A face attribute based recommendation system via integrating denoising autoencoder and hash coding. (March 2021)

• Record Type: Journal Article
• Authors: Liu, Fan; Chen, Zhiyu; Ding, Yuhua; Yang, Sai; Zhang, Tao
• Is Part Of: Computers & electrical engineering. Volume 90(2021)
• Publication Date: 2021-03
• Subjects: Recommendation -- Denoising autoencoder -- Face attribute -- Hash coding; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107020
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: The involvement of face attributes makes the system be used offline, and users do not have to log into an account. For the new user whose history data is unavailable, face attributes help the system make more accurate predictions because the user's expression can be regarded as the rating to the item. The proposed denoising autoencoder with hash coding and face attributes (DAE-H-Face) can extract compact binary user features, which can improve the computing efficiency. And the imposed hash constraint can reduce the information loss during the hash coding of DAE. The features from DAE-H-Face and DAE can further guarantee the representation ability and computing efficiency simultaneously. Graphical abstract: Abstract: Nowadays, with the rapid development of commerce, how to effectively improve the performance of an recommendation system has aroused great concern. However, traditional recommendation system requires users to log in their accounts, which brings poor user experience. This paper presents a novel recommendation system by using face recognition technologies to extract face attribute information as the input automatically. The system first obtains the user information of identity, gender, age, and then gets feedback by expression analysis. Based on the acquired face attributes, we propose to extract compact binary user features by integrating denoising autoencoder and hash coding, which can effectively improve the computing efficiency.The hash features from DAE-H-Face and DAE are further combined to enhance the representation ability. Finally, Hamming similarity-based collaborative filtering is used for recommendation. Experimental results on the MovieLens database show that the proposed recommendation method has better effectiveness and robustness. Moreover, the results also demonstrate its advantages to the cold start problem.