A Grey Weighting Density-Based Clustering Algorithm And LAO Wafer Defect Inspection Application
碩士 === 國立臺灣科技大學 === 自動化及控制研究所 === 100 === This thesis proposes Grey Weighting Density-Based Clustering Algorithm of Applications with Noise (GWDBSCAN). The algorithm uses data point gray value in four-quadrant for next growing concept of guidance. The growth direction is determined by the data point...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2012
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/72589855567977041978 |
| Summary: | 碩士 === 國立臺灣科技大學 === 自動化及控制研究所 === 100 === This thesis proposes Grey Weighting Density-Based Clustering Algorithm of Applications with Noise (GWDBSCAN). The algorithm uses data point gray value in four-quadrant for next growing concept of guidance. The growth direction is determined by the data points on the gray value, and the density-based clustering uses unclassified data points distribution direction of the trend to determine next virtual core point. The standard deviation of the image is applied to identify the background level for the LAO surface defect detection. The main inspected item is the slurry residue detection. The average standard deviation of the original image from the optical microscope is calculated. According to experimental results using five standards deviation to determine the threshold value can get best residual defects. Finally, this paper presents the GWDBSCAN clustering of image data. From the experimental results, each 1280*1024pixels of image with LAO residual defect can effectively locate position the defect and area. It also makes the grouping result more noticeable by using different color for understand any defect information. The defect conforms to the quality standard set more than 10μm.
|
|---|