TWI770817B - Defect detecting method, electronic device, and storage medium - Google Patents

Abstract

A defect detecting method is provided. The method includes dividing a number of product images to be detected into a linear image or a nonlinear image; obtaining a number of dimension reduction data by performing dimension reduction processing on the divided product images according to a number of dimension reduction algorithms; determining optimal dimension reduction data in the number of the dimension reduction data; inputting the optimal dimension reduction data into a gaussian mixture model to obtain score data of the product image; comparing the score data with a threshold, and judging whether the score data is less than a threshold; and determining that there is at least one defect in the product image when the score data is less than the threshold. An electronic device and a storage medium are also provided.

Description

Defect detection method, electronic device and storage medium

The invention relates to the technical field of appearance detection, and in particular, to a defect detection method, an electronic device and a storage medium.

With the development of science and technology, neural network models based on deep learning, such as convolutional neural networks, are widely used in the field of artificial intelligence, which can realize the automation of various functions, such as automatic detection of modulation data, image data and other data. Classification. When detecting defect signals in image data, it is usually necessary to train a convolutional neural network according to the data set, and perform feature extraction on the last convolutional layer in the training process, and then perform subsequent defect signal detection. However, when the similarity of the original image data is high, the similarity of the extracted features is also high and it is difficult to classify, thereby reducing the detection accuracy of the defect signal.

In view of this, it is necessary to provide a defect detection method, an electronic device and a storage medium, which directly perform dimension reduction processing on the image data to be detected, and perform defect detection in combination with a Gaussian mixture model, so as to improve the detection accuracy.

A first aspect of the present invention provides a flaw detection method, the method comprising: dividing a complex product image to be detected into a linear image or a nonlinear image; Perform dimensionality reduction processing on the product image divided by the image according to the complex dimensionality reduction algorithm to obtain complex dimensionality reduction data; determine the best dimensionality reduction data in the complex dimensionality reduction data; The data is input into a Gaussian mixture model to obtain the scoring data of the product image; the scoring data is compared with a threshold to determine whether the scoring data is less than the threshold; and when the scoring data is less than the threshold, Defects are determined to be present in the product image.

Preferably, the method further comprises: when the rating data is greater than or equal to the threshold, determining that there is no defect in the product image.

Preferably, the dividing the complex product image to be detected into a linear image or a nonlinear image includes: normalizing the product image to be detected; inputting the primitive value of the product image Linear scoring function to obtain the classification scores of the linear image and the nonlinear image; determine whether the classification score of the linear image is greater than the classification score of the nonlinear image; when determining the classification score of the linear image When the score is greater than the classification score of the nonlinear image, classify the product image as a linear image; and when the classification score of the linear image is not greater than the classification score of the nonlinear image , the product image is divided into non-linear images.

Preferably, performing dimensionality reduction processing on the product image divided by the image according to the complex dimensionality reduction algorithm to obtain complex dimensionality reduction data includes: when the product image is a linear image, using principal components respectively The analysis algorithm and the random projection algorithm are used to reduce the dimension of the product image; and when the product image is a non-linear image, the equal-metric mapping algorithm and the t-distributed random neighborhood embedding algorithm are respectively used to perform dimensionality reduction on the product image. Dimensionality reduction of the product image.

Preferably, the determining the best dimensionality reduction data in the complex dimensionality reduction data: calculating the average distance between the complex dimensionality reduction data obtained by each dimensionality reduction algorithm; and determining the complex dimensionality reduction with the largest distance average The data are the best dimensionality reduction data described.

Preferably, inputting the best dimensionality reduction data into a Gaussian mixture model to obtain the scoring data of the product image comprises: determining the number of Gaussian models in the Gaussian mixture model according to the number of types of defects to be detected; and Calculate the expected value of the Gaussian mixture model and the model parameter values of each iteration according to the optimal dimensionality reduction data and the EM algorithm; and calculate the Gaussian mixture according to the expected value and model parameter values calculated by each iteration The best parameters of the model are used as the scoring data.

Preferably, the threshold is the difference between the mean value of the model parameter values calculated by each repeated operation and three times the standard deviation of the scoring data.

Preferably, the method further comprises: marking the defective area on the product image, and displaying the marked product image on a display screen.

A second aspect of the present invention provides an electronic device, comprising: a processor; and a memory, wherein the memory stores a plurality of program modules, the plurality of program modules are loaded by the processor and execute the above-mentioned defects Detection method.

