Showing papers on "Handwriting recognition published in 2004"

'Online recognition of Chinese characters: the state-of-the-art

Abstract: Online handwriting recognition is gaining renewed interest owing to the increase of pen computing applications and new pen input devices. The recognition of Chinese characters is different from western handwriting recognition and poses a special challenge. To provide an overview of the technical status and inspire future research, this paper reviews the advances in online Chinese character recognition (OLCCR), with emphasis on the research works from the 1990s. Compared to the research in the 1980s, the research efforts in the 1990s aimed to further relax the constraints of handwriting, namely, the adherence to standard stroke orders and stroke numbers and the restriction of recognition to isolated characters only. The target of recognition has shifted from regular script to fluent script in order to better meet the requirements of practical applications. The research works are reviewed in terms of pattern representation, character classification, learning/adaptation, and contextual processing. We compare important results and discuss possible directions of future research.

Holistic word recognition for handwritten historical documents

Abstract: Most offline handwriting recognition approaches proceed by segmenting words into smaller pieces (usually characters) which are recognized separately. The recognition result of a word is then the composition of the individually recognized parts. Inspired by results in cognitive psychology, researchers have begun to focus on holistic word recognition approaches. Here we present a holistic word recognition approach for single-author historical documents, which is motivated by the fact that for severely degraded documents a segmentation of words into characters will produce very poor results. The quality of the original documents does not allow us to recognize them with high accuracy - our goal here is to produce transcriptions that will allow successful retrieval of images, which has been shown to be feasible even in such noisy environments. We believe that this is the first systematic approach to recognizing words in historical manuscripts with extensive experiments. Our experiments show recognition accuracy of 65%, which exceeds performance of other systems which operate on non-degraded input images (nonhistorical documents).

The writer independent online handwriting recognition system frog on hand and cluster generative statistical dynamic time warping

Abstract: In this paper, we give a comprehensive description of our writer-independent online handwriting recognition system frog on hand. The focus of this work concerns the presentation of the classification/training approach, which we call cluster generative statistical dynamic time warping (CSDTW). CSDTW is a general, scalable, HMM-based method for variable-sized, sequential data that holistically combines cluster analysis and statistical sequence modeling. It can handle general classification problems that rely on this sequential type of data, e.g., speech recognition, genome processing, robotics, etc. Contrary to previous attempts, clustering and statistical sequence modeling are embedded in a single feature space and use a closely related distance measure. We show character recognition experiments of frog on hand using CSDTW on the UNIPEN online handwriting database. The recognition accuracy is significantly higher than reported results of other handwriting recognition systems. Finally, we describe the real-time implementation of frog on hand on a Linux Compaq iPAQ embedded device.

Machine printed text and handwriting identification in noisy document images

Abstract: In this paper, we address the problem of the identification of text in noisy document images. We are especially focused on segmenting and identifying between handwriting and machine printed text because: 1) Handwriting in a document often indicates corrections, additions, or other supplemental information that should be treated differently from the main content and 2) the segmentation and recognition techniques requested for machine printed and handwritten text are significantly different. A novel aspect of our approach is that we treat noise as a separate class and model noise based on selected features. Trained Fisher classifiers are used to identify machine printed text and handwriting from noise and we further exploit context to refine the classification. A Markov Random Field-based (MRF) approach is used to model the geometrical structure of the printed text, handwriting, and noise to rectify misclassifications. Experimental results show that our approach is robust and can significantly improve page segmentation in noisy document collections.

System and method for recognizing word patterns in a very large vocabulary based on a virtual keyboard layout

Abstract: A word pattern recognition system based on a virtual keyboard layout combines handwriting recognition with a virtual, graphical, or on-screen keyboard to provide a text input method with relative ease of use. The system allows the user to input text quickly with little or no visual attention from the user. The system supports a very large vocabulary of gesture templates in a lexicon, including practically all words needed for a particular user. In addition, the system utilizes various techniques and methods to achieve reliable recognition of a very large gesture vocabulary. Further, the system provides feedback and display methods to help the user effectively use and learn shorthand gestures for words. Word patterns are recognized independent of gesture scale and location. The present system uses language rules to recognize and connect suffixes with a preceding word, allowing users to break complex words into easily remembered segments.

Systems and methods for collaborative note-taking

Abstract: Techniques are provided for determining collaborative notes and automatically recognizing speech, handwriting and other type of information. Domain and optional actor/speaker information associated with the support information is determined. An initial automatic speech recognition model is determined based on the domain and/or actor information. The domain and/or actor/speaker language model is used to recognize text in the speech information associated with the support information. Presentation support information such as slides, speaker notes and the like are determined. The semantic overlap between the support information and the salient non-function words in the recognized text and collaborative user feedback information are used to determine relevancy scores for the recognized text. Grammaticality, well formedness, self referential integrity and other features are used to determine correctness scores. Suggested collaborative notes are displayed in the user interface based on the salient non-function words. User actions in the user interface determine feedback signals. Recognition models such as automatic speech recognition, handwriting recognition are determined based on the feedback signals and the correctness and relevance scores.

