Entropy based Local Binary Pattern (ELBP) feature extraction technique of multimodal biometrics as defence mechanism for cloud storage

Cloud Computing (CC) is a technology that is growing by leaps and bounds and has attracted wide spectrum of users. The extensive usage of cloud technology is influenced by multiple factors like ease of use, pay-per usage strategy, easy access, cost-effectiveness etc. Though it is a widely used technology, challenges exist in the form of security threats. There are a variety of services that are offered by cloud. These include Software as a Service (SaaS), Infrastructure as a Service (IaaS) and Platform as a Service (PaaS). Storage is one of the key service offerings under IaaS. To provide a secure digital platform for users to work with, this research work proposes a novel security architecture for secured storage in cloud that provides a robust authentication by employing multiple biometric modalities from users and allow/deny access accordingly. The crux of better authentication relies on the way the features are extracted from multiple biometric sensors and matched with registered users. For this purpose, a novel feature extraction technique is proposed in this research work. Entropy Based Local Binary Pattern (ELBP) is a new texture-based feature extraction technique proposed to describe the entropy information into Local Binary Pattern histogram in one-dimensional space. ELBP feature extraction technique needs no quantization. Biometric images exhibit higher uniqueness and hence incorporating entropy values into local regions add higher information content to these images, thus leading to better feature extraction. The experiments are performed on biometric images from Chinese Academy of Science, Institute of Automation (CASIA) Iris, Face and Fingerprint databases and the results show that the proposed ELBP feature extraction achieves substantial improvement, in terms of various classification metrics like accuracy, precision, recall etc. in comparison with the conventional rotation invariant LBP methods. The Receiver Operating Characteristics Curve (ROC) also bears testimony to the performance of the authentication system. Keywords: Cloud Computing (CC) environment, Biometric modalities, Authentication, Feature extraction, Entropy based Local Binary Pattern (ELBP)