Studien tar sin utgångspunkt i kognitiva skrivteorier. Syftet med studien har varit att undersöka om handskrivnings- stavnings- och avkodningsförmåga hade statistiska samband med textlängd och textkvalitetsamt om det fanns några skillnader mellan flickor och pojkar. Studien ville även se om det var bokstävernas läslighet eller om det var elevens föreställning om bokstavens utseende som hade betydelse för textlängd och textkvalitet. I urvalet ingick 38 elever i år 2. Resultaten visade att förmåga att snabbt skriva läsliga bokstäver och att kunna stava ord hade samband med textlängd. Textlängd hade samband med textkvalitet, ordvariation och syntaktisk komplexitet. Handskrivning och stavning hade ett måttligt samband med innehållsliga aspekter av textkvalitet och de förklarade 60 % av variationen på textkvalitet. Handskrivning och stavning hade starka samband med textyteaspekter av textkvalitet. Handskrivning och stavning hade dessutom ett inbördes samband. Avkodning hade samband med stavning och med textyteaspekter av textkvalitet. Flickor var bättre på handskrivning och de hade bättre läsbarhet i sina texter. Flickor hade också högre skrivhastighet, ett mer varierat ordval i texterna och använde stor bokstav och skiljetecken på ett säkrare sätt jämfört med pojkar. Inga könsskillnader fanns vad gällde stavning och innehållsliga aspekter av textkvalitet. Resultatet indikerar att handskrivning och stavning inte kan negligeras i undervisningen eftersom de påverkar textlängd och olika aspekter av textkvalitet.

Handwriting recognizers frequently misinterpret digital ink input, requiring human verification of recognizer output to identify and correct errors, before the output of the recognizer can be used with any confidence int its correctness. Technologies like Anoto pens can make this error discovery and correction task more difficult, because verification of recognizer output may occur many hours after data input, creating an ``out-of-the-moment'' verification scenario. This difficulty can increase the number of recognition errors missed by users in verification. To increase the accuracy of human verified recognizer output, methods of aiding users in the discovery of handwriting recognition errors need to be created. While this need has been recognized by the research community, no published work exists examining this problem. This thesis explores the problem of creating error discovery aids for handwriting recognition. Design possibilities for the creation of error discovery aids are explored, and concrete designs for error discovery aids are presented. Evaluations are performed on a set of these proposed discovery aids, showing that the visual proximity aid improves user performance in error discovery. Following the evaluation of the discovery aids proposed in this thesis, the one discovery aid that has been proposed in the literature, confidence highlighting, is explored in detail and its potential as a discovery aid is highlighted. A technique is then presented, complimentary to error discovery aids, to allow a system to monitor and respond to user performance in errors discovery. Finally, a set of implications are derived from the presented work for the design of verification interfaces for handwriting recognition.

Most software programs that deal with mathematical objects require input expressions to be linearized using somewhat awkward and unfamiliar string-based syntax. It is natural to desire a method for inputting mathematics using the same two-dimensional syntax employed with pen and paper, and the increasing prevalence of pen- and touch-based interfaces causes this topic to be of practical as well as theoretical interest. Accurately recognizing two-dimensional mathematical notation is a difficult problem that requires not only theoretical advancement over the traditional theories of string-based languages, but also careful consideration of runtime efficiency, data organization, and other practical concerns that arise during system construction. This thesis describes the math recognizer used in the MathBrush pen-math system. At a high level, the two-dimensional syntax of mathematical writing is formalized using a relational grammar. Rather than reporting a single recognition result, all recognizable interpretations of the input are simultaneously represented in a data structure called a parse forest. Individual interpretations may be extracted from the forest and reported one by one as the user requests them. These parsing techniques necessitate robust tree scoring functions, which themselves rely on several lower-level recognition processes for stroke grouping, symbol recognition, and spatial relation classification. The thesis covers the recognition, parsing, and scoring aspects of the MathBrush recognizer, as well as the algorithms and assumptions necessary to combine those systems and formalisms together into a useful and efficient software system. The effectiveness of the resulting system is measured through two accuracy evaluations. One evaluation uses a novel metric based on user effort, while the other replicates the evaluation process of an international accuracy competition. The evaluations show that not only is the performance of the MathBrush recognizer improving over time, but it is also significantly more accurate than other academic recognition systems.

