Venu Govindaraju

A lexicon driven approach to handwritten word recognition for real-time applications

A fast method of handwritten word recognition suitable for real time applications is presented in this paper. Preprocessing, segmentation and feature extraction are implemented using a chain code representation of the word contour. Dynamic matching between characters of a lexicon entry and segment(s) of the input word image is used to rank the lexicon entries in order of best match. Variable duration for each character is defined and used during the matching. Experimental results prove that our approach using the variable duration outperforms the method using fixed duration in terms of both accuracy and speed. Speed of the entire recognition process is about 200 msec on a single SPARC-10 platform and the recognition accuracy is 96.8 percent are achieved for lexicon size of 10, on a database of postal words captured at 212 dpi.

Fingerprint enhancement using STFT analysis

Contrary to popular belief, despite decades of research in fingerprints, reliable fingerprint recognition is still an open problem. Extracting features out of poor quality prints is the most challenging problem faced in this area. This paper introduces a new approach for fingerprint enhancement based on short time Fourier transform (STFT) Analysis. STFT is a well-known technique in signal processing to analyze non-stationary signals. Here we extend its application to 2D fingerprint images. The algorithm simultaneously estimates all the intrinsic properties of the fingerprints such as the foreground region mask, local ridge orientation and local ridge frequency. Furthermore we propose a probabilistic approach of robustly estimating these parameters. We experimentally compare the proposed approach to other filtering approaches in literature and show that our technique performs favorably.

The role of holistic paradigms in handwritten word recognition

The holistic paradigm in handwritten word recognition treats the word as a single, indivisible entity and attempts to recognize words from their overall shape, as opposed to their character contents. In this survey, we have attempted to take a fresh look at the potential role of the holistic paradigm in handwritten word recognition. The survey begins with an overview of studies of reading which provide evidence for the existence of a parallel holistic reading process,in both developing and skilled readers. In what we believe is a fresh perspective on handwriting recognition, approaches to recognition are characterized as forming a continuous spectrum based on the visual complexity of the unit of recognition employed and an attempt is made to interpret well-known paradigms of word recognition in this framework. An overview of features, methodologies, representations, and matching techniques employed by holistic approaches is presented.

Behavioural biometrics: a survey and classification

This study is a survey and classification of the state-of-the-art in behavioural biometrics which is based on skills, style, preference, knowledge, motor-skills or strategy used by people while accomplishing different everyday tasks such as driving an automobile, talking on the phone or using a computer. The authors examine current research in the field and analyse the types of features used to describe different types of behaviour. After comparing accuracy rates for verification of users using different behavioural biometric approaches, researchers address privacy issues which arise or might arise in the future with the use of behavioural biometrics.

A minutia-based partial fingerprint recognition system

Matching incomplete or partial fingerprints continues to be an important challenge today, despite the advances made in fingerprint identification techniques. While the introduction of compact silicon chip-based sensors that capture only part of the fingerprint has made this problem important from a commercial perspective, there is also considerable interest in processing partial and latent fingerprints obtained at crime scenes. When the partial print does not include structures such as core and delta, common matching methods based on alignment of singular structures fail. We present an approach that uses localized secondary features derived from relative minutiae information. A flow network-based matching technique is introduced to obtain one-to-one correspondence of secondary features. Our method balances the tradeoffs between maximizing the number of matches and minimizing total feature distance between query and reference fingerprints. A two-hidden-layer fully connected neural network is trained to generate the final similarity score based on minutiae matched in the overlapping areas. Since the minutia-based fingerprint representation is an ANSI-NIST standard [American National Standards Institute, New York, 1993], our approach has the advantage of being directly applicable to existing databases. We present results of testing on FVC2002s DB1 and DB2 databases.

Robustness of multimodal biometric fusion methods against spoof attacks

In this paper, we address the security of multimodal biometric systems when one of the modes is successfully spoofed. We propose two novel fusion schemes that can increase the security of multimodal biometric systems. The first is an extension of the likelihood ratio based fusion scheme and the other uses fuzzy logic. Besides the matching score and sample quality score, our proposed fusion schemes also take into account the intrinsic security of each biometric system being fused. Experimental results have shown that the proposed methods are more robust against spoof attacks when compared with traditional fusion methods.

Review of Classifier Combination Methods

Classifier combination methods have proved to be an effective tool to increase the performance of pattern recognition applications. In this chapter we review and categorize major advancements in this field. Despite a significant number of publications describing successful classifier combination implementations, the theoretical basis is still missing and achieved improvements are inconsistent. By introducing different categories of classifier combinations in this review we attempt to put forward more specific directions for future theoretical research. We also introduce a retraining effect and effects of locality based training as important properties of classifier combinations. Such effects have significant influence on the performance of combinations, and their study is necessary for complete theoretical understanding of combination algorithms.

An architecture for handwritten text recognition systems

Abstract. This paper presents an end-to-end system for reading handwritten page images. Five functional modules included in the system are introduced in this paper: (i) pre-processing, which concerns introducing an image representation for easy manipulation of large page images and image handling procedures using the image representation; (ii) line separation, concerning text line detection and extracting images of lines of text from a page image; (iii) word segmentation, which concerns locating word gaps and isolating words from a line of text image obtained efficiently and in an intelligent manner; (iv) word recognition, concerning handwritten word recognition algorithms; and (v) linguistic post-pro- cessing, which concerns the use of linguistic constraints to intelligently parse and recognize text. Key ideas employed in each functional module, which have been developed for dealing with the diversity of handwriting in its various aspects with a goal of system reliability and robustness, are described in this paper. Preliminary experiments show promising results in terms of speed and accuracy.

Half-Against-Half multi-class support vector machines

A Half-Against-Half (HAH) multi-class SVM is proposed in this paper. Unlike the commonly used One-Against-All (OVA) and One-Against-One (OVO) implementation methods, HAH is built via recursively dividing the training dataset of K classes into two subsets of classes. The structure of HAH is same as a decision tree with each node as a binary SVM classifier that tells a testing sample belongs to one group of classes or the other. The trained HAH classifier model consists of at most K binary SVMs. For each classification testing, HAH requires at most K binary SVM evaluations. Both theoretical estimation and experimental results show that HAH has advantages over OVA and OVO based methods in the evaluation speed as well as the size of the classifier model while maintaining comparable accuracy.

Separating text and background in degraded document images - a comparison of global thresholding techniques for multi-stage thresholding

Before any processing of the textual content of a document image can be performed the text must be separated from the background of the image. Several thresholding algorithms have previously been proposed and are widely used in document processing. None have been shown effective at thresholding difficult documents where the background and foreground are non-uniform. In this paper we investigate the use of three global thresholding algorithms (Otsus, Kapurs entropy and Solihins quadratic integral ratio (QIR)) as the first stage in a multi-stage thresholding algorithm for use in degraded document images. It is concluded that Otsus and Kapurs algorithms do not work well for difficult documents as they tend to over-threshold the image, thus losing much of the useful information. The QIR algorithm is more accurate in separating the foreground and background in these images, leaving a range of undecided, fuzzy, pixels for later processing in a subsequent stage.