CN120147235A

CN120147235A - A medical device sterilization packaging visual inspection method, system and device

Info

Publication number: CN120147235A
Application number: CN202510179099.4A
Authority: CN
Inventors: 杜伟星
Original assignee: Beijing Fengtai Youanmen Hospital
Current assignee: Beijing Fengtai Youanmen Hospital
Priority date: 2025-02-18
Filing date: 2025-02-18
Publication date: 2025-06-13

Abstract

The present invention discloses a method, system and device for visual inspection of sterilized packaging of medical devices, which relates to the field of machine vision processing technology. The method corrects the original image to a standard coordinate system to eliminate perspective distortion, and uses a reference template to determine the effective inspection area of the packaging, performs multi-dimensional channel expansion, and obtains surface optical abnormality data by comparing with reference features. The deviation is calculated based on the predetermined sealing line position, and the sealing line consistency index is obtained through nonlinear polymerization. The comprehensive judgment index is calculated, and the qualified or unqualified signal of the packaging is output after comparison with the threshold, so as to realize the automatic inspection of the appearance and sealing of the sterilized packaging of medical devices. The effective inspection area is obtained by correcting the image and matching the reference template, and the judgment signal is output by calculating the comprehensive judgment index and comparing it with the predetermined threshold, thereby comprehensively improving the appearance and sealing inspection accuracy, robustness and inspection efficiency of the sterilized packaging of medical devices under the premise of multi-dimensionality and standardization.

Description

Visual detection method, system and device for medical instrument disinfection package

Technical Field

The invention relates to the technical field of machine vision processing, in particular to a visual detection method, a visual detection system and a visual detection device for sterilizing packaging of medical instruments.

Background

Medical devices often require harsh sterilization and aseptic packaging prior to shipment to ensure reduced risk of infection during clinical use. For this reason, the integrity, tightness, cleanliness, and accuracy of identification information of medical instrument packages are important in quality control. Conventional quality inspection methods typically rely on manual visual inspection or simple machine vision methods, which present a number of bottlenecks in the face of high speed, high volume production lines.

On the one hand, manual detection is easily influenced by factors such as experience, fatigue degree, subjective judgment and the like of operators, consistency and reliability of detection results are difficult to ensure, on the other hand, a simple machine vision detection means is often limited to basic analysis of two-dimensional gray scale or color images, and fine anomalies (such as micro scratches and stains) on the surface of a package, local breakage or deviation of a sealing line and structural anomalies cannot be comprehensively quantified and accurately judged due to insufficient multi-dimensional optical characteristics, micro differences and complex perspective distortion correction capability.

Furthermore, in the prior art, while some devices already have basic image correction and area identification capabilities, analysis of the package surface and seal line conditions is still too dependent on simple statistics and linear metrics. When facing complex materials, different batches and diversified package types, simple linear judgment is easy to miss or misjudge, and cannot meet strict quality standards of medical instruments.

Disclosure of Invention

Based on the above-mentioned shortcomings of the prior art, it is an object of the present invention to provide a visual inspection method, system and device for sterilizing packages of medical devices, which solves the above-mentioned technical problems.

In order to achieve the purpose, the invention provides the following technical scheme that the visual detection method for the medical instrument disinfection package comprises the following steps:

S1, correcting an acquired original package image, mapping the image to a standard coordinate system to eliminate shooting angles and perspective distortion, and carrying out region identification and mask extraction on the corrected image by utilizing a preset reference template to determine an effective detection region of the package;

S2, in the determined effective detection area, performing multidimensional channel expansion on the optical characteristics of the image, and performing difference measurement on the corrected image and the reference characteristics of a preset reference template to obtain data describing the optical abnormal characteristics of the package surface;

S3, according to the preset seal line position definition, calculating the deviation between the pixel points in the same effective detection area and the seal line reference characteristics, and obtaining a seal line consistency index through weighting and nonlinear deviation aggregation to reflect the deviation of the seal line on the structure and the intensity distribution;

and S4, calculating to obtain a comprehensive judgment index according to the surface optical abnormal characteristic data and the sealing line consistency index, comparing the comprehensive judgment index with a preset threshold value, and outputting a disqualification signal when the index exceeds the threshold value, or outputting a qualification signal, thereby realizing automatic visual detection and judgment of the appearance and the sealing performance of the medical instrument disinfection package.

