Sketch face recognition based on domain adaptation scaled entropy meta-network

• Published in: Measurement and control (London) Vol. 56; no. 5-6; pp. 953 - 965
• Main Authors: Cao, Lin, Chen, Changwu, Guo, Yanan, Du, Kangning
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 01.05.2023; Sage Publications Ltd; SAGE Publishing
• Subjects: Adaptation; Deep learning; Domains; Entropy; Face recognition; Machine learning; Sketches; Teaching methods; Training; generalized entropy loss; domain adaptation; meta learning; Sketch face recognition
• ISSN: 0020-2940; 2051-8730
• DOI: 10.1177/00202940221097979

In recent years, sketch face recognition has a wide application in law enforcement agencies and criminals. Deep learning plays a crucial role in the recent developments of face recognition, however, it is challenging to employ deep learning methods for sketch face recognition due to insufficient face photo–sketch data. Moreover, compared to photos, sketches lack detailed texture, and there exists a domain gap between photos and sketches, hence, traditional homogeneous face recognition methods perform poorly in sketch face recognition. In this paper, a novel deep learning method termed Domain Adaptation Scaled Entropy Meta-Network (DASEMN) is proposed to tackle sketch face recognition tasks. Specifically, a meta-learning training strategy is designed to tackle the few-shot problem and improve the generalization ability of the network. Then, a generalized entropy loss termed scaled mean entropy loss is proposed to guide the network to extract discriminate features. Finally, a domain adaptation module is introduced in the training set to reduce the domain gap between the sketch domain and the photo domain. Experiments on UoM-SGFS and CUFSF sketch face databases show that the proposed method is superior to other sketch face recognition methods.