Title: Physiological trait-based biometrical authentication of human-face using LGXP and ANN techniques
Authors: Rohit Raja; Tilendra Shishir Sinha; Raj Kumar Patra; Shrikant Tiwari
Addresses: Department of CSE, Sreyas Institute of Engineering and Technology, Nagole, Hyderabad, India ' Camellia Institute of Technology, Digberia, Madhyamgram, Kolkata, India ' Department of CSE, CMR Technical Campus, Kandlakoya(v) Medchal Road, Hyderabad, India ' Computer Science and Engineering, SSTC, SSGI CSVTU Raipur, Chhattisgarh State, India
Abstract: In the recent times, it has been found from the literature that, only front-view of human-face images are used for the authentication of the human being. Very little amount of work has been carried out using side-view and temporal-view of the human-face for the authentication of the human being. The main fact lies in the mentality of present youth, who are very busy in taking the photographs with different poses. Generally the poses are taken from side-view. Hence in the present paper, the main focus has been kept, in the authentication process using methods of recent trends in the field of engineering. The main objective is to handle the variability in human-face appearances due to changes in the viewing direction. Poses, illumination conditions, and expressions are considered as three main parameters, which are processed for the overall authentication process. For the overall processing, extensive feature set like texture, contrast, correlation and shape are extracted by employing modified region growing algorithm and texture feature by local Gabor XOR pattern (LGXP) and artificial neural network (ANN) technique. The present work has been analysed using the data of different subjects with varying ages.
Keywords: local Gabor XOR pattern; LGXP; modified region growing algorithm; artificial neural network; ANN; false matching rate; FMR; false non-matching rate; FNMR; genuine acceptance rate; GAR.
International Journal of Information and Computer Security, 2018 Vol.10 No.2/3, pp.303 - 320
Received: 26 Jan 2017
Accepted: 19 May 2017
Published online: 23 Apr 2018 *