HIGH PERFORMANCE SECURITY SYSTEM USING MULTIMODAL BIOMETRICS AND STEGANOGRAPHIC TECHNIQUE

Abstract The project proposes to implement the biometric security system based on combination of iris and palmprint with steganographic technique for authentication purpose. Here the data hiding approach involves to conceal secret personal informatics within their biometric for still enhance the privacy protection. Along with that, chaos encryption will be used to encrypt the secret data before embedding. A Biometric system is essentially a pattern recognition system that makes use of biometric traits to recognize individuals. The most unique phenotypic feature visible in a person's face is the detailed texture of each eye's iris. Palm is the inner surface of a hand between the wrist and the fingers. Palmprint is referred to principal lines, wrinkles and ridges on the palm. This system proposes a multi-resolution approach based on Wavelet Packet Transform (WPT) for texture analysis of iris and Webers local descriptors based texture analysis of palm print will be proposed here. The development of this approach is motivated by the observation that dominant frequencies of iris texture are located in the low and middle frequency channels. The hand palm print image is aligned and cropped according to the key points. The palmprint image is enhanced and resized. The features of palm print and iris are fused then compared with database image feature vectors and its recognized using Euclidean or Hamming distance. If this module is completed successfully then person information which contains person authentication number with four digits key will be matched with extracted data from already hidden image for second level security. Finally the multimodal system along with steganographic approach shows the better performance accuracy for this automatic identification and authentication application.

Existing method Authentication system with single biometric modality Finger printing is that much not flexible because we can make duplicates of fingers and bluff people. It is not that much efficient. RSA encryption and pixel difference expansion based embedding

Drawbacks Uni modal biometric system may not fulfill the requirements of demanding Applications interms of properties such as performance, acceptability More computational complexity High distortion and algorithm complexity

Proposed method Person authentication system based on multimodal biometrics and steganographic with cryptography technology, it involves Iris with palmprint recognition Chaos encryption Data concealment using adaptive lsb algorithm

Block diagram Individual Database Creation

Person Biometric

Embedding

Image with hidden data

Privacy Information

Chaos encryption

Recognition
Eye Image Iris Segmentation Wavelet packet features Multi modal Features

Hand Image

Palm Print Extraction

Weber local descriptors

RFID Matching

Database recovery

Features Extraction

Matching

Hidden Data Extraction and decryption

Personal data matching if authenticated

Authorized/ Unauthorized

Hardware Section
RF Module Micro Controller Unit Buzzer (Unauthorized)

Stepper Motor (authorized)

Modules Database Creation Data (Personal Ids) encryption Embedding Recognition Iris and Palmprint biometrics Features Extraction Matching Data extraction and matching

Advantages Low distortion due to data concealment Better data protection and less complexity

This system gives more security compared to unimodal system because of two biometric features

Application Defense systems Authentication and privacy protection

Software Required MATLAB 7.5 and above versions

References [1] Bradford Bonney, Robert Ives, Delores Etter, "Iris pattern extraction using bit planes and standard deviations", IEEE 2004 [2] Lu Chenghong, Lu Zhao yang, "Efficient iris recognition by computing discriminable textons", IEEE 2005. [3] Jie Wang, Xie Mei, "Iris Feature extraction based on wavelet packet analysis", IEEE 2006 [4] Chang, New multi-biometric approaches for improved person identification, PhD Dissertation, Department of Computer Science and Engineering, University of Notre Dame, 2004. Page No. 153-159. [5] D. Monar, A. Juels, and D. Wagner, Security and privacy issues in epassports, Cryptology ePrint Archive, Report 2005/095, 2005. Page No. 72-78. [6] Bergman, Multi-biometric match-on-card alliance formed, Biometric Technology Today, vol. 13, no. 5, 2005. Page No. 1-9.