| Summary: | 碩士 === 國立嘉義大學 === 資訊工程學系研究所 === 97 === Image segmentation is a technique which is used to segment region of interest in the image for further image processing. In general, the accuracy of segmentation result would affect result of further image processing or applications. Contour extraction is one of the most important image segmentation methods. When applying contour extraction to application of industrial inspection or machine vision with low-level processor, we not only consider accuracy but also consider automation and computational complexity. In this study, a contour extraction method is proposed, which consist of two parts. The first part is an automatic initial contour point selection mechanism for finding the initial contour points of contour segmental method for the second part of segmental contour tracing method, where contour pixels is obtain according to gradient value, direction and distance along two initial contour points. Finally, the result of the proposed method is compared with other methods.
|
|---|
