The Jag-Wave Feature Detection in 2D Images
Jingmin Gao, Yan Sun · 2009
In the field of image analysis and retrieval, the representations based on the shape of edge or boundary can be used to model complex forms and properties. In this paper, we give a detailed description of a new shape feature of edge or boundary, the jag-wave feature, which is usually treated as noise in image processing. The jag-wave feature is defined as a special kind of jagged or waved edge or boundary. We propose a detector of the jag-wave edge in images with the contour retrieval, ridge detection and corner detection in the color space. Finally, we give a case on jag-wave edge detector to distinguish whether the input image contains a stamp or not.