Madasu Hanmandlu

Unconstrained handwritten character recognition based on fuzzy logic

This paper presents an innovative approach called box method for feature extraction for the recognition of handwritten characters. In this method, the binary image of the character is partitioned into a fixed number of subimages called boxes. The features consist of vector distance (γ) from each box to a fixed point. To find γ the vector distances of all the pixels, lying in a particular box, from the fixed point are calculated and added up and normalized by the number of pixels within that box. Here, both neural networks and fuzzy logic techniques are used for recognition and recognition rates are found to be around 97 percent using neural networks and 98 percent using fuzzy logic. The methods are independent of font, size and with minor changes in preprocessing, it can be adopted for any language.

Fuzzy modeling based signature verification system

Presents an approach for the verification of a signature using fuzzy modeling. For feature extraction, a signature is enclosed in a box. Taking the left side bottom corner of the box as the origin, angles of all pixels are calculated and then distributions of angles are generated using fixed class intervals. By considering these distributions as fuzzy sets, a Takagi-Sugeno model is constructed by defining the output of the signature to be a fixed number. This model is then used for the twin-purpose of verification and forgery detection. The results are demonstrated on several signature samples.

Fuzzy Co-Clustering of medical images using bacterial foraging

A novel modification of the Fuzzy Clustering for Categorical Multivariate date (FCCM) algorithm termed as dasiaFuzzy Co-Clustering Algorithm for Images (FCCI)psila is proposed for clustering of medical images. The main aim of this work is to segment regions of interest in histo-pathological images which consist of groups of similar cells indicating some form of abnormality in the animal tissue. The proposed method relies on improved colour clustering results when FCCI is applied on images as compared to the conventional clustering techniques. The method also categorizes different types of lesions based on the co-clustering results. The objective function is optimized using the bacterial foraging algorithm which gives image specific values to the parameters involved in the algorithm. The colour segmentation results are found to be more accurate, producing well formed and valid clusters having ldquocrisppsila values of membership function with lesser number of iterations. The algorithm results in distinct co-clusters ranked in the order of their memberships.

Contour based matching technique for 3D object recognition

This paper presents a contour matching technique for the identification of an object model corresponding to an observed object from a list of object models from range data. There are three types of edge data associated with the object and the models. These data are utilized in a hierarchical fashion, each time employing one type of edge data for pruning the models during the matching. The matching uses quarternion theory and is more suitable for the recognition of symmetric objects. The results are illustrated through simulated examples.

A web-based collaborative enabled multimedia content authoring and management system for interactive and personalized online learning

This paper describes the design and implementation of a web-based collaborative enabled multimedia content authoring and management system (CMCAMS) for organizing, integrating and composing personalized and interactive course notes for online education. A 5-layered architecture is proposed for the CMCAMS and is implemented using the Java 2 Enterprise Edition (J2EE). A web-based distance education system has been developed over this framework to test its effectiveness. This system enables educators to manage personalized learning materials that are structured, profiled and streamed to students. It examines the users profile to identify what level of difficulty to incorporate and what kind of presentation style to adopt based on the bandwidth available to students. The CMCAMS uses XML and XSLT techniques to generates SMIL documents, which form the backbone for educational online materials. The CMCAMS has several essential features: (1) remote access, (2) easy to use, and (3) support for multi-style.

A New Scheme for the Polynomial Based Biometric Cryptosystems

This paper presents a new scheme for the fuzzy vault based biometric cryptosystems which explore the feasibility of a polynomial based vault for the biometric traits like iris, palm, vein, and so forth. Gabor filter is used for the feature extraction from the biometric data and the extracted feature points are transformed into Eigen spaces using Karhunen Loeve (K-L) transform. A polynomial obtained from the secret key is used to generate projections from the transformed features and the randomly generated points, known as chaff points. The points and their corresponding projections form the ordered pairs. The union of the ordered pairs from the features and the chaff points creates a fuzzy vault. At the time of decoding, matching scores are computed by comparing the stored and the claimed biometric traits, which are further tested against a predefined threshold. The number of matched scores should be greater than a tolerance value for the successful decoding of the vault. The threshold and the tolerance value are learned from the transformed features at the encoding stage and chosen according to the tradeoff in the error rates. The proposed scheme is tested on a variety of biometric databases and error rates obtained from the experimental results confirm the utility of the new scheme.

Surface Reconstruction from Multiple Views of Painted Curves

A normal to the extremal contour of a 3D object is the same as the normal computed for the image contour projected on the unit sphere by the rays grazing the extremal contour. This fact is utilized in the present work to derive the parameters of quadric surfaces. We require three views of the point of intersection of two painted curves on an object. Out of the three views, one view must be chosen such that the image contours of the curves appear close to the extremal contours. Then the normals to the image contours (i.e., apparent contours) and the normals to the surface curves (i.e., contour generators) can be related through differential geometry to yield quadric representation of a surface at the point of interest.

Personalization of Interactive News through J2EE, XML, XSLT, and SMIL in a Web-Based Multimedia Content Management System

This paper describes the design and implementation of a 5 layered web-based multimedia content management system (MCMS) using the Java 2 Enterprise Edition (J2EE). A prototype based on our framework has been implemented in the News On Demand KIOSK Network for organizing, integrating and composing of personalized digital news for interactive broadcasting. The aim of the MCMS project is to provide a collaborative environment among news producers for making them work more effectively despite the time and location constraints. The MCMS generates SMIL document that is structured, profiled and streamed to end-user using XML and XSLT techniques, which form the backbone of digital news broadcasting. The major contributions with regard to the digital MCMS can be summarized as: (1) Support for effective personalization of multimedia news content and presentation styles through the utilization of XML and XSLT. (2) Separation of design and content facilitated by MCMS. This allows journalist and editors to focus on content preparation rather than advanced HTML and SMIL coding. (3) Support for the re-use and re-purpose operations of the same multimedia elements to be part of the other digital news program. (4) Platform independent MCMS allowing an author to access the application everywhere via Internet without any need of additional hardware or software.

Estimation of motion from a sequence of images using spherical projective geometry

Motion is an important cue for many applications. Here we propose a solution for estimating motion from a sequence of images using three algorithms, namely, batch, recursive and bootstrap methods. The motion derived using spherical projection relates the image motion to the object motion. This equation is reformulated into a dynamical space state model, for which a Kalman filter can be easily applied to yield the estimate of depth. We also propose a new approach for establishing correspondences using local planar invariants and hierarchical groupings. The proposed algorithm provides a simple yet robust method having lower time complexity and less ambiguity in matching than its predecessors.