Differences between handwritten and typed essays were examined in high school adolescents with a learning disability (LD) who have writing difficulties. Despite being experienced at writing on the computer and possessing fluent typing skills, there were no differences found between the quality of handwritten and typed essays. Essays were scored against quality indices for lower-level transcription (i.e., mechanics), higher-level text generation (i.e., organization, theme development, vocabulary), spelling accuracy, word count, and grammar. No differences were found across any of these dimensions between conditions. Correlations were also examined to determine any similarities, or differences in relationship among the measures, between the handwritten and typed conditions. Similar associations were found across both conditions for total essay score, lower-level transcription, and handwriting/typing fluency. However, higher-level text generation for typed essays correlated with the measures of working memory, lexical access, and spelling, whereas none of these measures correlated with the higher-level text generation for handwritten essays. / Graduate / 0525 / 0529 / 0710 / rachel.jalbert@gmail.com

Thesis (M.S.)--Medical College of Ohio, 2004. / "In partial fulfillment of the requirements for the degree of Master of Science in Biomedical Sciences." Major advisor: Michael J. Dennis. Includes abstract. Document formatted into pages: iii, 62 p. Title from title page of PDF document. Includes bibliographical references (p. 57-61).

This work introduces two unconventional applications for sequence alignment algorithms outside the domain of bioinformatics: handwriting recognition and speech recognition. In each application we treated data samples, such as the path of a and written pen stroke, as a protein sequence and use the FastA sequence alignment tool to classify unknown data samples, such as a written character. That is, we handle the handwriting and speech recognition problems like the protein annotation problem: given a sequence of unknown function, we annotate the sequence via sequence alignment. This approach achieves classification rates of 99.65% and 93.84% for the handwriting and speech recognition respectively. In addition, we provide a framework for applying sequence alignment to a variety of other non–traditional problems. / Singapore-MIT Alliance (SMA)

Made available in DSpace on 2016-06-02T20:44:09Z (GMT). No. of bitstreams: 1 4124.pdf: 1362899 bytes, checksum: 96be172ffe08c1494e59baa3c7a77442 (MD5) Previous issue date: 2012-01-05 / Financiadora de Estudos e Projetos / Handwriting is an essencial skill for the performance of activities of daily life related to the expression of information in academic, work-related and leisure situations. Among adult population, there is a prevalence of two grasp forms used for handwriting, classified in neurophysiological development as mature or transitional grasps. These grasp patterns may be related to upper limb muscular and postural dysfunctions due to the use of different muscular groups in handwriting activity. The objective of this study was to analyze the electromyographic activity of upper trapezium, biceps braquii, extensor carpi radialis brevis and flexor digitorum superficialis among subjects who use the dynamic tripod grasp and the static tripod grasp during handwriting. Twenty-four university students between 18 and 28 years, without functional dysfunctions of the upper limbs underwent electromyographic analyze during a patterned handwriting task. A significant increase in electromyographic activity of upper trapezium and biceps braquii was observed among subjects who use the static tripod grasp. There was no significant change between the myoelectric activity of the extensorcarpi radialis brevis and flexor digitorum superficialis between the two groups. The increase in electromyographic activity among subjects using static tripod grasp indicates potential higher energy expenditure and increased risk of muscular lesions with the maintence of this motor pattern during handwriting tasks. Since the increased demand for speed and expression of information through handwriting is expected during academic life, the careful observation, evaluation and therapeutic monitoring could stimulate the development of mature grasps and optimize the performance of writing tasks, an important area of intervention and clinical research to occupational therapy. / A escrita manual é uma habilidade essencial para o desempenho de diversas atividades cotidianas, como meio de expressão de informações e conhecimentos em ambientes acadêmicos, laborais e em situações de entretenimento e lazer. Entre a população adulta observa-se a prevalência de duas categorias de preensões na escrita, classificadas do ponto de vista do desenvolvimento neurofisiológico como maduras ou de transição. Tais formas de preensão podem estar relacionadas a disfunções posturais no membro superior devido à utilização de diferentes grupos musculares. O objetivo do estudo foi analisar a atividade eletromiográfica dos músculos trapézio, bíceps braquial, extensor radial curto do carpo e flexor superficial dos dedos em indivíduos que utilizam a preensão trípode dinâmica e a preensão trípode estática durante a escrita manual. Vinte e quatro estudantes universitários entre 18 e 28 anos, sem acometimento funcional do membro superior foram submetidos a exame eletromiográfico durante uma tarefa de escrita manual padronizada. Observou-se aumento significativo na atividade mioelétrica do trapézio e bíceps braquial entre indivíduos que utilizam a preensão trípode estática. Não foi observada alteração significativa entre a atividade mioelétrica do extensor radial curto do carpo e flexor superficial dos dedos entre os dois grupos. A maior atividade eletromiográfica da musculatura proximal entre indivíduos que utilizam a preensão trípode estática aponta para um gasto energético mais elevado e potencial dano muscular durante a manutenção deste padrão motor nas tarefas de escrita manual. Uma vez que se observa aumento das exigências por velocidade e produção de informações escritas em ambiente acadêmico, a observação, avaliação e o acompanhamento terapêutico para o estímulo ao desenvolvimento de preensões maduras poderiam favorecer o desempenho de tarefas escritas, importante área de intervenção e investigação clínica da terapia ocupacional.

