Showing papers on "Handwriting published in 1992"

Lower-Level Developmental Skills in Beginning Writing.

Abstract: A battery of predictor measures (neuromotor, orthographic, visual-motor integration, syllable and phoneme segmentation, word finding, sentence syntax, reading, and verbal intelligence) and of writing criterion measures (handwriting, spelling, and composition) was administered to an equal number of girls and boys in the first, second, and third grades (N=30) to study the developmental skills children bring to the task of learning to write. This developmental approach is an important complement to the prevailing process and product approaches to writing research. Multiple regression and canonical correlation results supported thehypothesis that lower-level developmental variables are related to beginning writing skills. Rapid, automatic production of alphabet letters, rapid coding of orthographic information, and speed of sequential finger movement were the best predictors of handwriting and composition skills. Orthographic-phonological mappings and visual-motor integration were the best predictors of spelling. Canonical correlation analysis identified anorthographic-linguistic dimension and anautomaticity dimension in the battery of developmental skills and of writing products. Results also supported the hypothesis that the translation component in process models of writing has two separable sub-components — text generation and transcription. Lower-level developmental skills are thought to constrain the transcription sub-component.

Structured Document Image Analysis

Abstract: Document image analysis is the automatic computer interpretation of images of printed and handwritten documents, including text, drawings, maps, music scores, etc. Research in this field supports a rapidly growing international industry. This is the first book to offer a broad selection of state-of-the-art research papers, including authoritative critical surveys of the literature, and parallel studies of the architectureof complete high-performance printed-document reading systems. A unique feature is the extended section on music notation, an ideal vehicle for international sharing of basic research. Also, the collection includes important new work on line drawings, handwriting, character and symbol recognition, and basic methodological issues. The IAPR 1990 Workshop on Syntactic and Structural Pattern Recognition is summarized,including the reports of its expert working groups, whose debates provide a fascinating perspective on the field. The book is an excellent text for a first-year graduate seminar in document image analysis,and is likely to remain a standard reference in the field for years.

Writing device for storing handwriting

Abstract: A writing device for storing handwriting picks up a handwriting which is written on a paper using a lead, using a CCD area sensor by a predetermined sampling frequency, then stores the picked up image data by the storing device under the control of a microcomputer, so that data storing which data are effective for reproducing the handwriting using a comparatively simple program, is achieved.

Handwriting and perceptual-motor skills in clumsy, dysgraphic, and 'normal' children.

Abstract: Among various perceptual-motor tests, only visuomotor integration was significant in predicting accuracy of handwriting performance for the total sample of 59 children consisting of 19 clumsy children, 22 nonclumsy dysgraphic children, and 18 'normal' children. They were selected from a sample of 360 fourth-graders (10-yr.-olds). For groups of clumsy and 'normal' children, the prediction of handwriting performance is difficult. However, correlations among scores on 6 measures showed that handwriting was significantly related to visuomotor integration, visual form perception, and tracing in the total group and to visuomotor integration and visual form perception in the clumsy group. The weakest correlations occurred between tests measuring simple psychomotor functions and handwriting. Moreover, clumsy children were expected to do poorly on tests measuring aiming, tracing, and visuomotor integration, but not on tests measuring visual form perception and finger tapping. Dysgraphic children were expected to do poorly on visuomotor integration only.

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. >

Handwriting input apparatus for inputting handwritten data from unspecified direction

Abstract: The handwriting input device includes an integrated display input device formed by integrating a display device and a tablet for inputting coordinates one on the other. The integrated display input device is used to input coordinate data of a designated position to an input region displayed on the display device. In accordance with the input region containing coordinate data, handwritten characters, or the like are input to the handwriting input apparatus. The input region is shifted in an arbitrary direction by rotation and transfer in the screen of the display device. In the case where the input region is rotated.

Portable pen pointing device and a processing system with pen pointing device

Abstract: A portable pen pointing device and a processing system with pen pointing device which can be easily used. The portable pen pointing device includes a memory for storing user's specific penmanship/handwriting information and a pen interface unit for supplying the user's specific penmanship/handwriting information to a processor body of the processing system. The processor body interprets a writing sample on the basis of the user's specific penmanship/handwriting information supplied from the portable pen pointing device through the pen interface unit thereof. With this construction, there is no need to read information from a storage medium such as a flexible disk in which a user's specific dictionary for penmanship/handwriting interpretation is written. Also, an operation of establishing a certain writing environment becomes unnecessary or easy.

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.

Expertise in Person Recognition

Abstract: The dramatic effect of inversion on the episodic recognition of unfamiliar faces has been considered as proof of specific mechanisms for the processing of faces. This view was challenged by Diamond and Carey (1986), who observed similar effects when photographs of dogs were shown to dog experts. However, they compared experts with younger novices, they used identical photographs at encoding and at test, their experts were no more accurate than the novices in the recognition of dogs, and dog recognition is remote from other inputs to the person recognition system such as natural handwriting. In Experiment 1, the results of Diamond and Carey were replicated with natural handwriting as stimuli, with novices matched in age to the experts, and with different structural representations of the targets at encoding and during the recognition test. In Experiment2, younger novices participated, but this did not affect the pattern of results. Experiment 3 showed that the results were not due to floor effects.

