Object-level structured contour map extraction

Authors:
R. Bergevin;A. Bubel
Affiliations:
Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, Laval University, Ste-Foy, Que., Canada G1K 7P4;Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, Laval University, Ste-Foy, Que., Canada G1K 7P4
Venue:
Computer Vision and Image Understanding
Year:
2003

Citing 20
Cited 2

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Curvature Primal Sketch

IEEE Transactions on Pattern Analysis and Machine Intelligence
Corner detection and curve representation using cubic B-spline

Computer Vision, Graphics, and Image Processing
Trace Inference, Curvature Consistency, and Curve Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
A multiscale regularity measure as a geometric criterion for image segmentation

Machine Vision and Applications
Robust and Efficient Detection of Salient Convex Groups

IEEE Transactions on Pattern Analysis and Machine Intelligence
Deformable contours: modeling, extraction, detection and classification

Deformable contours: modeling, extraction, detection and classification
Inferring global perceptual contours from local features

International Journal of Computer Vision - Special issue on computer vision research at the University of Southern California
Segmentation and classification of edges using minimum description length approximation and complementary junction cues

Computer Vision and Image Understanding
Ziplock Snakes

International Journal of Computer Vision
Multiscale contour segmentation and approximation: an algorithm based on the geometry of regular inscribed polygons

Computer Vision and Image Understanding
Part-Based 3D Descriptions of Complex Objects from a Single Image

IEEE Transactions on Pattern Analysis and Machine Intelligence
Grouping ., -, →, 0 - , into regions, curves, and junctions

Computer Vision and Image Understanding - Special issue on perceptual organization in computer vision
Generic Object Recognition: Building and Matching Coarse Descriptions from Line Drawings

IEEE Transactions on Pattern Analysis and Machine Intelligence
Detection of General Edges and Keypoints

ECCV '92 Proceedings of the Second European Conference on Computer Vision
The Role of Key-Points in Finding Contours

ECCV '94 Proceedings of the Third European Conference-Volume II on Computer Vision - Volume II
Extracting Salient Curves from Images: An Analysis of the Saliency Network

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Ground from Figure Discrimination

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
3-D Structures for Generic Object Recognition

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Detection and characterization of junctions in a 2D image

Computer Vision and Image Understanding

Detection and characterization of junctions in a 2D image

Computer Vision and Image Understanding
Shape representation by a network of V4-like cells

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new approach is proposed to extract an object-level structured contour map from the junctions in a 2D image. Local junction structures are paired in order to initialize and globally constrain the contour extraction process. An original optimization method is applied to detect and describe the contours in respect of their inherent shape and structure. Any given contour is described using a proper number of constant-curvature primitives according to the complexity of its shape. The contour map produced is represented as a graph. The characterized contours correspond to the edges of the graph and their topological structure is described by the junctions at the vertices. An elaborated experimental evaluation illustrates the capabilities of the proposed approach in demanding situations.