An Efficient Biometric Multimodal Fingerprint and Iris using an SVM Classifier and Adaptive Neuro Fuzzy Inference System (ANFIS)

Recent times witnessed much advancement in the field of biometric and multimodal biometric fields. This is typically observed in the area, of security, privacy, and forensics. Even for the best of unimodal biometric systems, it is often not possible to achieve a higher recognition rate. Fusion of matching scores of multiple biometric traits is becoming more and more prevalent and is a very likely approach to boost the system's accuracy. The finger print and iris are among the most promising biometric authentication that can accurately identify and analysis a person as their unique qualities can be rapidly extracted during the recognition process. This biometric recognition and verification often deals with non-ideal scenarios such as faint images, off-angles, reflections, expression changes. In this work, a novel method for identification of fingerprint and IRIS is projected using an ANFIS-based matching algorithm, which is suitable for large-scale identification systems. An important feature and objective of the proposed system is to enhance accuracy and efficiency. The features of the fingerprint and Iris image is extracted using SIFT algorithm. The features are perfectly extracted from fingerprint and eye image using this algorithm. Then the extracted features are given to the Regressive SVM and Hamming Distance classifier. The regressive support vector machine and hamming distance is used as a classifier, it accurately matches the two set of fingerprint and iris features quickly.