Showing papers on "Handwriting recognition published in 1992"

Methods of combining multiple classifiers and their applications to handwriting recognition

Abstract: Possible solutions to the problem of combining classifiers can be divided into three categories according to the levels of information available from the various classifiers. Four approaches based on different methodologies are proposed for solving this problem. One is suitable for combining individual classifiers such as Bayesian, k-nearest-neighbor, and various distance classifiers. The other three could be used for combining any kind of individual classifiers. On applying these methods to combine several classifiers for recognizing totally unconstrained handwritten numerals, the experimental results show that the performance of individual classifiers can be improved significantly. For example, on the US zipcode database, 98.9% recognition with 0.90% substitution and 0.2% rejection can be obtained, as well as high reliability with 95% recognition, 0% substitution, and 5% rejection. >

Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers

Abstract: The classification and recognition of two-dimensional patterns independently of their position, orientation, and size by using high-order networks are discussed. A method is introduced for reducing and controlling the number of weights of a third-order network used for invariant pattern recognition. The method leads to economical networks that exhibit high recognition rates for translated, rotated, and scaled, as well as locally distorted, patterns. The performance of these networks at recognizing types and handwritten numerals independently of their position, size, and orientation is compared with and found superior to the performance of a layered feedforward network to which image features extracted by the method of moments are presented as input. >

Handwritten digit recognition by neural networks with single-layer training

Abstract: It is shown that neural network classifiers with single-layer training can be applied efficiently to complex real-world classification problems such as the recognition of handwritten digits. The STEPNET procedure, which decomposes the problem into simpler subproblems which can be solved by linear separators, is introduced. Provided appropriate data representations and learning rules are used, performance comparable to that obtained by more complex networks can be achieved. Results from two different databases are presented: an European database comprising 8700 isolated digits and a zip code database from the US Postal Service comprising 9000 segmented digits. A hardware implementation of the classifier is briefly described. >

Off-line cursive word recognition

Abstract: The state of the art in handwriting recognition, especially in cursive word recognition, is surveyed, and some basic notions are reviewed in the field of picture recognition, particularly, line image recognition. The usefulness of 'regular' versus 'singular' classes of features is stressed. These notions are applied to obtain a graph, G, representing a line image, and also to find an 'axis' as the regular part of G. The complements to G of the axis are the 'tarsi', singular parts of G, which correspond to informative features of a cursive word. A segmentation of the graph is obtained, giving a symbolic description chain (SDC). Using one or more as robust anchors, possible words in a list of words are selected. Candidate words are examined to see if the other letters fit the rest of the SDC. Good results are obtained for clean images of words written by several persons. >

Recovery of temporal information from static images of handwriting

Abstract: A taxonomy of local, regional, and global temporal clues that, along with a detailed examination of the document, allow temporal properties to be recovered from the image is provided. It is shown that this system will benefit from obtaining a comprehensive understanding of the handwriting signal and that it requires a detailed analysis of stroke and sub-stroke properties. It is suggested that this task requires breaking away from traditional thresholding and thinning techniques, and a framework for such analysis is presented. It is shown how the temporal clues can reliably be extracted from this framework and how many of the seemingly ambiguous situations can be resolved by the derived clues and knowledge of the writing process. >

On-line handwriting recognition

Abstract: For large-alphabet languages, like Japanese, handwriting input using an online recognition technique is essential for input accuracy and speed. However, there are serious problems that prevent high recognition accuracy of unconstrained handwriting. First, the thousands of ideographic Japanese characters of Chinese origin (called Kanji) can be written with wide variations in the number and order of strokes and significant shape distortions. Also, writing box-free recognition of characters is required to create a better man-machine interface. Intense research performed over the past 15 years to answer the most pressing recognition problems is described. Prototype systems are also described. The man-machine interfaces made possible by online handwriting recognition and anticipated advances in both hardware and software are discussed. >

High-performance reading machines

Abstract: The architecture of a reading machine designed to achieve a high rate of correct interpretation of text as well as high speed in performing the interpretation is described. The refinement of the architecture for a specialized reading machine, to find and interpret addresses on a stream of postal letters, is also described. The addresses can be either machine-printed or handwritten. The primary subtasks correspond to finding the block of text corresponding to the destination address, recognizing characters and words within the address, and interpreting the text using postal directories. The need for multiple algorithms and multiple scales for recognition (holistic and analytic) and for methods for combining results of multiple algorithms, the efficacy of artificial neural nets and fuzzy matching, and the feasibility of reading unconstrained handwritten words when there exist accompanying numeric fields that limit word choices are shown. >