The present invention is further configured that step S1 includes:

Defining a mapping relation from an original coordinate system (x, y) to a standard coordinate system (u, v) to align the corrected image with a standard reference coordinate;

Mapping the gray value of each pixel (x, y) in the original image to the corresponding position of the corrected coordinates (u, v) based on the defined mapping relation, and generating a corrected image;

Performing feature separation processing on the corrected image and a preset reference template, extracting difference features through a feature separation function and outputting a corresponding mask;

and judging the conditions of the mask, marking the mark meeting the conditions as effective pixels, and defining the area formed by all the effective pixels as an effective packaging area.

The invention is further arranged that the feature separation function is M (u, v) =exp| (X ^′ (u, v) -R (u, v))|, wherein M (u, v) is a mask of coordinates (u, v), X ^′ (u, v) is a gray value of a corrected image pixel (u, v), and R (u, v) is a gray value of a predetermined reference template pixel (u, v);

and D (u, v) =f (M (u, v) ltoreq.eta), wherein D (u, v) is the effective packaging area, f (·) is a condition judgment function, 1 is output when the condition is met, and otherwise 0 is output, eta is a condition threshold.

The present invention is further configured that step S2 includes:

Non-linearly mapping the correction image and the single channel image of the predetermined reference template image to a multi-dimensional channel;

And calculating the difference value of the multidimensional channel of the correction image and the preset reference template, and fusing to generate a difference measure through product operation among the channels.

The invention is further arranged that the calculation logic for the nonlinear mapping of the single-channel images of the correction image and the predetermined reference template image to the multidimensional channel is Z (u, v, ρ) = (X ^′(u,v)+Δ(ρ))^τ(ρ),Y(u,v,ρ)＝(R(u,v)+Δ(ρ))^τ(ρ)), wherein Z (u, v, ρ) is the characteristic representation of the nonlinear mapping of the correction image to the ρ channel, delta (ρ) is the channel offset parameter for introducing the displacement in the channel, tau (ρ) is the channel nonlinear index, Y (u, v, ρ) is the characteristic representation of the nonlinear mapping of the predetermined reference template image to the ρ channel;

The computation logic of the difference metric is: where H (u, v) is the difference metric, Ω is the total number of channels, and ζ is the correction parameter.

The present invention is further configured such that step S3 includes:

Calculating, for each pixel (u, v) of the predetermined seal line position, an intensity deviation delta (u, v) of the pixel from the seal line reference feature;

And obtaining a seal line consistency index by weighting and nonlinear deviation aggregation on a preset seal line according to the intensity deviation delta (u, v).

The invention is further configured that the calculation logic of the intensity deviation delta (u, v) is delta (u, v) =x ^′ (u, v) -W (u, v), wherein W (u, v) is the gray value of the seal line reference feature;

the calculation logic of the seal line consistency index is as follows: s is a seal line consistency index, (u, v) E C indicates that the pixel (u, v) belongs to a seal line set C, pi is a weighting function, theta and Is a non-integer positive real power exponent, is used for carrying out nonlinear amplification on the deviation, sigma is a channel amplification parameter, is used for carrying out nonlinear inhibition on the deviation in a denominator term, and kappa is a correction parameter.

The present invention is further configured such that step S4 includes:

performing regional aggregation on the difference metrics to generate overall surface anomaly metric parameters, wherein SH= Σ _u,v H (u, v), and SH is the overall surface anomaly metric parameters;

And calculating according to the overall surface anomaly measurement parameter and the sealing line consistency index to obtain a comprehensive judgment index, wherein Q=alpha.SH+beta.S, and alpha and beta are weight coefficients.

