Showing papers on "Handwriting recognition published in 2003"

Word image matching using dynamic time warping

Abstract: Libraries and other institutions are interested in providing access to scanned versions of their large collections of handwritten historical manuscripts on electronic media. Convenient access to a collection requires an index, which is manually created at great labor and expense. Since current handwriting recognizers do not perform well on historical documents, a technique called word spotting has been developed: clusters with occurrences of the same word in a collection are established using image matching. By annotating "interesting" clusters, an index can be built automatically. We present an algorithm for matching handwritten words in noisy historical documents. The segmented word images are preprocessed to create sets of 1-dimensional features, which are then compared using dynamic time warping. We present experimental results on two different data sets from the George Washington collection. Our experiments show that this algorithm performs better and is faster than competing matching techniques.

Large vocabulary off-line handwriting recognition: A survey

Abstract: Considerable progress has been made in handwriting recognition technology over the last few years. Thus far, handwriting recognition systems have been limited to small and medium vocabulary applications, since most of them often rely on a lexicon during the recognition process. The capability of dealing with large lexicons, however, opens up many more applications. This article will discuss the methods and principles that have been proposed to handle large vocabularies and identify the key issues affecting their future deployment. To illustrate some of the points raised, a large vocabulary off-line handwritten word recognition system will be described.

Recognition of cursive Roman handwriting: past, present and future

Abstract: This paper reviews the state of the art in off-line Roman cursive handwriting recognition. The input provided to an off-line handwriting recognition system is an image of a digit, a word, or - more generally -some text, and the system produces, as output, an ASCII transcription of the input. This task involves a number of processing steps, some of which are quite difficult. Typically, preprocessing, normalization, feature extraction, classification, and postprocessing operations are required. We'll survey the state of the art, analyze recent trends, and try to identify challenges for future research in this field.

Segmentation of Bangla unconstrained handwritten text

Abstract: To take care of variability involved in the writing style ofdifferent individuals in this paper we propose a robustscheme to segment unconstrained handwritten Banglatexts into lines, words and characters. For linesegmentation, at first, we divide the text into verticalstripes. Stripe width of a document is computed bystatistical analysis of the text height in the document.Next we determine horizontal histogram of these stripesand the relationship of the minimal values of thehistograms is used to segment text lines. Based onvertical projection profile lines are segmented intowords. Segmentation of characters from handwrittenword is very tricky as the characters are seldomvertically separable. We use a concept based on waterreservoir principle for the purpose. Here we, at first,identify isolated and connected (touching) characters ina word. Next touching characters of the word aresegmented based on the reservoir base area points andstructural feature of the component.

HMM based approach for handwritten arabic word recognition using the IFN/ENIT - database

Abstract: An offline recognition system for Arabic handwrittenwords is presented. The recognition system is based ona semi-continuous 1-dimensional HMM. From each binaryword image normalization parameters were estimated. Firstheight, length, and baseline skew are normalized, then featuresare collected using a sliding window approach. Thispaper presents these methods in more detail. Some parameterswere modified and the consequent effect on the recognitionresults are discussed. Significant tests were performedusing the new IFN/ENIT - database of handwritten Arabicwords. The comprehensive database consists of 26459Arabic words (Tunisian town/village names) handwrittenby 411 different writers and is free for non-commercial research.In the performed tests we achieved maximal recognitionrates of about 89% on a word level.

Unsupervised feature selection using multi-objective genetic algorithms for handwritten word recognition

Abstract: In this paper a methodology for feature selection in unsupervisedlearning is proposed. It makes use of a multi-objectivegenetic algorithm where the minimization of thenumber of features and a validity index that measures thequality of clusters have been used to guide the search towardsthe more discriminant features and the best numberof clusters. The proposed strategy is evaluated usingtwo synthetic data sets and then it is applied to handwrittenmonth word recognition. Comprehensive experimentsdemonstrate the feasibility and efficiency of the proposedmethodology.

