Abstract: The increasing applications of Face recognition system in various fields are the motivating factor for me to propose new methods to improve the recognizing rate of the face images. The aim of this paper is to develop a robust method for face recognition and classification of persons in-order to increase the recognition rate by improving the efficiency of the system and reducing its complexity. I desired to develop this project to automate the entire process of face recognition given a set of facial database and to improve the performance of the face recognition system. The proposed approach is based on the fusion of face and fingerprint traits at feature extraction level. Here the independent features of the two modalities are extracted and then fused together for further recognition and classification. Two different algorithms are used in extracting the features of face and fingerprint traits. I have applied SIFT algorithm for extracting the facial features and Minutiae algorithm for extracting the features of fingerprint. Later, the features are combined together and the Euclidean distance metrics is used for recognition and the classification of persons is done using the labels. The proposed system has been proved to be efficient and the accuracy of recognition has been improved.
Keywords: SIFT Algorithm, Minutiae Algorithm, Euclidean distance, Feature extraction, Classifiers.
Title: AN IMPLEMENTATION OF FEATURE-LEVEL FUSION OF FACIAL AND THUMB PRINT IMAGES
Author: L Logeswari, Dr.R.Indra Gandhi
International Journal of Computer Science and Information Technology Research
ISSN 2348-120X (online), ISSN 2348-1196 (print)
Research Publish Journals
