Abstract
Research of 3D shape retrieval has been popular recently. However, only small amount of research has focused on partial 3D shape retrieval. In this paper, we propose new features KAZE+VLAD for partial 3D shape retrieval. In KAZE+VLAD, firstly, extracts the KAZE as local features from Depth Buffer images generated from multiple view points of the 3D Object. Secondly, integrates local features into features of 3D object by encoding method. We used VLAD for encoding method. We used a modified Princeton Segmentation Benchmark, and conducted comparative experiments between our proposed and previous features.
