Face Recognition Research and Development

Face recognition aims to identify or verify the identity of a person through his or her face images or videos. It is one of the most important research topics in computer vision with great commercial applications [37, 59, 86, 210], like biometric authentication, financial security, access control, intelligent surveillance, etc. Because of its commercial potential and practical value, face recognition has attracted great interest from both academia and industry. The concept of face recognition probably appeared as early as 1960s [10], when researchers tried to use a computer to recognize the human face. In the 1990s and early 2000s, face recognition had rapid development and methodologies were dominated by holistic approaches (e.g., linear space [11], manifold learning [70], and sparse representations [227, 253]), which extract low-dimensional features by taking the whole face as the input.