Made available in DSpace on 2016-06-02T20:44:13Z (GMT). No. of bitstreams: 1 5786.pdf: 915408 bytes, checksum: cdfcad18479891c2bc47d026d878c5e8 (MD5) Previous issue date: 2014-02-24 / Universidade Federal de Minas Gerais / Handwriting acquisition is an important factor for good school performance that due to motor components required for its execution may be compromised in schoolchildren born preterm. OBJECTIVES: To investigate the relationship between fine motor coordination and the quality of handwriting in school age children born preterm and full term. METHOD: This was a descriptive study wit group comparison, the study group was composed of students of both genders, preterm infants between born in 2004, 2005 and 2006 with gestational age between 32 and 36 weeks, birthweight ≤ 2500g, and the comparison group, with children born during the same period, with gestational age ≥ 37 weeks, birth weight ≥ 2500g, which were matched according to gender, age, socioeconomic status, and school level. The study was conducted in a small town in the interior of São Paulo state and the study was approved by the ethics committee and the town´s Departments of Health and Education. Parents or guardians from both groups were interviewed to collect personal data and information on family dynamics and socioeconomic status and they responded to the questionnaires Developmental Coordination Disorder Questionnaire (DCDQ Brazil), the Brazil Criteria for Economic Classification (CCEB), and the Parents Questionnaire of the Avaliação da Coordenação e Destreza Motora (ACOORDEM). The children fine motor skills were assessed with the ACOORDEM and the classroom teachers responded the ACOORDEM´s Teacher´s Questionnaire as well as the Escala de Transtorno de Déficit de Atenção e Hiperatividade versão para professores (ETDAH) (Scale for Attention Deficit Hyperactivity Disorder - teacher's version ). RESULTS: Data analysis indicated that the town under investigation does not offer any follow-up or support service specific for prematurity. The teaching methods in local early childhood education does not seem to be achieving desired levels because students from both groups had higher than expected difficulties in the handwriting tasks. The study also lends support to the relationship between preterm birth and unfavorable socioeconomic conditions. Regarding fine motor skills and handwriting, there was significant difference in some specific items of the tests, but not in the total scores, however the preterm group tended to present lower performance in handwriting, fine motor skills, global motor coordination and greater probability of signs of attention deficit and hyperactivity. Significant correlations were found between handwriting quality writing and the performance on some items of the motor tests. CONCLUSION: The results indicated that preterms are more likely to present motor and writing difficulties when compared to the full term peers, although with a larger sample the results might have reached statistical significance. Further studies