Principal Curvature-Based Region Detector for Object Recognition

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 using a combination of grayscale morphological closing and a new "eigenvector flow" hysteresis thresholding. Robustness across scales is achieved by selecting the maximal 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 ...

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Hongli Deng, Wei Zhang, Eric N. Mortensen, Thomas G. Dietterich, Linda G. Shapiro
• Keywords: Computer Vision, CVPR 2007, Maximal Stable Regions, Multi-scale Principal Curvature, Principal Curvature Image, Robust Watershed Regions, Stable Watershed Regions