A third aspect of the present invention provides a storage medium on which at least one computer instruction is stored, and the instruction is loaded by a processor to execute the above-mentioned defect detection method.

The above flaw detection method, electronic device and storage medium directly perform dimensionality reduction processing on the image data to be detected, and combine the Gaussian mixture model to perform flaw detection, which does not need to extract convolution features during the data processing process, which simplifies the operation process. Avoid loss of information, thereby effectively improving the accuracy of flaw detection.

1: Electronic device

10: Processor

100: Defect Detection System

101: Get Mods

102: Divide modules

103: Dimensionality Reduction Module

104: Determine the module

105: Computing Modules

106: Judgment Module

107: Display Module

20: Memory

30: Computer Programs

40: Display screen

S301~S309: Steps

FIG. 1 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention.

FIG. 2 is a schematic structural diagram of a defect detection system provided by a preferred embodiment of the present invention.

FIG. 3 is a flowchart of a defect detection method provided by a preferred embodiment of the present invention.

In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments may be combined with each other in the case of no conflict.

In the following description, many specific details are set forth in order to facilitate a full understanding of the present invention, and the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terms used herein in the description of the present invention are for the purpose of describing specific embodiments only, and are not intended to limit the present invention.

Please refer to FIG. 1 , which is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention.

The defect detection method in the present invention is applied in the electronic device 1 . The electronic device 1 may be an electronic device installed with a defect detection program, such as a personal computer, a server, etc., wherein the server may be a single server, a server cluster, a cloud server, or the like.

The network where the electronic device 1 is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (Virtual Private Network, VPN) and the like.

The electronic device 1 includes, but is not limited to, a processor 10 , a memory 20 , a computer program 30 stored in the memory 20 and running on the processor 10 , and a display screen 40 . For example, the computer program 30 is a defect detection program. When the processor 10 executes the computer program 30 , the steps in the defect detection method are implemented, such as steps S301 to S309 shown in FIG. 3 . Alternatively, when the processor 10 executes the computer program 30 , the functions of each module/unit in the defect detection system, such as modules 101 to 107 in FIG. 2 , are implemented.

Exemplarily, the computer program 30 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 20 and executed by the processor 10 to The present invention has been completed. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 30 in the electronic device 1 . For example, the computer program 30 can be divided into an acquisition module 101 , a division module 102 , a dimension reduction module 103 , a determination module 104 , a calculation module 105 , a judgment module 106 and a display module 107 in FIG. 3 . . For the specific functions of each module, please refer to the function of each module in the embodiment of the defect detection system.

Those skilled in the art can understand that the schematic diagram is only an example of the electronic device 1, and does not constitute a limitation on the electronic device 1, and may include more or less components than the one shown, or combine some components, or different Components, for example, the electronic device 1 may also include input and output devices, network access devices, bus bars, and the like.

The so-called processor 10 may be a central processing unit (Central Processing Unit, CPU), and may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC) , Off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor 10 can also be any conventional processor, etc. The processor 10 is the control center of the electronic device 1, and uses various interfaces and lines to connect the entire electronic device 1. various parts.

The memory 20 can be used to store the computer programs 30 and/or modules/units, and the processor 10 runs or executes the computer programs and/or modules/units stored in the memory 20, And call the data stored in the memory 20 to realize various functions of the electronic device 1 . The memory 20 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; storage data The area can store data created according to the use of the electronic device 1 (such as audio data, phone book, etc.) and the like. In addition, the memory 20 may include a volatile memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a secure digital ( Secure Digital, SD) card, flash memory card (Flash Card), at least one disk memory device, flash memory device, or other memory device.

Please refer to FIG. 2 , which is a functional module diagram of a defect detection system provided by a preferred embodiment of the present invention.

In some embodiments, the defect detection system 100 operates in the electronic device 1 . The defect detection system 100 may include a plurality of functional modules composed of program code segments. The program codes of each program segment in the defect detection system 100 may be stored in the memory 20 of the electronic device 1 and executed by the at least one processor 10 to implement the defect detection function.

In this embodiment, the defect detection system 100 can be divided into a plurality of functional modules according to the functions performed by the defect detection system 100 . Referring to FIG. 2 , the functional modules may include an acquisition module 101 , a division module 102 , a dimension reduction module 103 , a determination module 104 , a calculation module 105 , a judgment module 106 and a display module 107 . The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can perform fixed functions, and are stored in the memory 20 . It can be understood that, in other embodiments, the above-mentioned modules can also be program instructions or firmware solidified in the processor 10 .

