Showing papers by "Ching Y. Suen published in 1999"

An HMM-based approach for off-line unconstrained handwritten word modeling and recognition

Abstract: Describes a hidden Markov model-based approach designed to recognize off-line unconstrained handwritten words for large vocabularies. After preprocessing, a word image is segmented into letters or pseudoletters and represented by two feature sequences of equal length, each consisting of an alternating sequence of shape-symbols and segmentation-symbols, which are both explicitly modeled. The word model is made up of the concatenation of appropriate letter models consisting of elementary HMMs and an HMM-based interpolation technique is used to optimally combine the two feature sets. Two rejection mechanisms are considered depending on whether or not the word image is guaranteed to belong to the lexicon. Experiments carried out on real-life data show that the proposed approach can be successfully used for handwritten word recognition.

Analysis of class separation and combination of class-dependent features for handwriting recognition

Abstract: In this paper, we propose a new approach to combine multiple features in handwriting recognition based on two ideas: feature selection-based combination and class dependent features. A nonparametric method is used for feature evaluation, and the first part of this paper is devoted to the evaluation of features in terms of their class separation and recognition capabilities. In the second part, multiple feature vectors are combined to produce a new feature vector. Based on the fact that a feature has different discriminating powers for different classes, a new scheme of selecting and combining class-dependent features is proposed. In this scheme, a class is considered to have its own optimal feature vector for discriminating itself from the other classes. Using an architecture of modular neural networks as the classifier, a series of experiments were conducted on unconstrained handwritten numerals. The results indicate that the selected features are effective in separating pattern classes and the new feature vector derived from a combination of two types of such features further improves the recognition rate.

Identification of fork points on the skeletons of handwritten Chinese characters

Abstract: This paper describes techniques for stroke extraction used in the recognition of handwritten Chinese characters. A new set of feature points is proposed for the analysis of skeleton images. Based on a geometrical graph, a novel criterion is proposed for the identification of fork points in a skeleton image which correspond to joint points in the original character image. Experimental results indicate that the proposed method correctly determines the fork points, and is effective in unifying the joint points.

Recognition of handwritten numerals by quantum neural network with fuzzy features

Abstract: This paper describes a new kind of neural network – Quantum Neural Network (QNN) – and its application to the recognition of handwritten numerals. QNN combines the advantages of neural modelling and fuzzy theoretic principles. Novel experiments have been designed for in-depth studies of applying the QNN to both real data and confusing images synthesized by morphing. Tests on synthesized data examine QNN's fuzzy decision boundary with the intention to illustrate its mechanism and characteristics, while studies on real data prove its great potential as a handwritten numeral classifier and the special role it plays in multi-expert systems. An effective decision-fusion system is proposed and a high reliability of 99.10% has been achieved.

Extraction of bankcheck items by mathematical morphology

Abstract: This paper presents a technique for extracting the user-entered information from bankcheck images based on a layout-driven item extraction method. The baselines of checks are detected and eliminated by using gray-level mathematical morphology. A priori information about the positions of data is integrated into a combination of top-down and bottom-up analyses of check images. The handwritten information is extracted by a local thresholding technique and the information lost during baseline elimination is restored by mathematical morphology with dynamic kernels. A goal-directed evaluation of the extraction approaches is proposed, and both qualitative and quantitative analyses show noticeable advantages of the proposed approach over the existing approaches.

A recent development in image analysis of electrophoresis gels

Abstract: Electrophoresis is an electrochemical separation process in which molecules, such as protein or RNA/DNA fragments, are made to migrate through a specific substrate, such as a polyacrylamide gel, under the influence of an electric current. The technique has a wide range of applications, in DNA sequencing and in studying variation in the identity and amount of proteins obtained from different sources. Techniques of image analysis and pattern recognition can be used to extract qualitative as well as quantitative information from the images, and spare human beings from voluminous, tedious image interpretation. More importantly, computerized data handling and interpretation provide accuracy and rapid speed without human errors. Here, we report the application of a newly developed system to the analysis of biological specimens that have undergone gel electrophoresis. The result of this application shows the capability to identify unique banding patterns of cDNA profiles, which paves the way for future full-scale investigation in the use of pattern recognition principles in biomedical information handling and interpretation.

Categorizing Document Images into Script and Language Classes

Abstract: In order to properly archive and index large numbers of international documents, several challenging processing steps must be completed even before optical character recognition (OCR) can be applied. We present a system that preclassifies documents for further processing and OCR. The system operates in four phases: preprocessing (including skew detection, segmentation, and noise removal), script (Latin, Arabic, Ideographic, or Cyrillic) classification, shape coding, and language classification for seven European languages.

Influence of word length on handwriting recognition

Abstract: Two strategies can be considered in handwriting recognition: phrase or word approaches. In this paper, we demonstrate the superiority of the phrase-based strategy, especially in city name recognition. The performance of an HMM-based off-line system using an analytic approach with explicit segmentation is evaluated on two databases: (i) city names in full, and (ii) city names in single words. A difference in performance is observed, principally caused by the dissimilarity of word lengths between the two databases. After generating other data sets and lexicons, experiments were performed yielding results which lead us to conclude that word length in the data set, as well as in lexicons, significantly influences recognition performance, and also that it is preferable to perform city name recognition based on the phrase approach rather than by word recognition.

Rejection Criteria and Pairwise Discrimination of Handwritten Numerals Based on Structural Features

Abstract: This paper presents a new structural method for the recognition of handwritten numerals. Contour shape features, such as convex arcs, concave arcs, line segments, end-point arcs and holes from the contours of numeric characters, are used to describe numeral characters. A new method of measuring the similarity between a sample and class is proposed. A two-stage recognition methodology is also presented, in which two rejection criteria are introduced. In the first stage of recognition, an input sample is given an identity or categorised as either first class or second class rejection, based on similarity measures between the input sample and each of the ten numeral classes. In the second stage of recognition, strategies are introduced to modify the structural description of the input sample if it is in first class rejection and a classifier focused on pairwise discrimination is applied if the input sample is in second class rejection. Experimental results indicate that the overall performance of the proposed method compares favourably with those achieved by other methods found in the literature.

Model-based character extraction from complex backgrounds

Abstract: This paper proposes a model-based character extraction method. We model a pixel belonging to a character as a double-edge, whose range is defined by the stroke width, and whose intensity is proportional to the local contrast. By extracting such double-edge feature at a predefined stroke width, sharply changing as well as slowly varying backgrounds can be eliminated. A set of morphological operators is designed to extract the double-edge feature at each pixel of the raw image, and the characters are extracted by thresholding these features. A goal directed evaluation of extraction of the courtesy amount from bank cheques reveals the advantages of the proposed method over other existing methods. Visual inspection of legal amount extraction shows further promise in extracting characters from complex backgrounds.

A lexicon driven approach for off-line recognition of unconstrained handwritten Korean words

Abstract: We propose a new method for the recognition of unconstrained handwritten words consisting of Korean and numeric characters. To overcome the difficulty of separating touching characters, we adopt an over-segmentation technique and we find the optimal segment combination using a lexicon-driven word scoring technique and a nearest neighbor classifier. The optimal combination gives the final segmentation positions for individual characters with the best matching word in the lexicon. The proposed system has yielded an accuracy of 90.64% for 908 word images on live mail pieces.