Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Attention-modulated triplet network for face sketch recognition

Fan, Liang, Sun, Xianfang ORCID: https://orcid.org/0000-0002-6114-0766 and Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884 2021. Attention-modulated triplet network for face sketch recognition. IEEE Access 9 , 12914 - 12921. 10.1109/ACCESS.2021.3049639

[thumbnail of 09316170.pdf] PDF - Published Version
Available under License Creative Commons Attribution.

Download (6MB)

Abstract

In this paper, a novel triplet network is proposed for face sketch recognition. A spatial pyramid pooling layer is introduced into the network to deal with different sizes of images, and an attention model on the image space is proposed to extract features from the same location in the photo and sketch. Our attention mechanism builds and improves recognition accuracy by searching similar regions of the images, which include abundant information in order to distinguish different persons in photos and sketches. So that the cross-modality differences between photo and sketch images are reduced when they are mapped into a common feature space. Our proposed solution is tested on composite face photo-sketch datasets, including UoM-SGFS and e-PRIP dataset, and achieves better performance than the state-of-the-art result. Especially for Set B in UoM-SGFS dataset, the accuracy is higher than 81%.

Item Type: Article
Date Type: Published Online
Status: Published
Schools: Computer Science & Informatics
Additional Information: This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
Publisher: Institute of Electrical and Electronics Engineers
ISSN: 2169-3536
Date of First Compliant Deposit: 5 July 2021
Date of Acceptance: 31 December 2020
Last Modified: 08 May 2023 13:14
URI: https://orca.cardiff.ac.uk/id/eprint/142312

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics