Defect Detection Method Of LCD Complex Display Screen Combining Feature Matching and Color Correction

Abstract

Aiming at the defect detection problem in the complex detection picture of LCD, a defect detection method of complex display picture combining feature matching and color correction is proposed in this paper. Firstly, the image registration method of Speeded Up Robust Features (SURF) and projection transformation is used for high-precision geometric registration between the detected image and the standard image; Secondly, the average brightness of the RGB three channels of the image is calculated respectively, and the image color correction of adaptive histogram matching is proposed. The histogram of the low brightness channel is specified as the histogram of the high brightness channel, and the final registered image pair is obtained. Finally, support vector machine (SVM) is used to classify the residual image to obtain the binary image of defect detection. The experimental results show that the proposed method can detect complex picture display defects under illumination change and geometric distortion, the detection accuracy is 99.43%, and the recall rate is 86.19%; It has engineering application prospect.