Ibrahim Venkat

Normal Forms of Spiking Neural P Systems With Anti-Spikes

Spiking neural P systems with anti-spikes (ASN P systems, for short) are a variant of spiking neural P systems, which were inspired by inhibitory impulses/spikes or inhibitory synapses. In this work, we consider normal forms of ASN P systems. Specifically, we prove that ASN P systems with pure spiking rules of categories (a, a) and (a, a̅) without forgetting rules are universal as number generating devices. In an ASN P system with spiking rules of categories (a, a̅) and (a̅, a) without forgetting rules, the neurons change spikes to anti-spikes or change anti-spikes to spikes; such systems are proved to be universal. We also prove that ASN P systems with inhibitory synapses using pure spiking rules of category (a, a) and forgetting rules are universal. These results answer an open problem and improve a corresponding result from [IJCCC, IV(3), 2009, 273-282].

Robust Gait Recognition by Learning and Exploiting Sub-gait Characteristics

Gait recognition algorithms often perform poorly because of low resolution video sequences, subjective human motion and challenging outdoor scenarios. Despite these challenges, gait recognition research is gaining momentum due to increasing demand and more possibilities for deployment by the surveillance industry. Therefore every research contribution which significantly improves this new biometric is a milestone. We propose a probabilistic sub-gait interpretation model to recognize gaits. A sub-gait is defined by us as part of the silhouette of a moving body. Binary silhouettes of gait video sequences form the basic input of our approach. A novel modular training scheme has been introduced in this research to efficiently learn subtle sub-gait characteristics from the gait domain. For a given gait sequence, we get useful information from the sub-gaits by identifying and exploiting intrinsic relationships using Bayesian networks. Finally, by incorporating efficient inference strategies, robust decisions are made for recognizing gaits. Our results show that the proposed model tackles well the uncertainties imposed by typical covariate factors and shows significant recognition performance.

Towards a robust affect recognition

Proposing a fully automatic 3D facial expression recognition framework.Investigating the capability of conformal mapping in the field of expression recognition.Enhancing the probability estimation of SVM for expression recognition.The results outperformed the previous studies significantly. Facial expressions are a powerful tool that communicates a persons emotional state and subsequently his/her intentions. Compared to 2D face images, 3D face images offer more granular cues that are not available in the 2D images. However, one major setback of 3D faces is that they impose a higher dimensionality than 2D faces. In this paper, we attempt to address this problem by proposing a fully automatic 3D facial expression recognition model that tackles the high dimensionality problem in a twofold solution. First, we transform the 3D faces into the 2D plane using conformal mapping. Second, we propose a Differential Evolution (DE) based optimization algorithm to select the optimal facial feature set and the classifier parameters simultaneously. The optimal features are selected from a pool of Speed Up Robust Features (SURF) descriptors of all the prospective facial points. The proposed model yielded an average recognition accuracy of 79% using the Bosphorus database and 79.36% using the BU-3DFE database. In addition, we exploit the facial muscular movements to enhance the probability estimation (PE) of Support Vector Machine (SVM). Joint application of feature selection with the proposed enhanced PE (EPE) yielded an average recognition accuracy of 84% using the Bosphorus database and 85.81% using the BU-3DFE database, which is statistically significantly better (at p < 0.01 and p < 0.001 , respectively) if compared to the individual exploit of the optimal features only.

Blind reliable invisible watermarking method in wavelet domain for face image watermark

In this paper, we have combined watermarking and biometrics for possible improvement in owner identification/verification technology. We have proposed and compared wavelet based four blind invisible watermarking methods that have used face image as watermark. Two watermarking methods are based on the discrete wavelet transform (DWT) and rest two watermarking methods are based on the redundant discrete wavelet transform (RDWT). One watermarking method in each transform incorporates weighted binary coding to achieve improved reliability of extracted watermark. Other watermarking methods replace original image coefficients with face image coefficients. We have observed that DWT based watermarking methods outperform RDWT based watermarking methods. We have compared the robustness of the proposed watermarking methods against various common image processing attacks/operations. We have observed that DWT based watermarking method coupled with weighted binary coding has the best performance without attacks; peak signal to noise ratio value of watermarked image is greater than 50 dB and normalized correlation coefficient value of extracted watermark is 1 at the watermark embedding strength of 1. Moreover, the same watermarking method has the best robustness against most of the attacks.

