Showing papers on "Handwriting recognition published in 1993"

Improvements of a lexicon directed algorithm for recognition of unconstrained handwritten words

Abstract: Discusses improvements made to a lexicon directed algorithm for recognition of unconstrained handwritten words (cursive, discrete, or mixed) such as those encountered in mail pieces. The procedure consists of binarization, pre-segmentation, intermediate feature extraction, segmentation recognition, and post-processing. The segmentation recognition and the post-processing are repeated for all lexicon words while the binarization to the intermediate feature extraction are applied once for an input word. The result of performance evaluation using large handwritten address block database is described, and algorithm improvements are described and discussed, in order to achieve higher recognition accuracy and speed. As a result the performance for lexicons of size 10, 100, and 1000 are improved to 98.01%, 95.46%, and 91.49% respectively. The processing speed for each lexicon is improved to 2.0, 2.5, and 3.5 sec/word on a SUN SPARC station 2. >

Universal symbolic handwriting recognition system

Abstract: A universal symbolic handwriting recognition system for converting user entered time ordered stroke sequences into computer readable text is described. The system operates on two levels: (1) a word-level recognizer, which recognizes the entire group of strokes as a unit, and (2) a parser-level recognizer, which breaks the strokes into segments and recognizes groups of stroke segments within a word, thus recognizing separate characters or character sequences within a word to build a complete recognition string. In both recognition levels, the system trains on actual user samples, either on an entire word, or on a character or character sequence within a word. It does so by building a user specific sample recognition data-base file of text/pattern pairs, where the text is specified by the user in a word confirmation process and the pattern, composed of an index and a feature vector, is created from the actual user input strokes. Thus, as the user continues to use the recognition system and augments his/her user specific sample recognition data-base file, the correct recognition rate climbs approaching 100 percent in normal usage. The word-level recognizer can also be used to train on abbreviations, custom shorthands, and pictographic characters, such as the Japanese Kanji, or Chinese. An abbreviated Japanese Kanji or Chinese handwritten entry can even be trained for recognition. The text in the user specific sample data-base file is maintained in the Unicode format, and the user can specify the recognized return string format as either Unicode, ANSI, or JIS.

Segmenting handwritten signatures at their perceptually important points

Abstract: A new algorithm for segmenting continuous handwritten signatures sampled by a digitizer is described. The segmentation points are found using a two-step procedure. The principal step is to construct a function that weights the perceptual importance of every signature point according to its specific neighboring points. The second step points out the various local maxima of this function that correspond to where the signature should be segmented. The method is well illustrated and tested on a number of signatures that require different kinds of segmentation decisions. >

Sophisticated topology of hidden Markov models for cursive script recognition

Abstract: The paper describes an adaptation of hidden Markov models (HMM) to automatic recognition of unrestricted handwritten words. Many interesting details of a 50,000 vocabulary recognition system for US city names are described. This system includes feature extraction, classification, estimation of model parameters, and word recognition. The feature extraction module transforms a binary image to a sequence of feature vectors. The classification module consists of a transformation based on linear discriminant analysis and Gaussian soft-decision vector quantizers which transform feature vectors into sets of symbols and associated likelihoods. Symbols and likelihoods form the input to both HMM training and recognition. HMM training performed in several successive steps requires only a small amount of gestalt labeled data on the level of characters for initialization. HMM recognition based on the Viterbi algorithm runs on subsets of the whole vocabulary. >

Preprocessing and feature extraction for a handwriting recognition system

Abstract: Offline cursive script word recognition has received increasing attention during the last years. Impressive progress has been achieved in reading isolated single characters during the last decade. Cursive script recognition still lacks a good recognition rate. Since there is a high variability in unconstrainted handwritten script words, the domain is much more difficult than single character recognition. To achieve acceptable results, the context has to be restricted by a given lexicon of all possible words. The only accessible information is the binary image of the cursive script word. Since handling of raster data is cumbersome, connectivity analysis is applied as a first processing step. Thereafter it is necessary to reduce the variability as much as possible without losing relevant information. Therefore, some normalization steps angle, rotation stroke width, and size. The normalization techniques of the authors' system and the subsequent feature extraction are presented. The proposed algorithms are every efficient because they are based on the contour information provided by connectivity analysis. >