Continuous parameter hidden Markov model approach to automatic handwriting recognition

Abstract: A computer-based system and method for recognizing handwriting. The present invention includes a pre-processor, a front end, and a modeling component. The present invention operates as follows. First, the present invention identifies the lexemes for all characters of interest. Second, the present invention performs a training phase in order to generate a hidden Markov model for each of the lexemes. Third, the present invention performs a decoding phase to recognize handwritten text. Hidden Markov models for lexemes are produced during the training phase. The present invention performs the decoding phase as follows. The present invention receives test characters to be decoded (that is, to be recognized). The present invention generates sequences of feature vectors for the test characters by mapping in chirographic space. For each of the test characters, the present invention computes probabilities that the test character can be generated by the hidden Markov models. The present invention decodes the test character as the recognized character associated with the hidden Markov model having the greatest probability.

Hidden Markov models for character recognition

Abstract: A hierarchical system for character recognition with hidden Markov model knowledge sources which solve both the context sensitivity problem and the character instantiation problem is presented. The system achieves 97-99% accuracy using a two-level architecture and has been implemented using a systolic array, thus permitting real-time (1 ms per character) multifont and multisize printed character recognition as well as handwriting recognition. >

Handwriting recognition by character template

Abstract: A method for entry and recognition of elements from a set of symbols, involving a template of line segments displayed on an electronic writing surface. A stylus is applied to the electronic writing surface so as to trace a desired symbol. A computing arrangement is used to "snap" the strokes made by the stylus onto the corresponding template line segments. Upon completion of a symbol, a code is made to represent the line segments and this code is used to reference entries in a data structure to identify the appropriate corresponding computer code. If there is no match, the code for the line segments and a corresponding set of computer codes can be added to the table. This method takes advantage of natural handwriting skills and can be used for a variety of symbol sets.

Reading handwritten digits: a ZIP code recognition system

Abstract: A neural network algorithm-based system that reads handwritten ZIP codes appearing on real US mail is described. The system uses a recognition-based segmenter, that is a hybrid of connected-components analysis (CCA), vertical cuts, and a neural network recognizer. Connected components that are single digits are handled by CCA. CCs that are combined or dissected digits are handled by the vertical-cut segmenter. The four main stages of processing are preprocessing, in which noise is removed and the digits are deslanted, CCA segmentation and recognition, vertical-cut-point estimation and segmentation, and directly lookup. The system was trained and tested on approximately 10000 images, five- and nine-digit ZIP code fields taken from real mail. >

Off-line Arabic character recognition

Abstract: A personal computer-based Arabic character recognition system that performs three preprocessing stages sequentially, thinning, stroke segmentation, and sampling, is described. The eight-direction code used for stroke representation and classification, the character classification done at primary and secondary levels, and the contextual postprocessor used for error detection and correction are described. Experimental results obtained using samples of handwritten and typewritten Arabic words are presented. >

A model-based segmentation framework for computer processing of handwriting

Abstract: Describes a model-based segmentation framework for the partitioning of handwriting (handprinted characters, cursive script, signatures). The model accounts for handwriting generation in terms of response patterns that result from the activation by the central nervous system of curvilinear and angular velocity generators, characterized by log-normal impulse responses. In this context, a handwritten trace can be segmented into a hierarchy of well-defined elements: components, strings and curvilinear and angular strokes. One striking conclusion from this approach is that strokes have to be superimposed to generate a smooth handwritten trace and are thus hidden in the trajectory signal. The segmentation algorithm avoids this problem by using an analysis-by-synthesis technique to segment a specific curve. >

A statistical mixture approach to automatic handwriting recognition

Abstract: Method and apparatus for automatic recognition of handwritten text based on a suitable representation of handwriting in one or several feature vector spaces(s), Gaussian modeling in each space, and mixture decoding to take into account the contribution of all relevant prototypes in all spaces. The feature vector space(s) is selected to encompass both a local and a global description of each appropriate point on a pen trajectory. Windowing is performed to capture broad trends in the handwriting, after which a linear transformation is applied to suitably eliminate redundancy. The resulting feature vector space(s) is called chirographic space(s). Gaussian modeling is performed to isolate adequate chirographic prototype distributions in each space, and the mixture coefficients weighting these distributions are trained using a maximum likelihood framework. Decoding can be performed simply and effectively by accumulating the contribution of all relevant prototype distributions. Post-processing using a language model may be included.

