We present a novel approach to the problem of establishing the best match between an open contour and a part of a closed contour. At the heart of the proposed scheme lies a novel shape descriptor that also permits the quantification of local scale. Shape descriptors are computed along open or closed contours in a spatially non-uniform manner. The resulting ordered collections of shape descriptors constitute the global shape representation. A variant of an existing DTW matching technique is proposed to handle the matching of shape representations. Due to the properties of the employed shape descriptor, sampling scheme and matching procedure, the proposed approach performs partial shape matching that is invariant to Euclidean transformations, starting point as well as to considerable shape deformations. Additionally, the problem of matching closed-to-closed contours is naturally treated as a special case. Extensive experiments on benchmark datasets but also in the context of specific applications, demonstrate that the proposed scheme outperforms existing methods for the problem of partial shape matching and performs comparably to methods for full shape matching.
A video with sample qualitative results.
Download video showing human upper body detection, as an application of the proposed partial shape matching method.
Download video showing hand posture recognition, as an application of the proposed partial shape matching method.
Follow this link to see the results of the proposed method on the exhaustive MPEG7 shape classification experiment. The first shape in each line is a query shape. The rest 40 shapes are those retrieved by the proposed method in the order of decreasing similarity. There exist 1400 rows, one for each of the 1400 shapes of the MPEG7 dataset. A red vertical line separates the first 20 matches from the rest, since in the MPEG7 dataset, there exist 20 shapes in each shape class. Matches have been obtained before the application of graph transduction (GT), so that the merit of the proposed method can be assessed without the improvement introduced by GT.
- Michel Damien, Iasonas Oikonomidis, Antonis Argyros.
- This work was partially supported by the IST-FP7-IP-215821 project GRASP.
- D. Michel, I. Oikonomidis, A.A. Argyros, “Scale invariant and deformation tolerant partial shape matching”, in Image and Vision Computing Journal, Elsevier.
The electronic versions of the above publications can be downloaded from my publications page.