The obtaining module 101 is configured to obtain, when a defect detection request is received, an image of a product to be inspected according to the defect detection request.

In this embodiment, the defect detection request can be triggered by a user (eg, triggered by a preset function button), or can be triggered automatically within a preset time.

In this embodiment, the defect detection request includes at least detection object information. Specifically, the defect detection request is parsed to obtain the detection object information in the defect detection request, and the to-be-detected product image is acquired from the to-be-detected image library according to the detection object information. Wherein, the detection object information may be a product name, a product model, and the like.

The dividing module 102 is used to divide the complex product images to be detected into linear images or non-linear images.

In this embodiment, the division module 102 normalizes the product image to be detected, and inputs the primitive value of the product image into a linear scoring function to obtain a linear image and a nonlinear image The classification score of the linear image is determined to determine whether the classification score of the linear image is greater than the classification score of the nonlinear image. When it is determined that the classification score of the linear image is greater than the classification score of the nonlinear image When the product image is divided into linear images, when the classification score of the linear image is not greater than the classification score of the nonlinear image, the product image is divided into nonlinear images .

For example, the linear scoring function is f ( x _i , W , b ) = Wx _i + b . Suppose each image data is stretched into a column vector of length D of size [D x 1]. Among them, the matrix W of size [KxD] and the column vector b of size [Kx1] are the parameters of the linear scoring function, xi contains all the primitive information of the i-th image, and these primitive information are pulled into a A column vector of [px1] with W of size [qxp] and b of size [qx1]. Among them, p is the number of primitive points of the product image, and q is the number of categories. In this embodiment, q is 2. Therefore, P digits (original primitive values) are input into the linear scoring function, and the linear scoring function outputs 2 digits (scores obtained from different classifications), and then the scores of the different classifications are compared. Among them, the parameter W is the weight, and b is called the bias vector.

The dimensionality reduction module 103 is configured to perform dimensionality reduction processing on the product image divided by the image according to a complex dimensionality reduction algorithm to obtain complex dimensionality reduction data.

In this embodiment, when the product image is a linear image, the dimensionality reduction module 103 uses a principal component analysis algorithm (PCA) and a random projection algorithm (Random Project) to analyze the product image respectively. Dimensionality reduction. When the product image is a non-linear image, the dimensionality reduction module 103 uses an isometric mapping algorithm (Isomap) and a t-distributed stochastic neighborhood embedding algorithm (t-SNE) to analyze the product image respectively. Dimensionality reduction.

Specifically, when using the principal component analysis algorithm for dimensionality reduction, the dimensionality reduction module 103 first subtracts the sample average from the sample data, then calculates the principal components of the data by calculating the data covariance matrix, and finally converts the data by The transformation matrix is mapped onto the principal components, enabling dimensionality reduction of product images.

RK×N，用亂數填充所述映射矩陣，歸一化所述映射矩陣中的每一行，然後藉由y=RX對資料降維。其中，X為輸入資料，y降維後的資料。 When the random projection algorithm is used for dimension reduction, the dimension reduction module 103 first selects the mapping matrix R

RK×N, fill the mapping matrix with random numbers, normalize each row in the mapping matrix, and then reduce the dimension of the data by y=RX. Among them, X is the input data, and y is the data after dimension reduction.

When using the isometric mapping algorithm for dimensionality reduction, the dimensionality reduction module 103 determines the k nearest neighbors of the product image primitive points in the sample data, and sets the distance between the primitive points and the k nearest neighbors as the Euclidean distance , the distance from other points is set to infinity, the shortest path algorithm is used to calculate the distance between any two primitive points, and the distance is used as the input data of the multi-dimensional scaling analysis algorithm. The analysis algorithm outputs the projection of the product image primitive points in the low-dimensional space, so as to obtain the reduced-dimensional image.

When the t-distributed stochastic neighbor embedding algorithm (t-SNE) is used for dimension reduction, the dimension reduction module 103 uses stochastic neighbor embedding (SNE) to convert the sample data, that is, the height between the primitive points of the product image. The dimensional Euclidean distance is converted into a conditional probability representing similarity. For the low-dimensional counterparts of high-dimensional data points Xi and Xj, similar conditional probabilities are calculated, using gradient descent to minimize the KL distance, and define the perplexity, thus Obtain the corresponding low-dimensional data.

