Scale-invariant shape features for recognition of object categories

We introduce a new class of distinguished regions based on detecting the most salient convex local arrangements of contours in the image. The regions are used in a similar way to the local interest points extracted from gray-level images, but they capture shape rather than texture. Local convexity is characterized by measuring the extent to which the detected image contours support circle or arc-like local structures at each position and scale in the image. Our saliency measure combines two cost functions defined on the tangential edges near the circle: a tangential-gradient energy term, and an entropy term that ensures local support from a wide range of angular positions around the circle. The detected regions are invariant to scale changes and rotations, and robust against clutter, occlusions and spurious edge detections. Experimental results show very good performance for both shape matching and recognition of object categories.

[1]  Keiichi Abe,et al.  Parts of planar shapes , 1996, Pattern Recognit..

[2]  Tony Lindeberg,et al.  Scale selection for differential operators , 1994 .

[3]  Andrea Salgian,et al.  A Perceptual Grouping Hierarchy for Appearance-Based 3D Object Recognition , 1999, Comput. Vis. Image Underst..

[4]  Yehezkel Lamdan,et al.  Object recognition by affine invariant matching , 2011, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  David A. Forsyth,et al.  Canonical Frames for Planar Object Recognition , 1992, ECCV.

[6]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

[7]  Bernt Schiele,et al.  Analyzing appearance and contour based methods for object categorization , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[8]  Chin-Chen Chang,et al.  A shape recognition scheme based on relative distances of feature points from the centroid , 1991, Pattern Recognition.

[9]  Cordelia Schmid,et al.  Shape recognition with edge-based features , 2003, BMVC.

[10]  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..

[11]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  H. Blum.  Biological shape and visual science. I. , 1973, Journal of theoretical biology.

[13]  Shimon Ullman,et al.  Recognizing solid objects by alignment with an image , 1990, International Journal of Computer Vision.

[14]  Martial Hebert,et al.  Shape-based recognition of wiry objects , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Rachid Deriche,et al.  Using Canny's criteria to derive a recursively implemented optimal edge detector , 1987, International Journal of Computer Vision.

[16]  H. Barlow.  Vision Science: Photons to Phenomenology by Stephen E. Palmer , 2000, Trends in Cognitive Sciences.

[17]  Ralph Roskies,et al.  Fourier Descriptors for Plane Closed Curves , 1972, IEEE Transactions on Computers.

[18]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.