OREGON STATE UNIVERSITY

You are here

Principal Curvature-Based Region Detector for Object Recognition

TitlePrincipal Curvature-Based Region Detector for Object Recognition
Publication TypeConference Paper
Year of Publication2007
AuthorsDeng, H., W. Zhang, E. N. Mortensen, T. G. Dietterich, and L. G. Shapiro
Conference Name2007 IEEE Conference on Computer Vision and Pattern Recognition
Pagination1 - 8
Date Published06/2007
PublisherIEEE
Conference LocationMinneapolis, MN
ISBN Number1-4244-1180-7
Keywordseigenvalues and eigenfunctions, image matching, object recognition
Abstract

This paper presents a new structure-based interest region detector called principal curvature-based regions (PCBR) which we use for object class recognition. The PCBR interest operator detects stable watershed regions within the multi-scale principal curvature image. To detect robust watershed regions, we "clean" a principal curvature image by combining a grayscale morphological close with our new "eigenvectorflow" hysteresis threshold. Robustness across scales is achieved by selecting the maximally stable regions across consecutive scales. PCBR typically detects distinctive patterns distributed evenly on the objects and it shows significant robustness to local intensity perturbations and intra-class variations. We evaluate PCBR both qualitatively (through visual inspection) and quantitatively (by measuring repeatability and classification accuracy in real-world object-class recognition problems). Experiments on different benchmark datasets show that PCBR is comparable or superior to state-of-art detectors for both feature matching and object recognition. Moreover, we demonstrate the application of PCBR to symmetry detection.

DOI10.1109/CVPR.2007.382972