Detection device of display panel and detection method thereof, electronic device and readable medium

1. A detection device of a display panel, comprising:

an image receiver configured to receive a detection image of a display panel to be detected; and

a detector configured to input the detection image of the display panel to be detected into a detection model and generate a detection result by the detection model, the detection model being pre-constructed and configured to detect the display panel;

wherein the detection model comprises:

a defect classification identification sub-model configured to identify a classification of a defect of the display panel to be detected;

a defect position identification sub-model configured to mark a position of the defect of the display panel to be detected;

wherein the defect classification identification sub-model comprises a plurality of base models and a secondary model;

the plurality of base models are configured to determine an initial classification of the defect of the display panel to be detected; and

the secondary model is configured to determine a final classification of the defect of the display panel to be detected according to input data obtained by integrating output data of the plurality of base models.

2. The detection device of claim 1 , wherein the plurality of base models are based on a same Convolutional Neural Network model, and different base models are obtained by respectively training the Convolutional Neural Network model with a plurality of first training data sets satisfying different probability distributions.

3. The detection device of claim 2 , wherein the plurality of first training data sets comprise sample sets obtained by respectively sampling an original data set according to different predetermined sampling ratios, the different predetermined sampling ratios are sampling ratios of detection images of different classifications of defects determined according to the different probability distributions, and the original data set comprises a plurality of detection images of different display panels with known defects.

4. The detection device of claim 3 , wherein the Convolutional Neural Network model comprises a fully-connected layer, a supplementary convolution layer, a batch normalization layer, and a random discard layer;

the supplementary convolution layer is configured to convolve data to be input into the fully-connected layer such that the data convolved by the supplementary convolution layer meets an input dimension of the fully-connected layer;

the batch normalization layer is configured to normalize the data to be input into the fully-connected layer;

the random discard layer is configured to randomly discard a part of neural network units of the Convolutional Neural Network model to avoid overfitting; and

when the Convolutional Neural Network model is trained, the fully-connected layer is initialized with a first algorithm, the fully-connected layer is regularized with a second algorithm, and the supplementary convolution layer is initialized with a third algorithm.

5. The detection device of claim 2 , wherein the Convolutional Neural Network model comprises a fully-connected layer, a supplementary convolution layer, a batch normalization layer, and a random discard layer;

the supplementary convolution layer is configured to convolve data to be input into the fully-connected layer such that the data convolved by the supplementary convolution layer meets an input dimension of the fully-connected layer;

the batch normalization layer is configured to normalize the data to be input into the fully-connected layer;

the random discard layer is configured to randomly discard a part of neural network units of the Convolutional Neural Network model to avoid overfitting; and

when the Convolutional Neural Network model is trained, the fully-connected layer is initialized with a first algorithm, the fully-connected layer is regularized with a second algorithm, and the supplementary convolution layer is initialized with a third algorithm.

6. The detection device of claim 1 , wherein the secondary model is a classifier comprising a plurality of fully-connected layers and a normalized exponential function layer.

7. The detection device of claim 1 , wherein the defect position identification sub-model is an object detector.

8. A detection method of a display panel, comprising:

inputting a detection image of a display panel to be detected into a detection model and detecting the display panel to be detected, the detection model being pre-constructed and configured to detect the display panel;

wherein the detection model comprises:

a defect classification identification sub-model configured to identify a classification of a defect of the display panel to be detected;

a defect position identification sub-model configured to mark a position of a defect of the display panel to be detected; and

wherein the defect classification identification sub-model comprises a plurality of base models and a secondary model;

the plurality of base models are configured to respectively determine an initial classification of the defect of the display panel to be detected; and

the secondary model is configured to determine a final classification of the defect of the display panel to be detected according to input data obtained by integrating output data of the plurality of base models.

9. The detection method of claim 8 , wherein the plurality of base models are obtained by respectively training a same Convolutional Neural Network model with a plurality of first training data sets satisfying different probability distributions.

10. The detection method of claim 9 , further comprising generating the plurality of first training data sets, which comprises:

generating an original data set comprising a plurality of detection images of different display panels with known defects;

respectively determining sampling ratios of detection images of different classifications of defects corresponding to a plurality of probability distributions; and

respectively sampling the original data set according to the sampling ratios of the detection images of different classifications of defects to obtain the plurality of first training data sets.

11. The detection method of claim 10 , wherein the Convolutional Neural Network model comprises a fully-connected layer, a supplementary convolution layer, a batch normalization layer and a random discard layer;

the supplementary convolution layer is configured to convolve data to be input into the fully-connected layer such that the data convolved by the supplementary convolution layer meets an input dimension of the fully-connected layer;

the batch normalization layer is configured to normalize the data to be input into the fully-connected layer;

the random discard layer is configured to randomly discard a part of neural network units of the Convolutional Neural Network model to avoid overfitting; and

when the Convolutional Neural Network model is trained, the fully-connected layer is initialized with a first algorithm, the fully-connected layer is regularized with a second algorithm, and the supplementary convolution layer is initialized with a third algorithm.

12. An electronic device, comprising:

one or more processors;

a memory, storing one or more programs, which when executed by the one or more processors, cause the one or more processors to perform the detection method of a display panel of claim 10 ; and

one or more I/O interfaces connected between the one or more processors and the memory and configured to exchange information between the one re more processors and the memory.

13. The detection method of claim 9 , wherein the Convolutional Neural Network model comprises a fully-connected layer, a supplementary convolution layer, a batch normalization layer and a random discard layer;

the supplementary convolution layer is configured to convolve data to be input into the fully-connected layer such that the data convolved by the supplementary convolution layer meets an input dimension of the fully-connected layer;

the batch normalization layer is configured to normalize the data to be input into the fully-connected layer;

the random discard layer is configured to randomly discard a part of neural network units of the Convolutional Neural Network model to avoid overfitting; and

when the Convolutional Neural Network model is trained, the fully-connected layer is initialized with a first algorithm, the fully-connected layer is regularized with a second algorithm, and the supplementary convolution layer is initialized with a third algorithm.

14. An electronic device, comprising:

one or more processors;

a memory, storing one or more programs, which when executed by the one or more processors, cause the one or more processors to perform the detection method of a display panel of claim 13 ; and

one or more I/O interfaces connected between the one or more processors and the memory and configured to exchange information between the one re more processors and the memory.

15. An electronic device, comprising:

one or more processors;

a memory, storing one or more programs, which when executed by the one or more processors, cause the one or more processors to perform the detection method of a display panel of claim 9 ; and

one or more I/O interfaces connected between the one or more processors and the memory and configured to exchange information between the one re more processors and the memory.

16. The detection method of claim 8 , wherein the secondary model is a classifier comprising a plurality of fully-connected layers and a normalized exponential function layer.

17. An electronic device, comprising:

one or more processors;

a memory, storing one or more programs, which when executed by the one or more processors, cause the one or more processors to perform the detection method of a display panel of claim 16 ; and

one or more I/O interfaces connected between the one or more processors and the memory and configured to exchange information between the one re more processors and the memory.

18. The detection method of claim 8 , wherein the defect position identification sub-model is an object detector.

19. An electronic device, comprising:

one or more processors;

a memory, storing one or more programs, which when executed by the one or more processors, cause the one or more processors to perform the detection method of a display panel of claim 8 ; and

one or more I/O interfaces connected between the one or more processors and the memory and configured to exchange information between the one re more processors and the memory.

20. A non-transitory computer-readable storage medium, storing a computer program, which when executed by a processor, causes the processor to perform the detection method of a display panel of claim 8 .