COMPARISON BETWEEN ARTIFICIAL NEURAL NETWORK AND SUPPORT VECTOR MACHINE USING A PROPOSED BIOMETRIC WATERMARKING ALGORITHM

Biometric recognition refers to an automatic recognition of individuals based on their physiological and/or behavioral characteristic. Biometric technologies are available today that can be used in security systems to help protect assets. Biometric technologies can be used to verify or establish a person s identity. Protection of biometric data and templates is a crucial issue for the security of biometric systems, and biometric watermarking is introduced for this purpose. However watermarking introduces extra information into the biometric data which leads to certain image distortion. Applications of such a system, include computer systems security, secure electronic banking, mobile phones, credit cards, secure access to buildings, health and social services. Biometric technologies have been used in federal applications such as access control, criminal identification, and border security. In this paper, we make an attempt in such investigations by protecting two human features (fingerprint and part from DNA sequence) in a third one (iris imagef namely protection of fingerprint and DNA sequence by hiding them in cover image (iris image) as watermarks using a proposed biometric watermarking algorithm. The obtained watermarked images are used for the identification by the Artificial Neural Network (ANN) and Support Vector Machine (SVM). Experimental results from our prototype system showed that using ANN is preferable for identification with the color images by the additive method in our application.