Improved Multi-Model Biometric Authentication using Watermarking and Visual Cryptography
Main Article Content
Abstract
Information security is one of the most promising research area that confirms the secure data communication between distance users. There are number of cryptographic and steganography techniques to secure the information. In this work, a hybrid multi-model biometric architecture is presented that combines the watermarking, cryptography and biometric authentication. This multi-model architecture includes two types of biometric images i.e. iris and finger print image. This presented hybrid model is defined in three different layer where each layer defines a separate level of security. In first stage, the visual cryptography is performed by using the half tone fingerprint and iris images. This visual cryptography will use the random sequence algorithm to perform the visual cryptography. The cryptographic image will not increase the size of the image. At the second stage, this visual cryptographic image will be stored behind any source biometric object. To perform the image watermarking in other image, DWT based image will be implemented. Now this dual biometric embedded cover image will be communicated at the receiver side. On the receiver side, the reverse process of watermark recovery and the retrieval of biometric image from the cryptographic watermarked object. At the final stage, these two biometric images will be compared with the biometric image dataset to confirm the biometric authentication. To perform this authentication, the weighted PCA will be implemented. The proposed work will be implemented in matlab environment. The analysis of the work will be performed on each stage of the presented model.
Keywords: Iris, Fingerprint, Authentication, Visual Cryptography, Watermarking.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.