The determining module 104 is used for determining the best dimension reduction data among the plurality of dimension reduction data.

In this embodiment, the determining module 104 calculates the average distance between the complex dimensionality reduction data obtained by each dimensionality reduction algorithm, and determines the complex dimensionality reduction data with the largest distance average value as the optimal dimensionality reduction data . It should be noted that the larger the distance between the dimensionality reduction data, the better the dimensionality reduction effect. In this embodiment, the distance between the complex dimensionality reduction data is the distance of the data points in the adjacency graph.

The calculation module 105 is used for inputting the best dimensionality reduction data into a Gaussian mixture model to obtain the scoring data of the product image.

In this embodiment, the calculation module 105 performs mean pooling on the optimal dimensionality reduction data to obtain a target vector, and then inputs the target vector into a pre-trained Gaussian mixture model to obtain the Scoring data. Wherein, the Gaussian mixture model can accurately quantify the score corresponding to the target vector by using a Gaussian probability density function (normal distribution image curve).

Specifically, the calculation module 105 determines the number of Gaussian models in the Gaussian mixture model according to the number of types of defects to be detected, and calculates the Gaussian model according to the optimal dimensionality reduction data and the EM (Expectation-Maximum) algorithm. The expected value of the mixture model and the model parameter value of each repeated operation, and the optimal parameter of the Gaussian mixture model is calculated according to the expected value and model parameter value calculated for each repeated operation as the scoring data. In this embodiment, the number of Gaussian models in the Gaussian mixture model is two.

In this embodiment, the computing module 105 can divide the training sample data into a training set, a test set and a verification set, and then based on the maximum expectation algorithm, repeatedly train the complex low-dimensional vectors in the training set, Obtain the learner, then use the complex low-dimensional vector in the test set to test the learner, and obtain the test result, when the test result is less than the configuration value, the calculation module 105 uses the complex low-dimensional vector in the verification set. The vector adjusts the parameters in the learner to obtain the pre-trained Gaussian mixture model. In this embodiment, the calculation module 105 calculates the complex number The number of low-dimensional vectors. When the number is less than a preset number, the data augmentation algorithm is used to increase the number of the complex low-dimensional vectors.

The judging module 106 is configured to compare the scoring data with a threshold, and judge whether the scoring data is less than the threshold.

In this embodiment, the threshold value is the difference between the mean value of the model parameter values calculated by each repeated operation and three times the standard deviation of the scoring data.

The determining module 104 further determines that there is a defect in the product image when the rating data is less than the threshold.

The determining module 104 further determines that there is no defect in the product image when the rating data is greater than or equal to the threshold.

The display module 107 is used for marking the defective area on the product image, and displaying the marked product image on the display screen.

Please refer to FIG. 3 , which is a flowchart of a defect detection method provided by a preferred embodiment of the present invention. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

S301, when a defect detection request is received, acquire a product image to be detected according to the defect detection request.

In this embodiment, the defect detection request can be triggered by a user (eg, triggered by a preset function button), or can be triggered automatically within a preset time.

In this embodiment, the defect detection request includes at least detection object information. Specifically, the defect detection request is parsed to obtain the detection object information in the defect detection request, and the to-be-detected product image is acquired from the to-be-detected image library according to the detection object information. Wherein, the detection object information may be a product name, a product model, and the like.

S302: Divide the complex product image to be detected into a linear image or a nonlinear image.

In this embodiment, the product image to be detected is subjected to normalization processing, and the primitive values of the product image are input into a linear scoring function to obtain the classification scores of the linear image and the nonlinear image. Whether the classification score of the linear image is greater than the classification score of the nonlinear image, when it is determined that the classification score of the linear image is greater than the classification score of the nonlinear image, the product The image is divided into linear images, and when the classification score of the linear image is not greater than the classification score of the non-linear image, the product image is divided into non-linear images.

For example, the linear scoring function is f ( x _i , W , b ) = Wx _i + b . Suppose each image data is stretched into a column vector of length D of size [D x 1]. Among them, the matrix W of size [KxD] and the column vector b of size [Kx1] are the parameters of the linear scoring function, xi contains all the primitive information of the i-th image, and these primitive information are pulled into a A column vector of [px1] with W of size [qxp] and b of size [qx1]. Among them, p is the number of primitive points of the product image, and q is the number of categories. In this embodiment, q is 2. Therefore, P digits (original primitive values) are input into the linear scoring function, and the linear scoring function outputs 2 digits (scores obtained from different classifications), and then the scores of the different classifications are compared. Among them, the parameter W is the weight, and b is called the bias vector.

