| Summary: | 碩士 === 國立交通大學 === 電控工程研究所 === 103 === In general, a reliable and automatic semiconductor fabrication processes is of great importance to product yield and cost reduction. In the past, we made use of human vision to do die defect detection and classification, which is hindered by the easy fatigue and fuzziness of human eyes and the decision difference between inspectors.
In this thesis, we implement a vision-based automatic defect classification system. In our defect detection component, we have used the MAD method to align the test image to the reference image. To acquire the binary defect images, we subtract the test image from the reference image, and then we convert the difference image into the binary image by setting a threshold. Moreover, we removed the scattering noises by setting a minimum number of connected noisy pixels required. Finally, we extract all defects in the test image in order to perform the defect classification.
For defect classification, we revise the Vector Quantization Algorithm with Kohonen learning rule. Because of the initial seeds have been selected randomly, it will lead to various clustering outcomes. We derive distance based vector quantization with first seed selection measure and it can obtain high classification accuracy and consistent classification result.
|
|---|