Method and apparatus for scaling handwritten character input for handwriting recognition

Abstract: A method, computer program product, and a data processing system for scaling handwritten character input for performing handwriting recognition. A stroke parameter is derived from a handwritten character stroke and an input area is calculated in which the handwritten character stroke was supplied. The stroke parameter is scaled according to the input area.

Integrated handwriting recognition and interpretation using finite-state models

Abstract: The interpretation of handwritten sentences is carried out using a holistic approach in which both text image recognition and the interpretation itself are tightly integrated. Conventional approaches follow a serial, first-recognition then-interpretation scheme which cannot adequately use semantic–pragmatic knowledge to recover from recognition errors. Stochastic finite-sate transducers are shown to be suitable models for this integration, permitting a full exploitation of the final interpretation constraints. Continuous-density hidden Markov models are embedded in the edges of the transducer to account for lexical and morphological constraints. Robustness with respect to stroke vertical variability is achieved by integrating tangent vectors into the emission densities of these models. Experimental results are reported on a syntax-constrained interpretation task which show the effectiveness of the proposed approaches. These results are also shown to be comparatively better than those achieved with other conventional, N-gram-based techniques which do not take advantage of full integration.

Online handwritten script recognition

Abstract: Automatic identification of handwritten script facilitates many important applications such as automatic transcription of multilingual documents and search for documents on the Web containing a particular script. The increase in usage of handheld devices which accept handwritten input has created a growing demand for algorithms that can efficiently analyze and retrieve handwritten data. This paper proposes a method to classify words and lines in an online handwritten document into one of the six major scripts: Arabic, Cyrillic, Devnagari, Han, Hebrew, or Roman. The classification is based on 11 different spatial and temporal features extracted from the strokes of the words. The proposed system attains an overall classification accuracy of 87.1 percent at the word level with 5-fold cross validation on a data set containing 13,379 words. The classification accuracy improves to 95 percent as the number of words in the test sample is increased to five, and to 95.5 percent for complete text lines consisting of an average of seven words.

Discriminative learning quadratic discriminant function for handwriting recognition

Abstract: In character string recognition integrating segmentation and classification, high classification accuracy and resistance to noncharacters are desired to the underlying classifier. In a previous evaluation study, the modified quadratic discriminant function (MQDF) proposed by Kimura et al. was shown to be superior in noncharacter resistance but inferior in classification accuracy to neural networks. This paper proposes a discriminative learning algorithm to optimize the parameters of MQDF with aim to improve the classification accuracy while preserving the superior noncharacter resistance. We refer to the resulting classifier as discriminative learning QDF (DLQDF). The parameters of DLQDF adhere to the structure of MQDF under the Gaussian density assumption and are optimized under the minimum classification error (MCE) criterion. The promise of DLQDF is justified in handwritten digit recognition and numeral string recognition, where the performance of DLQDF is comparable to or superior to that of neural classifiers. The results are also competitive to the best ones reported in the literature.

Using HMM based recognizers for writer identification and verification

Abstract: In this paper, we use HMM based recognizers for the identification and verification of persons based on their handwriting. For each writer, we build an individual recognizer and train it on text lines of that writer. This gives us recognizers that are experts on the handwriting of exactly one writer. In the identification or verification phase, a text line of unknown origin is presented to each of these recognizers and each one returns a transcription that includes the log-likelihood score for the considered input. These scores are sorted and the resulting ranking is used for both identification and verification. In an identification experiment in 96.56% of all cases the writer out of a set of 100 writers is correctly identified. Second, in a verification experiment using over 8,600 text lines from 120 writers an equal error rate (EER) of about 2.5% is achieved.

System and method for accepting disparate types of user input

Abstract: A user interface allows a user to input handwritten, key-press, and spoken text in a seamless, synchronized manner. A text input panel accepts soft keyboard presses and handwritten words, characters, and gestures. A text recognizer/synchronizer integrates textual input from various sources while recognizing and preserving the order in which a user entered text via the soft keyboard, via handwriting, and/or by speaking. Synchronized text may be displayed in a stage area of the text input panel before being passed to an operating system message router and/or an application program. While in handwriting recognition mode, various permutations and combinations of a word recognition area, a character recognition area, and a keybar/keypad may optionally be displayed.

