3D Model Retrieval Based on V System Rotation Invariant Moments

This paper proposes a novel methodology based on V-system polynomials for content-based search and retrieval of 3D objects. The V-system is composed by piecewise polynomials, and is capable of exactly describing the geometric information expressed by the popularly and widely used spline curves and surface. We define rotation invariant moments-v-system moment by combining V-system polynomials with spherical harmonics. After preprocessing for translation and scale invariance, the spherical extension is used as input for V-system moments and the values of obtained coefficients are considered as components of the feature vector. We evaluate on the Princeton Shape Benchmark, the proposed descriptors regarding computational aspects and shape retrieval performance. The-performance of the proposed method is compared to some previous approaches by means of precision/recall tests. Generally, results show that the new approach introduces improvements in the SD model retrieval process.