Handwriting and spelling: dyslexic children's abilities compared with children of the same chronological age and younger children of the same spelling level

Abstract: Summary. Handwriting speed and spelling were examined in a group of 10-year-old dyslexic children compared with children of the same age and with younger children of the same spelling level. The children wrote lists of words onto a digitizer pad in three different conditions: a dictation, copying from a sheet on the desk and copying from a wall chart. The words ranged in complexity from simple monosyllabic phoneme to grapheme words to words needing orthographic and morphological information and non-words. There were differences in writing speed between the 10-year-olds and 8-year-olds in most conditions. There were no significant differences in speed of writing or pausing between the dyslexic children and the 10-year-olds. There was a difference in the number of errors in the spelling of non-words, the dyslexic children being inferior to both the other groups. The only difference between the dyslexic children and the 8-year-olds was in speed of writing in copying from the desk and in writing complex words. The performance of the dyslexic group was more similar to that of the 8-year-olds in the dictation but to the 10-year-olds in the copying conditions. Independent judges had no difficulty in identifying the 10-year-olds' writing but confused that of the 8-year-olds with the dyslexic children's. It is proposed that the dyslexic children had automatised movement patterns linked to spelling equivalent to their same age peers but that these patterns were built on accumulated inaccuracies in both letter formation and spelling.

Early Spelling Acquisition: Does Writing Really Beat the Computer?:

Abstract: This research evaluated the efficacy of handwriting, letter tiles, and computer-based instruction on the early spelling acquisition of normal achieving (NLD) and learning disabled (LD) elementary students. The study replicated and extended the Cunningham and Stanovich (1990) study. Forty-eight primary-grade students (24 non-learning disabled; 24 learning disabled) received spelling training under three experimental conditions that involved different types of instructional activity: writing, sorting letter tiles, or typing on the computer. Results indicated no significant differences between the LD and NLD groups on words spelled correctly for any of the three conditions. Since the number of spelling words learned was low across conditions and groups, the number of correctly learned bigrams was examined. No within-group differences emerged for condition (writing, tile, computer); however, significant differences between the groups were found on number of bigrams learned for writing, tile, and computer, wit...

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. >

Chapter 4 Handwriting as A Motor Task: Experimentation, Modelling, and Simulation

Abstract: Publisher Summary This chapter reviews some of the experimental and theoretical research in the field of handwriting, where an increased activity has been displayed over the past two decades. Attention is paid to the specific features of the current research methodology and of handwriting as a motor task, including its effector-anatomy and geometry aspects. The theoretical framework into which most of the research findings are accommodated is a multi-stage model with a mixed hierarchical and parallel architecture. It is also devoted to the constraints determining the selection of stroke sequences in graphic action when copying unfamiliar patterns. It concentrates on the motor aspects. After a brief historical introduction, it discusses experimental techniques, data and modeling. The chapter explores the brief review of rule-governed aspects of graphic behavior. The chapter concludes with a discussion of computational approaches. These are concerned not only with the simulation of handwriting production, but also with the automatic recognition of cursive script, an extremely difficult task which requires support from insights in the motor aspects of handwriting generation.

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.

Improving handwriting through kinaesthetic sensitivity practice.

Abstract: Children in their first two years of formal education (kindergarten and year one) were assessed for handwriting performance. Those with poor handwriting were given practice on one of three tasks: kinaesthetic acuity, kinaesthetic memory and perception or a handwriting task. Both forms of kinaesthetic sensitivity practice produced significant improvement in handwriting performance by the year one children, while handwriting practice did not. The younger children did not demonstrate as clear cut gains as the older. These results support the findings of previous research which indicates the importance of kinaesthetic ability for performance of complex motor tasks.

The write stuff: Evaluations of graphology, the study of handwriting analysis.

Abstract: Like fingerprints, each person's handwriting is unique and may be used as a means of identification. Expert document examiners have long been used by courts to determine the authenticity of signatures and other writing samples. But is there more that handwriting can reveal about a person beyond individual identification? Many claim that such analysis has been perfected in the science of "graphology" and that personality traits and accurate character readings can be deduced from a person's penmenship. In this definitive study of graphology, Barry and Dale Beyerstein provide a balanced evaluation of claims that personality, aptitude, and psychological and physical health can be determined through handwriting analysis. The contributors include both practicing graphologists, who present their case and describe their practices and methods, as well as critics from many fields, who evaluate graphology in terms of brain research; assess its accuracy through objective tests of validity; contrast graphology with verifiable psychological assessment techniques; and review the legality of using graphology in employee selection, psychological diagnosis, and the criminal justice system. A major thrust of the book is a consideration of why graphology seems so accurate to many personnel managers when it has been unable to pass objective tests of validity designed by experts in the psychology of individual differences. In addition, a brief history of graphology is offered, which traces its roots to the ancient practice of sympathetic magic. Also presented is a philosophical discussion which compares the practice and philosophical assumptions of graphology with the scientific method. For critics andproponents alike, The Write Stuff will serve as an invaluable reference work.

