Journal of Systems Engineering and Electronics ›› 2018, Vol. 29 ›› Issue (1): 196-202.doi: 10.21629/JSEE.2018.01.20

• Software Algorithm and Simulation • Previous Articles     Next Articles

Pre-detection and dual-dictionary sparse representation based face recognition algorithm in non-sufficient training samples

Jian ZHAO*(), Chao ZHANG(), Shunli ZHANG(), Tingting LU(), Weiwen SU(), Jian JIA()   

  • Received:2017-01-16 Online:2018-02-26 Published:2018-02-23
  • Contact: Jian ZHAO E-mail:zjctec@nwu.edu.cn;zchaos@stumail.nwu.edu.cn;slzhang@nwu.edu.cn;201520936@stumail.nwu.edu.cn;suww523@stumail.nwu.edu.cn;jiajian@nwu.edu.cn
  • About author:ZHAO Jian was born in 1973. He received his Ph.D. degree in signal and information processing from Northwestern Polytechnical University. From 2004 to 2006, he completed his postdoctoral thesis in computer science and technology. From 2006 to 2008, he completed his postdoctoral thesis in electronic science and technology. He has also been a professor in Northwest University. His research interests include signal and information processing, computer science, Internet of Things, and information security. E-mail: zjctec@nwu.edu.cn|ZHANG Chao was born in 1992. He is currently working towards his M.S. degree in signal and information processing from Northwest University. His research interests include face recognition, digital image watermarking and machine learning. E-mail: zchaos@stumail.nwu.edu.cn|ZHANG Shunli was born in 1973. He received his Ph.D. degree in aeronautical and astronautical manufacturing engineering from Northwestern Polytechnical University in 2010. He is currently a professor at School of Information Science and Technology, Northwest University. His research interests include computed tomography, image processing and parallel computing. E-mail: slzhang@nwu.edu.cn|LU Tingting was born in 1990. She is working towards her M.S. degree in communications and information systems at Northwestern University. Her research interests include facial expression recognition and voice emotion recognition. E-mail: 201520936@stumail.nwu.edu.cn|SU Weiwen was born in 1992. She is currently working towards her M.S. degree in signal and information processing from Northwest University. Her research interests include speech recognition and pattern recognition. E-mail: suww523@stumail.nwu.edu.cn|JIA Jian was born in 1977. He received his M.S. degree in mathematics from Northwest University in 2001, and his Ph.D. degree in pattern recognition and intelligent systems from the Institute of Intelligent Information Processing of Xidian University in 2008. He is currently an associate professor in Northwest University. His current research interests include image processing and wavelet analysis. E-mail: jiajian@nwu.edu.cn
  • Supported by:
    the National Natural Science Foundation of China(61379010);the National Natural Science Foundation of China(61772421);This work was supported by the National Natural Science Foundation of China (61379010; 61772421)

Abstract:

Face recognition based on few training samples is a challenging task. In daily applications, sufficient training samples may not be obtained and most of the gained training samples are in various illuminations and poses. Non-sufficient training samples could not effectively express various facial conditions, so the improvement of the face recognition rate under the non-sufficient training samples condition becomes a laborious mission. In our work, the facial pose pre-recognition (FPPR) model and the dualdictionary sparse representation classification (DD-SRC) are proposed for face recognition. The FPPR model is based on the facial geometric characteristic and machine learning, dividing a testing sample into full-face and profile. Different poses in a single dictionary are influenced by each other, which leads to a low face recognition rate. The DD-SRC contains two dictionaries, full-face dictionary and profile dictionary, and is able to reduce the interference. After FPPR, the sample is processed by the DD-SRC to find the most similar one in training samples. The experimental results show the performance of the proposed algorithm on olivetti research laboratory (ORL) and face recognition technology (FERET) databases, and also reflect comparisons with SRC, linear regression classification (LRC), and two-phase test sample sparse representation (TPTSSR).

Key words: face recognition, facial pose pre-recognition (FPPR), dual-dictionary, sparse representation method, machine learning