The invention also provides a visual inspection system for medical instrument sterilization packages, the system comprising:

The correction module is used for correcting the acquired original package image, mapping the image to a standard coordinate system so as to eliminate shooting angles and perspective distortion, and carrying out region identification and mask extraction on the corrected image by utilizing a preset reference template so as to determine an effective detection region of the package;

The measuring module is used for carrying out multidimensional channel expansion on the optical characteristics of the image in the determined effective detection area and carrying out difference measurement on the corrected image and the reference characteristics of a preset reference template so as to obtain data describing the optical abnormal characteristics of the package surface;

The calculation module is used for calculating the deviation between the pixel points in the same effective detection area and the reference characteristics of the sealing line according to the preset position definition of the sealing line, and obtaining a consistency index of the sealing line through weighting and nonlinear deviation aggregation so as to reflect the deviation of the sealing line on the structure and the intensity distribution;

and the judging module is used for calculating and obtaining a comprehensive judging index according to the surface optical abnormal characteristic data and the sealing line consistency index, comparing the comprehensive judging index with a preset threshold value, outputting a disqualification signal when the index exceeds the threshold value, and outputting a qualification signal if the index does not exceed the threshold value, so as to realize automatic visual detection and judgment of the appearance and the sealing performance of the medical instrument disinfection package.

The invention also provides a visual inspection device for medical instrument disinfection packages, which comprises:

One or more processors;

a storage medium storing one or more programs that, when executed by the one or more processors, cause the apparatus to implement a medical device sterilization wrap visual inspection method as set forth in any one of the preceding claims.

The invention provides a visual inspection method, a system and a device for sterilizing packaging of medical instruments, wherein the method comprises the steps of correcting an acquired original packaging image, mapping the image to a standard coordinate system to eliminate shooting angle and perspective distortion, carrying out region identification and mask extraction on the corrected image by utilizing a preset reference template to determine an effective detection region of the packaging, carrying out multidimensional channel expansion on the optical characteristics of the image in the determined effective detection region, carrying out difference measurement on the reference characteristics of the corrected image and the preset reference template to obtain optical abnormal characteristic data describing the surface of the packaging, carrying out deviation calculation on pixel points in the same effective detection region and the reference characteristics of the sealing line according to the position definition of the preset sealing line, and carrying out weighting and nonlinear deviation aggregation to obtain a consistency index of the sealing line to reflect the deviation of the sealing line on structure and intensity distribution:

1. the detection precision and the robustness are improved, namely the interference of shooting angles and perspective distortion on a detection result can be eliminated by defining the mapping relation from an original image to a standard coordinate system and correcting the image; performing region identification and mask extraction on the corrected image by using a preset reference template, ensuring that the subsequent optical characteristic analysis and tightness detection focus on the inside of an effective region, and reducing misjudgment caused by background stray information;

2. The multi-dimensional optical characteristic enhancement and the accurate difference measurement are realized, namely the multi-dimensional channel expansion is carried out on the optical characteristics of the image in the determined effective detection area, the limitation of the traditional two-dimensional gray scale or simple color characteristics is broken through, and the characteristic space with more expressive force is obtained through the nonlinear mapping and offset adjustment among the channels. The corrected image and the reference feature are subjected to difference measurement, so that the surface optical anomaly is more easily amplified and identified in multiple dimensions, and the detection sensitivity and reliability of weak defects are effectively improved;

3. And carrying out fine-granularity seal line analysis and structure consistency measurement, namely carrying out deviation calculation on pixel points in an effective detection area and seal line reference characteristics according to preset seal line position definition, and obtaining a seal line consistency index by adopting weighting and nonlinear deviation aggregation. The index can quantify the local abnormal condition of the sealing line at the structure and brightness distribution level, so that potential defects such as poor sealing, line deviation and the like are more intuitively and obviously displayed, and the sealing quality and sterility of the package are ensured;

