Digital Image Processing-project-Image Segmentation
The goal of this project was to design, implement and test one of several region based segmentation algorithms on a set of images. In our work, we adopted an approach based on “Edge Flow: A Framework of Boundary Detection and Image Segmentation” by W. Ma and B. Manjunath, Proc. research CVPR, June 1997.
Edge detection and image segmentation is a crucial initial step in most computer vision applications before performing high-level tasks such as object recognition and scene interpretation. In the edge flow approach, the detection and localization of edges are performed first by identifying a flow direction at each pixel location that points to the closest boundary; then followed by the detection of locations that encounter two opposite directions of edge flow. The method based on edge flow has several salient features to solve this general problem:
a. Use a predictive coding model for identifying and integrating the different types of image boundaries;
b. Boundary detection is based on a flow field propagation;
c. Very few free parameters that control the segmentation are needed. This makes the method more appropriate for large image datasets.