In this paper, entitled “TSS & TSB: Tensor scale descriptors within circular sectors for fast shape retrieval” and published at the Pattern Recognition Letters Journal, the authors propose a novel region-based descriptors for shape-based image retrieval and analysis. They focus on shape description and matching, proposing novel descriptors for pairwise matching that can be used with re-ranking techniques to boost the results, and also with combined classifier approaches.
Two descriptors are proposed: Tensor Scale Sector descriptor (TSS), in which local distributions of relative orientations within circular sectors are used to compose a fixed-length feature vector for a region-based representation; Tensor Scale Band descriptor (TSB), in which histograms of relative orientations for each circular band are used to compose a fixed-length feature vector with linear time matching.
Anderson M. Freitas, Ricardo da S. Torres, Paulo A.V. Miranda, TSS & TSB: Tensor scale descriptors within circular sectors for fast shape retrieval, Pattern Recognition Letters, Volume 83, Part 3, 1 November 2016, Pages 303-311, ISSN 0167-8655, http://dx.doi.org/10.1016/j.patrec.2016.06.005.