Name
Abstract | ||
|---|---|---|
The aim is to design a self-adapting contrast enhancement algorithm that can remove the background noise and divide the foreground and background very well. For the self-adapting contrast enhancement algorithm, we looked for all background RGB pixel values, and found the minimum values in the RGB components so that ∂=255/min(Ipixel(R, G, B)). The results were compared to classical contrast enhancement techniques. Five steps to extract the wafer contour, respectively, were the preservation filter, self-adapting contrast enhancement, closing morphological operation, image binarization based on the Otsu method and using the first derivative extract contour. The results of contour extraction were compared with the traditional Canny, Sobel and Scharr algorithms using different parameter values. The experiment results showed that the self-adapting contrast enhancement algorithm could remove the background noise effectively compared to traditional methods. In comparison with the Canny, Sobel and Scharr algorithms, the first derivative after the original image filtering by optimized self-adapting contrast enhancement algorithm was better at extracting wafer contours. Therefore, we concluded that the wafer self-adapting contrast enhancement algorithm method was correct and feasible. The theories in this paper could be applied to image processing in the agricultural, industrial, and military fields. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1007/s11042-019-08019-9 | Multimedia Tools and Applications |
Keywords | Field | DocType |
Self-adapting, Wafer, Edge extraction, Contrast enhancement, Defect detection | Background noise,Computer science,Image processing,Sobel operator,Otsu's method,Artificial intelligence,RGB color model,Computer vision,Wafer,Pattern recognition,Algorithm,Filter (signal processing),Pixel | Journal |
Volume | Issue | ISSN |
78 | 22 | 1380-7501 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhiyong Yu | 1 | 0 | 2.03 |
| Jin Wang | 2 | 0 | 3.04 |
| Guodong Lu | 3 | 68 | 14.74 |