4. The comprehensive judgment index improves the overall detection efficiency, namely the surface optical abnormal characteristic data and the sealing line consistency index are subjected to nonlinear fusion to form the comprehensive judgment index. The index realizes higher-level comprehensive evaluation on the basis of multi-source information coupling, can judge the appearance quality and the sealing state of the package at the same time, and can keep higher distinguishing capability under different types and degrees of abnormal conditions. And comparing the comprehensive judgment index with a preset threshold value, and outputting a qualified or unqualified signal, thereby achieving the effects of quick, automatic and standardized quality control.

The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:

FIG. 1 is a flow chart illustrating a visual inspection method for sterilizing a package of medical devices according to an exemplary embodiment of the present invention;

Fig. 2 is a schematic structural view of a visual inspection system for sterilizing a package of medical devices according to an exemplary embodiment of the present invention.

Detailed Description

Further advantages and effects of the present invention will become readily apparent to those skilled in the art from the disclosure herein, by referring to the accompanying drawings and the preferred embodiments. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be understood that the preferred embodiments are presented by way of illustration only and not by way of limitation.

It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.

In the following description, numerous details are set forth in order to provide a more thorough explanation of embodiments of the present invention, it will be apparent, however, to one skilled in the art that embodiments of the present invention may be practiced without these specific details, in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the embodiments of the present invention.

Example 1

A visual inspection method for a medical instrument sterilization package, as shown in fig. 1, comprising:

In particular, step S1 is intended to provide a stable, standardized coordinate system and effective area basis for subsequent feature analysis and judgment. By mapping the originally acquired packaging image to a standard reference coordinate system and extracting the effective detection area according to the reference template, the invention can ensure that the subsequent analysis of the consistency of the optical characteristics and the sealing line is performed under a standard, repeatable and high-confidence standard, and the invention further provides that the step S1 comprises:

Defining the mapping relation from the original coordinate system (x, y) to the standard coordinate system (u, v) to align the corrected image with the standard reference coordinate, wherein the pixel distribution of the original image is specifically affected by the pose (including camera inclination, distance change, perspective distortion and the like) during shooting. By means of camera calibration means (usually calibration plates, markers of known dimensions, etc. are used in practice) mapping parameters can be obtained so that the original image coordinates (x, y) can be mapped to standard reference coordinates (u, v). The standard coordinate system is an idealized and undistorted plane coordinate system, and in the coordinate system, the boundary, the mark and the characteristic position of the package are strictly aligned with a preset template, so that a consistent image reference relationship can be obtained in the standard coordinate system after mapping and correction no matter how the original shooting visual angle changes;

and specifically, after the coordinate mapping relation exists, the gray value of the (x, y) position in the original image is interpolated and mapped to the (u, v) position. Each pixel of the corrected image generated by this process can be considered to correspond directly to the reference template in the same standard coordinate frame;

The invention further provides that the feature separation function is M (u, v) =exp| (X ^′ (u, v) -R (u, v))|, wherein M (u, v) is a mask of coordinates (u, v), X ^′ (u, v) is a gray value of a pixel (u, v) of the correction image, and R (u, v) is a gray value of a pixel (u, v) of the predetermined reference template;

And judging the conditions of the mask, marking the mark meeting the conditions as effective pixels, and defining the area formed by all the effective pixels as an effective packaging area. And D (u, v) =f (M (u, v) ltoreq.eta), wherein D (u, v) is the effective packaging area, f (·) is a condition judgment function, 1 is output when the condition is met, and otherwise 0 is output, eta is a condition threshold. Specifically, a mask M (u, v) has been calculated in the preceding step for describing the feature difference between the corrected image and the reference template. To translate this continuous or nonlinear metric into an indication of the effective area that is actually available, a conditional judgment needs to be applied to M (u, v). By setting a condition threshold value eta, it is judged whether M (u, v) satisfies a specific condition, M (u, v) is smaller than or equal to eta, and thereby the pixel satisfying the condition is judged as an "effective pixel". And defining all pixel point sets meeting the conditions as an effective package area D (u, v), and reserving only pixels close to the reference feature as an effective area through threshold screening. This can significantly reduce interference of background pixels with subsequent detection and analysis, making subsequent assessment of optical anomaly characteristics and seal line conditions more accurate and efficient.

