Showing papers on "Intelligent word recognition published in 1996"

Handwritten word recognition using segmentation-free hidden Markov modeling and segmentation-based dynamic programming techniques

Abstract: A lexicon-based, handwritten word recognition system combining segmentation-free and segmentation-based techniques is described. The segmentation-free technique constructs a continuous density hidden Markov model for each lexicon string. The segmentation-based technique uses dynamic programming to match word images and strings. The combination module uses differences in classifier capabilities to achieve significantly better performance.

Language-independent and segmentation-free optical character recognition system and method

Abstract: A language-independent and segment free OCR system and method comprises a unique feature extraction approach which represents two dimensional data relating to OCR as one independent variable (specifically the position within a line of text in the direction of the line) so that the same CSR technology based on HMMs can be adapted in a straightforward manner to recognize optical characters. After a line finding stage, followed by a simple feature-extraction stage, the system can utilize a commercially available CSR system, with little or no modification, to perform the recognition of text by and training of the system. The whole system, including the feature extraction, training, and recognition components, are designed to be independent of the script or language of the text being recognized. The language-dependent parts of the system are confined to the lexicon and training data. Furthermore, the method of recognition does not require pre-segmentation of the data at the character and/or word levels, neither for training nor for recognition. In addition, a language model can be used to enhance system performance as an integral part of the recognition process and not as a post-process, as is commonly done with spell checking, for example.

Effective Training of a Neural Network Character Classifier for Word Recognition

Abstract: We have combined an artificial neural network (ANN) character classifier with context-driven search over character segmentation, word segmentation, and word recognition hypotheses to provide robust recognition of hand-printed English text in new models of Apple Computer's Newton Message Pad. We present some innovations in the training and use of ANNs as character classifiers for word recognition, including normalized output error, frequency balancing, error emphasis, negative training, and stroke warping. A recurring theme of reducing a priori biases emerges and is discussed.

Large vocabulary recognition of on-line handwritten cursive words

Abstract: This paper presents a writer independent system for large vocabulary recognition of on-line handwritten cursive words. The system first uses a filtering module, based on simple letter features, to quickly reduce a large reference dictionary (lexicon) to a more manageable size; the reduced lexicon is subsequently fed to a recognition module. The recognition module uses a temporal representation of the input, instead of a static two-dimensional image, thereby preserving the sequential nature of the data and enabling the use of a Time-Delay Neural Network (TDNN); such networks have been previously successful in the continuous speech recognition domain. Explicit segmentation of the input words into characters is avoided by sequentially presenting the input word representation to the neural network-based recognizer. The outputs of the recognition module are collected and converted into a string of characters that is matched against the reduced lexicon using an extended Damerau-Levenshtein function. Trained on 2,443 unconstrained word images (11 k characters) from 55 writers and using a 21 k lexicon we reached a 97.9% and 82.4% top-5 word recognition rate on a writer-dependent and writer-independent test, respectively.

Off-line cursive handwriting recognition compared with on-line recognition

Abstract: Off-line handwriting recognition has wider applications than on-line recognition, yet it seems to be a harder problem. While on-line recognition is based on pen trajectory data, off-line recognition has to rely on pixel data only. We present a comparison between an off-line and an on-line recognition system using the same databases and system design. Both systems use a sliding window technique which avoids any segmentation before recognition. The recognizer is a hybrid system containing a neural network and a hidden Markov model. New normalization and feature extraction techniques for the off-line recognition are presented, including a connectionist approach for non-linear core height estimation. Results for uppercase, cursive and mixed case word recognition are reported. Finally a system combining the on- and off-line recognition is presented.

Segmentation and coding of Arabic handwritten words

Abstract: We propose a segmentation method and handwritten word coding method by human observation for automatic document processing in Arabic. The system is composed of three levels. The first level deals with the word segmentation into portions of characters called graphemes. The second level analyses these graphemes and codes the word by a sequence of observations similar to human perception. The results of these two levels are used in the recognition level (the third level) which are presented as perspective in this paper.

