A Comprehensive Survey to Face Hallucination

• Published in: International journal of computer vision Vol. 106; no. 1; pp. 9 - 30
• Main Authors: Wang, Nannan, Tao, Dacheng, Gao, Xinbo, Li, Xuelong, Li, Jie
• Format: Journal Article
• Language: English
• Published: Boston Springer US 2014; Springer; Springer Nature B.V
• Subjects: Algorithms; Analysis; Applied sciences; Artificial Intelligence; Bayesian analysis; Biometrics; Computer Imaging; Computer Science; Computer science; control theory; systems; Customer relationship management; Exact sciences and technology; Facial recognition technology; Hallucinations; Image Processing and Computer Vision; Image processing systems; Intelligent systems; Learning and adaptive systems; Machine learning; Pattern Recognition; Pattern Recognition and Graphics; Pattern recognition. Digital image processing. Computational geometry; Security management; Studies; Surveillance; Vision; Vision systems; Face super-resolution; Heterogeneous image transformation; Face sketch-photo synthesis; Face hallucination; High resolution; Entertainment; Image processing; Image interpretation; Review; Freehand sketch; Image synthesis; Holism; Facies; Illumination; Sparse representation; Probability learning; Monitoring; Intelligent system; Bayes estimation; Computer vision; Image resolution; Subspace method; Low resolution; Police; Luminance; Surveillance; Authentication; Artificial intelligence
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-013-0645-9

This paper comprehensively surveys the development of face hallucination (FH), including both face super-resolution and face sketch-photo synthesis techniques. Indeed, these two techniques share the same objective of inferring a target face image (e.g. high-resolution face image, face sketch and face photo) from a corresponding source input (e.g. low-resolution face image, face photo and face sketch). Considering the critical role of image interpretation in modern intelligent systems for authentication, surveillance, law enforcement, security control, and entertainment, FH has attracted growing attention in recent years. Existing FH methods can be grouped into four categories: Bayesian inference approaches, subspace learning approaches, a combination of Bayesian inference and subspace learning approaches, and sparse representation-based approaches. In spite of achieving a certain level of development, FH is limited in its success by complex application conditions such as variant illuminations, poses, or views. This paper provides a holistic understanding and deep insight into FH, and presents a comparative analysis of representative methods and promising future directions.