Online handwriting recognition for Tamil

Abstract: A system for online recognition of handwritten Tamil characters is presented. A handwritten character is constructed by executing a sequence of strokes. A structure- or shape-based representation of a stroke is used in which a stroke is represented as a string of shape features. Using this string representation, an unknown stroke is identified by comparing it with a database of strokes using a flexible string matching procedure. A full character is recognized by identifying all the component strokes. Character termination, is determined using a finite state automaton. Development of similar systems for other Indian scripts is outlined.

A modified direction feature for cursive character recognition

Abstract: This paper describes a neural network-based technique for cursive character recognition applicable to segmentation-based word recognition systems. The proposed research builds on a novel feature extraction technique that extracts direction information from the structure of character contours. This principal is extended so that the direction information is integrated with a technique for detecting transitions between background and foreground pixels in the character image. The proposed technique is compared with the standard direction feature extraction technique, providing promising results using segmented characters from the CEDAR benchmark database.

Handwritten CAPTCHA: using the difference in the abilities of humans and machines in reading handwritten words

Abstract: Handwritten text offers challenges that are rarely encountered in machine-printed text. In addition, most problems faced in reading machine-printed text (e.g., character recognition, word segmentation, letter segmentation, etc.) are more severe, in handwritten text. In this paper we present the application of human interactive proofs (HIP), which is a relatively new research area with the primary focus of defending online services against abusive attacks. It uses a set of security protocols based on automatic tests that humans can pass but the state-of-the-art computer programs cannot. This is accomplished by exploiting the differential in the proficiency between humans and computers in reading handwritten word images.

Recent advancements in automatic signature verification

Abstract: This paper presents some of the main strategies for dynamic and static verification of handwritten signatures and focuses the most promising directions of scientific research, starting from the analysis of the literature of the last decade.

Recognition of Bangla Handwritten Characters Using an MLP Classifier Based on Stroke Features

Abstract: A recognition scheme for handwritten basic Bangla (an Indian script) characters is proposed. No such work has been reported before on a reasonably large representative database. Here a moderately large database of Bangla handwritten character images is used for the recognition purpose. A handwritten character is composed of several strokes whose characteristics depend on the handwriting style. The strokes present in a character image are identified in a simple fashion and 10 certain features are extracted from each of them. These stroke features are concatenated in an appropriate order to form the feature vector of a character image on the basis of which an MLP classifier is trained using a variant of the backpropagation algorithm that uses self-adaptive learning rates. The training and test sets consist respectively of 350 and 90 sample images for each of 50 Bangla basic characters. A separate validation set is used for termination of training of the MLP.

Handwriting segmentation of unconstrained Oriya text

Abstract: Segmentation of handwritten text into lines, words and characters is one of the important steps in the handwritten recognition system. For the segmentation of unconstrained Oriya handwritten text into individual characters, a water reservoir-concept based scheme is proposed in this paper. Here, at first, the text image is segmented into lines, and then lines are segmented into individual words, and words are segmented into individual characters. For line segmentation the document is divided into vertical stripes. Analyzing the heights of the water reservoirs obtained from different components of the document, the width of a stripe is calculated. Stripe-wise horizontal histograms are then computed and the relationship of the peak-valley points of the histograms is used for line segment. Based on vertical projection profile and structural features of Oriya characters, text lines are segmented into words. For character segmentation, at first, isolated and connected (touching) characters in a word are detected. Using structural, topological and water-reservoir-concept based features touching characters of the word are then segmented.

Distinguishing text from graphics in on-line handwritten ink

Abstract: We present a system that separates text from graphics strokes in handwritten digital ink. It utilizes not just the characteristics of the strokes, but also the information provided by the gaps between the strokes, as well as the temporal characteristics of the stroke sequence. It is built using machine learning techniques that infer the internal parameters of the system from real digital ink, collected using a tablet PC.

Comparison of elastic matching algorithms for online Tamil handwritten character recognition

Abstract: We present a comparison of elastic matching schemes for writer dependent on-line handwriting recognition of isolated Tamil characters. Three different features are considered namely, preprocessed x-y coordinates, quantized slope values, and dominant point coordinates. Seven schemes based on these three features and dynamic time warping distance measure are compared with respect to recognition accuracy, recognition speed, and number of training templates. Along with these results, possible grouping strategies and error analysis is also presented in brief.

