Title: An adaptive feature combination method based on ranking order for 3D model retrieval

Authors: Qiang Chen; Bin Fang; Yinong Chen; Yan Tang

Addresses: College of Computer and Information Science, Southwest University, Tiansheng Rd. 2, 400715 Chongqing, China ' School of Computer Science, Chongqing University, Shazhengjie 174, 400030 Chongqing, China ' School of Computing, Informatics and Decision Systems Engineering, Arizona State University, P.O. Box 878809, Tempe, AZ 85287-8809, USA ' College of Computer and Information Science, Southwest University, Tiansheng Rd. 2, 400715 Chongqing, China

Abstract: Directly combining several complementary features may increase the retrieval precision for 3D models. However, in most cases, we need to set the weights manually and empirically. In this paper, we propose a new schema for automatically choosing the proper weights for different features on each database. The proposed schema utilises the ranking order of the retrieval results, and it is invariant to the magnitude scaling. We choose the best feature as the standard one, and the relevance values between the standard and other features are the weights for feature combination. Furthermore, we propose an improved re-ranking algorithm for further improving the retrieval performance. Experiment shows the proposed method can automatically choose the proper weights for different features, and the experiment results on the existing features exceed the benchmark.

Keywords: 3D retrieval; re-ranking; ranking order; feature combination.

DOI: 10.1504/IJCSE.2019.10026145

International Journal of Computational Science and Engineering, 2019 Vol.20 No.4, pp.516 - 525

Received: 17 Jun 2017
Accepted: 15 Sep 2017

Published online: 12 Jan 2020 *

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