Raja K B

Optimized Face Recognition Algorithm using Spatial and Transform Domain Techniques

The biometrics is used to identify or verify persons effectively in the real time scenario. In this paper, we propose Optimized Face Recognition Algorithm using Spatial and Transform Domain Techniques. The face images are preprocessed using Discrete Wavelet Transform (DWT), resize and filtering. The Compound Local Binary Pattern (CLBF) is used to generate magnitude and sign components from preprocessed face images. The histogram is applied on sign and magnitude components of CLBF to compress number of features. The generated histogram features are concatenated to form CLBP-Histogram features. The Fast Fourier Transformation (FFT) is applied on preprocessed image and FFT magnitude features are generated. The CLBP-Histogram features are fused with FFT magnitude features to generate final feature set. The final feature sets of test image and data base images are compared using Euclidian Distance (ED) to recognise a person. It is observed that the performance parameter of the proposed algorithm is better compared to existing algorithms.

Real-Time Link-Reliability Routing for QoS in Wireless Sensor Networks

This paper proposes a Real-Time Link Reliability Routing protocol for wireless sensor networks (WSNs). The protocol achieves to reduce packet deadline miss ratio while considering link reliability, two-hop velocity and power efficiency and utilizes memory and computational effective methods for estimating the link metrics. Numerical results provide insights that the protocol has a lower packet deadline miss ratio and improved sensor network lifetime. The results show that the proposed protocol is a feasible solution to the QoS routing problem in wireless sensor networks that support real-time applications.

Face Recognition based on STWT and DTCWT using two dimensional Q-shift Filters

The Biometrics is used to recognize a person effectively compared to trad itional methods of identification. In this paper, we propose a Face recognition based on Single Tree Wavelet Transform (STWT) and Dual Tree Complex Wavelet transform (DTCWT). The Face Images are preprocessed to enhance quality of the image and resize. DTCWT and STWT are applied on face images to extract features. The Euclidian dist ance is used to compare features of database image with test face images to compute performance parameters. The performance of STWT is compared with DTCWT. It is observed that the DTCWT gives better results compared to STWT technique.

Transform Domain Based Iris Recognition using EMD and FFT

Iris is one of the physiological trait which is used to identify the individuals. In this paper Transform Domain Based Iris Recognition using EMD and FFT is proposed. Circular Hough Transform is used in the Preprocessing stage to extract circular part of eye. The circular iris part is converted into rectangular rubber sheet model in Region of Interest (ROI).Empirical Mode Functions (EMF)’s are obtained by applying Empirical Mode Decomposition (EMD) on the Iris. FFT is also applied on ROI to extract the features. These features are added arithmetically to obtain final features. The features of the database are compared with test iris using Euclidian Distance(ED) to compute performance parameters. It is observed that the values of CRR and EER are better in the case of propsed algorithm compared to existing algorithms.

FPGA Implementation of Fingerprint Recognition System using Adaptive Threshold Technique

The real time fingerprint biometric system is implemented using FGPA. In this paper, we propose FPGA Implementation of Fingerprint Recognition System using Adaptive Threshold Technique with novel adaptive threshold for each person. The fingerprint images are considered from FVC2004 (DB3_A) and processed to resize fingerprint size to 256X256. The DWT is applied on fingerprint and considered only LL coefficients as features of fingerprint. The Adaptive Threshold value for each person is computed using Deviations between two successive samples of a person, Average Deviation, Standard Deviation and constant. The Adaptive Threshold for test image is computed using Deviations between test images and samples of database, Average Deviation, Standard Deviation and constant. If the Average Threshold of test image is less than Average Threshold of a person then it is considered as match else mismatched. It is observed that the success rate of identifying a person is high in the proposed method compared to existing techniques and also the device utilization in the proposed architecture is less compared to existing architectures.

Reliable Adaptive Replication Routing for Wireless Sensor Networks

In this paper, we consider the problem of reliable communication, the packet-loss prevention and packet-loss recreation recovery techniques are widely used and have many practical challenges. Hence, we propose a Reliable Adaptive Replication Routing (RARR) Algorithm, here the packet loss replication is accomplished in several hops and End-to-End (E2E) reliability is improved compared to conventional single E2E paths. RARR algorithm is comprised of a link capacity estimator, random disseminator and a replicator. The protocol employs an adaptive neighbor knowledge scheme which differentiates the density of nodes in the deployed scenario and hence reduces the overheads compared to the existing Proliferation Routing scheme. Simulation results demonstrate the effectiveness of this scheme and show that the proposed protocol is a feasible solution to increase the service quality (i.e., E2E transmission success rate, energy efficiency) compared with the well-known routing techniques. The proposed protocol is scalable and practical, and it dynamically adapts to the network topology.

Real-Time Traffic-Differentiated QoS Routing for Wireless Sensor Networks

Wireless sensor networks (WSNs) emerge as underlying infrastructures for new classes of large scale networked embedded systems. However, WSNs system designers must fulfill the Qualityof-Service (QoS) requirements imposed by the applications (and users). Very harsh and dynamic physical environments and extremely limited resources are major obstacles for satisfying QoS metrics such as reliability, timeliness, and system lifetime. The limited communication range of WSN nodes, link asymmetry, and the characteristics of the physical environment lead to a major source of QoS degradation in WSNs. This paper proposes a Real-Time Traffic-Differentiated Routing protocol for Wireless Sensor Networks (WSNs). It targets WSN applications having different types of data traffic with several priorities. The protocol achieves to increase packet reception ratio and reduce end-to-end delay while considering multi-queue priority policy, two-hop neighborhood information, link reliability and power efficiency. The protocol is modular and utilizes memory and computational effective methods for estimating the link metrics. Numerical results show that the proposed protocol is a feasible solution to addresses QoS service differentiation for traffic with different priorities.