DocumentCode :
2370395
Title :
A principal component neural network-based face recognition system and ASIC implementation
Author :
Prasanna, Chakka Siva Sai ; Sudha, N. ; Kamakoti, V.
Author_Institution :
Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., Madras, India
fYear :
2005
fDate :
3-7 Jan. 2005
Firstpage :
795
Lastpage :
798
Abstract :
Principal component analysis (PCA) finds wide usage in computer-aided vision applications and one such application is face recognition. The neural network that performs PCA is called a principal component neural network (PCNN). This paper presents a new PCNN-based face recognition system. The proposed recognition system can tolerate local variations in the face such as expression changes and directional lighting. An optimal digital hardware design is proposed for PCNN. An ASIC implementation of the proposed design yields a throughput of processing about 11,000 inputs per second during the training phase and about 19,000 inputs per second during the retrieval phase. The customized hardware-based recognition is about 105 times faster than a software-based recognition in a PC. Such results are valuable for high-speed applications.
Keywords :
application specific integrated circuits; computer vision; face recognition; neural net architecture; principal component analysis; ASIC implementation; PCA; PCNN; computer-aided vision; digital hardware design; directional lighting; face recognition system; hardware-based recognition; principal component analysis; principal component neural network; Application software; Application specific integrated circuits; Computer applications; Computer vision; Face detection; Face recognition; Hardware; Neural networks; Principal component analysis; Throughput;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
VLSI Design, 2005. 18th International Conference on
ISSN :
1063-9667
Print_ISBN :
0-7695-2264-5
Type :
conf
DOI :
10.1109/ICVD.2005.29
Filename :
1383372
Link To Document :
بازگشت