System design and assessment methodology for face recognition algorithms

Authors:
Hyeonjoon Moon
Affiliations:
Center for Emotion Recognition and Robot Vision (CERRV), School of Computer Engineering, Sejong University, Seoul, Korea
Venue:
SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
Year:
2004

Citing 8
Cited 0

Introduction to statistical pattern recognition (2nd ed.)

Introduction to statistical pattern recognition (2nd ed.)
Example-Based Learning for View-Based Human Face Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Filtering for Texture Classification: A Comparative Study

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Verification Protocol and Statistical Performance Analysis for Face Recognition Algorithms

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
A Virtual Mirror Interface Using Real-Time Robust Face Tracking

FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Beyond Eigenfaces: Probabilistic Matching for Face Recognition

FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Performance evaluation methodology for face recognition algorithms

Performance evaluation methodology for face recognition algorithms
Statistical approach to shape from shading: Reconstruction of three-dimensional face surfaces from single two-dimensional images

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

For biometric person authentication, system design and assessment methodology form essential part of the entire process We design a performance evaluation methodology for face recognition system based on identification and verification model To validate our model, we designed a projection-based face recognition system which requires numerous design decisions We explicitly state the design decisions by introducing a generic modular face recognition system We explore various implementations for preprocessing, representation and recognition modules Our experiment includes major factors for system design and assessment: (1) changing the illumination normalization preprocessing; (2) varying the number of features in the representation; and (3) changing the similarity measure in recognition process We perform experiments and present results for identification and verification scenarios.