Title :
Eye-Distance Based Mask Selection for Person Identification
Author :
Rahman, Khandaker Abir ; Hossain, Md Shafaeat ; Bhuiyan, Md Al-Amin ; Zhang, Tao ; Hasanuzzaman, Md ; Ueno, H.
Author_Institution :
Dept. of Comput. Sci. & Eng., Univ. of Dhaka, Dhaka, Bangladesh
Abstract :
This paper presents a multi-resolution masks based pattern matching method for person identification. The system is commenced with the construction of multi-resolution mask cluster pyramid, where the mask size is chosen depending on the distance between two eyes, computed from the detected face. Experimental results show the effectiveness of the system with significantly higher precision, recall rates and matching probability comparing with conventional single resolution mask based person identification systems.
Keywords :
biometrics (access control); distance measurement; eye; face recognition; image resolution; probability; eye-distance based mask selection; face detection; multiresolution mask cluster pyramid; pattern matching method; person identification; probability; Automation; Computational efficiency; Computer science; Convolution; Electronic mail; Eyes; Face detection; Informatics; Pattern matching; Principal component analysis; multi-resolution masks; person identification; single resolution mask;
Conference_Titel :
Multimedia and Ubiquitous Engineering, 2009. MUE '09. Third International Conference on
Conference_Location :
Qingdao
Print_ISBN :
978-0-7695-3658-3
DOI :
10.1109/MUE.2009.30