No abstract

No abstract

No abstract

In the present scenario, multimodal biometric authentication is one of the emerging fields, which is applied in different applications like prison security, criminal identification, banking security, etc. The objective of this research work is to develop an effective feature selection algorithm to determine the optimal feature values for further improving the performance of multimodal biometric authentication. Initially, the input images were collected from Chinese Academy of Science Institute for Automation (CASIA) dataset. Then, feature extraction was carriedout by using Local Binary Pattern (LBP), minutiae feature extraction, Histogram of Oriented Gradient (HOG), and Gray-Level Co-Occurrence Matrix (GLCM) features like cluster prominence, Inverse Difference Moment Normalized (IDMN), and autocorrelation. After feature extraction, modified reliefF feature selection algorithm was used for rejecting the irrelevant features or for choosing the optimal features. In modified algorithm, Chebyshev distance measure was utilized instead of Manhattan distance in order to find the nearest miss and nearest hit instances. At last, the optimal feature values were given as the input for Multi-Support Vector Machine (MSVM) classifier for classifying an individual as an authorized or unauthorized person. The experimental result showed that the proposed system improved the classification accuracy up to 7% as related to the existing systems in terms of accuracy.

No abstract