Specifically, in step S2, the image is lifted from the single channel feature to the multi-channel feature space, and the difference between the corrected image and the reference template is measured in the high-dimensional space. The core idea of the logic is that under single channel (e.g. gray scale) conditions, the resolution of tiny anomalies is limited and is susceptible to illumination, color or material changes. When a single channel image is expanded into multi-dimensional channels through a non-linear mapping, each channel may highlight a particular class of optical characteristics or brightness distribution characteristics. Therefore, when the difference measurement is carried out on the corrected image and the reference template in the multichannel space, the surface abnormality and structural deviation can be captured more comprehensively and finely, and the overall detection precision is further improved, and the invention is further provided that the step S2 comprises the following steps:

The invention further provides that the calculation logic for non-linear mapping of the correction image with the single channel image of the predetermined reference template image to the multidimensional channel is Z (u, v, p) = (X ^′(u,v)+Δ(ρ))^τ(ρ),Y(u,v,ρ)＝(R(u,v)+Δ(ρ))^τ(ρ)), wherein Z (u, v, p) is a characteristic representation of the correction image non-linear mapping to the p channel, delta (p) is a channel offset parameter for introducing a displacement in the channel, tau (p) is a channel non-linear index, Y (u, v, p) is a characteristic representation of the predetermined reference template image non-linear mapping to the p channel, in particular, the original single channel gray image is expanded to the multidimensional channel characteristic representation by introducing a channel offset to a non-linear power mapping, such that each pixel point (u, v) is no longer described by a single gray value after mapping, but is also represented by a set of characteristic values Z (u, v, 1), Z (u, v, 2), Z (u, p) and Y (u, v, p) as well as a characteristic representation of the p channel, and the luminance of each of the non-linear mapping is enhanced by a specific luminance non-linear mapping to the specific luminance non-linear power of the p channel, the method can more effectively highlight tiny abnormal features in the subsequent difference measurement of the corrected image and the reference template, the value of the offset parameter delta (rho) is determined according to the brightness distribution of the target image and a specific detection target, the value range is [ -0.5,0.5], the nonlinear index tau (rho) is a non-integer positive real number, the value range is (0.5, 2), and the single-channel gray value cannot be simultaneously sensitive to different brightness regions. Through the offset and nonlinear indexes, the multiple channels can emphasize the slight changes of different brightness intervals respectively, so that the capability of detecting tiny anomalies on the surface is effectively improved;

and calculating the difference value of the multidimensional channel of the correction image and the preset reference template, and fusing to generate a difference measure through product operation among the channels. The computation logic of the difference metric is: Where H (u, v) is the difference metric, Ω is the total number of channels, and ζ is the correction parameter. Specifically, after the correction image and the reference template image are subjected to multidimensional channel feature mapping, a difference value of the correction image and the reference template image is calculated in each channel. In order to avoid linearization caused by simple addition of the difference values, the logic selects and fuses the differences by using product operation among channels, and finally obtains the difference degree through nonlinear correction and normalization processing, and the multi-channel product fusion is matched with the nonlinear correction, so that the tiny differences can be amplified in specific channels. When an abnormality exists, at least one channel can generate a larger difference value, and then the product is diffused into the overall difference measurement, so that the detectability of the abnormality is improved, if part of channels are affected by noise or local illumination change, the stable performance of the rest channels can still enhance the comprehensive effect through the product, the system is prevented from being greatly interfered due to single-point abnormality, and the stability and repeatability of detection are improved.

