PointFlow: A Model for Automatically Tracing Object Boundaries and Inferring Illusory Contours
In this paper, we propose a novel method for tracing object boundaries automatically based on a method called “PointFlow” in image induced vector fields. The PointFlow method comprises two steps: edge detection and edge integration. Basically, it uses an ordinary differential equation for describing the movement of points under the action of an image-induced vector field and generates induced trajectories. The trajectories of the flows allow to find and integrate edges and determine object boundaries. We also extend the original PointFlow method to make it adaptable to images with complicated scenes. In addition, the PointFlow method can be applied to infer certain illusory contours.
We test our method on real image dataset. Compared with the other classical edge detection and integration models, our PointFlow method is better at providing precise and continuous curves. The experimental results clearly exhibit the robustness and effectiveness of the proposed method.
KeywordsAutomatically tracing object boundaries Induced vector field PointFlow Differential equations Illusory contours
- 8.Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceeding on 8th International Conference of Computer Vision, vol. 2, pp. 416–423, July 2001Google Scholar
- 10.Rubner, Y., Tomasi, C.: Coalescing texture descriptors. In: ARPA Image Understanding, Workshop, pp. 927–935 (1996)Google Scholar
- 12.Ziou, D., Tabbone, S.: Edge detection techniques - an overview. Int. J. Pattern Recogn. Image Anal. 8, 537–559 (1998)Google Scholar