M second images in the following manner: first, Laplace transform the image to obtain the pixel matrix corresponding to the image; then calculate the variance of all elements constituting the pixel matrix; and finally use the variance as the clarity of the image. According to another embodiment of the present disclosure, the clarity acquisition module 620 is also used to perform Gaussian filtering on the image before performing Laplace transform on the image, and/or convert the image into a grayscale image.

The first determination module 630 is used to determine that the first image is a clear image when the clarity of the first image is greater than a blur threshold; wherein the blur threshold is determined based on the distribution of the clarity of M second images; wherein the M second images and the first image are images taken for the same scene.

According to an embodiment of the present disclosure, the image acquisition module 610 is further configured to acquire M second images.

The definition obtaining module 620 is further used to obtain the definition of each second image.

The second determination module 640 is used to determine a blur threshold based on the distribution of the sharpness of the M second images.

According to an embodiment of the present disclosure, the second determination module 640 includes a distribution histogram generation submodule 641 , a gradient detection submodule 642 , and a threshold determination submodule 643 .

The distribution histogram generation submodule 641 is used to generate a distribution histogram of the sharpness of the M second images.

The gradient detection submodule 642 is used to perform gradient detection on the distribution histogram to determine the location of the trough.

The threshold determination submodule 643 is used to use the clarity value corresponding to the position of the trough as the blur threshold.

According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

For example, any multiple of the image acquisition module 610, the clarity acquisition module 620, the first determination module 630, the second determination module 640, the distribution histogram generation submodule 641, the gradient detection submodule 642, and the threshold determination submodule 643 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the image acquisition module 610, the clarity acquisition module 620, the first determination module 630, the second determination module 640, the distribution histogram generation submodule 641, the gradient detection submodule 642, and the threshold determination submodule 643 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the image acquisition module 610, the clarity acquisition module 620, the first determination module 630, the second determination module 640, the distribution histogram generation submodule 641, the gradient detection submodule 642, and the threshold determination submodule 643 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be performed.

Fig. 7 schematically shows a block diagram of an electronic device 700 suitable for implementing the image recognition method according to an embodiment of the present disclosure. The electronic device 700 shown in Fig. 7 is only an example and should not bring any limitation to the functions and scope of use of the embodiment of the present disclosure.

As shown in FIG7 , the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and/or a related chipset and/or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

In RAM 703, various programs and data required for the operation of electronic device 700 are stored. Processor 701, ROM 702 and RAM 703 are connected to each other via bus 704. Processor 701 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 702 and/or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 700 may further include an input/output (I/O) interface 705, which is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.

According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and/or installed from the removable medium 711. When the computer program is executed by the processor 701, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

The present disclosure also provides a computer-readable storage medium, which may be included in the device/apparatus/system described in the above embodiments; or may exist independently without being assembled into the device/apparatus/system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 702 and/or RAM 703 described above and/or one or more memories other than ROM 702 and RAM 703.

An embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains a program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the image recognition method provided by the embodiment of the present disclosure.

When the computer program is executed by the processor 701, the above functions defined in the system/device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 709, and/or installed from the removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

It will be appreciated by those skilled in the art that the features described in the various embodiments and/or claims of the present disclosure may be combined and/or combined in a variety of ways, even if such combinations and/or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and/or claims of the present disclosure may be combined and/or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. However, these embodiments are only for the purpose of illustration and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims (11)

1. An image recognition method, comprising:

Acquiring a first image;

Obtaining the definition of the first image; and

When the definition of the first image is larger than a fuzzy threshold value, determining that the first image is a clear image; wherein the blur threshold is determined based on a distribution of sharpness of the M second images; wherein M is an integer greater than 1;

and dividing the distribution of the definition of the M second images into two different definition values of normal distribution to serve as the blurring threshold value, wherein the M second images and the first image are images shot for the same scene.

2. The method of claim 1, wherein the method further comprises:

Obtaining M second images;

obtaining the definition of each second image; and

The blur threshold is determined based on a distribution of the sharpness of the M second images.

3. The method of claim 2, wherein the determining the blur threshold based on a distribution of sharpness of the M second images comprises:

Generating a distribution histogram of the definition of the M second images;

gradient detection is carried out on the distribution histogram, and the position of the trough is determined; and

And taking a definition value corresponding to the position of the trough as the blurring threshold value.

4. The method of claim 2, wherein prior to the acquiring the M second images, the method further comprises:

and taking the first image as one second image to expand M second images.

5. The method of any of claims 1-4, wherein the sharpness of each of the first image and the M second images is obtained by:

Carrying out Laplace transformation on the image to obtain a pixel matrix corresponding to the image;

Calculating variances of all elements constituting the pixel matrix; and

The variance is taken as the sharpness of the image.

6. The method of claim 5, wherein obtaining sharpness of each image further comprises, prior to subjecting the image to the Laplacian transform,

Performing Gaussian filtering on the image; and/or

The image is converted into a gray scale image.

7. An image recognition apparatus comprising:

The image acquisition module is used for acquiring a first image;

a definition obtaining module, configured to obtain definition of the first image; and

The first determining module is used for determining that the first image is a clear image when the definition of the first image is larger than a blurring threshold value; wherein the blur threshold is determined based on a distribution of sharpness of the M second images; and M is an integer greater than 1, and the definition values of the definition distribution of the M second images are divided into two different normal distributions to serve as the blurring threshold value, wherein the M second images and the first image are images shot for the same scene.

8. An automated sorting robot comprising:

The camera is used for acquiring a first image;

The sorting unit is used for sorting cargoes;

a processor for:

Acquiring the first image;

obtaining sharpness of the first image:

When the definition of the first image is larger than a fuzzy threshold value, determining that the first image is a clear image; wherein the blur threshold is determined based on a distribution of sharpness of the M second images; wherein M is an integer greater than 1, and the sharpness values of the two different normal distributions are used as the blur threshold, and the M second images and the first image are images shot for the same scene; and

And controlling the sorting unit to sort cargoes based on the first image determined to be a clear image.

9. The automated sorting robot of claim 8, wherein said processor is further configured to: and when the definition of the first image is smaller than or equal to a blurring threshold value, determining the first image as a blurring image, and controlling the camera to acquire the first image again.

10. An electronic device, comprising:

One or more processors; and

One or more memories for storing one or more programs,

Wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-6.

11. A computer readable storage medium having stored thereon executable instructions which when executed by a processor cause the processor to implement the method according to any of claims 1 to 6.