G. Josemin Bala

A comparative study on ICA and LPP based Face Recognition under varying illuminations and facial expressions

Dimensionality reduction has been a key problem in Face Recognition. Independent Component Analysis (ICA) is a recent approach for dimensionality reduction. Locality Preserving Projections (LPP) is also a recently proposed new method in pattern recognition for feature extraction and dimension reduction. In this paper we have developed and analyzed the face recognition rate of ICA and LPP under varying illuminations and facial expressions. Analyzes is performed on YALEB databases which contains 64 illuminations conditions (5760 images) and ATT databases which contains major facial expressions (400 images). From the results we conclude that the best algorithm to recognize images with varying illuminations is ICA. On the other hand to recognize image with varying facial expressions, LPP is better to use because it has better recognition rate.

A pattern based PSO approach for block matching in motion estimation

Block matching motion estimation is a popular method in developing video coding applications. A new algorithm has been proposed for reducing the number of search points using a pattern based particle swarm optimization (PSO) for motion estimation. The conventional particle swarm optimization has been modified to provide accurate solutions in motion estimation problems. This leads to very low computational cost and good estimation accuracy. Due to the center biased nature of the videos, the proposed approach uses an initial pattern to speed up the convergence of the algorithm. Simulation results show that improvements over other fast block matching motion estimation algorithms could be achieved with 31%~63% of search point reduction, without degradation of image quality.

Performance analysis of virtual clusters in personal communication networks

The objective of the paper is to analyze the performance of virtual cluster architectures in wireless networks. The key issues in wireless domain are flooding, connectivity, and power management. These issues arise during the path finding and maintenance between source and destination nodes. To overcome these issues three approaches are introduced in this paper namely; fusion virtual structure, link quality connected dominating set and cluster backbone approach. These approaches follow the distributed localized computations for virtual cluster constructions and focus on fundamental connectivity problems and are partially involved in power saving process of individual nodes. The proposed methods are analyzed in terms of backbone size, packet delivery ratio and normalized routing overhead and the results are witnessed by simulation.

Recognizing facial images using ICA, LPP, MACE Gabor Filters, Score Level Fusion Techniques

We have developed and analyzed Independent Component Analysis (ICA), Locality Preserving Projections (LPP), Minimum Average Correlation Energy (MACE) Gabor Filters, Score Level Fusion Techniques (SLFT) for Face Recognition in the presence of various noises and blurring effects. ICA considers statistical characteristics in second order or higher order. LPP is used to generate an unsupervised neighborhood graph on training data, and then finds an optimal locality preserving projection matrix under certain criterion. MACE Gabor filter synthesizes a filter using a set of training images that would produce correlation output that minimizes correlation values at locations other than the origin and the value at the origin is constrained to a specific peak value. ICA, LPP, MACE Gabor Filter, SLFT are the 4 systems developed which were trained in the absence of noise, blurring effect but tested by imposing different levels of noises and blurring effects. To compare the performances six public face databases: IITK, ATT, JAFEE, CALTECH, GRIMACE, and SHEFFIELD are considered.

Robust Face Recognition in the Presence of Noises and Blurring Effects by Fusing Appearance Based Techniques and Sparse Representation

In real life, images obtained from video cameras or scanners are usually exposed to different levels of noises and blurring effects. In this paper we propose a new robust score level fusion technique to recognize faces in the presence of noise and blurring effects. The Proposed Score Level Fusion Technique (PSLFT) is obtained by using combinatory approach and Z-Score normalization using the scores obtained from appearance based techniques: Principal Component Analysis (PCA), Fisher faces (FF), Independent Component Analysis (ICA), Fourier Spectra (FS), Singular Value Decomposition (SVD) and Sparse Representation (SR). The system is trained in the absence of noise, blurring effect but tested by imposing different levels of noises and blurring effects thus we have tried to imitate the real world scenarios. To investigate the performance of PSLFT, we simulate the real world scenario by adding noises: Median noise, Salt and pepper noise and also adding blurring effects: Motion blur and Gaussian blur. To evaluate performance of the PSLFT, we have considered six standard public face databases: IITK, ATT, JAFEE, CALTECH, GRIMANCE, and SHEFFIELD.

Efficient self-organized backbone formation in mobile ad hoc networks (MANETs)

In wireless networks other than source and destination nodes, intermediate nodes play a major role for routing and other control transfer functions. Hence the network must be formed by self-organized intermediate nodes. This feature of the node is also used to protect the network from uncertainties like link, node failures. The main objective of this paper is to give the characteristics of intermediate nodes; how they support the quality of service issues. Existing research work in this area mainly concentrates on backbone construction and there is no solution for self-organized backbone formation. A new distributed localized algorithm is proposed to construct and maintain the backbone network named as SOB-T or M (self-organized backbone- tree or mark), which means that tree or marking scheme are used to construct the backbone network. The QoS parameters like throughput, delay and number of control messages are analyzed in this paper.

