The Detection and Classification of Lead Frame Defects Using Neural Networks

• Main Authors: Fuji Chuang, 莊富傑
• Other Authors: CHIOU, YIH-CHIH
• Format: Others
• Language: zh-TW
• Published: 1999
• Online Access: http://ndltd.ncl.edu.tw/handle/44883327211863894990

碩士 === 中華大學 === 機械與航太工程研究所 === 87 === As the pitch getting finer and the lead number getting higher, the inspection of IC lead frame using bare eyes becomes more difficult. To lessen the workload of human inspectors, an effective method for the detection and classification of defects is presented. First, the proposed method uses image-processing techniques such as image enhancement, image segmentation, edge detection, morphological operation, and labeling to locate defects. Next, feature extraction techniques are applied to measure such features as perimeter, moments, area, eccentricity, compactness, roughness, and standard deviation of gray level. Finally, by inputting the extracted features of each defect to a pre-trained feedforward backpropagation network, the defect can be classified into pinhole, scratch, or contamination. To automate the inspection process, image processing, feature extraction, artificial neural network, as well as stage and light source control techniques have been integrated into an effective defect detection and classification system. The experimental results show that on an average, the system can finish inspecting an image in 0.4 second and the recognition rate is 99.22%. In summary, the developed system not only can replace the convention inspection method, but also increase the accuracy and efficiency of lead frame inspection.