Mobile phone screen MURA defect detection method based on convolution neural network pruning algorithm

Abstract

The invention relates to a mobile phone screen MURA defect detection method based on a convolution neural network pruning algorithm. The mobile phone screen MURA defect detection method based on a convolution neural network pruning algorithm includes the steps: 1) customizing a depth convolution neural network, and utilizing the existing training data to train a neural network of detecting a mobile phone screen MURA defect; 2) utilizing an adaptive template coupling method to perform pruning operation on the convolution neural network, reducing the network scale, and reducing the algorithm running time; 3) zooming the mobile phone screen images shot by a high resolution camera, forming an image pyramid, for the image of each scale, utilizing a sliding window method to segment the images into small blocks, and taking all the small blocks of images as one group and sending the group to the convolution neural network; and 4) selecting all the characteristic images of the intermediate layer as the response images for the defect, and utilizing a threshold segmentation method to finally obtain the area position of the mobile phone screen MURA defect.

Description

technical field [0001] The invention belongs to the field of target detection and recognition, and relates to detecting a specific target from an image, in particular to a method for detecting defects on a mobile phone screen. Background technique [0002] There are many deficiencies in the traditional method of manual detection of screen defects. Today, with the rapid development of industrial production, it has been completely unable to meet the requirements of high efficiency and accuracy in today's industrial production. For mobile phone screen manufacturers, it has become an urgent need to find an efficient and accurate automatic testing equipment to replace manual testing. With the development of computer vision, image processing and other fields, the automatic detection system based on machine vision has become a good solution. This solution uses a high-resolution industrial camera to collect mobile phone screen images, and then processes the image information in rea...

AI Technical Summary

Problems solved by technology

Due to the particularity of the screen, the moiré pattern on the image is inevitable when taking pictures, and the traditional algorithm cannot solve the moiré pattern problem well

In addition, although the traditional algorithm can detect obvious linear and point-like defects, the accuracy rate is very low for the faint group-like MURA defects on imaging

Finally, the traditional screen defect detection algorithm needs to adjust a large number of parameters, especially when the screen product is changed, adjusting a large number of parameters will lead to a waste of time

Images