Handwritten Korean character image database PE92

Abstract: The purpose of the current PE92 database project is two fold. One is to provide a comprehensive set of character image data to a developer of a recognition system so that the developer can concentrate on developing an algorithm. The other is to offer a means by which an evaluator can compare various algorithms objectively. The authors collected 100 sets of KS 2350 handwritten Korean character images. They tried to collect as many writing styles as possible. The first 70 sets were generated by more than 500 different writers, and each of the remaining 30 sets was written by the same person. Writers wrote down the characters in prespecified boxes and the database was created by scanning the data sheets by an image scanner. Each image is the size of 100/spl times/100 with 256 gray levels. Finally, the authors analyze the quality of the database created and calculated various statistics of the database PE92. >

Hidden control neural architecture modeling of nonlinear time varying systems and its applications

Abstract: The application of neural networks to modeling time-invariant nonlinear systems has been difficult for complicated nonstationary signals, such as speech, because the networks are unable to characterize temporal variability. This problem is addressed by proposing a network architecture, called the hidden control neural network (HCNN), for modeling signals generated by nonlinear dynamical systems with restricted time variability. The mapping implemented by a multilayered neural network is allowed to change with time as a function of an additional control input signal. The network is trained using an algorithm based on 'backpropagation' and segmentation algorithms for estimating the unknown control together with the network's parameters. Application of the network to the segmentation and modeling of a signal produced by a time-varying nonlinear system, speaker-independent recognition of spoken connected digits, and online recognition of handwritten characters demonstrates the ability of the HCNN to learn time-varying nonlinear dynamics and its potential for high-performance recognition of signals produced by time-varying sources. >

System and method of pattern recognition employing a multiprocessing pipelined apparatus with private pattern memory

Abstract: A computer implemented apparatus and method of pattern recognition utilizing a pattern recognition engine coupled with a general purpose computer system. The present invention system provides increased accuracy and performance in handwriting and voice recognition systems and may interface with general purpose computer systems. A pattern recognition engine is provided within the present invention that contains five pipelines which operate in parallel and are specially optimized for Dynamic Time Warping and Hidden Markov Models procedures for pattern recognition, especially handwriting recognition. These pipelines comprise two arithmetic pipelines, one control pipeline and two pointer pipelines. Further, a private memory is associated with each pattern recognition engine for library storage of reference or prototype patterns. Recognition procedures are partitioned across a CPU and the pattern recognition engine. Use of a private memory allows quick access of the library patterns without impeding the performance of programs operating on the main CPU or the host bus. Communication between the CPU and the pattern recognition engine is accomplished over the host bus.

Interpretation of handwritten addresses in US mailstream

Abstract: Determining the delivery location for mail pieces based on handwritten addresses is a problem that trained humans can normally solve As a problem in machine reading and interpretation, it presents many challenges A method for determining the delivery point codes (DPCs) for handwritten addresses by computer is described Solution to the task requires locating and recognizing address components (eg, ZIP Code, street number, PO box number) and using multiple information sources to assign the DPC to an address The methodology uses diverse pattern recognition techniques, image processing algorithms (thresholding, underline removal, separation of lines, location and recognition of address components), and access to United States Postal Service (USPS) databases to determine the DPC >

On-line handwriting recognition using continuous parameter hidden Markov models

Abstract: The problem of the automatic recognition of handwritten text is addressed. The text to be recognized is captured online and the temporal sequence of the data is presented. The approach is based on a left-to-right hidden markov model (HMM) for each character that models the dynamics of the written script. A mixture of Gaussian distributions is used to represent the output probabilities at each arc of the HMM. Several strategies for reestimating the model parameters are discussed. Experiments show that this approach results in significant decreases in error rate for the recognition of discretely written characters compared with elastic matching techniques. The HMM outperforms the elastic matching technique for both writer-dependent and writer-independent recognition tasks. >

Variable duration hidden Markov model and morphological segmentation for handwritten word recognition

Abstract: A complete system for the recognition of unconstrained handwritten words using a continuous density variable duration hidden Markov model (CDVDHMM) is described. A new segmentation algorithm based on mathematical morphology is used to translate the 2-D image into a 1-D sequence of sub-character symbols. This sequence of symbols is modeled by the CDVDHMM. Generally, there are two information sources associated with the written text. While the shape information of each character symbol is modeled as a mixture Gaussian distribution, the linguistic knowledge, i.e., constraint, is modeled as a Markov chain. In this context, the variable duration state is used to take care of the segmentation ambiguity among the consecutive characters. Some experimental results are described to demonstrate the success of the proposed scheme. >