Enhanced modified orthogonal search for motion estimation

Motion estimation is an important part of video encoding systems. This paper presents a novel enhanced modified orthogonal search (EMOS) algorithm for block based motion estimation. The performance of this algorithm is evaluated with various video sequences and the results are compared to a traditional well-known full search algorithm (FSA), three step search (3SS), orthogonal search (OS), and modified orthogonal search (MOS). This paper introduces a half way stop technique to reduce computational complexity in the existing OS & MOS. The centre biased search pattern is facilitated for small motions. The enhanced modified orthogonal based search pattern is investigated in comparison with orthogonal and modified orthogonal search pattern and demonstrates significant speedup gain over them. The proposed EMOS algorithm can find the same motion vector with fewer search points than the OS & MOS algorithm. The quality of the reconstructed frame is comparable with that of the full search method, 3SS, OS & MOS. The advantage of proposed motion estimation technique is further justified by experimental results.

ODROID XU4 based implementation of decision level fusion approach for matching computer generated sketches

Abstract Implementing computer vision applications on energy efficient and powerful single board computer devices is a hot topic of research. ODROID-XU4 is one such latest single board computing device which is extremely energy efficient and powerful, having a small form factor when compared to any other ARM based embedded devices. It supports open source operations systems and runs a variety of Linux flavors including Ubuntu and various Android versions including Lollipop. Moreover, it supports USB 3.0, eMMC 5.0 and Gigabit Ethernet interfaces thus, making the device feasible to transfer data at a very high speed. The key contribution of this paper is we have developed a novel technique to match computer generated sketches with face photos and implemented it on ODROID XU4 single board computer which makes it feasible to be used in real-time. Human face is detected on the face photos using Viola Jones method. On the detected faces and computer generated sketches, feature extraction is performed using supervised auto-encoder to build deep architecture and matching is performed between computer generated sketches and face photos using Parallel Convolutional Neural Network (PCNN). Finally decision level fusion is performed to find the optimal matching result. In this study, the authors have performed pilot testing of their technique and results of their analysis are presented to the readers.

A Comparative Study on Score Level Fusion Techniques and MACE Gabor Filters for Face Recognition in the Presence of Noises and Blurring Effects

Face recognition has been an intensely researched field of computer vision for the past couple of decades. Though significant strides have been made in tackling the problem in controlled domains, significant challenges remain in solving it in the unconstrained domain. Two such scenarios are while recognizing faces acquired from distant cameras and when images are corrupted. The main factors that make this a challenging problem are image degradation due to noise and blur. In this paper we have developed and analyzed Score Level Fusion Technique (SLFT) of appearance based techniques and Minimum Average Correlation Energy (MACE) Gabor filter for face recognition in the presence of various noises and blurring effects. In SLFT the scores are obtained by using combinatory approach and Z-Score normalization of appearance based techniques: Principal Component Analysis (PCA), Fisher faces (FF), Independent Component Analysis (ICA), Fourier Spectra (FS), Singular Value Decomposition (SVD) and Sparse Representation (SR). MACE Gabor filter is designed to minimize the average correlation energy (ACE) of the correlation outputs due to the training images while simultaneously satisfying the correlation peak constraints at the origin. The effect of minimizing the ACE is that the resulting correlation planes would yield values close to zero everywhere except at the location of a trained object, where it would produce a strong peak. We simulate the real world scenario by adding noises: Median noise, Salt and pepper noise and also adding blurring effects: Motion blur and Gaussian blur. To compare the performance of SLFT and MACE Gabor filter, we have considered six standard public face databases: IITK, ATT, JAFEE, CALTECH, GRIMANCE, and SHEFFIELD.

STAB-WIN: Self Organized, Topology Control Ability Backbone Node in Wireless Networks

The objective of the paper is to construct a backbone node with self organization, topology control and reconfiguration capabilities. The key issues in wireless networks are maintain a topology with minimum degree, self organization during link or node failure and reconstruction ability when the backbone changes the position. Existing research works concentrate on any one of the issues by a backbone, but nodes in wireless are battery operated. To solve the all issues separately more power is required. To overcome the existing issues we propose a localized approach namely STAB-WIN, which will solve all the issues without affecting the entire system performance using local updates. This research work focuses on multiservice ability of a node to meet the design goals of next generation networks. Our approach is witnessed by the simulation results on analyzing the parameters like scalability which includes backbone size, routing overhead, control transfer and QoS parameters.