Fundamentals of digital image processing
Fundamentals of digital image processing
What Size Test Set Gives Good Error Rate Estimates?
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital compression for multimedia: principles and standards
Digital compression for multimedia: principles and standards
Journal of Cognitive Neuroscience
Pattern Recognition
On the Relevance of Facial Expressions for Biometric Recognition
Verbal and Nonverbal Features of Human-Human and Human-Machine Interaction
Biometric Face Recognition with Different Training and Testing Databases
Verbal and Nonverbal Features of Human-Human and Human-Machine Interaction
Biometric dispersion matcher versus LDA
Pattern Recognition
On-line signature verification system with failure to enrol management
Pattern Recognition
Application of Kekre's fast code book generation algorithm for face recognition
Proceedings of the International Conference and Workshop on Emerging Trends in Technology
Low-complexity algorithms for biometric recognition
COST 2102'07 Proceedings of the 2007 COST action 2102 international conference on Verbal and nonverbal communication behaviours
Biometric system verification close to "real world" conditions
BioID_MultiComm'09 Proceedings of the 2009 joint COST 2101 and 2102 international conference on Biometric ID management and multimodal communication
Gender recognition using PCA and DCT of face images
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part II
Biometric database acquisition close to “real world” conditions
COST'09 Proceedings of the Second international conference on Development of Multimodal Interfaces: active Listening and Synchrony
Hi-index | 0.10 |
In this paper we propose a low-complexity face verification system based on the Walsh-Hadamard transform. This system can be easily implemented on a fixed point processor and offers a good compromise between computational burden and verification rates. We have evaluated that with 36 integer coefficients per face we achieve better Detection Cost Function (6.05%) than the classical eigenfaces approach (minimum value 6.99% with 126 coefficients), with a smaller number of coefficients.