Writer-adaptation for on-line handwritten character recognition

Abstract: The authors have designed a writer-adaptable character recognition system for online characters entered on a touch terminal. It is based on a Time Delay Neural Network (TDNN) that is pre-trained on examples from many writers to recognize digits and uppercase letters. The TDNN without its last layer serves as a preprocessor for an optimal hyperplane classifier that can be easily retrained to peculiar writing styles. This combination allows for fast writer-dependent learning of new letters and symbols. The system is memory and speed efficient. >

Segmentation and classification for mixed text/image documents using neural network

Abstract: A segmentation and classification method for separating a document image into printed character, handwritten character, photograph, and painted image regions is presented. A document image is segmented into rectangular areas. Each of which contains a cluster of image elements. A layered feed-forward neural network is then used to classify each segmented area using the histograms of gradient vector directions and luminance levels. A high classification performance was obtained, even with a small number of training samples. It is confirmed that the histograms of gradient vector directions and luminance levels are significantly effective features for the classification of the four kinds of image regions. Increasing the number of the discrimination areas improves the classification performance sufficiently even using a small number of training samples for the neural network. >

On-line Japanese character recognition experiments by an off-line method based on normalization-cooperated feature extraction

Abstract: It is shown that an offline character recognition method is effective for use in an online Japanese character recognition. Major conventional online recognition methods have restricted the number and the order of strokes. The offline method removes these restrictions, based on pattern matching of orientation feature patterns. It has been improved with developments in nonlinear shape normalization, nonlinear pattern matching, and the normalization-cooperated feature extraction method. It was used to examine 52,944 online Kanji characters in 1,064 categories. The recognition rate achieved 95.1%, and the cumulation recognition rate within the best five candidates was 99.3%. >

Integrated segmentation and recognition through exhaustive scans or learned saccadic jumps

Abstract: This paper advances two approaches to integrating handwritten character segmentation and recognition within one system, where the underlying function is learned by a backpropagation neural network. Integrated segmentation and recognition is necessary when characters overlap or touch, or when an individual character is broken up. The first approach exhaustively scans a field of characters, effectively creating a possible segmentation at each scan point. A neural net is trained to both identify when its input window is centered over a character, and if it is, to classify the character. This approach is similar to most recently advanced approaches to integrating segmentation and recognition, and has the common flaw of generating too many possible segmentations to be truly efficient. The second approach overcomes this weakness without reducing accuracy by training a neural network to mimic the ballistic and corrective saccades (eye movements) of human vision. A single neural net learns to jump from character to character, making corrective jumps when necessary, and to classify the centered character when properly fixated. The significant aspect of this system is that the neural net learns to both control what is in its input window as well as to recognize what is in the window. High accuracy results are reported for a standard database of handprinted digits for both approaches.

High-speed character recognition using a dual cellular neural network architecture (CNND)

Abstract: An effective character recognition procedure implemented on a new type of hardware system and using a new architecture called CNND is proposed. This CNND contains one or more analog cellular neural networks (CNNs) and some digital logic, combining the advantages of the fast analog CNN signal processing and the fast and easy decision capability of digital logic. It is shown that the CNND system can be used for recognition of multifont printed or handwritten characters and could recognize 100,000 char/s with a recognition rate of more than 95%. The more advantage of the system over competing types is that there is not an extra feature extraction procedure implemented in slow hardware. >

A multi-classifier combination strategy for the recognition of handwritten cursive words

Abstract: A recognition scheme for reading handwritten cursive words using three word recognition techniques is described. The focus is on the implementation used to combine the three techniques based on a comparative study of different strategies. The first holistic recognition technique derives a global encoding of the word. The other techniques both rely on the segmentation of the word into letters, but differ in the character classifier they use. The former runs a statistical linear classifier, and the latter runs a neural network with a different representation of the input data. The testing, comparison, and combination studies have been performed on word images from mail provided by the USPS. The top choice recognition rates achieved so far correspond to 88%, 76%, 65% with respect to lexicon sizes of 10, 100, and 1000 words. >

Estimation of baseline, line spacing and character height for handwriting recognition

Abstract: A line space baseline adjuster in a handwriting recognition system achieves improved recognition accuracy by normalizing the Cartesian coordinates of the writings captured by a digitizer to coincide with prototype character space. The normalization techniques include weighted average estimation, prototype extraction estimation, extreme point clustering estimation and a combination of prototype extraction estimation and extreme point clustering estimation.

