A High-Speed Defect Detection System With TFT LCD

碩士 === 逢甲大學 === 自動控制工程所 === 94 === The purpose of this research is to develop an automatic optical inspection system for TFT(Thin Film Transistor) LCD(Liquid Crystal Display). It uses a PC-BASED multiple threads software system. With the calculation results of image processing technology and genetic...

Full description

Bibliographic Details
Main Authors: Yao-Chang Liao, 廖燿璋
Other Authors: Chern-Sheng Lin
Format: Others
Language:zh-TW
Published: 2005
Online Access:http://ndltd.ncl.edu.tw/handle/07991349145552511752
Description
Summary:碩士 === 逢甲大學 === 自動控制工程所 === 94 === The purpose of this research is to develop an automatic optical inspection system for TFT(Thin Film Transistor) LCD(Liquid Crystal Display). It uses a PC-BASED multiple threads software system. With the calculation results of image processing technology and genetic algorithm, the system can adjust the inspection function parameters automatically, and also drive motion card to control servo motor when it moves in feedback mode. During the process of moving, it will yield a signal to notify image capturing card and line scan CCD(Charge Coupled Device).Under dual CPU systems design, it will use multiple constructions method to calculate its gray value, and also modify its tolerance. . We use an new algorithm, including closing, opening, etching, dilating, and genetic method, that assist with calculating the location and rotation angle for transistor patterns precisely and quickly. The system can adjust parameters of inspection platform according to the observed performance. The parameter adaptation occurs in parallel to the running of genetic algorithm and imaging processing methods. The proposed method is compared with the algorithms that use man-made parameter sets. It is different from existing techniques that plan the design of genetic networks. The experimental results show that the proposed method offers advantages over the other competing methods. This system brings higher quality to the LCD production line. This multipurpose image-based measurement method, using unsophisticated and economical equipment, is also verified in defect detection in the micro-fabrication process.