A segmentation-free approach to text recognition with application to Arabic text

Abstract: As the recognition rates and speeds of optical character recognition (OCR) systems steadily improve, the problem of OCR--and subsequently research interest--is shifting from recognizing: isolated, high-quality characters to reading cursive scripts and degraded documents. In recognizing such texts, a major undertaking is segmenting cursive words into characters and isolating merged characters. In OCR systems that recognize cursive text, the segmentation subsystem becomes the pivotal stage in the system to which a sizable portion of processing is devoted and a considerable share of recognition errors is attributed. The most notable feature of Arabic writing is its cursiveness. It also poses the most difficult problem for recognition algorithms. In this work, we describe the design and implementation of a system that is automatically trainable and that recognizes noisy and cursive words. To recognize a word, the system does not segment it into symbols (character shapes) in advance; rather, it recognizes the input word by detecting a set of "shape primitives" on the word. It then matches the regions of the word (represented by the detected primitives) to a set of symbol models. A spatial arrangement of symbol models that are matched to regions of the word, then, becomes the description of the recognized word. Since the number of potential arrangements of all symbol models is large, the system imposes a set of word structure and spatial consistency. It searches the space comprised of the arrangements that satisfy the constraints and tries to maximize the a posteriori probability of the symbol-models' arrangement. Large-scale experimentation with the system on isolated characters reveals that it has a recognition rate of 99.7% for synthetically degraded symbols and 94.1% for scanned symbols. Experimentation on isolated words reveals that the system has a recognition rate of 99.4% for noise-free words, 95.6% for synthetically degraded words, and 73% for scanned words. The main theoretical contribution of this work is in laying the foundation for a segmentation-free approach for Arabic word recognition. Recognition is based on maximizing the probability of the word given the detected primitives. The system is designed to minimize training effort and is extensible as training determines the symbols the system recognizes.

A comparison between continuous and discrete density hidden Markov models for cursive handwriting recognition

Abstract: This paper presents the results of the comparison of continuous and discrete density hidden Markov models (HMMs) used for cursive handwriting recognition. For comparison, a subset of a large vocabulary (1000 word), writer-independent online handwriting recognition system for word and sentence recognition was used, which was developed at Duisburg University. This system has some unique features that are rarely found in other HMM-based character recognition systems, such as: (1) option between discrete, continuous, or hybrid modeling of HMM probability density distributions; (2) large vocabulary recognition based on either printed or cursive word or complete sentence input; (3) optimized HMM topology with an unusually large number of HMM states; and (4) use of multiple label streams for coding of handwritten information. Emphasis in this paper is on the comparison between continuous and discrete density HMMs, since this is still an open question in handwriting recognition, and is crucial for the future development of the system. However, in order to give a complete description of the basic system architecture, some of the above mentioned issues are also addressed. The surprising result of our investigation was the fact that discrete density models led to better results than continuous models, although this is generally not the case for HMM-based speech recognition systems. With the optimized system, a 70% word recognition rate was obtained for a challenging large-vocabulary, writer-independent sentence input task.

Recognition of handwritten numerals using Gabor features

Abstract: We study a Gabor filter-based feature extraction method for handwritten numeral character recognition. The performance of the Gabor filter-based method is demonstrated on the ETL-1 database. Experimental results suggest that the Gabor filter-based method should be considered in recognition of handwritten numeric characters.

Language-independent OCR using a continuous speech recognition system

Abstract: In this paper we show how continuous speech recognition methods can be used for character recognition resulting in a technology that is language independent and does not require presegmentation of the data at the character and word levels. In multifont experiments on the ARPA Arabic OCR Corpus an average character error rate of 1.9% is obtained using the BBN BYBLOS continuous speech recognition system with no modifications. A first experiment using the identical system and procedures, trained and tested on a subset of the English Univ. of Washington OCR corpus resulted in 1.4% character error.