Recognizing occluded faces by exploiting psychophysically inspired similarity maps

The presence of occlusions in facial images is inevitable in unconstrained scenarios. However recognizing occluded faces remains a partially solved problem in computer vision. In this contribution we propose a novel Bayesian technique inspired by psychophysical mechanisms relevant to face recognition to address the facial occlusion problem. For some individuals certain facial regions, e.g. features comprising of some of the upper face, might be more discriminative than the rest of the features in the face. For others, it might be the features over the mid face and some of the lower face that are important. The proposed approach in this paper, will allow for such a psychophysical analysis to be factored into the recognition process. We have discovered and modeled similarity mappings that exist in facial domains by means of Bayesian Networks. The model can efficiently learn and exploit these mappings from the facial domain and hence capable of tackling uncertainties caused by occlusions. The proposed technique shows improved recognition rates over state of the art techniques.

Intelligent Evacuation Management Systems: A Review

Crowd and evacuation management have been active areas of research and study in the recent past. Various developments continue to take place in the process of efficient evacuation of crowds in mass gatherings. This article is intended to provide a review of intelligent evacuation management systems covering the aspects of crowd monitoring, crowd disaster prediction, evacuation modelling, and evacuation path guidelines. Soft computing approaches play a vital role in the design and deployment of intelligent evacuation applications pertaining to crowd control management. While the review deals with video and nonvideo based aspects of crowd monitoring and crowd disaster prediction, evacuation techniques are reviewed via the theme of soft computing, along with a brief review on the evacuation navigation path. We believe that this review will assist researchers in developing reliable automated evacuation systems that will help in ensuring the safety of the evacuees especially during emergency evacuation scenarios.

ABC algorithm as feature selection for biomarker discovery in mass spectrometry analysis

Mass spectrometry technique is gradually gaining momentum among the recent techniques deployed by several analytical research labs which intends to study biological or chemical properties of complex structures such as protein sequences. Literature reveals that reasoning voluminous mass spectrometry data via sophisticated computational techniques inspired by observing natural processes adapted by biological life has been yielding fruitful results towards the advancement of fields including bioinformatics and proteomics. Such advanced approaches provide efficient ways to mine mass spectrometry data in order to extract discriminating features that aid in discovering vital information, specifically discovering disease-related protein patterns in complex protein sequences. This study reveals the use of artificial bee colony (ABC) as a new feature selection technique incorporated with SVM classifier. Results achieved 96 and 100% for sensitivity and specificity respectively in discriminating cirrhosis and liver cancer cases.

A P System Model for Contextual Array Languages

A P system model, called Contextual array P system, that makes use of array objects and contextual array rules, is introduced and its generative power in the description of picture arrays is examined, by comparing it with certain other array generating devices.

P Systems with Parallel Rewriting for Chain Code Picture Languages

Chain code pictures are composed of unit lines in the plane, drawn according to a sequence of instructions left, right, up, down codified by words over \(\varSigma = \{ {l}, r, u, d \}\). P systems to generate such languages have been considered in previous work with sequential rewriting in the membranes. We consider here parallel rewriting, with the advantage of reducing the number of membranes. We also consider the problem of generating the finite approximations of space-filling curves, the Hilbert curve and the Peano curve.

Edge preserving image enhancement via harmony search algorithm

Population based metaheuristic algorithms have been providing efficient solutions to the problems posed by various domains including image processing. In this contribution we address the problem of image enhancement with a specific focus on preserving the edges inherent in images with the aid of a musically inspired harmony search based metaheuristic algorithm. We demonstrate the significance of our proposed intuitive approach which combines efficient techniques from the image processing domain as well as from the optimization domain. Pertaining to the problem under consideration, further we compare our results with the state-of-the-art histogram equalization approach.