Title :
Facial features for identification
Author :
Kouzani, A.Z. ; Nahavandi, S.
Author_Institution :
Sch. of Eng. & Technol., Deakin Univ., Geelong, Vic., Australia
Abstract :
A person identification system is presented in this paper. The system exploits the localised self-similarity in face images in order to develop an identification method. The identification method is insensitive to partial image variations that are due to translation, rotation or scale. The performance of the system is evaluated by studying the results of its application to ensembles of face images
Keywords :
biometrics (access control); face recognition; feature extraction; fractals; identification; invariance; software performance evaluation; face image ensembles; facial features; localised self-similarity; partial image variations; performance evaluation; person identification system; rotation invariance; scale invariance; translation invariance; Australia; Facial features; Hidden Markov models; Image motion analysis; Independent component analysis; Optical devices; Partitioning algorithms; Pixel; Shape; Vents;
Conference_Titel :
Systems, Man, and Cybernetics, 2000 IEEE International Conference on
Conference_Location :
Nashville, TN
Print_ISBN :
0-7803-6583-6
DOI :
10.1109/ICSMC.2000.886045