Generation of synthetic training data for an HMM-based handwriting recognition system

Abstract: A perturbation model for generating synthetic text lines from existing cursively handwritten lines of text produced by human writers is presented. Our purpose is to improve the performance of an HMM-based off-line cursive handwriting recognition system by providing it with additional synthetic training data. Two kinds of perturbations are applied, geometrical transformations and thinning/thickening operations. The proposed perturbation model is evaluated under different experimental conditions.

Method and system for three-dimensional handwriting recognition

Abstract: The present invention relates to three-dimensional (3D) handwriting recognition methods and systems. The present invention provides a 3D handwriting recognition method and corresponding system which allows to generate 3D motion data by tracking corresponding 3D motion, calculate corresponding 3D coordinates, construct corresponding 3D tracks, derive 2D projection plane based on some strokes 3D tracks of on character, and generate 2D image for handwriting recognition by mapping the 3D tracks onto the said 2D projection plane. The 3D handwriting recognition method according to the present invention can use the processing power of system more efficiently and highly improve the system performance. So that the system can get the final input result in a much shorter time after the user finishes writing a character without a long time waiting between two characters input, thus the user has more pleased and natural input experience.

Individuality of handwritten characters

Abstract: Analysis of handwritten characters (allographs) plays animportant role in forensic document examination. However,so far there lacks a comprehensive and quantitative study onindividuality of handwritten characters. Based on a largenumber of handwritten characters extracted from handwritingsamples of 1000 individuals in US, the individuality ofhandwritten characters has been quantitatively measuredthrough identification and verification models. Our studyshows that in general alphabetic characters bear more individualitythan numerals and use of a certain number ofcharacters will significantly outperform the global featuresof handwriting samples in handwriting identification andverification. Moreover, the quantitative measurement ofdiscriminative powers of characters offers a general guidancefor selecting most-informative characters in examiningforensic documents.

The state of the art in Japanese online handwriting recognition compared to techniques in western handwriting recognition

Abstract: This paper compares the current state of the art in online Japanese character recognition with techniques in western handwriting recognition. It discusses important developments in preprocessing, classification, and postprocessing for Japanese character recognition in recent years and relates them to the developments in western handwriting recognition. Comparing eastern and western handwriting recognition techniques allows learning from very different approaches and understanding the underlying common foundations of handwriting recognition. This is very important when it comes to developing compact modules for integrated systems supporting many writing systems capable of recognizing multilanguage documents.

Analysis of handwriting individuality using word features

Abstract: Analysis of allographs (characters) and allograph combinations(words) is the key for obtaining the discriminatingelements of handwriting. While allographs usually inhabitin words and segregation of a word into allographs ismore subjective than objective, especially for cursive writing,analysis of handwritten words is a natural and betteroption. In this study, a handwritten word image is characterizedby gradient, structural, and concavity features, andindividuality of handwritten words is experimented throughwritership identification and verification on over 12,000word images extracted from 3000 handwriting samples of1000 individuals in U.S.. Experimental results show thathandwritten words are very effective in differentiating handwritingand carry more individuality than most handwrittencharacters (allographs).

Writer identification using innovative binarised features of handwritten numerals

Abstract: The objective of this paper is to present a number of features that can be extracted from handwritten digits and used for author verification or identification of a person's handwriting. The features under consideration are mainly computational features some of which cannot be easily evaluated by humans. On the other hand, these features can be extracted by computer algorithms with a high degree of accuracy. The eleven features used are described. All features were appropriately binarized so that binary feature vectors of constant lengths could be formed. These vectors were then used for author discrimination, using the Hamming distance measure. For this task a writer database consisting of 15 writers was created. Each writer was asked to write random strings of 0 to 9 at least 10 times. The results indicate that the combined features work well at discriminating writers and warrant further detailed investigation. Although the set of features was designed for dealing with handwritten digits (as may be written on cheques), it may also be used for isolated alphabetic characters.

