Single-side light-entering-type light guide plate defect extraction method

Abstract

The invention provides a single-side light-entering-type light guide plate defect extraction method. The method comprises the following steps of acquiring a light guide plate image; extracting a lightguide plate body image; acquiring a width M and a height N; carrying out rapid defect detection; rapidly detecting whether a defect exists; removing a noise interference; carrying out gray scale transformation, OTSU threshold segmentation and automatic partition detection; traversing the gray scale range of light guide point area pixels; determining whether a light guide plate has bright and darkpoints; carrying out morphological processing; determining whether a pressing damage or a foreign matter exists; carrying out image segmentation; and determining whether a guide scratch defect existsand extracting an unaccepted product defect area. By using the exploited light-guide-plate adaptive automatic partitioning algorithm, according to the density of surface light guide holes, the different detection areas are automatically divided, a detection algorithm is automatically adjusted and defect extraction is realized. The operation efficiency and the accuracy of the algorithm are high, the stability and the robustness are high, the common defect can be identified and a high detection capability is possessed for an uncommon small defect.

Description

technical field [0001] The invention relates to a defect detection algorithm, in particular to a method for extracting defects of a single side light-incidence type light guide plate. Background technique [0002] Light Guide Plate (LGP) is made of optical-grade acrylic / PC sheet, and then high-tech materials with high reflectivity and non-absorbing light are used to engrave and V-shaped cross grid on the bottom surface of the optical-grade acrylic sheet Engraving, UV screen printing technology to print light guide dots. LGP has distinctive features such as ultra-thin, ultra-bright, uniform light guide, energy-saving, environmental protection, no dark area, durable, not easy to yellow, simple and quick installation and maintenance, etc. It is widely used in the backlight of LCD monitors, ultra-thin advertising light boxes, medical X-ray film viewer, flat-panel lighting, light effect application of bright light engineering, luminous signboard and other occasions. During 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) The factory has a high degree of reliance on quality management personnel, the mobility of operating personnel is high, and there are differences in training levels and subjective identifications among different personnel, resulting in the inability to guarantee the accuracy and consistency of detection; (5) due to the use of human eyes to identify Judgment, auxiliary measurement tools are difficult 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

In addition, the current light guide plate defect detection algorithm can only detect light guide plates with evenly arranged light guide points, but cannot detect light guide plates with one-sided light input and uneven light guide points.

Images