Contour Completion Around a Fixation Point
Toshiro Kubota

TL;DR
This paper introduces two algorithms for completing contours around a fixation point by finding shortest cycles in an angularly ordered graph, demonstrating promising results on natural images.
Contribution
The paper proposes two novel edge grouping algorithms for contour completion around a fixation point, improving upon previous methods by restricting search space and greedy optimization.
Findings
Algorithms successfully completed contours in natural images.
Restricted search space improved efficiency and accuracy.
Results indicate promising potential for visual contour completion tasks.
Abstract
The paper presents two edge grouping algorithms for finding a closed contour starting from a particular edge point and enclosing a fixation point. Both algorithms search a shortest simple cycle in \textit{an angularly ordered graph} derived from an edge image where a vertex is an end point of a contour fragment and an undirected arc is drawn between a pair of end-points whose visual angle from the fixation point is less than a threshold value, which is set to in our experiments. The first algorithm restricts the search space by disregarding arcs that cross the line extending from the fixation point to the starting point. The second algorithm improves the solution of the first algorithm in a greedy manner. The algorithms were tested with a large number of natural images with manually placed fixation and starting points. The results are promising.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMedical Image Segmentation Techniques · Advanced Image and Video Retrieval Techniques · Visual Attention and Saliency Detection
