Rahul Raman

Lip pattern recognition based on local feature extraction

Lip is claimed to be a unique organ in human body and hence a candidate for being a biometric. The uniqueness of lip has been proven by the researchers by using color information and shape analysis. These measures of lip are unique for every person. This paper proposes that grayscale lip images constitute local features. The claim has been experimentally established by extracting local features from 23 grayscale lip images from 10 different subjects and measuring the accuracy of match. There are two techniques applied for extraction and matching of local features from lip, viz. SIFT and SURF. The accuracy turns out to be very high (>90%) in both the experiments conducted.

Direction Estimation for Pedestrian Monitoring System in Smart Cities: An HMM Based Approach

The paper proposes a novel approach for direction estimation of a moving pedestrian as perceived in a 2-D coordinate of field camera. The proposed direction estimation method is intended for pedestrian monitoring in traffic control systems. Apart from traffic control, direction of motion estimation is also very important in accident avoidance system for smart cars, assisted living systems, in occlusion prediction for seamless tracking in visual surveillance, and so on. The proposed video-based direction estimation method exploits the notion of perspective distortion as perceived in monocular vision of 2-D camera co-ordinate. The temporal pattern of change in dimension of pedestrian in a frame sequence is unique for each direction; hence, the dimensional change-based feature is used to estimate the direction of motion; eight discrete directions of motion are considered and the hidden Markov model is used for classification. The experiments are conducted over CASIA Dataset A, CASIA Dataset B, and over a self-acquired dataset: NITR Conscious Walk Dataset. The balanced accuracy of direction estimation for these experiments yields satisfactory results with accuracy indices as 94.58%, 90.87%, and 95.83%, respectively. The experiment also justifies with suitable test conditions about the characteristic features, such as robustness toward improper segmentation, partial occlusion, and changing orientation of head or body during walk of a pedestrian. The proposed method can be used as a standalone system or can be integrated with existing frame-based direction estimation methods for implementing a pedestrian monitoring system.

Detection of Web-Based Attacks by Analyzing Web Server Log Files

In today’s scenario, Web traffic is increasing everyday in the world and has overtaken P2P traffic. The Websites are getting hacked on daily basis. These rises in hacking activity pose a greater threat than the network attacks as they threaten to steal crucial and important information from Website. This information can be related to the users, employee, and other important data stored in applications and database linked to the Website. Increase in Web network traffic has opened new and more efficient attack vectors for the hackers and attackers to work with. Attackers take advantage of the vulnerability in traditional firewalls deployed on Website. These firewalls are not designed to protect Web applications; lots of Websites are getting attacked by malicious scripts and users. In this paper, many Web attacks are carried out on Web applications hosted on local server to analyze the log file created after the attacks. A Web application log file allows a detailed analysis of a user action. We have simulated some Web attacks using MATLAB. Results extracted from this process helps in the recognition of majority of the attacks and helps in prevention from further exploitation.

Direction prediction for avoiding occlusion in visual surveillance

Occurrence of occlusion while providing visual surveillance leads to anarchy as the track of the subject under motion may be lost. This often results into the failure of the surveillance system. The approach of predicting motion of moving subjects and hence the chances of their mutual occlusion gives an upper hand to surveillance system to take in-time necessary action towards mitigation of loss of track during dynamic occlusion. Direction of motion of a moving subject plays a major role while studying its motion. Direction along with the velocity of a subject in a 3D plane completely describes the motion of any subject. This article proposes a model‘-based approach for direction prediction of a moving subject in a 3D global plane as acquired in a 2D camera plane. The proposed approach uses the eight discrete directions of motion as proposed in and models different directions. The proposed direction prediction method is experimentally verified with six different classifiers, i.e. regression analysis, simple logistic regression, MLP, k-NN, SVM and Bays classifier over existing as well as self-acquired databases. The initial simulation results are motivating as the overall accuracies achieved through different classifiers are of the range of 87–94

Acquisition and corpus description of a constrained lip database captured from handheld devices: NITRLipV2 (MobioLip)

\%

NITRLipV1: a constrained lip database captured in visible spectrum

%, which advocates the suitability of the said approach.

Multi-camera localisation: a review

There has been a significant research devoted towards detection of a moving object in an image sequence. Detected moving objects usually contain some errors (some pixels belonging to the object are marked as non-objects and vice versa). To achieve a refined detection of moving object in the video, there is a need of post processing of the binary blobs detected as objects in every frame of the video. This article introduces a novel blob reconstruction method that overcomes the mentioned limitation through optical flow based nullification, bifurcation, and unification of detected blobs. To claim the performance of the proposed method, a comparison is made with ten widely used object detection methods on twenty four standard moving-object scene videos. Comparison is made based on standard parameters like accuracy, precision, recall, and F-measure. The results clearly indicates the efficacy of the proposed method. Following this, results on a priliminary case study on placodal cell migration during early development of ectodermal organ of human and mice has been made employing the proposed model which promisingly tracks the cell migration.

Beyond estimating discrete directions of walk: a fuzzy approach

This report describes the dataset NITRLipV2 which is a constrained lip database captured in visible spectrum from handheld device. The database provides images of lips of different subjects. The images can be used by researchers to investigate in the domain of lip-image based user identification when images are captured from front camera of handheld devices like mobile phone.