A K-Means Clustering Based Shape Retrieval Technique for 3d Mesh Models

Abstract

Due to the large size of shape databases, importance of effective and robust method in shape retrieval has been increased. Researchers mainly focus on finding descriptors which is suitable for rigid models. Retrieval of non-rigid models is a still challenging field which needs to be studied more. For non-rigid models, descriptors that are designed should be insensitive to different poses. For nonrigid model retrieval, we propose a new method which first divides a model into clusters using geodesic distance metric and then computes its descriptor using the area of these clusters. A skeleton-based Kmeans clustering method is utilized for dividing the model into clusters. Each cluster is represented by an area based descriptor which is invariant to scale and orientation. Articulated objects from human to animals are employed in this study's experiments for the validation of the proposed retrieval algorithm.

A Robust Scheme for 3D Point Cloud Copy Detection

“…Rich surface and hidden geometric/graph structure amply depict the discrepancy among shapes. The shape descriptors mentioned in [51] are practical in retrieval for polygon meshes and point clouds, e.g., global information [32], local features [11,43,39,12], Zernike moment [30], distribution [33,27], skeleton [37], topology [3,41]. Recently, deep learning methods for 3D shape retrieval based on shape structure have been proposed.…”