Indian Journal of Science and Technology
Year: 2015, Volume: 8, Issue: 35, Pages: 1-10
D. Binu1* and P. Malathi2
1 Sri Ramakrishna Institute of Technology, Coimbatore - 641010, Tamil Nadu, India; [email protected]
2 Bharathiyar Institute of Engineering for Women, Salem - 636112, Tamil Nadu, India; [email protected]
Objective: Biometric image retrieval becomes the most popular application scenario in the real world where the many application are started to use bio metric authentication. It plays a key role in the security management system of the real world application to prevent the malicious user access. Storage and management of the bio metric details of multiple users are the biggest issue which may lead to inefficient performance. In our previous work, two model bio metric based human recognition is introduced where the iris and finger prints are considered. But it may not recognize the human system in case of missing information and the corruption of extracted features. To overcome this problem in this work multi model based human recognition is introduced. Methodology: The four models considered in this work are: Iris, finger print, face and the palm print. The unique methodology is used for extracting the features from these models. In the previous research work, Speeded Up Robust Features (SURF) algorithm is used for iris feature extraction and Improved Locality-Sensitive Hashing (ILSH) indexing method is used for finger print feature extraction. In our proposed methodology, weighted attributes sparse code words indexing is proposed for face image retrieval where the attribute scores are selected optimally by using the BAT algorithm and a Novel hierarchical Indexing approach is proposed for Palm Print Image Retrieval. Finally these extracted features are fused together to generate a single model from the multiple models by using the approach called uni-model indexing scheme. Findings: The experimental tests conducted prove that the proposed methodology provides better result than the existing approach in terms of improved retrieval accuracy. This simulation evaluation is done in the MATLAB simulation environment for the both existing and proposed approach which is then compared with each other to obtain the performance improvement. Applications: The findings of this work prove that the proposed approach provides better result than the existing approach in terms of improved accuracy. This approach can be applied in the many research field where the security is required for preventing from the intruders attack like military, hospital management etc.
Keywords: Face, Finger Print, Fusion, Iris, Multi-Model Retrieval, Palm Print
Subscribe now for latest articles and news.