S303 , performing a dimensionality reduction process on the product image divided by the image according to a complex dimensionality reduction algorithm to obtain complex dimensionality reduction data.

Specifically, when using the principal component analysis algorithm for dimensionality reduction, first subtract the sample mean from the sample data, then calculate the principal components of the data by calculating the data covariance matrix, and finally map the data to the principal components by using the transformation matrix. , so as to achieve dimensionality reduction of product images.

RK×N，用亂數填充所述映射矩陣，歸一化所述映射矩陣中的每一行，然後藉由y=RX對資料降維。其中，X為輸入資料，y降維後的資料。 When using the random projection algorithm for dimensionality reduction, first select the mapping matrix R

RK×N, fill the mapping matrix with random numbers, normalize each row in the mapping matrix, and then reduce the dimension of the data by y=RX. Among them, X is the input data, and y is the data after dimension reduction.

When using the isometric mapping algorithm for dimensionality reduction, determine the k-nearest neighbors of the product image primitive points in the sample data, and set the distance between the primitive points and the k-nearest neighbors as the Euclidean distance. The distance is set to infinity, the shortest path algorithm is used to calculate the distance between any two primitive points, the distance is used as the input data of the multi-dimensional scaling analysis algorithm, and the product is output by the multi-dimensional scaling analysis algorithm Projection of image primitive points in a low-dimensional space to obtain a reduced-dimensional image.

When using the t-distributed stochastic neighbor embedding algorithm (t-SNE) for dimensionality reduction, the sample data, that is, the high-dimensional Euclidean distance between the primitive points of the product image, is converted by the stochastic neighbor embedding (SNE). In order to express the conditional probability of similarity, for the low-dimensional counterparts of high-dimensional data points Xi and Xj, the similar conditional probability is calculated, the gradient descent method is used to minimize the KL distance, and the perplexity is defined to obtain the corresponding low-dimensional data.

S304, determine the best dimensionality reduction data in the complex dimensionality reduction data.

In this embodiment, the average distance between the complex dimension reduction data obtained by each dimension reduction algorithm is calculated, and the complex dimension reduction data with the largest distance average value is determined as the optimal dimension reduction data.

S305, inputting the best dimensionality reduction data into a Gaussian mixture model to obtain rating data of the product image.

In this embodiment, mean pooling is performed on the optimal dimensionality reduction data to obtain a target vector, and then the target vector is input into a pre-trained Gaussian mixture model to obtain the scoring data. Wherein, the Gaussian mixture model can accurately quantify the score corresponding to the target vector by using a Gaussian probability density function (normal distribution image curve).

Specifically, the number of Gaussian models in the Gaussian mixture model is determined according to the number of types of defects to be detected, and the expected value and each Gaussian mixture model are calculated according to the optimal dimensionality reduction data and the EM (Expectation-Maximum) algorithm. The model parameter value of the repeated operation, and the optimal parameter of the Gaussian mixture model is calculated according to the expected value and the model parameter value calculated in each repeated operation as the scoring data.

In this embodiment, the training sample data can be divided into a training set, a test set and a validation set, and then based on the maximum expectation algorithm, repeated operations are performed to train the complex numbers in the training set to be low dimensional vector to obtain the learner, then use the complex low-dimensional vector in the test set to test the learner to obtain the test result, when the test result is less than the configuration value, use the complex low-dimensional vector in the verification set to adjust the parameters in the learner to obtain the pre-trained Gaussian mixture model. In this embodiment, the number of the complex low-dimensional vectors is calculated, and when the number is less than a preset number, the data augmentation algorithm is used to increase the number of the complex low-dimensional vectors.

S306, compare the scoring data with a threshold, and determine whether the scoring data is less than the threshold.

In this embodiment, the threshold value is the difference between the mean value of the model parameter values calculated by each repeated operation and three times the standard deviation of the scoring data. When the score data is less than the threshold, the process goes to S307. When the score data is greater than or equal to the threshold, the process proceeds to S309.

S307, it is determined that there is a defect in the product image.

S308 , marking the defective area on the product image, and displaying the marked product image on the display screen.

S309, it is determined that there is no defect in the product image.