Whither the pen-based interface?

Abstract: :This paper reports the results of six experiments to investigate the kinds of applications for which a pen-based interface might be useful, the kinds of users who might adopt pen-based interfaces. and the features or components of the pen-based interface that users find acceptable. The experiments revealed a strong user acceptance of pen-based systems for software navigation and position control across a range of applications, and showed that the responses of current nonusers were very similar to those of experienced users when using pen-based systems. The results also suggest that, contrary to conventional wisdom, handwriting recognition is unlikely to be widely accepted as a direct keyboard substitute for general-purpose computing. The paper discusses alternatives to handwriting recognition for pen-based character input, and ends with a brief discussion of future directions in pen-based interface research.

Method and apparatus for improving prototypes of similar characters in on-line handwriting recognition

Abstract: A method, and apparatus for accomplishing same, of providing character prototypes for use by a handwriting character recognition system 10. A first method includes a first step of providing a first handwritten character; a second step of copying the first character to provide a second character; and a third step of modifying the second character to (a) emphasize dissimilarities between the second character and the first character and to (b) de-emphasize similarities between the second character and the first character. A second method includes a first step of providing a first handwritten character and a second handwritten character, the first and the second handwritten characters each being comprised of a plurality of points. A second step of the method matches corresponding points between the first character and the second character. A third step of the method processes pairs of matching points to separate one from another each point of the matching pair by an amount proportional to an initial separation between each matched corresponding point, so as to emphasize dissimilarities between the first character and the second character.

Handwritten word recognition using HMM with adaptive length Viterbi algorithm

Abstract: The authors have developed a handwritten word recognition scheme based on a single contextual, discrete symbol probability hidden Markov model (HMM) incorporated with an adaptive length Viterbi algorithm. This work attempts to extend the earlier HMM scheme for naturally segmented word recognition to cursive and nonsegmented word recognition. The algorithm presegments the script into characters and/or fractions of characters, dynamically selects the correct segmentation points, determines the word length, and recognizes the word according to the maximum path probability. The HMM is on top of, but independent of, script segmentation and character recognition techniques, and therefore leaves room for further improvement. The experiments have shown promising results and directions for further improvement. >

Shape description by UNL Fourier features-an application to handwritten character recognition

Abstract: Handwritten characters are forms. Thus they are accessible to form description methods. The authors present a universal shape characterization method applied to the domain of off-line handwritten characters. The test universe is restricted to the ten Arabic numerals but can be extended to any other characters. The authors point out previous work in the area of 2D shape classification and handwriting recognition. The theoretical concept of the authors' shape descriptor is introduced together with a recipe to apply it in the real case of discrete binary images. Results of classification experiments are presented. >

On Handwriting Recognition System Performance: Some Experimental Results

Abstract: Performance of a rule-based handwriting recognition system is considered. Performance limits of such systems are defined by the robustness of the character templates and the ability of the system to segment characters. Published performance figures, however, are typically based on pre-segmented characters. Six experiments are reported (using a total of 128 subjects) that tested a state-of-the-art recognition system under more realistic conditions. Variables investigated include display format (grid, lined, and blank), surface texture, feedback (location and time delay), amount of training, practice, and effects of use over an extended period. Results indicated that novice users writing on a lined display (the most preferred format) averaged 57% recognition performance. By giving subjects continuous feedback of results, training, and after about 10 minutes of use, the system averaged 90.6% character recognition. Following three hours of interrupted use and with performance incentives, subjects achieved an ...

Elastic prototype averaging in online handwriting recognition

Abstract: An elastic-matching alignment technique for providing an averaged prototype in a handwriting recognition system that improves the alignment of parametric representations of recognized characters to be averaged. The point-to-point correspondence resulting from an elastic match of two characters is obtained by using backpointers during the calculation of the match. A character is added to a prototype set if it is new or is not correctly recognized within a fixed threshold. Otherwise, the character is averaged into the closest prototype of its class to provide a new average prototype.

