Sargur N. Srihari

Online and off-line handwriting recognition: a comprehensive survey

Handwriting has continued to persist as a means of communication and recording information in day-to-day life even with the introduction of new technologies. Given its ubiquity in human transactions, machine recognition of handwriting has practical significance, as in reading handwritten notes in a PDA, in postal addresses on envelopes, in amounts in bank checks, in handwritten fields in forms, etc. This overview describes the nature of handwritten language, how it is transduced into electronic data, and the basic concepts behind written language recognition algorithms. Both the online case (which pertains to the availability of trajectory data during writing) and the off-line case (which pertains to scanned images) are considered. Algorithms for preprocessing, character and word recognition, and performance with practical systems are indicated. Other fields of application, like signature verification, writer authentification, handwriting learning tools are also considered.

Decision combination in multiple classifier systems

A multiple classifier system is a powerful solution to difficult pattern recognition problems involving large class sets and noisy input because it allows simultaneous use of arbitrary feature descriptors and classification procedures. Decisions by the classifiers can be represented as rankings of classifiers and different instances of a problem. The rankings can be combined by methods that either reduce or rerank a given set of classes. An intersection method and union method are proposed for class set reduction. Three methods based on the highest rank, the Borda count, and logistic regression are proposed for class set reranking. These methods have been tested in applications of degraded machine-printed characters and works from large lexicons, resulting in substantial improvement in overall correctness. >

Off-line cursive script word recognition

Cursive script word recognition is the problem of transforming a word from the iconic form of cursive writing to its symbolic form. Several component processes of a recognition system for isolated offline cursive script words are described. A word image is transformed through a hierarchy of representation levels: points, contours, features, letters, and words. A unique feature representation is generated bottom-up from the image using statistical dependences between letters and features. Ratings for partially formed words are computed using a stack algorithm and a lexicon represented as a trie. Several novel techniques for low- and intermediate-level processing for cursive script are described, including heuristics for reference line finding, letter segmentation based on detecting local minima along the lower contour and areas with low vertical profiles, simultaneous encoding of contours and their topological relationships, extracting features, and finding shape-oriented events. Experiments demonstrating the performance of the system are also described. >

Individuality of handwriting.

Motivated by several rulings in United States courts concerning expert testimony in general, and handwriting testimony in particular, we undertook a study to objectively validate the hypothesis that handwriting is individual. Handwriting samples of 1,500 individuals, representative of the U.S. population with respect to gender, age, ethnic groups, etc., were obtained. Analyzing differences in handwriting was done by using computer algorithms for extracting features from scanned images of handwriting. Attributes characteristic of the handwriting were obtained, e.g., line separation, slant, character shapes, etc. These attributes, which are a subset of attributes used by forensic document examiners (FDEs), were used to quantitatively establish individuality by using machine learning approaches. Using global attributes of handwriting and very few characters in the writing, the ability to determine the writer with a high degree of confidence was established. The work is a step towards providing scientific support for admitting handwriting evidence in court. The mathematical approach and the resulting software also have the promise of aiding the FDE.

On measuring the distance between histograms

Abstract A distance measure between two histograms has applications in feature selection, image indexing and retrieval, pattern classification and clustering, etc. We propose a distance between sets of measurement values as a measure of dissimilarity of two histograms. The proposed measure has the advantage over the traditional distance measures regarding the overlap between two distributions; it takes the similarity of the non-overlapping parts into account as well as that of overlapping parts. We consider three versions of the univariate histogram, corresponding to whether the type of measurement is nominal, ordinal, and modulo and their computational time complexities are Θ(b), Θ(b) and O(b2) for each type of measurements, respectively, where b is the number of levels in histograms.

Analysis of textual images using the Hough transform

The analysis of images of printed pages of text is considered. Since printed text can be viewed as textured line, the use of the Hough transform for detecting straight lines is proposed as an analysis tool. Methods for handling several discretization problems that arise in mapping the rectangular image space to the (ρ, Θ) accumulator array are described. Several applications of analyzing the accumulator array are proposed. They include detecting the text skew angle, determining the signature of a text line so as to accept or reject a block as containing only text, using profile analysis to segment text into lines, and determining whether a textual block is rightside-up or otherwise.

Classification of newspaper image blocks using texture analysis

Abstract An important step in the analysis of images of printed documents is the classification of segmented blocks into categories such as half-tone photographs, text with large letters, text with small letters, line drawings, etc. In this paper, a method to classify blocks segmented from newspaper images is described. It is assumed that homogeneous rectangular blocks are first segmented out of the image using methods such as run-length smoothing and recursive horizontal/vertical cuts. The classification approach is based on statistical textural features and feature space decision techniques. Two matrices, whose elements are frequency counts of black-white pair run lengths and black-white-black combination run lengths, are used to derive texture information. Three features are extracted from the matrices to determine a feature space in which block classification is accomplished using linear discriminant functions. Experimental results using different block segmentation results, different newspapers, and different image resolutions are given. Performance and speed with different image resolutions are indicated.

Document image binarization based on texture features

Binarization has been difficult for document images with poor contrast, strong noise, complex patterns, and/or variable modalities in gray-scale histograms. We developed a texture feature based thresholding algorithm to address this problem. Our algorithm consists of three steps: 1) candidate thresholds are produced through iterative use of Otsus algorithm (1978); 2) texture features associated with each candidate threshold are extracted from the run-length histogram of the accordingly binarized image; 3) the optimal threshold is selected so that desirable document texture features are preserved. Experiments with 9,000 machine printed address blocks from an unconstrained US mail stream demonstrated that over 99.6 percent of the images were successfully binarized by the new thresholding method, appreciably better than those obtained by typical existing thresholding techniques. Also, a system run with 500 troublesome mail address blocks showed that an 8.1 percent higher character recognition rate was achieved with our algorithm as compared with Otsus algorithm.

OFFLINE SIGNATURE VERIFICATION AND IDENTIFICATION USING DISTANCE STATISTICS

This paper describes a novel approach for signature verification and identification in an offline environment based on a quasi-multiresolution technique using GSC (Gradient, Structural and Concavity) features for feature extraction. These features when used at the word level, instead of the character level, yield promising results with accuracies as high as 78% and 93% for verification and identification, respectively. This method was successfully employed in our previous theory of individuality of handwriting developed at CEDAR — based on obtaining within and between writer statistical distance distributions. In this paper, exploring signature verification and identification as offline handwriting verification and identification tasks respectively, we depict a mapping from the handwriting domain to the signature domain.

Representation of Three-Dimensional Digital Images

Three-dimensional digital images are encountered m a variety of problems, including computed tomography, biological modeling, space planning, and computer vision. A wide spectrum of data structures are available for the computer representation of such images. This paper is a tutorial survey of three-dimensmnal spatial-data representation methods emphasizing techniques that apply to cellular (or voxel-based) images. We attempt to unify data structures for representing interior, surface, and structural information of objects in such images by companng their relative efficmncy. The derivation of high-level representatmns from serial sectmn images is also discussed The representations include topological representations (Euler characteristic and adjacency trees), geometrical representatmns {borders, medial axes, and features), and spatial organization representations {generalized cyhnders and skeletons).