A Hierarchical Object Recognition System Based on Multi-scale Principal Curvature Regions

This paper proposes a new generic object recognition system based on multi-scale affine-invariant image regions. Image segments are obtained by a watershed transform of the principal curvature of a contrast enhanced image. Each region is described by an intensity-based statistical descriptor and a PCA-SIFT descriptor. The spatial relations between regions are represented by a cluster-index distribution histogram. With these new descriptors, we develop a hierarchical object recognition system which uses an improved boosting feature selection method (Opelt et al., 2004) to construct layer classifiers by automatically selecting the most discriminative features in each layer. All layer classifiers are then combined to give the final classification. This system is tested on various object recognition problems. Experimental results show that the new hierarchical system outperforms the comparable solutions on most of the datasets tested

[1]  C. Schmid,et al.  Object Class Recognition Using Discriminative Local Features , 2005 .

[2]  Ali Shokoufandeh,et al.  View-based object recognition using saliency maps , 1999, Image Vis. Comput..

[3]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[4]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Neil A. Dodgson,et al.  The decolorize algorithm for contrast enhancing, color to grayscale conversion , 2005 .

[6]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, CVPR 2004.

[7]  Carsten Steger,et al.  An Unbiased Detector of Curvilinear Structures , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Peter Auer,et al.  Weak Hypotheses and Boosting for Generic Object Detection and Recognition , 2004, ECCV.

[9]  Shimon Ullman,et al.  Feature hierarchies for object classification , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[10]  Michel Vidal-Naquet,et al.  A Fragment-Based Approach to Object Representation and Classification , 2001, IWVF.

[11]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[12]  Guillaume Bouchard,et al.  Hierarchical part-based visual object categorization , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[13]  Dan Roth,et al.  Learning to detect objects in images via a sparse, part-based representation , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.