If the modules/units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on this understanding, the present invention realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, When the computer program is executed by the processor, the steps of the above method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of original code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, pen drive, Mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), etc.

The defect detection method, electronic device and storage medium provided by the present invention directly perform dimensionality reduction processing on the image data to be detected, and combine the Gaussian mixture model for defect detection, which does not need to extract convolution features in the data processing process, simplifying the process The operation process is improved to avoid loss of information, thereby effectively improving the accuracy of defect detection.

It will be apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, but that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as exemplary and not restrictive, and the scope of the present invention is defined by the appended claims rather than the foregoing description, and is therefore intended to fall within the scope of the application. All changes within the meaning and scope of equivalents to the scope of the patent are included in the present invention. Any reference signs in the patentable scope should not be construed as limiting the claimed scope. Furthermore, it is clear that the word "comprising" does not exclude other units or steps and the singular does not exclude the plural. Plural units or devices stated in the scope of the device application can also be realized by software or hardware by the same unit or device. The terms first, second, etc. are used to denote names and do not denote any particular order.

To sum up, the present invention complies with the requirements of an invention patent, and a patent application can be filed in accordance with the law. However, the above descriptions are only the preferred embodiments of the present invention, and for those who are familiar with the art of the present invention, equivalent modifications or changes made in accordance with the spirit of the present invention should all be covered within the scope of the following patent application.

S301~S309: Steps

Claims (9)

A defect detection method, wherein the method comprises: dividing a complex product image to be detected into a linear image or a non-linear image; reducing the image division of the product image according to a complex dimensionality reduction algorithm dimensionality processing to obtain complex dimensionality reduction data; determining the best dimensionality reduction data in the complex dimensionality reduction data, including: calculating the average distance between the complex dimensionality reduction data obtained by each dimension reduction algorithm, and determining the average distance The largest complex dimensionality reduction data is the best dimensionality reduction data; the best dimensionality reduction data is input into the Gaussian mixture model to obtain the scoring data of the product image; the scoring data is compared with the threshold, and the judgment whether the scoring data is less than the threshold; and when the scoring data is less than the threshold, determining that a defect exists in the product image. The defect detection method according to claim 1, wherein the method further comprises: when the score data is greater than or equal to the threshold, determining that there is no defect in the product image. The defect detection method according to claim 1, wherein the dividing the complex product images to be detected into linear images or non-linear images comprises: normalizing the product images to be detected; The primitive value of the product image is input into a linear scoring function to obtain the classification score of the linear image and the nonlinear image; it is judged whether the classification score of the linear image is greater than the classification score of the nonlinear image ; dividing the product image into a linear image when it is determined that the classification score of the linear image is greater than the classification score of the nonlinear image; and When the classification score of the linear image is not greater than the classification score of the nonlinear image, the product image is divided into nonlinear images. The defect detection method according to claim 1, wherein the complex dimensionality reduction data obtained by performing dimensionality reduction processing on the product image divided by the image according to a complex dimensionality reduction algorithm comprises: when the product image is When it is a linear image, the principal component analysis algorithm and the random projection algorithm are respectively used to reduce the dimension of the product image; and when the product image is a nonlinear image, the isometric mapping algorithm and A t-distributed random neighborhood embedding algorithm performs dimensionality reduction on the product image. The defect detection method according to claim 1, wherein the inputting the best dimensionality reduction data into a Gaussian mixture model to obtain the scoring data of the product image comprises: determining the Gaussian according to the number of defect types to be detected the number of Gaussian models in the mixture model; and calculating the expected value of the Gaussian mixture model and the model parameter values for each iteration according to the optimal dimensionality reduction data and the EM algorithm; and the expected value calculated according to each iteration and The optimal parameters of the Gaussian mixture model are calculated from the model parameter values as the scoring data. The defect detection method according to claim 5, wherein the threshold is the difference between the mean value of the model parameter values calculated by each repeated operation and three times the standard deviation of the scoring data. The defect detection method according to claim 1, wherein the method further comprises: marking the product image with a flawed area, and displaying the marked product image on a display screen. An electronic device, wherein the electronic device comprises: a processor; and a memory, wherein a plurality of program modules are stored in the memory, and the plurality of program modules are loaded by the processor and executed as claimed in item 1 The flaw detection method described in any one of to 7. A storage medium having at least one computer instruction stored thereon, wherein the instruction is loaded by a processor and executes the defect detection method according to any one of claim 1 to claim 7.

Images