A Flexible and Efficient Hardware Architecture for Real-Time Face Recognition Based on Eigenface
- 24 May 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 83 (21593469) , 280-281
- https://doi.org/10.1109/isvlsi.2005.5
Abstract
We describe a flexible and efficient multilane architecture for real-time face recognition system based on modular principal component analysis (PCA) method in a field programmable gate array (FPGA) environment. We have shown in Gottumukkal R., and Asan K.V., (2004) that modular PCA improves the accuracy of face recognition when the face images have varying expression and illumination. The flexible and parallel architecture design consists of multiple processing elements to operate on predefined regions of a face image. Each processing element is also parallelized with multiple pipelined paths/lanes to simultaneously compute weight vectors of the non-overlapping region, hence called multilane architecture. The architecture is able to recognize a face image from a database of 1000 face images in 11ms.Keywords
This publication has 6 references indexed in Scilit:
- A pipelined architecture for real-time correction of barrel distortion in wide-angle camera imagesIEEE Transactions on Circuits and Systems for Video Technology, 2005
- An improved face recognition technique based on modular PCA approachPattern Recognition Letters, 2004
- System level design of real time face recognition architecture based on composite PCAPublished by Association for Computing Machinery (ACM) ,2003
- Human and machine recognition of faces: a surveyProceedings of the IEEE, 1995
- Face recognition: features versus templatesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991