Recognition of on-line handwritten mathematical formulas in the E-chalk system

Abstract: In this article, we present a system for the recognition ofon-line handwritten mathematical formulas which is usedin the electronic chalkboard (E-chalk), a multimedia systemfor distance-teaching. We discuss the classification of symbolsand the construction of the tree of spatial relationshipsamong them. The classification is based on support vectormachines and the construction of formulas is based onbaseline structure analysis.

Optimizing the number of states, training iterations and Gaussians in an HMM-based handwritten word recognizer

Abstract: In off-line handwriting recognition, classifiers based on hidden Markov models (HMMs) have become very popular. However, while there exist well-established training algorithms, such as the Baum-Welsh procedure, which optimize the transition and output probabilities of a given HMM architecture, the architecture itself, and in particular the number of states, must be chosen "by hand". Also the number of training iterations and the output distributions need to be defined by the system designer. In this paper we examine some optimization strategies for an HMM classifier that works with continuous feature values and uses the Baum-Welch training algorithm. The free parameters of the optimization procedure introduced in this paper are the number of states of a model, the number of training iterations, and the number of Gaussian mixtures for each state. The proposed optimization strategies are evaluated in the context of a handwritten word recognition task.

Script-based classification of hand-written text documents in a multilingual environment

Abstract: Script-based text document classification is an important field of research in the context of multilingual textual document processing But, all script identification techniques available in the literature so far do not consider handwritten documents Variations in the writing style, character size, inter-line and inter-word spacings, etc make the recognition process difficult and unreliable when these script identification algorithms, more specifically visual appearance based approaches, are applied directly on hand-written documents Therefore, in this paper, we propose to preprocess the input document images so as to compensate for the variations due to writing style and thereby making them suitable for analysis on the basis of their visual appearances Accordingly, we apply denoising, thinning, pruning, m-connectivity and text size normalization in sequence Multi-channel Gabor filtering is used to extract texture features that characterize the visual appearances of the document images Experimental result proves the potentiality of our proposed method of script identification for hand-written text document classification

A hybrid on/off line handwritten signature verification system

Abstract: This paper proposes a new hybrid handwritten signature verification system where the on-line reference data acquired through a digitizing tablet serves as the basis for the segmentation process of the corresponding scanned off-line data. Local foci of attention over the image are determined through a self-adjustable learning process in order to pinpoint the feature extraction process. Both local and global primitives are processed and the decision about the authenticity of the specimen is defined through similarity measurements. The global performance of the system is measured using two different classifiers.

Scaled text replacement of ink

Abstract: Systems, methods, and computer-readable media for processing electronic ink: (a) receive electronic ink input; (b) convert the input to machine-generated objects; and (c) render the objects such that their size substantially corresponds to the input's original size. The input ink may constitute text, and the machine-generated objects may correspond to words, lines, and/or other groupings of text generated by a handwriting recognizer. To enable quick and easy identification of recognizer errors, in at least some systems and methods, a user may select one or more words, which will cause the system to display the original ink corresponding to the selected word(s). Such systems also may display alternative words generated by the recognizer corresponding to the selected original ink and allow the user to select one of the alternatives to make corrections in the recognized text (akin to using a spell-checking or handwriting recognition program).

Multi-modal handwriting recognition correction

Abstract: Systems, methods, and computer-readable media for processing electronic ink receive an electronic ink input; convert the electronic ink input to a first machine-generated object using handwriting recognition; display the first machine-generated object on a display; receive speech input; convert the speech input to a second machine-generated object using speech recognition; generate a list of machine-generated objects based on the electronic ink input, the list including the first machine-generated object and alternative machine-generated objects and functioning as a dictionary for converting the speech input; and replace the first machine-generated object with the second machine-generated object. The machine-generated objects may correspond to words, lines, and/or other groupings of machine-generated text. A user may confirm that the second machine-generated object should replace the first machine-generated object and the system will perform the replacement. The systems and methods may generate a list of alternative machine-generated object candidates to the first machine-generated object based on handwriting recognition of the electronic ink input alone or in combination with a statistical language model.