Apparatus for reading handwriting

Abstract: Apparatus for reading handwriting including apparatus (20) for sensing features of handwriting of an individual which features are highly characteristic of the individual but which also contain information relating to symbols being written and apparatus, which is configured for the individual, for providing a non-individual dependent output (26) indicating the symbols being written in response to the sensed features.

Handwritten input information processor

Abstract: PURPOSE:To deal with vertical/horizontal writing and Japanese words by specifying an editing proofreading symbol which is the most similar to a handwriting form without regard to the directional habit of the handwriting form. CONSTITUTION:A tablet controller 58 controls a tablet provided on a display and tablet block 59 as a coordinate input means generating coordinate data corresponding to handwriting by a stylus pen 60. CPU 51 is provided with functions as a symbol discriminating means recognizing the handwriting form based on coordinate data generated by the coordinate input means and specifying the editing proofreading symbol which is the most similar to the recognized handwriting form from among plural editing proofreading symbol previously defined within a system ROM 52 without regard to the directional habit of the handwriting form and an editing proofreading means executing an editing proofreading processing to an editing proofreading object in correspondence to a function assigned to the specified editing proofreading symbol. Thereby, this processor can handle vertical/horizontal handwriting and Japanese words.

Design and Collection of a Handwriting Sample Image Database

Abstract: NIST, under sponsorship from the Bureau of the Census, has collected a database consisting of 2,100 pages of binary image data of handprinted characters including numerals and text. NIST Special Database 1 contains handwriting samples from 2,100 writers geographically distributed across the United States, NIST is currently using this database to research field-isolation, box detection and removal, character segmentation, and writer-independent neural character recognition. In addition to advancing the design of algorithms, this database and its study can aid the social sciences. Observations can be compiled and used to improve form design and field layout strategies. Region-based studies and comparisons are also possible due to regionally distributed and referenced populations of writers in the database. In creating this large database, obstacles to the effective archiving of images have been dealt with and eliminated. This paper describes the database's content in terms of its collection, organization, and usefulness. The strategies and conventions used to develop NIST Special Database 1 can be applied to any discipline requiring the use of image archives.

Handwriting Speed, Specific Learning Difficulties and the GCSE

Abstract: Summary The need for clear criteria necessary for special arrangements for the GCSE is put forward in the context of increasing numbers of referrals of candidates with specific learning difficulties. Slow writing speed is suggested as a difficulty where there is a lack of research and appropriate published tests. Psychologists, however, are expected to evaluate a candidate's performance and make recommendations regarding extra time. The small scale study described below looks at a number of factors, including the predictive validity of short tests of a few minutes duration. Problems with such tests are explored and areas for further research are suggested.

A handwriting model for syntactic recognition of cursive script

Abstract: Defines an operational handwriting model for online syntactic recognition of cursive script. To represent handwriting, it uses characteristic points linked together by segments of uniform curvature. The model acts as a guide for the extraction of attributed primitives used in shape grammars that model allographs and their adjacency rules. The handwriting model is evaluated by human readers in a comparative analysis of original cursive letter sequences versus their reconstructed traces. Also, its performance is measured in terms of mean reconstruction error and data compression rate. >

Offline recognition of handwritten cursive words

Abstract: A robust algorithm for offline cursive script recognition is described. The algorithm uses a generate-and-test paradigm to analyze cursive word images. The generate phase of the algorithm intelligently segments the word after analyzing certain structural features present in the word. The test phase determines the most likely character candidates among the segmentation points by using a recognition algorithm trained on generalized cursive letter shapes. In a sense, word recognition is done by sliding a variable sized window across the word looking for recognizable characters and strokes. The output of this system is a list of all plausible interpretations of the word. This list is then analyzed by a two-step contextual post- processor which first matches all of the interpretations to a supplied dictionary using a string matching algorithm. This eliminates the least likely interpretations. The remaining candidates are then analyzed for certain character spatial relationships (local reference line finder) to finally rank the dictionary. The system has the advantage of not requiring explicit word training yet is able to recognize many handwriting styles. This system is being successfully tested on a database of handwritten words extracted from live mail with dictionary sizes of up to 300 words. Planned extensions include developing a multilevel generate-and-test paradigm which can handle any type of handwritten word.

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. >

Simulation of impairment of force amplitude and force timing in Parkinsonian handwriting

Abstract: Previous research gave rise to the hypothesis that Parkinsonian handwriting is impaired more in terms of force amplitude than force timing. We simulated the type of impairment found in Parkinsonian handwriting. The simulations demonstrated that impairment of force amplitude and of force duration produce distinct handwriting distortions. Force-amplitude impairment causes an altered baseline within a word whereas a force-timing impairment causes loops at the sharp movement reversals required for specific allographs, e.g., cursive-script «u». In comparison to age-matched controls, it was found that Parkinsonians exhibit substantial problems in maintaining a straight baseline but few problems with sharp movement reversals