Robust and Efficient Detection of Salient Convex Groups
IEEE Transactions on Pattern Analysis and Machine Intelligence
Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Contour and Texture Analysis for Image Segmentation
International Journal of Computer Vision
Segmentation of Multiple Salient Closed Contours from Real Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Path-Based Clustering for Grouping of Smooth Curves and Texture Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network
Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network
CPM: A Deformable Model for Shape Recovery and Segmentation Based on Charged Particles
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pictorial Structures for Object Recognition
International Journal of Computer Vision
Salient Closed Boundary Extraction with Ratio Contour
IEEE Transactions on Pattern Analysis and Machine Intelligence
Parsing Images into Regions, Curves, and Curve Groups
International Journal of Computer Vision
Primal sketch: Integrating structure and texture
Computer Vision and Image Understanding
Hi-index | 0.03 |
We present a graph-based contour extraction algorithm for images with low contrast regions and faint contours. Our innovation consists of a new graph setup that exploits complementary information given by region segmentation and contour grouping. The information of the most salient region segments is combined together with the edge map obtained from the responses of an oriented filter bank. This enables us to define a new contour flow on the graph nodes, which captures region membership and enhances the flow in the low contrast or cluttered regions. The graph setup and our proposed region based normalization give rise to a random walk that allows bifurcations at junctions arising between region boundaries and favors long closed contours. Junctions become key routing points and the resulting contours enclose globally significant regions.