Abstrait

Security System in ATM using Multimodal Biometric System and Steganographic Technique

Prerana Kamble, Sangita Nikumbh

The paper proposes to implement the biometric security system based on combination of iris and palm print 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. 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. Palm print 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 Weber’s local descriptors based texture analysis of palm print will be proposed here. Weber local descriptor is used to represents the changes of illumination in an image and it determines the features such as differential excitation and gradient orientation. 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 palm print 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. Crime which is happening in ATM became a serious issue that affects not only customers but also bank operators. The main solution to this problem is Multimodal biometrics. Finally the multimodal system along with Steganographic approach shows the better performance accuracy for this automatic identification and authentication in ATM system.