Off-line handwriting identification using HMM based recognizers

Abstract: An off-line, text independent system for writer identification using hidden Markov model (HMM) based recognizers is described. For each writer we build an individual recognizer and train it on text lines written by that writer. A text line of unknown origin is presented to each of these recognizers. As a result we get, from each recognizer, a transcription including the log-likelihood score for the considered input. We rank all scores, and based on the assumption that the recognizer with the highest log-likelihood is the one that has been trained using text lines of this writer, we assign the text line to the writer whose score ranks first. We tested our system using over 2,200 text lines from 50 writers and have in 94.47% of all cases correctly identified the writer. Using a simple confidence measure to define a rejection mechanism, we achieved an error rate of 0% by rejecting 15% of the results.

Text alignment with handwritten documents

Abstract: Today's digital libraries increasingly include not only printed text but also scanned handwritten pages and other multimedia material. There are, however, few tools available for manipulating handwritten pages. Here, we propose an algorithm based on dynamic time warping (DTW) for a word by word alignment of handwritten documents with their (ASCII) transcripts. We see at least three uses for such alignment algorithms. First, alignment algorithms allow us to produce displays (for example on the Web) that allow a person to easily find their place in the manuscript when reading a transcript. Second, such alignment algorithms allow us to produce large quantities of ground truth data for evaluating handwriting recognition algorithms. Third, such algorithms allow us to produce indices in a straightforward manner for handwriting material. We provide experimental results of our algorithm on a set of 70 pages of historical handwritten material & specifically the writings of George Washington. Our method achieves 74.5% accuracy on line by line alignment and 60.5% accuracy when aligning whole pages at time.

Apparatus and method for handwriting recognition

Abstract: An apparatus for handwriting recognition has a touch-sensitive display screen providing a handwriting input area capable of detecting a handwritten user input. The apparatus also has a processing device configured to interpret the handwritten user input as a symbol from a plurality of predefined symbols. The handwriting input area includes a writing start area, and the processing device is configured to provide a visual indication of the writing start area on the display screen. The processing device is configured to interpret the user input as a symbol only if the user input starts within the writing start area.

Systems and methods for biometric identification using handwriting recognition

Abstract: A biometric handwriting identification system converts characters and a writing sample into mathematical graphs. The graphs comprise enough information to capture the features of handwriting that are unique to each individual. Optical character recognition (OCR) techniques can then be used to identify these features in the handwriting sample so that drafts from two different samples can be aligned to compare to determine if the features in the writing sample correlate with each other.

Support vector machines for handwritten numerical string recognition

Abstract: In this paper we discuss the use of SVMs to recognize handwritten numerical strings. Such a problem is more complex than recognizing isolated digits since one must deal with problems such as segmentation, overlapping, unknown number of digits, etc. In order to perform our experiments, we have used a segmentation-based recognition system using heuristic over-segmentation. The contribution of this paper is twofold. Firstly, we demonstrate by experimentation that SVMs improve the overall recognition rates. Secondly, we observe that SVMs deal with outliers such as over- and under-segmentation better than multi-layer perceptron neural networks.

Online handwriting recognition using support vector machine

Abstract: Discrete hidden Markov model (HMM) and hybrid of neural network (NN) and HMM are popular methods in handwritten word recognition system. The hybrid system gives better recognition result due to better discrimination capability of the NN [Y. Bengio et al., 1995]. Support vector machine (SVM) is an alternative to NN. In speech recognition (SR), SVM has been successfully used in the context of a hybrid SVM/HMM system. It gives a better recognition result compared to the system based on hybrid NN/HMM [A. Ganapathiraju, January 2002]. This paper describes the work in developing a hybrid SVM/HMM OHR system. Some preliminary experimental results of using SVM with RBF kernel on IRONOFF, UNIPEN and IRONOFF- UNIPEN character database are provided.

Noisy text categorization

Abstract: This work presents categorization experiments performed over noisy texts. By noisy, we mean any text obtained through an extraction process (affected by errors) from media other than digital texts (e.g., transcriptions of speech recordings extracted with a recognition system). The performance of a categorization system over the clean and noisy (word error rate between /spl sim/ 10 and /spl sim/ 50 percent) versions of the same documents is compared. The noisy texts are obtained through handwriting recognition and simulation of optical character recognition. The results show that the performance loss is acceptable for recall values up to 60-70 percent depending on the noise sources. New measures of the extraction process performance, allowing a better explanation of the categorization results, are proposed.

Combined speech and handwriting recognition

Abstract: The invention relates to the combination of speech recognition with handwriting and/or character recognition. This includes the innovation of selecting one or more best-scoring recognition candidates as a function of recognition of both handwritten and spoken representations of a sequence of one or more words to be recognized. It also includes the innovation of using character or handwriting recognition of one or more letters to alphabetically filter speech recognition of one or more words. It also includes the innovations of using speech recognition of one or more letter-identifying words to alphabetically filter handwriting recognition, and of using speech recognition to correct handwriting recognition of one or more words.