should include larger and more homogeneous samples, with respect to gestational age and birth weight of the preterms. / A aquisição da escrita é um importante fator para o bom desempenho escolar que, devido a componentes motores exigidos para sua execução, pode estar comprometida em escolares nascidos pré-termo. OBJETIVOS: Investigar a relação entre coordenação motora fina e qualidade da escrita em escolares nascidos pré-termo e a termo. MÉTODO: Trata-se de estudo descritivo de comparação entre grupos, sendo o grupo de estudo composto por escolares de ambos os gêneros, nascidos com idade gestacional entre 32 e 36 semanas e peso ao nascer ≤ 2500g nos anos de 2004, 2005 e 2006, e o grupo comparado, composto por escolares nascidos no mesmo período, de ambos os gêneros e com idade gestacional ≥37 semanas, peso ao nascer ≥ 2500g, que foram emparelhados de acordo com o gênero, idade, sala escolar e condição socioeconômica. O estudo foi realizado em uma cidade de pequeno porte do interior paulista e foi autorizado por comitê de ética e pelas Secretarias de Saúde e Educação do Município. Os pais dos escolares de ambos os grupos foram entrevistados para coleta de dados pessoais, de dinâmica familiar e condição socioeconômica, e responderam aos questionários Developmental Coordination Disorder Questionnaire (DCDQ-Brasil), Critério de Classificação Econômica Brasil (CCEB) e ao Questionário de Pais da Avaliação da Coordenação e Destreza Motora (ACOORDEM) Os escolares foram avaliados com a ACOORDEM, com observação direta de desempenho motor, e os professores responsáveis pelas salas de aula de cada escolar responderam aos seguintes questionários: questionário para professores da ACOORDEM e a Escala de Transtorno de Déficit de Atenção e Hiperatividade versão para professores (ETDAH). RESULTADOS: A análise dos dados apontou que o município estudado não oferece nenhum serviço de acompanhamento e suporte a prematuridade. Os métodos de ensino na educação infantil municipal parecem não estar alcançando os níveis desejados, uma vez que escolares de ambos os grupos tiveram dificuldades acima do esperado para a idade nas provas de escrita. O estudo também dá suporte à relação entre condições socioeconômicas desfavoráveis e o nascimento pré-termo. Com relação à coordenação fina e escrita, houve diferença significativa em alguns itens específicos dos testes, mas não nos scores gerais, porém os pré-termos obtiveram desempenho inferior nos testes de escrita, coordenação fina, coordenação global e maior probabilidade de sinais de déficit de atenção e hiperatividade. Foi encontrada também correlação entre a qualidade na escrita e o desempenho em alguns itens dos testes motores. CONCLUSÃO: Os resultados apontaram mais probabilidade a dificuldades motoras e na escrita entre pré-termos, se comparados aos a termos, embora acredite-se que uma maior amostra pudesse oferecer maios significância. Para próximos estudos sugere-se que se utilizem uma amostra maior e mais homogênea no que diz respeito a idade gestacional e peso ao nascer dos pré-termos.