Robust and highly customizable recognition of online handwritten Japanese characters

Abstract: This paper describes a new online handwritten character recognition system which is composed of coarse classification, linear-time elastic matching, structured character pattern representation and context post-processing. It has marked 90 to 95% correct recognition rates without learning to a large database of on-line handwritten Japanese text. The recognition time is about 0.3 sec./input character on an i486 DX2/66 MHz processor. The system is not only robust to pattern distortions but also highly customizable for personal use. Upon the request of learning an input pattern, it investigates which subpattern (radical) or the pattern as a whole is non-standard, registers the (sub)pattern and extends the effect of the registration to all the character categories whose shapes include it.

Dynamic-programming-based handwritten word recognition using the Choquet fuzzy integral as the match function

Abstract: The Choquet fuzzy integral is applied to handwritten word recognition. A handwritten word recognition system is described. The word recognition system assigns a recognition confidence value to each string in a lexicon of candidate strings. The system uses a lexicon-driven approach that integrates segmentation and recognition via dynamic programming matching. The dynamic programming matcher finds a segmentation of the word image for each string in the lexicon. The traditional match score between a segmentation and a string is an average. In this paper, fuzzy integrals are used instead of an average. Experimental results demonstrate the utility of this approach. A surprising result is obtained that indicates a simple choice of fuzzy integral works better than a more complex choice.

Context-based spelling correction for Japanese OCR

Abstract: We present a novel spelling correction method for those languages that have no delimiter between words, such as Japanese, Chinese, and Thai. It consists of an approximate word matching method and an N-best word segmentation algorithm using a statistical language model. For OCR errors, the proposed word-based correction method outperforms the conventional character-based correction method. When the baseline character recognition accuracy is 90%, it achieves 96.0% character recognition accuracy and 96.3% word segmentation accuracy, while the character recognition accuracy of character-based correction is 93.3%.

HMM-based handwritten symbol recognition using on-line and off-line features

Abstract: This paper addresses the problem of recognizing on-line sampled handwritten symbols. Within the proposed symbol recognition system based on hidden Markov models different kinds of feature extraction algorithms are used analysing on-line features as well as off-line features and combining the classification results. By conducting writer-dependent recognition experiments, it is demonstrated that the recognition rates as well as the reliability of the results is improved by using the proposed recognition system. Furthermore, by applying handwriting data not representing symbols out of the given alphabet, an increase of their rejection rate is obtained.

Combining structural and statistical features for the recognition of handwritten characters

Abstract: The authors present a feature vector for the recognition of handwritten characters which combines the strengths of both statistical and structural feature extractors. Thanks to a combination of seven complementary families of features (ranging from pure structural to pure statistical and including both local and global features), a complete description of the characters can be achieved thus providing a wide range of identification clues. The recognition system has been tested on three categories of handwritten characters: handwritten well-segmented digits extracted from the NIST Database, uppercase letters collected from US dead letter envelopes and graphemes generated by a handwritten cursive word segmentation performed on US address word images. We thus demonstrate in this paper that high recognition rates with very low substitution rates can he achieved by means of the same general-purpose structural/statistical feature based vector.

Word-level recognition of multifont Arabic text using a feature vector matching approach

Abstract: Many text recognition systems recognize text imagery at the character level and assemble words from the recognized characters. An alternative approach is to recognize text imagery at the word level, without analyzing individual characters. This approach avoids the problem of individual character segmentation, and can overcome local errors in character recognition. A word-level recognition system for machine-printed Arabic text has been implemented. Arabic is a script language, and is therefore difficult to segment at the character level. Character segmentation has been avoided by recognizing text imagery of complete words. The Arabic recognition system computes a vector of image-morphological features on a query word image. This vector is matched against a precomputed database of vectors from a lexicon of Arabic words. Vectors from the database with the highest match score are returned as hypotheses for the unknown image. Several feature vectors may be stored for each word in the database. Database feature vectors generated using multiple fonts and noise models allow the system to be tuned to its input stream. Used in conjunction with database pruning techniques, this Arabic recognition system has obtained promising word recognition rates on low-quality multifont text imagery.

