Title: New descriptors' combination for 3D mesh correspondence and retrieval

Authors: Roaa Soloh; Abdallah El Chakik; Hassan Alabboud; Ahmad Shahin; Adnan Yassine

Addresses: LIA Laboratory, Doctoral School of Sciences and Technology, Lebanese University, AZM Center, Mitein Street, Tripoli, Lebanon; Normandie University, UNIHAVRE, LMAH, FR CNRS 3335, ISCN, 76600, Le Havre, France ' Department of Computer Science, Beirut Arab University, Tripoli, Lebanon ' Common Core Department (Department of Applied Mathematics), Faculty of Economics and Business Administration (Branch 3), Lebanese University, Tripoli, Lebanon ' LIA Laboratory, Doctoral School of Sciences and Technology, Lebanese University, AZM Center, Mitein Street, Tripoli, Lebanon; Department of Computer Information Systems, Faculty of Business – 3, Lebanese University, Kobbeh Campus, Tripoli, Lebanon ' Normandie University, UNIHAVRE, LMAH, FR CNRS 3335, ISCN, 76600, Le Havre, France; Normandie University, UNIHAVRE, ISEL, 76600, Le Havre, France

Abstract: 3D models that are widely used nowadays are mostly represented by meshes or point clouds. These models are appearing in many fields like computer vision, informatics, engineering, as well as medicine. In this paper, we aim to find a superior one-to-one correspondence between 3D models in order to obtain optimal matching and retrieval. To do so, we detect feature points using the well known 3D Harris detector, followed by proposing a combination of local shape descriptors to form a compact feature vector for the keypoints extracted that consist of: Gaussian curvature, curvature index, and shape index. Lastly we model the matching problem as combinatorial problem solved using brute-force approach, and Hungarian one, comparing the efficiency between them. Our proposed combination of descriptors show good performance and compromise numerical values specifically using the Hungarian algorithm where its results demonstrate our proposed approach. Moreover, cosine similarity is used behind the retrieval system between these features of each pairs in the database, and our system gives accurate retrieval for several models, and acceptable percentages for others.

Keywords: 3D meshes; feature detection and extraction; matching problems; shape retrieval; Hungarian algorithm; brute-force algorithm.

DOI: 10.1504/IJCVR.2022.123845

International Journal of Computational Vision and Robotics, 2022 Vol.12 No.4, pp.377 - 396

Received: 15 Jan 2021
Accepted: 04 Jun 2021
Published online: 04 Jul 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article