Multi-scale Fourier descriptor based on arch features for shape retrieval

Zhili Song; Chaopeng Shi

doi:10.1117/12.2637505

13 May 2022 Multi-scale Fourier descriptor based on arch features for shape retrieval

Zhili Song, Chaopeng Shi

Proceedings Volume 12248, Second International Conference on Sensors and Information Technology (ICSI 2022); 1224815 (2022) https://doi.org/10.1117/12.2637505
Event: 2nd International Conference on Sensors and Information Technology (ICSI 2022), 2022, Nanjing, China

Abstract

Improving retrieval accuracy and matching efficiency are the two main goals of shape retrieval. In order to improve the accuracy of shape retrieval and the efficiency of matching, it is necessary to design a compact and discriminative shape descriptor. The Multi-Scale Arch Height (MSAH) shape descriptor has good retrieval performance, but the description of the shape is still insufficient. Therefore, a multi-scale Fourier shape descriptor based on arch features is proposed. The proposed shape descriptor fully describes the global characteristics and local details of the shape. While maintaining high retrieval accuracy, it also has high computational efficiency. We tested the proposed descriptor on MPEG-7 image library. The results demonstrate that the performance of the proposed descriptor is better than the Multi-Scale Arch Height (MSAH) shape descriptor and other classic Fourier descriptors.

Citation Download Citation

Zhili Song and Chaopeng Shi "Multi-scale Fourier descriptor based on arch features for shape retrieval", Proc. SPIE 12248, Second International Conference on Sensors and Information Technology (ICSI 2022), 1224815 (13 May 2022); https://doi.org/10.1117/12.2637505

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available