Palmprint Recognition using Hybrid Features with Gabor Wavelet, Wavelet Moments and Random Forest Classifier
Abstract: The identification of individuals by their palmprints, considered as a new member of the family of biometric modalities, has become a very active area of research in recent years. The work done so far has been based on palmprints image representation techniques for better classification. This paper is divided into two phases, training phase and testing phase. In training phase there are three sub processes; pre-processing, feature extraction and dimensionality reduction. Pre-processing is done with the help of image resizing and RGB to Gray conversion. For feature extraction, we have used Gabor wavelet and wavelet moments. Principal Component analysis (PCA) is used for dimensionality reduction. The extracted features are then stored in database. In the testing phase the same process is done up to the PCA and then the similarity measure with database is done. Random Forest Classifier is used for similarity measure. The MATLAB image processing tool box is used to implement proposed Palmprint recognition system.

Authors: Jahnvi Thahirani, Rohitashva Jajoo

File Name: Jahnvi_70100-18-101.pdf
 Download Abstract | Download Full Paper

© 2016 IJDACR Journal. All rights reserved.