A template-matching pandemonium recognizes unconstrained handwritten characters with high accuracy

Abstract: Psychological data suggest that internal representations such as mental images can be used as templates in visual pattern recognition. But computational studies suggest that traditional template matching is insufficient for high-accuracy recognition of real-life patterns such as handwritten characters. Here we explore a model for visual pattern recognition that combines a template-matching and a feature-analysis approach: Character classification is based on weighted evidence from a number of analyzers (demons), each of which computes the degree of match between the input character and a stored template (a copy of a previously presented character). The template-matching pandemonium was trained to recognize totally unconstrained handwritten digits. With a mean of 37 templates per type of digit, the system has attained a recognition rate of 95.3%, which falls short of human performance by only 2%–3%.

Algorithm for stroke width compensation of handwritten characters

Abstract: An algorithm is proposed to compensate the stroke width of a handwritten character image. This can make character feature extraction and recognition more accurate in practical applications.

A segmentation and recognition strategy for handwritten phrases

Abstract: A segmentation and recognition method for handwritten phrases, such as street names, is presented in this paper. Some of the challenges posed by the problem are: (1) identifying correct word gaps from character gaps and (2) minimization of computational complexity during the recognition of potential words. A trainable word segmentation scheme using a neural network is introduced. The network learns the type of spacing (including size) that one should expect between different pairs of characters in handwritten text. The concept of variable duration, which is obtained during the training phase of a word recognition engine we have developed, is expanded to reduce the computational complexity which has been a serious concern in this type of application.

Content-oriented categorization of document images

Abstract: We have developed a technique that categorizes document images based on their content. Unlike conventional methods that use optical character recognition (OCR), we convert document images into word shape takens, a shape-based representation of words. Because we have only to recognize simple graphical features from image, this process is much faster than OCR. Although the mapping between word shape tokens and words is one-to-many, they are a rich source of information for content characterization. Using a vector space classifier with a scanned document image database, we show that the word shape token-based approach is quite adequate for content-oriented categorization in terms of accuracy compared with conventional OCR-based approaches.

Morphological approach to character recognition in machine-printed Persian words

Abstract: Based on the capabilities of morphological operators in extracting shape features, a new method for character recognition in Persian machine printed documents is introduced. Given the image of a printed character is available with high enough SNR such that its regular shape is preserved, some common primitive patterns can always be found after thinning different images of a single character. This property has inspired the development of our morphological processing in which the hit-or-miss operator is used to determine which patterns exist or do not exist in the input images of the recognition system. All the required processing before feature extraction including image enhancement, segmentation, and thinning are also performed using the hit-or-miss operator. Having the input words described in terms of some pre-defined patterns, the system knowledge base, holding descriptions for all characters, is searched for possible matches. Finding a match ends in the recognition of a character. This approach is proved to be fast and reliable in practice.© (1996) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

A chain coding approach for real-time recognition of on-line handwritten characters

Abstract: A novel chain coding approach is proposed for real-time recognition of isolated on-line handwritten English characters. A new type of generalized chain code (GCC) is proposed for lossless encoding of the variably-spaced handwritten data points produced naturally by an electronic writing tablet due to the fixed sampling rate and the variable writing speed. Distinctive features for each character are then extracted based on the segmented cumulative differential normalized GCC values and structural descriptors. Experiments showed successful real-time recognition of isolated on-line handwritten lowercase English characters on a 486 class PC.

Structural Learning of Character Patterns for On-Line Recognition of Hand-Written Japanese Characters

Abstract: This paper describes the structural learning of Kanji patterns in on-line handwritten character recognition. Upon the request to learn an input pattern, the system investigates which subpattern or the pattern as a whole is non-standard, registers the (sub)pattern and extends the effect of the registration to all the character categories whose shapes include it. A character pattern representation dictionary stores character patterns as combinations of subpatterns so that a common subpattern is shared by all the character categories which include it in their shapes. The recognizer constructs all template patterns from its constituent subpatterns for matching them with an input pattern. Registration of a character pattern invokes identification and registration of a non-standard subpattern in it so that the effect extends to all the characters whose shapes include it. A preliminary evaluation shows it is highly effective without any bad side effect.