HUMAN RECOGNITION USING BIOMETRIC AUTHENTICATION SYSTEM

A model is designed to work for Face recognition, Finger Print recognition, and Signature recognition for recognizing the individual person test images out of training images. There are various methods for recognition and images need to have good sensor quality. A Fisher LDA approach which produces a set of Eigen faces and fisher faces to obtain projected images has been implemented. In this paper both PCA and LDA techniques have been used. Minutiae matching algorithm which after several preprocessing stages produces minutiae points on finger print has been implemented. The offline signature is taken for verification and recognition system; Global features are extracted and matched. A set of fisher images are projected and reconstructed. The test image is also projected and a minimum error reconstruction value is calculated. If error is less than a threshold value, then it recognizes the face from the database. A set of false minutia points are extracted and efficiently the minutia points are removed from the finger and made into a template and verification is done with other template for producing percentage score of the matching template. After extracting Global features from the signature, the same steps are applied for the input signature and matched with the database of signature images. Multimodal biometric authentication is applied for verification and identification of humans where same the human being database is matched with the input image.

[1]  Vinayak Ashok Bharadi,et al.  Fingerprint Core Point Detection Algorithm using Orientation Field Based Multiple Features , 2010 .

[2]  P. Balasubramanie,et al.  Wavelet Feature Based Neural Classifier System for Object Classification with Complex Background , 2007, International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007).

[3]  Davinder Kaur,et al.  Fingerprint Recognition using Image Segmentation , 2011 .

[4]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[5]  Hamid Hassanpour,et al.  IMAGE QUALITY ENHANCEMENT USING PIXEL-WISE GAMMA CORRECTION , 2011 .

[6]  M.V. Karki,et al.  Off-Line Signature Recognition and Verification Using Neural Network , 2007, International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007).

[7]  Hamid Hassanpour,et al.  An Improved Pixon-Based Approach for Image Segmentation , 2011 .

[8]  M. Elif Karsligil,et al.  Off-line signature verification and recognition by Support Vector Machine , 2005, 2005 13th European Signal Processing Conference.

[9]  Lishi Zhang,et al.  Application of improved Fisher Linear Discriminant Analysis approaches , 2011, MSIE 2011.

[10]  Jim Austin,et al.  Combining multiple face recognition systems using Fisher's linear discriminant , 2004, SPIE Defense + Commercial Sensing.

[11]  A. M. Patil,et al.  Face Recognition by PCA Technique , 2009, 2009 Second International Conference on Emerging Trends in Engineering & Technology.

[12]  K. Murugesan,et al.  Efficient Face Recognition in Video by Bit Planes Slicing , 2012 .