Local shape features for object recognition

We present a shape matching algorithm based on the chamfer distance transform which can be easily integrated into the well-known SIFT framework. The shape matching was designed to overcome the limitations of SIFT matching for objects which lack texture and have the majority of their features located on the object boundary.

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

[2]  Dariu Gavrila,et al.  Real-time object detection for "smart" vehicles , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  Bernt Schiele,et al.  An Evaluation of Local Shape-Based Features for Pedestrian Detection , 2005, BMVC.

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

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

[6]  Dariu Gavrila,et al.  Multi-feature hierarchical template matching using distance transforms , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[7]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[8]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[10]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[11]  C. Schmid,et al.  Scale-invariant shape features for recognition of object categories , 2004, CVPR 2004.