Machine vision
Robust and Efficient Detection of Salient Convex Groups
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Framework for Performance Characterization of Intermediate-Level Grouping Modules
IEEE Transactions on Pattern Analysis and Machine Intelligence
Convexity rule for shape decomposition based on discrete contour evolution
Computer Vision and Image Understanding
Shape Similarity Measure Based on Correspondence of Visual Parts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Finding Perceptually Closed Paths in Sketches and Drawings
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Salient Closed Boundary Extraction with Ratio Contour
IEEE Transactions on Pattern Analysis and Machine Intelligence
Convex Grouping Combining Boundary and Region Information
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Global Detection of Salient Convex Boundaries
International Journal of Computer Vision
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
Robust photometric invariant features from the color tensor
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
Convexity represents an important principle of grouping in visual perceptual organization. This paper presents a new technique for contour grouping based on convexity and has the following two properties. Firstly it finds groupings that form contours of high convexity which are not strictly convex. Secondly it finds groupings that form both open and closed contours of high convexity. The authors are unaware of any existing technique which exhibits either of these properties. Contour grouping is posed as the problem of finding minimum cost paths in a graph. The proposed method is evaluated against two highly cited benchmark methods which find strictly convex contours. Both qualitative and quantitative results on natural images demonstrate the proposed method significantly outperforms both benchmark methods.