The present invention is further configured such that step S3 includes:

The invention further provides that the intensity deviation delta (u, v) of the pixels from the seal line reference feature is calculated for each pixel (u, v) of the predetermined seal line position, and the calculation logic of the intensity deviation delta (u, v) is delta (u, v) =x ^′ (u, v) -W (u, v), wherein W (u, v) is the gray value of the seal line reference feature, and in particular, whether the seal line is complete, uniform and free of anomaly is an important quality decision criterion in medical instrument sterilization package detection. For this purpose, it is necessary to quantify and analyze the gray scale characteristics of each pixel at a predetermined seal line position in an image, compare the pixel value X ^′ (u, v) of the corresponding seal line position in a corrected image with the standard gray scale value W (u, v) of the seal line reference characteristic, and describe the degree of deviation of the pixel point from the ideal seal line state in actual production by calculating the intensity deviation Δ (u, v). The deviation value is the basis for carrying out nonlinear weighted aggregation and consistency index calculation subsequently;

And obtaining a seal line consistency index by weighting and nonlinear deviation aggregation on a preset seal line according to the intensity deviation delta (u, v). The calculation logic of the seal line consistency index is as follows: s is a seal line consistency index, (u, v) E C indicates that the pixel (u, v) belongs to a seal line set C, pi is a weighting function, theta and Is a non-integer positive real power exponent, is used for carrying out nonlinear amplification on the deviation, sigma is a channel amplification parameter, is used for carrying out nonlinear inhibition on the deviation in a denominator term, and kappa is a correction parameter. Specifically, the above-described calculation logic has obtained, for each pixel (u, v) in the seal line pixel set C, a corresponding intensity deviation Δ (u, v) in the preceding step. The deviation is utilized to construct a sealing line consistency index S by weighting and nonlinear deviation aggregation to quantify the integral consistency degree of the sealing line on the structure and brightness distribution, and the non-integer positive real power exponent thetaAccording to the sensitivity requirement on the deviation, the value range is (0.5, 2), and the channel amplification parameter sigma is a positive number for adjusting the denominator term amplification effect;

the present invention is further configured such that step S4 includes:

And carrying out regional aggregation on the difference metrics to generate an overall surface anomaly metric parameter, SH= Σ _u,v H (u, v), wherein SH is the overall surface anomaly metric parameter, and specifically, the surface optical anomaly metric matrix H (u, v) and the seal line consistency index S are obtained in the previous step. Step S4, summing H (u, v) in an effective area to obtain an integral surface anomaly measure parameter SH, wherein the integral surface anomaly measure parameter describes the aggregation condition of integral anomaly degree of a package surface;

And calculating according to the overall surface anomaly measurement parameter and the sealing line consistency index to obtain a comprehensive judgment index, wherein Q=alpha.SH+beta.S, and alpha and beta are weight coefficients. Specifically, compared with the method of only looking at a single index, the method has the advantages that the surface abnormality and the quality of the sealing line are simultaneously incorporated into the decision process by integrating SH and S through the comprehensive decision index Qs, so that the final decision is more comprehensive. The method can not ignore the tiny but widely distributed surface problems, can not release the requirement on the local abnormal sensitivity of the sealing line, realizes the fusion and simplification of the multidimensional characteristics of the packaging quality, provides a judging mechanism with strong adaptability and easy regulation and control, and is beneficial to efficiently and accurately screening qualified and unqualified medical instrument packages on an industrial production line.

Example two

Referring to fig. 2, the exemplary visual inspection system for sterilizing packaging of medical devices includes:

It should be noted that, the visual inspection system for medical instrument sterilization packages provided in the foregoing embodiment and the visual inspection method for medical instrument sterilization packages provided in the foregoing embodiment belong to the same concept, and the specific manner in which each module and unit perform the operation has been described in detail in the method embodiment, which is not repeated herein. In practical application, the visual inspection system for sterilizing and packaging medical instruments provided by the embodiment can distribute the functions to different functional modules according to needs, namely, the internal structure of the system is divided into different functional modules to complete all or part of the functions described above, and the visual inspection system is not limited in this place.

