Visual inspection method for defects of double-side incident light guide plate

Abstract

The present invention provides a double-side light incident type light guide plate defect visual detection method, which simultaneously detects the line-scan grayscale image of the light guide plate and the area array grayscale image of the light guide plate, and the line-scan grayscale image of the light guide plate can detect scratches, For subtle defects such as crushing, bright and dark spots, etc., the area array grayscale image of the light guide plate can detect whether there is a dark shadow on the light guide plate after being illuminated. The invention has strong adaptability to changes in illumination and light guide plate types; Simultaneous detection improves the detection accuracy without increasing the detection time; the detection accuracy is greatly improved; the invention has high operating efficiency, strong stability and robustness, and can not only identify common defects, but also identify small defects that are not common It has relatively high detection ability.

Description

technical field [0001] The invention relates to a method for extracting surface defects of a light guide plate based on machine vision technology, which belongs to the field of computer vision, in particular to a defect detection algorithm. Background technique [0002] The main material of Light Guide Plate (LGP) is optical acrylic (PMMA) plate, and its chemical name is methyl methacrylate. The transparent acrylic plate after special scientific processing, as long as it is installed on the side The illuminant (ordinary fluorescent tube, CCFL cold cathode tube, light-emitting diode and other light sources can be selected depending on the size of the light guide plate, generally installed on both sides of the length), the entire plane of the acrylic plate will emit bright, uniform and soft light after power on. Transparent acrylic sheet has high light transmittance, strong expansion and impact ability, and is widely used in the screens of various electronic products. In the ...

AI Technical Summary

Problems solved by technology

There are many limitations and problems in manual detection: (1) The working environment of the employees is poor, and the strong light operation is easy to make the employees' eyesight worse, which may cause the employees to suffer from occupational diseases for a long time; Defects have high requirements on the skills and experience of employees, and it is not easy for employees to master work skills; (3) Affected by employee experience, work mood fluctuations, and reduced concentration, it is not easy to intercept all product defects, resulting in product quality fluctuations; ( 4) Due to the use of human eye recognition judgments, it is difficult for auxiliary measurement tools to form quantifiable quality standards

Using Curvelet transform, non-subsampling Contourlet transform, shearlet transform, wavelet transform and multi-scale analysis technology, the operation efficiency of the algorithm cannot meet the requirements, and it is difficult to realize in the embedded system; the correct recognition rate of some surface defects is relatively low, and the accuracy cannot be satisfied Require

Images