ICMR 2013 - Proceedings of the 3rd ACM International Conference on Multimedia Retrieval, 127–134. A shape-based approach for leaf classification using multiscale triangular representation. Mouine, S., Yahiaoui, I., & Verroust-Blondet, A. Robust symbolic representation for shape recognition and retrieval. Pattern Recognition Techniques, Technology and Applications. A survey of shape feature extraction techniques. As majority of the STTD formulation deals with integer arithmetic therefore simple multipliers with less area and power is suffice for its VLSI implementation, thereby, amicable for real-time applications. Exhaustive investigations on publicly available dataset namely MPEG7 Part B, Tari-1000 and Kimia’s 99 reveal consistent accuracy of 99% offered by STTD across these datasets when compared with its competitors. Then, an auto encoder operates on the constructed feature database and classifies the diverse shapes based on the intra and inter-class relationship that exist amongst the different features. Upon triangle formulation the respective features are capitulated using simple geometrical means which is then transformed into a shape histogram.
STTD dually tessellates the image into square tiles and later decomposes them into triangles. The descriptor labelled as Squared-Triangle Tessellation Descriptor (STTD), enforces strict geometrical congruency to facilitate effective feature extraction and representation. Accordingly, a simple tessellation operation that geometrically explores the spatial data for realizing efficient and precise shape descriptor is dealt in this paper.
Recent studies on shape retrieval stress for the realization of highly efficient feature descriptors realized with reduced complexity.
0 kommentar(er)
