MMBAS-NS: Multimodal Biometric Authentication System and Key Generation Algorithm for Network Security on Mobile Phones
Saritha Reddy Venna1, Ramesh Babu Inampudi2

1Saritha Reddy Venna, Research Scholar, Department of CSE, Acharya Nagarjuna University, Guntur (A.P), India.
2Ramesh Babu Inampudi, Professor, Department of CSE, Acharya Nagarjuna University, Guntur (A.P), India.
Manuscript received on 06 February 2019 | Revised Manuscript received on 19 February 2019 | Manuscript Published on 04 March 2019 | PP: 189-199 | Volume-7 Issue-5S2 January 2019 | Retrieval Number: ES2029017519/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Nowadays mobile devices are an important part of our everyday lives since they enable us to access a large variety of ubiquitous services. In recent years, the availability of these ubiquitous and mobile services has significantly increased due to the different form of connectivity provided by mobile devices. In the same trend, the number and typologies of vulnerabilities exploiting these services and communication channels have increased as well. As the number of vulnerabilities and, hence, of attacks increase, there has been a corresponding rise of security solutions proposed by researchers. To overcome these issues in security solutions, we introduce a new method based on cryptographic generation system. We proposed a new multimodal biometric authentication system, here key values are created via the use of multiple biometrics instead of a single biometric, in an effort to generate strong and repeatable cryptographic keys. In this work, a multimodal biometric authentication system (MMBAS) is developed using face, fingerprint and retina images and key generation is also done using these images. Initially images are pre-processed using adaptive median filtering and Otsu’s segmentation algorithm for background subtraction. Then minutiae feature of these images are extracted with the use of Local Binary Pattern (LBP) algorithm and then the feature vectors of face, fingerprint and retina are fused using XOR operation. Later the fused feature vector is used for cryptographic key generation. The evaluation is performed on network security for showing the reliability of the newly introduced approach in terms of Precision, Recall, Accuracy and false rejection rate.
Keywords: Biometrics, Authentication System, Key Generation, Network Security, Face, Fingerprint, Retina.
Scope of the Article: Security, Trust and Privacy