Is the pen mightier than the keyboard

Abstract: The authors investigate whether pen-based interfaces are acceptable for general business applications in terms of user performance and user preferences. In six experiments novice and experienced subjects compared a pen-based interface to a keyboard across four general business applications: text editing, spreadsheet, graphics, and disk management. The study found that subjects executed most of the tasks more slowly with a pen-based interface than with the keyboard. Subjects reported that the handwriting recognition component of the pen-based interface was too inaccurate, too slow, and too demanding for user attention. However, they responded well to the touch-button software navigation and screen position control components, suggesting potential for future use. >

Online recognition of connected handwriting by segmentation and template matching

Abstract: Users interact with pen-based computers by drawing on the display with a stylus. Handwriting is the obvious method for entering data onto these machines. This requires cursive script recognition (CSR), which comprehends unconstrained, natural handwriting. The authors have developed an online CSR system that can be used by any person with reasonably neat script. This paper describes the segmentation and template matching process used. >

Improving on-line handwriting recognition using a prototype confusability dialogue

Abstract: A handwriting recognition system in which a user, on-line can reduce similarity between different prototypes. The user interactively can delete a prototype or add a new prototype, while at the same time is not allowed to delete a prototype when it is the only prototype for a given character.

Robust recognition of handwritten numerals based on dual cooperative network

Abstract: An approach to robust recognition of handwritten numerals using two operating parallel networks is presented. The first network uses inputs in Cartesian coordinates, and the second network uses the same inputs transformed into polar coordinates. How the proposed approach realizes the robustness to local and global variations of input numerals by handling inputs both in Cartesian coordinates and in its transformed Polar coordinates is described. The required network structures and its learning scheme are discussed. Experimental results show that by tracking only a small number of distinctive features for each teaching numeral in each coordinate, the proposed system can provide robust recognition of handwritten numerals. >

Handwriting recognition system and method

Abstract: of EP0539749Method and apparatus for automatic recognition of handwritten text based on a suitable representation of handwriting in one or several feature vector spaces(s), Gaussian modeling in each space, and mixture decoding to take into account the contribution of all relevant prototypes in all spaces. The feature vector space(s) is selected to encompass both a local and a global description of each appropriate point on a pen trajectory. Windowing is performed to capture broad trends in the handwriting, after which a linear transformation is applied to suitably eliminate redundancy. The resulting feature vector space(s) is called chirographic space(s). Gaussian modeling is performed to isolate adequate chirographic prototype distributions in each space, and the mixture coefficients weighting these distributions are trained using a maximum likelihood framework. Decoding can be performed simply and effectively by accumulating the contribution of all relevant prototype distributions. Post-processing using a language model may be included.

Off-line Handwriting Recognition by Recurrent Error Propagation Networks

Abstract: Recent years have seen an upsurge of interest in computer handwriting recognition as a means of making computers accessible to a wider range of people. A complete system for off-line, automatic recognition of handwriting is described, which takes word images scanned from a handwritten page and produces word-level output. Normalisation and preprocessing methods are described and details of the recurrent error propagation network and Viterbi decoder used for recognition are given. Results are reported and compared with those presented by researchers using other methods.

Handwritten numeral recognition based on hierarchically self-organizing learning networks with spatio-temporal pattern representation

Abstract: An approach for tracing, representation, and recognition of a handwritten numeral in an offline environment is presented. A 2D spatial representation of a numeral is first transformed into a 3D spatiotemporal representation by identifying the tracing sequence based on a set of heuristic rules acting as transformation operators. Given the dynamic information of the tracing sequence, a multiresolution critical-point segmentation method is proposed to extract local feature points, at varying degrees of scale and coarseness. A neural network architecture, the hierarchically self-organizing learning (HSOL) network (S. Lee, J.C. Pan, 1989), especially for handwritten numeral recognition, is presented. Experimental results based on a bidirectional HSOL network indicated that the method is robust in terms of variations, deformations, and corruption, achieving about 99% recognition rate for the test patterns. >

Handwritten digit recognition using neural networks

Abstract: Character and handwriting recognition is one of the most difficult problems of pattern recognition and artificial intelligence. Unlike the machine generated character, which is uniform throughout a document and often uniform between machines, each human being has a unique style of writing characters. With the infinite number of ways to record a character, it is a wonder that a person can understand his own script, let alone the script of another. Training a computer to recognize human-produced characters is a tremendous task in which researchers are just beginning to achieve some success. Primarily these methods rely on the use of algorithms to determine the similarities of two characters. Neural networks are an alternative technique now being explored. Four separate methods will be discussed in this paper. The first involves normalization, skeletonization, and feature extraction of a handwritten digit before application to a neural network for classification. The second simply applies a normalized digit to the neural net's input, and the network performs a 2-dimensional convolution on it in order to classify the digit. The third method involves a hierarchical network. The final technique incorporates time information into the system while using simple preprocessing and a small number of parameters. Their advantages and disadvantages are compared and discussed.