Title :
Principal Curvature-Based Region Detector for Object Recognition
Author :
Deng, Hongli ; Zhang, Wei ; Mortensen, Eric ; Dietterich, Thomas ; Shapiro, Linda
Author_Institution :
Oregon State Univ., Corvallis
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.
Keywords :
eigenvalues and eigenfunctions; image matching; object recognition; benchmark datasets; eigenvectorflow hysteresis threshold; feature matching; object recognition; principal curvature image; principal curvature-based region detector; robust watershed region; Biomedical imaging; Computer vision; Detectors; Gray-scale; Hysteresis; Image edge detection; Inspection; Noise robustness; Object detection; Object recognition;
Conference_Titel :
Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on
Conference_Location :
Minneapolis, MN
Print_ISBN :
1-4244-1179-3
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2007.382972