Embodiments of the present application also provide a visual inspection apparatus for a medical instrument sterilization wrap, comprising one or more processors, and a storage medium storing one or more programs, which when executed by the one or more processors, cause the apparatus to implement a visual inspection method for a medical instrument sterilization wrap provided in the above embodiments.

The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.

It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B, and may mean that a exists alone, while a and B exist alone, and B exists alone, wherein a and B may be singular or plural. In addition, the character "/" herein generally indicates that the associated object is an "or" relationship, but may also indicate an "and/or" relationship, and may be understood by referring to the context.

In the present application, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (a, b, or c) of a, b, c, a-b, a-c, b-c, or a-b-c may be represented, wherein a, b, c may be single or plural.

It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided by the present application, it should be understood that the disclosed system may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. The storage medium includes a U disk, a removable hard disk, a read-on-y memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A visual inspection method for sterilization packaging of medical devices, characterized by comprising:

S1: Correct the acquired original packaging image and map the image to a standard coordinate system to eliminate the shooting angle and perspective distortion, and use a predetermined reference template to perform region recognition and mask extraction on the corrected image to determine the effective inspection area of the packaging;

S2: within the determined effective detection area, perform multi-dimensional channel expansion on the optical characteristics of the image, and measure the difference between the corrected image and the reference characteristics of the predetermined reference template to obtain data describing the optical abnormality characteristics of the packaging surface;

S3: According to the predetermined seal line position definition, the deviation between the pixel points in the same effective detection area and the seal line reference feature is calculated, and the seal line consistency index is obtained by weighted and nonlinear deviation aggregation to reflect the deviation of the seal line in structure and intensity distribution;

S4: A comprehensive judgment index is calculated based on the surface optical abnormality feature data and the sealing line consistency index, which is used to comprehensively evaluate the appearance and sealing status of the package. The comprehensive judgment index is compared with a predetermined threshold value. When the index exceeds the threshold value, an unqualified signal is output, otherwise a qualified signal is output, thereby realizing automated visual inspection and judgment of the appearance and sealing of the sterilized packaging of medical devices.

2. A medical device sterilization packaging visual inspection method according to claim 1, characterized in that step S1 comprises:

Define the mapping relationship from the original coordinate system (x, y) to the standard coordinate system (u, v) so that the rectified image is aligned with the standard reference coordinates;

Based on the defined mapping relationship, the grayscale value of each pixel (x, y) in the original image is mapped to the corresponding position of the corrected coordinates (u, v) to generate a corrected image;

Perform feature separation processing on the corrected image and the predetermined reference template, extract the difference features through the feature separation function and output the corresponding mask;

The mask is subjected to conditional judgment, pixels meeting the condition are marked as valid pixels, and an area consisting of all valid pixels is defined as a valid packaging area.

3. A medical device sterilization packaging visual inspection method according to claim 2, characterized in that the feature separation function is: M(u,v)=exp|(X ^′ (u,v)-R(u,v))|, wherein M(u,v) is the mask of the coordinate (u,v), X ^′ (u,v) is the gray value of the corrected image pixel (u,v), and R(u,v) is the gray value of the predetermined reference template pixel (u,v);

Valid packaging area: D(u,v)=f(M(u,v)≤η), where D(u,v) is the valid packaging area, f(·) is the conditional judgment function, which outputs 1 when the condition is met, otherwise it outputs 0, and η is the conditional threshold.

4. A medical device sterilization packaging visual inspection method according to claim 3, characterized in that step S2 comprises:

Nonlinearly mapping the single-channel images of the correction image and the predetermined reference template image to multi-dimensional channels;

The difference value of the multi-dimensional channel between the corrected image and the predetermined reference template is calculated, and the difference metric is generated by fusing them through the product operation between the channels.

