What Size Test Set Gives Good Error Rate Estimates?
IEEE Transactions on Pattern Analysis and Machine Intelligence
Making large-scale support vector machine learning practical
Advances in kernel methods
Biometric Identification through Hand Geometry Measurements
IEEE Transactions on Pattern Analysis and Machine Intelligence
Biometrics, Personal Identification in Networked Society: Personal Identification in Networked Society
Biometrics
An introduction to biometric recognition
IEEE Transactions on Circuits and Systems for Video Technology
| Hi-index | 0.00 |
A biometric verification system based on the hand knuckles texture is presented in this paper. The system selects the knuckles area of the hand image and work out three different versions of the image called: gray scale, enhance black and white, and Gabor filtered. The first 15 by 15 DCT coefficients of each knuckle image version are obtained and save as three different feature sets. In order to verify the claimed identity, a support vector machine for feature set is used and the three schemes are combined at score level. The system has been tested with a multisession database which contains 42 individuals. Training with the first session images and testing with the second and third session images the system reaches an EER equal to 2, 86%.