Hybrid on-line handwriting recognition and optical character recognition system

Abstract: The hybrid handwriting recognition method includes the steps of (a), in response to a handwriting input from a user, providing dynamic, time ordered stroke information; (b) determining a first list comprised of at least one probable character that the dynamic, time ordered stroke information is intended to represent; (c) converting the dynamic, time ordered stroke information to static stroke information; (d) determining a second list comprised of at least one probable character that the static stroke information represents; and (e) merging the first list and the second list to provide a third, unified list comprised of at least one element representing a most probable character that the dynamic, time ordered stroke information is intended to represent. The step of converting includes the steps of generating a static, bit-mapped representation of the dynamic stroke information, and generating one or more first stroke features based on contour directions of the bit-mapped stroke information. The first stroke features are applied as inputs to a plurality of neural network recognizers.

Strategies for handwritten words recognition using hidden Markov models

Abstract: Several approaches for the application of hidden Markov models to the recognition of handwritten words are described. All approaches share the same description of words through strings of symbols. They differ with respect to the size of the vocabulary which has to be recognized. The authors distinguish between two cases: where the vocabulary is small and constant, and where the vocabulary is limited but dynamic in the sense that it is a varying subset of an open one. The authors also describe an application of hidden Markov models to the representation of contextual knowledge and propose some strategies to reject unreliable word interpretations, in particular when the word corresponding to the image is not guaranteed to belong to the lexicon. >

Dynamic handwritten Chinese signature verification

Abstract: A dynamic handwritten Chinese signature verification system based upon a Bayesian neural network is presented. Due to a great deal of variability of handwritten Chinese signatures, the proposed Bayesian neural network is trained by an incremental learning vector quantization (ILVQ) algorithm, which endows this system with incremental learning ability, and outputs a posteriori probability to give a more reliable distance estimation. The performance analysis was based upon a set of signature data consisting of 800 true specimens, 200 simple forgeries and 200 skilled forgeries. The experimental results show the type I error is about 2% and the type II error rates are about 0.1% and 2.5% for simple and skilled forgeries, respectively. >

Pen-based user interfaces

Abstract: Pen-based user interfaces are emerging as an increasingly important aspect of computer and communications applications. This paper provides a brief summary of the major attributes of pen-based interfaces, including: — The use of pen devices for pointing and selecting tasks, — The use of pen-based gestures for command invocation, — Issues and applications of electronic ink, which is used for various graphics and informal note-taking tasks, and — A summary of current issues with pen-based handwriting recognition.

A post-processing error correction scheme using a dictionary for on-line handwriting recognition

Abstract: A dictionary based post-processing technique for an on-line handwriting recognition system is described. An input word has all punctuation removed, and the word is checked against a word processing dictionary. If any word matches against the dictionary, it is verified as a valid word. If it does not verify, a stroke match function and a spell-aid dictionary are used to construct a list of possible words. In some cases, the list is appended with possible words based on changing the first character of the originally recognized word. A character-match score, a substitution score and a word length are assigned to the items on the list. A word hypothesis is constructed from the list with each such word being assigned a score. The word with the best score is chosen as the output word for the processor.

Recognition of handwritten digits by combining independent learning vector quantizations

Abstract: Classifiers derived by learning vector quantization (LVQ) have well-defined decision regions that can be combined to construct a more accurate classifier. A given point may be included in a number of decision regions associated with different LVQ classifiers. The relative densities of classes in each region can be combined to obtain a final classification. The method allows useful inferences from small training sets, which is needed for problems involving large variations within each class. In an application of this method to the recognition of handwritten digits, it is shown that the classifier can be improved almost monotonically without suffering from over-adaptation to the training data. >

A statistical approach with HMMs for on-line cursive Hangul (Korean script) recognition

Abstract: A statistical approach to recognizing on-line cursive Hangul character is proposed. Viewing a handwritten Hangul syllable as an alternating sequence of letters and ligatures, all handwritten legal characters are modeled with a finite state network that is a concatenation of letter and ligature HMMs. Given an input to the network, recognition, which corresponds to finding the most likely path, is performed using the dynamic programming technique. Experiments have shown that letter boundary detection as well as handwriting variability resolution is achieved with good results. >