An integrated system for handwritten document image processing

Abstract: In this paper we attempt to face common problems of handwritten documents such as nonparallel text lines in a page, hill and dale writing, slanted and connected characters. Towards this end an integrated system for document image preprocessing is presented. This system consists of the following modules: skew angle estimation and correction, line and word segmentation, slope and slant correction. The skew angle correction, slope correction and slant removing algorithms are based on a novel method that is a combination of the projection profile technique and the Wigner–Ville distribution. Furthermore, the skew angle correction algorithm can cope with pages whose text line skew angles vary, and handle them by areas. Our system can be used as a preprocessing stage to any handwriting character recognition or segmentation system as well as to any writer identification system. It was tested in a wide variety of handwritten document images of unconstrained English and Modern Greek text from about 100 writers. Add...

A contour code feature based segmentation for handwriting recognition

Abstract: The purpose of this paper is to present a novel contourcode feature in conjunction with a rule basedsegmentation for cursive handwriting recognition. Aheuristic segmentation algorithm is initially used to oversegment each word. Then the prospective segmentationpoints are passed through the rule-based module todiscard the incorrect segmentation points and include anymissing segmentation points. The proposed rule-basedmodule validates every segmentation points againstclosed area, average character size, left character anddensity. During the left char validation, a contour codefeature is extracted and checked weather the left of theprospective segmentation point is a character or rubbish(non-char). The neural network used for this validationwas trained on character and non-character database.Following the segmentation, the contour between correctsegmentation points is passed through the featureextraction module that extracts the contour code, afterwhich another trained neural network is used forclassification. The recognized characters are groupedinto words and passed to a variable length lexicon thatretrieves words that has highest confidence value.

Ensembles of classifiers for handwritten word recognition

Abstract: Handwritten text recognition is one of the most difficult problems in the field of pattern recognition. Recently, a number of classifier creation and combination methods, known as ensemble methods, have been proposed in the field of machine learning. They have shown improved recognition performance over single classifiers. In this paper the application of some of those ensemble methods in the domain of offline cursive handwritten word recognition is described. The basic word recognizers are given by hidden Markov models (HMMs). It is demonstrated through experiments that ensemble methods have the potential of improving recognition accuracy also in the domain of handwriting recognition.

Lexicon-driven HMM decoding for large vocabulary handwriting recognition with multiple character models

Abstract: This paper presents a handwriting recognition system that deals with unconstrained handwriting and large vocabularies. The system is based on the segmentation-recognition paradigm where words are first loosely segmented into characters or pseudocharacters and the final segmentation is obtained during the recognition process, which is carried out with a lexicon. Characters are modeled by multiple hidden Markov models (HMMs), which are concatenated to build up word models. The lexicon is organized as a tree structure, and during the decoding words with similar prefixes share the same computation steps. To avoid an explosion of the search space due to the presence of multiple character models, a lexicon-driven level building algorithm (LDLBA) is used to decode the lexical tree and to choose at each level the more likely models. Bigram probabilities related to the variation of writing styles within the words are inserted between the levels of the LDLBA to improve the recognition accuracy. To further speed up the recognition process, some constraints are added to limit the search efforts to the more likely parts of the search space. Experimental results on a dataset of 4674 unconstrained words show that the proposed recognition system achieves recognition rates from 98% for a 10-word vocabulary to 71% for a 30,000-word vocabulary and recognition times from 9 ms to 18.4 s, respectively.

Generation of handwritten characters with Bayesian network based on-line handwriting recognizers

Abstract: In this paper, we propose a new character generationmethod from on-line handwriting recognizers basedon Bayesian networks. On-line handwriting recognizersare trained with handwriting samples from many writers.Then, character shapes are generated from given texts bysearching the most probable input point sequences. SinceBayesian network based classifiers have large number ofparameters for modeling components and their relationships,they generate more natural character shapes thanvarious kinds of hidden Markov models.

