P. Sojan Lal

Trigger Based Security Alarming Scheme for Moving Objects on Road Networks

The advent of modern monitoring applications such as location based services, presents several new challenges when dealing with continuously evolving spatio-temporal information. Spatio-Temporal data analysis plays a central role in many security-related applications including those relevant to transportation infrastructure, border and inland security. This paper reviews a novel binary encoding scheme to store location information and proposes a trigger based security alarming scheme when an object enters into a sensitive area with proper messages to the security people.

Combining singular point and co-occurrence matrix for fingerprint classification

Fingerprint classification is an important part of fingerprint identification system that works on large databases to increase its matching speed. In this paper, an automatic fingerprint classification method is proposed to classify the fingerprint images by combining singular points and Gray Level Co-occurrence Matrix (GLCM) features. Co-occurrence matrices can be used to extract features from the fingerprint image because these are composed of regular texture patterns. First, the fingerprint image is preprocessed and a unique reference point is detected to determine a Region-of-Interest (ROI). ROI is then partitioned into 4 different regions to extract 4 sets of 4 GLCM features from each region. To achieve this, 4 co-occurrence matrixes are computed from each region with a predefined set of parameters. A feature vector consisting of 64 features is used to train a feed-forward neural network for classifying the input image into 5 different classes. The accuracy of 97.14% with no rejection is achieved and the experiment result shows that the method is reliable for fingerprint classification.

A Forecasting Model for the Pages Crawled by Search Engine Crawlers at a Web Site

World Wide Web is exploding in terms of the number of web sites and users. Without search engines the web sites will not be visible to the users. Different search engine crawlers behave in different ways while they access a web site. The number of visits and pages crawled by search engines could be helpful in identifying their behavior and also the server load. A forecasting model in time series has been proposed for predicting the number of pages crawled by search engines. This model was compared with the actual values and it was found feasible. General Terms Web log mining, Web analytics

Extracting Extended Web Logs to Identify the Origin of Visits and Search Keywords

Web Usage Mining is the extraction of information from web log data. The extended web log file contains information about the user traffic and behavior, the browser type, its version and operating system used. Mining these web logs provide the origin of visit or the referring website and popular keywords used to access a website. This paper proposes an indiscernibility approach in rough set theory to extract information from extended web logs to identify the origin of visits and the keywords used to visit a web site which will lead to better design of websites and search engine optimization.

Spatio-temporal similarity of web user session trajectories and applications in dark web research

Trajectory similarity of moving objects resembles path similarity of user click-streams in web usage mining. By analyzing the URL path of each user, we are able to determine paths that are very similar and therefore effective caching strategies can be applied. In recent years, World Wide Web has been increasingly used by terrorists to spread their ideologies and web mining techniques have been used in cyber crime and terrorism research. Analysis of space and time of click stream data to establish web session similarity from historical web access log of dark web will give insights into access pattern of terrorism sites. This paper deals with the variations in applying spatio-temporal similarity measure of moving objects proposed by the authors in PAISI 2010, to web user session trajectories treating spatial similarity as a combination of structural and sequence similarity of web pages. A similarity set formation tool is proposed for web user session trajectories which has applications in mining click stream data for security related matters in dark web environment. The validity of the findings is illustrated by experimental evaluation using a web access log publically available.

Fingerprint reference point identification based on chain encoded discrete curvature and bending energy

Reference point identification is important in automatic fingerprint recognition system as it can be used to align fingerprints in a correct orientation in spite of the possibility of different transformations in fingerprint images. It is also used in fingerprint classification, as it is desirable to classify fingerprint images for forensic type applications which require the input image to be verified against a large database. The important feature information useful for classification is centered near the reference point. Most of the current approaches for identifying the reference point either require determining ridge orientation or use some complex filters. These methods either operate on 2D (two dimensional) or are not robust to rotation or cannot be applied to every class of fingerprint image. This paper proposes a method to reliably identify unique reference point that operates in 1D (one dimensional). The method treats the fingerprint ridges as a non-overlapped sequence of chain code segments. A modified k-curvature method has been proposed to find the high-curvature area of fingerprint ridges. The reference point localization is based on the property of the ridge’s bending energy. The proposed method is tested on FVC2002 and FVC2004 standard datasets, and the experimental results show that the proposed algorithm can accurately locate reference point for all types of fingerprint images.

Analysis of the sequence length of visitors from the entry point and their repeated visits

World Wide Web has grown-up exponentially during the last decade and subsequently web log files contain tremendous information about the user traffic and behavior. The sequence length of visitors, the depth to which a user visits a website, can be analyzed to study the behavior of visitors and it may vary depending on the entry point to the website. A statistical analysis was done to see the differences in sequence length of visitors entered through home page and other pages. We also intend to see whether sequence length increases in repeated visits. The hypothesis was tested and it revealed that there is a considerable difference in the sequence length of visitors from home page and other pages. It was observed that sequence length decreases in repeated visits. We have also analyzed whether this result varies with time. The analysis helps in setting appropriate commercial marketing strategy.

Combining Chain-Code and Fourier Descriptors for Fingerprint Matching

The performance of an fingerprint recognition system is measured by its accuracy in recognition. For a feature-based fingerprint recognition system, the accuracy is heavily depend on the chosen feature set. A fingerprint image may suffer from problems like translation, rotation, scaling and elastic distortion due to different imaging conditions. A fingerprint recognition algorithm should address these problems before building the feature set. We present a novel method of representing the fingerprint ridge shape as the feature set by combining chain code and fourier descriptor for fingerprint recognition. Experimental results shows that our proposed algorithm is reliable for fingerprint recognition.

Reference point estimation in fingerprint image

Due to different imaging conditions, a fingerprint image may suffer from problems like translation, rotation, scaling and elastic distortion. A fingerprint recognition algorithm should address these problems for efficiency. One solution is to uniquely detect a reference point and align the fingerprint image based on the detected reference point. Accurate estimation of reference point is one of the major challenges in an automatic fingerprint recognition system. This paper presents a novel method to estimate a reference point for all types of fingerprints by tracing the chain coded contour of a fingerprint image. Chain codes are used to represent an image contour by a connected sequence of straight line segments of specified length and direction. The algorithm identifies the unique reference point as the point of maximum curvature changes in the fingerprint convex ridges. Experimental results show that our proposed algorithm can uniquely estimate a reference point for all types of fingerprints.

Pre- and Post-fingerprint Skeleton Enhancement for Minutiae Extraction

Automatic personal identification system by extracting minutiae points from the thinned fingerprint image is one of the popular methods in a biometric system based on fingerprint. Due to various structural deformations, extracted minutiae points from a skeletonized fingerprint image may contain a large number of false minutiae points. This largely affects the overall matching performance of the system. The solution is to validate the minutiae points extracted and to select only true minutiae points for the subsequent matching process. This paper proposes several pre- and post-processing techniques which are used to enhance the fingerprint skeleton image by detecting and canceling the false minutiae points in the fingerprint image. The proposed method is tested on FVC2002 standard dataset and the experimental results show that the proposed techniques can remove false minutiae points.