End-Stop Exemplar Based Recognition
An approach to exemplar based recognition of visual shapes is presented. The shape information is described by attributed interest points (keys) detected by an end-stop operator. The attributes describe the statistics of lines and edges local to the interest point, the position of neighboring interest points, and (in the training phase) a list of recognition names. Recognition is made by a simple voting procedure. Preliminary experiments indicate that the recognition is robust to noise, small deformations, background clutter and partial occlusion.
- 2.S. Agerwal, D. Roth: Learning a Sparse Representation for Object Detection, Proc. 7’th ECCV, 2002, LNGS 2353, pp. 113–127Google Scholar
- 3.A. Garg, S. Agerwal, T.S. Huang: Fusion of Global and Local Information for Object Detection, Proc. 6’th Int. Conf. on Pattern Recognition, vol. 2, 2002, pp. 723–726Google Scholar
- 4.S. Belongie, J. Malik, J. Puzicha: Shape Matching and Object Recognition Using Shape Contexts, IEEE trans. PAMI, (24)24, 2002, pp. 509–521Google Scholar
- 6.D. Lowe: Object Recognition from Local Scale-Invariant Features, Proc. 7’th ICCV, 1999, pp. 1150–1157Google Scholar
- 8.C. Schmid, R. Mohr: Local Grayvalue Invariants for Image Retrieval, IEEE trans. PAMI, 19(5), 1997, pp.530–535Google Scholar