Generation and Use of Synthetic Training Data in Cursive Handwriting Recognition

Abstract: Three different methods for the synthetic generation of handwritten text are introduced. These methods are experimentally evaluated in the context of a cursive handwriting recognition task, using an HMM-based recognizer. In the experiments, the performance of a traditional recognizer, which is trained on data produced by human writers, is compared to a system that is trained on synthetic data only. Under the most elaborate synthetic handwriting generation model, a level of performance comparable to, or even slightly better than, the system trained on the writing of humans was observed.

Towards automatic video-based whiteboard reading

Abstract: As whiteboards have become a popular tool in meeting rooms, there has been a growing interest in making use of the whiteboard as a user interface for human computer interaction. Therefore, systems based on electronic whiteboards have been developed in order to serve as meeting assistants for e.g. collaborative working. However, as special pens and erasers are required, the natural interaction is restricted. In order to render this communication method more natural it was proposed to retain ordinary whiteboard and pens and to visually observe the writing process using a video camera by Stafford-Fraser and Robinson (1996). In this paper a prototype system for automatic video-based whiteboard reading is presented. The system is designed for recognizing unconstrained handwritten text and is further characterized by an incremental processing strategy in order to facilitate recognizing portions of text as soon as they have been written on the board. We present the methods employed for extracting text regions, pre-processing, feature extraction, and statistical modeling and recognition. Evaluation results on a writer independent unconstrained handwriting recognition task demonstrate the feasibility of the proposed approach.

Combining online and offline handwriting recognition

Abstract: This work describes an online handwriting recognition system working in combination with an offline recognizer. The online input data is first transcribed by theonline recognizer, then converted into an offline bitmapand recognized by the offline system. The outputs ofthe two recognizers are then combined probabilisticallyresulting in a classifier out-performing both individualsystems. Experiments were performed over a databaseof single digits. The error rate of the online recognizeris reduced by 43% when the combination with the offlinesystem is applied.

Offline recognition of large vocabulary cursive handwritten text

Abstract: This paper presents a system for the offline recognitionof cursive handwritten lines of text. The system is based oncontinuous density HMMs and Statistical Language Models.The system recognizes data produced by a single writer.No a-priori knowledge is used about the content of the textto be recognized. Changes in the experimental setup withrespect to the recognition of single words are highlighted.The results show a recognition rate of ~85% with a lexiconcontaining 50'000 words. The experiments were performedover a publicly available database.

On-line overlaid-handwriting recognition based on substroke HMMs

Abstract: This paper proposes a novel handwriting recognition interfacefor wearable computing where users write characterscontinuously without pauses on a small single writingbox. Since characters are written on the same writingarea, they are overlaid with each other. Therefore thetask is regarded as a special case of the continuous characterrecognition problem. In contrast to the conventionalcontinuous character recognition problem, location informationof strokes does not help very much in the proposedframework. To tackle the problem, substroke based hiddenMarkov models (HMMs) and a stochastic bigram languagemodel are employed. Preliminary experiments were carriedout on a dataset of 578 handwriting sequences with acharacter bigram consisting of 1,016 Japanese educationalKanji and 71 Hiragana characters. The proposed methoddemonstrated promising performance with 69.2% of hand-writingsequences beeing correctly recognized when differentstroke order was permitted, and the rate was improvedup to 88.0% when characters were written with fixed strokeorder.

Combining model-based and discriminative classifiers: application to handwritten character recognition

Abstract: Handwriting recognition is such a complex classification problem that it is quite usual now to make co-operate several classification methods at the pre-processing stage or at the classification stage. In this paper, we present an original two stages recognizer. The first stage is a model-based classifier that stores an exhaustive set of character models. The second stage is a discriminative classifier that separates the most ambiguous pairs of classes. This hybrid architecture is based on the idea that the correct class almost systematically belongs to the two more relevant classes found by the first classifier. Experiments on the Unipen database show a 30% improvement on a 62 class recognition problem.