5. A medical device sterilization packaging visual inspection method according to claim 4, characterized in that the calculation logic of nonlinearly mapping the single-channel image of the correction image and the predetermined reference template image to the multidimensional channel is: Z(u,v,ρ)＝(X ^′ (u,v)+Δ(ρ)) ^τ(ρ) , Y(u,v,ρ)＝(R(u,v)+Δ(ρ)) ^τ(ρ) , wherein Z(u,v,ρ) is the feature representation of the nonlinear mapping of the correction image to the ρ channel, Δ(ρ) is the channel offset parameter used to introduce displacement in the channel, τ(ρ) is the channel nonlinear index, and Y(u,v,ρ) is the feature representation of the nonlinear mapping of the predetermined reference template image to the ρ channel;

The calculation logic of the difference metric is: Among them, H(u,v) is the difference metric, Ω is the total number of channels, and ξ is the correction parameter.

6. A medical device sterilization packaging visual inspection method according to claim 3, characterized in that step S3 comprises:

For each pixel (u, v) at the predetermined sealing line position, the intensity deviation Δ(u, v) between the pixel and the sealing line reference feature is calculated;

According to the intensity deviation Δ(u,v), the sealing line consistency index is obtained by weighting and nonlinear deviation aggregation for the predetermined sealing line.

7. A medical device sterilization packaging visual inspection method according to claim 6, characterized in that the calculation logic of the intensity deviation Δ(u,v) is: Δ(u,v)=X ^′ (u,v)-W(u,v), where W(u,v) is the gray value of the sealing line reference feature;

The calculation logic of the sealing line consistency index is: S is the sealing line consistency index, (u,v)∈C means that the pixel (u,v) belongs to the sealing line set C, Π is the weighting function, θ and is a non-integer positive real power exponent, used to perform nonlinear amplification on the deviation, σ is the channel amplification parameter, used to perform nonlinear suppression on the deviation in the denominator, and κ is the correction parameter.

8. A medical device sterilization packaging visual inspection method according to claim 7, characterized in that step S4 comprises:

The difference metrics are regionally aggregated to generate the overall surface anomaly metric parameter, SH = ∑ _u,v H(u,v), where SH is the overall surface anomaly metric parameter;

The comprehensive judgment index is calculated based on the overall surface anomaly measurement parameters and the sealing line consistency index, Q = α·SH + β·S, where α and β are weight coefficients.

9. A medical device sterilization packaging visual inspection system, used to implement a medical device sterilization packaging visual inspection method according to any one of claims 1 to 8, characterized in that it comprises:

Correction module: Correct the original packaging image obtained, map the image to the standard coordinate system to eliminate the shooting angle and perspective distortion, and use the predetermined reference template to perform area recognition and mask extraction on the corrected image to determine the effective detection area of the packaging;

Measuring module: within the determined effective detection area, the optical characteristics of the image are expanded in multiple dimensions, and the difference between the corrected image and the reference characteristics of the predetermined reference template is measured to obtain data describing the optical abnormality characteristics of the packaging surface;

Calculation module: According to the predetermined seal line position definition, the deviation between the pixel points in the same effective detection area and the seal line reference features is calculated, and the seal line consistency index is obtained through weighted and nonlinear deviation aggregation to reflect the deviation of the seal line in structure and intensity distribution;

Judgment module: A comprehensive judgment index is calculated based on the surface optical abnormality feature data and the sealing line consistency index, which is used to comprehensively evaluate the appearance and sealing status of the package. The comprehensive judgment index is compared with the predetermined threshold. When the index exceeds the threshold, an unqualified signal is output, otherwise a qualified signal is output, thereby realizing automated visual inspection and judgment of the appearance and sealing of the sterilized packaging of medical devices.

10. A visual inspection device for sterilization packaging of medical devices, characterized in that the device comprises:

one or more processors;

A storage medium for storing one or more programs, which, when executed by the one or more processors, enables the device to implement a visual inspection method for sterilization packaging of medical devices as described in any one of claims 1 to 8.