Paper
Detection Optimization for Biometric Applications with Non-Linear Classification Models
- Authors:
- Sorin Soviany; Cristina Soviany; Sorin Pu?coci; Mariana Jurian
- Abstract
- The paper proposes a classification method for people identification accuracy improvement in which the biometric system is trained not for all enrolled individuals but only for a few target identities to be recognized, therefore reducing the computational complexity for the large-scale biometric identification. The biometric detectors are relying on non-linear models which are more suitable for the real biometric data with high degree of intra-class variance; therefore they improve the people recognition accuracy even for the most difficult cases.
- Keywords
- Detector; Identification; Non-Linear
- StartPage
- 1
- EndPage
- 9
- Doi