Boosting contextual information in content-based image retrieval
Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval
A New Accumulator-Based Approach to Shape Recognition
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
Human Activity Recognition Using the 4D Spatiotemporal Shape Context Descriptor
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
Finger recognition for hand pose determination
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Improving motion-based object detection by incorporating object-specific knowledge
International Journal of Intelligent Information and Database Systems
CAD model visual registration from closed-contour neighborhood descriptors
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part II
Automatic registration of large-scale multi-sensor datasets
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
Palette power: enabling visual search through colors
Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining
Hi-index | 0.00 |
This paper outlines a novel approach to the analysis of shape which addresses the following constituents of a theory of shape: flexible shape representation is achieved by stochastic sampling of contours and by attaching a particularly rich descriptor, the shape context, to each point. The shape context captures the distribution of shape points relative to the reference point and thus offers a globally discriminative characterization for each shape point. The proposed shape descriptor allows for a highly effective procedure that recovers shape correspondences by employing a weighted bipartite matching procedure. An established point correspondence then allows us to recover the optimal transformation between shapes. Regularized thin-plate splines provide a flexible class of transformation maps and are discussed in detail. Finally, we treat shape similarity and shape recognition in some detail. Results are presented for silhouettes, trademarks, handwritten digits and the COIL dataset.