Automatic Image Alignment System and Defect Inspection of Wafer Surface and Optical Mask by Using Probability Neural Network With Image Operations

• Main Authors: Jian Yu Luo, 駱建宇
• Other Authors: Mu Jung Chen
• Format: Others
• Language: zh-TW
• Published: 2011
• Online Access: http://ndltd.ncl.edu.tw/handle/02666418127231131041

碩士 === 明新科技大學 === 精密機電工程研究所 === 99 === This research proposes self-learning methods to inspect defects of wafer surfaces and optical masks by using probability neural network (PNN) with image operations. The research includes the integration of mechanical, optical and electronic hardware, and development of automatic image alignment and defect inspection methods. In the aspect of automatic image alignment, the alignment system employs a CCD camera to capture the images of PCB boards and processes the original images through threshold, particle filter and Laplacian filter for image enhancement. According to the offsets of the PCB holes, the system can drive a three-axis positioning stage for image alignment to replace the traditional manual and mechanical alignment methods. In the aspect of defect inspection, the image complexity of the background and noises of wafer surfaces and optical masks image can be reduced by image processing. Through calculating feature parameters for horizontal and vertical line-type subimages, the feature parameters were also considered as the input parameters of the PNN. Finally, the inspection systems of wafer surface and optical mask were successfully established and defects can be classified. Experimental results show that the developed method can successfully isolate and inspect the defects of wafer surfaces and optical masks.