Contour Grouping: Focusing on Image Patches Around Edges
Contour grouping is an important issue in computer vision. However, traditional ways tackling the problem usually fail to provide as satisfying results as human vision can do. One important feature of human vision mechanism is that human vision tends to group together edges that are not only geometrically and topologically related, but also similar in their appearances – the appearances of image patches around them including their brightness, color, texture cues, etc. But in traditional grouping approaches, after edges or lines have been detected, the appearances of image patches around them are seldom considered again, leading to the results that edges belonging to boundaries of different objects are sometimes falsely grouped together. In this paper, we introduce an appearance feature to describe the appearance of an image patch around a line segment, and incorporate this appearance feature into a saliency measure to evaluate contours on an image. The most salient contour is found by optimizing this saliency measure using a genetic algorithm. Experimental results prove the effectiveness of our approach.
Unable to display preview. Download preview PDF.
- 2.Stahl, J.S., Wang, S.: Convex grouping combining boundary and region information (2005)Google Scholar
- 3.Elder, J.H., Johnston, L.A.: Contour grouping with prior models. IEEE Trans. Pattern Anal. Machine Intell. 25 (2003)Google Scholar
- 4.Kass, M., Witkin, A., Terzopoulos, D.: Snake: active contour models. Int. J. Computer Vision, 321–331 (1988)Google Scholar
- 5.Cohen, L.D., Cohen, I.: A finite element method applied to new active contour models and 3d reconstruction form cross section. IEEE Trans. Pattern Anal. Machine Intell. 22, 764–779 (1998)Google Scholar
- 6.Osher, S., Sethian, J.: Fronts propagating with curvature dependent speed: algorithms based on hamilton-jacobi formulations (1988)Google Scholar
- 11.Liu, S., Babbs, C., Delp, E., Delp, P.: Line detection using a spatial characteristic model. IEEE Trans. Image Processing (1999)Google Scholar