The aim of this diploma thesis is to introduce the reader to a new writing model Comenia Script and the results of its establishing during the first years of a school attendance. The theoretical part deals with a developement of a script, a characteristic of a cursive Latin alphabet writing and Comenia Script and a contemporary education of a first-year writing. In the practical part the findings gathered during the participant observation of the entrusted sample of respondents were analysed and the questionnaire survey focussed on attitudes of involved pupils' parents was evaluated.

[pt] Esta dissertação investiga a utilização de Redes Neurais Artificiais (RNAs) na área de reconhecimento de caracteres, em particular de dígitos manuscritos. Nesta investigação foram utilizadas amostras reais de dígitos isolados e de códigos postais brasileiros relativos e vários escritores. O trabalho consiste de quatro partes principais: o estudo das metodologias de reconhecimento e da semântica e estrutura de representação de caracteres; o desenvolvimento das etapas de pré-processamento dos dígitos; o desenvolvimento das RNAs para o reconhecimento de dígitos manuscritos; e o estudo de casos. No estudo sobre a metodologia de reconhecimento de caracteres fez-se um levantamento preliminar das diversas aplicaões de sistemas OCR (Optical Character Recognition). Enfatizou-se a classificação dos diversos tipos de semânticas existentes de acordo com a aplicação específica, bem como a estrutura geral de um sistema OCR. O estudo também consistiu da análise e apresentação de modelos convencionais e de sistemas inteligentes na implementação da etapa de classificação dos sistemas OCR. O desenvolvimento do pré-processamento dos dígitos envolveu um extenso estudo bibliográfico de diversas metodologias para cada uma de suas etapas. Foram estudados os algoritmos mais empregados nas etapas de pré- processamento de um sistema. OCR: conversão de níveis de cinza para representação binária ( thresholding), filtragem, segmentação e normalização. A partir desse estudo, foram selecionados e desenvolvidos determinados tipos de algoritmos para o pré-processamento. No desenvolvimento de RNAs para o reconhecimento de dígitos manuscritos fez-se uma investigação de diversas metodologias, incluindo as arquiteturas e os algoritmos de aprendizado mais empregados. Neste estudo, constatou-se a predominância do uso do algoritmo de retropropagação do erro (BackPropagation) para o treinamento das redes nas aplicações de reconhecimento de caracteres manuscritos. As arquiteturas propostas neste trabalho foram escolhidas de acordo com dois tipos de aplicados de reconhecimento: reconhecimento de dígitos manuscritos isolados e reconhecimento automático de código postal. No estudo de casos, as RNAs foram modeladas para fazer o reconhecimento automático de código postal. Este estudo consistiu de um conjunto de implementações com o objetivo de testar o desempenho de um sistema OCR baseado em redes neurais. Foram feitos testes com dois tipos de sistemas de reconhecimento por redes neurais: redes totalmente conectadas e redes parcialmente. Para os dois casos foram utilizados amostras reais colhidas de 73 escritores. Os resultados obtidos com os dois tipos de redes foram comparados e comprovaram a superioridade das RNAs com arquitetura parcialmente conectada no reconhecimento de dígitos altamente ruidosos. Comparações também foram feitas com outras técnicas convencionais de reconhecimento, obtendo-se resultados, em muitos casos, superiores. / [en] This dissertation investigates the use of Artificial Neural Networks (ANNs) for character recognition, especially handwritten digits. Real samples of isolated and postal code digits were used from different writers. The dissertation covers four main part: the study of methodologies, semantics and structure on character recognition and its representation; the development of the digits preprocessing phases; the design of ANNs to handwritten digits recognition; and the case studies. The first part of this dissertation studies methodologies, semantics and structures used on character recognition. The result of this study is an overview of the major aplication in OCR (Optical Character Recognition). Different kinds of semantics and their structures were classified according to each specific application. Several conventional models and intelligent systems, used in the classification stage of OCR systems, had also been discussed. The development of the digits preprocessing involved the investigation of different methodologies related to each preprocessing phase. The most used algorithm for each preprocessing phase were considered: thresholding, smoothing, segmentation and normalization. According to this study, specific algorithms were selected and developed. In the design of ANNs for handwritten digits recognition, different methodologies had been investigated, including the architetures and the learning algorithms most used. This overview confirmed the predominance of BackPropagation as the training algorithm for the Neural Network in this application. The architetures proposed in this work had been selected according to two types of applications of character recognition: isolated handwritten digits recognition and postal address code recognition. The case studies consisted of the designing of an ANN to postal address code recognition. The case studies involved testing the system performance for two kinds of ANNs: fully connected networks and partially connected networks. In both cases, samples of 73 writers were used. The results were compared to each other, confirming the superiority of partially connected ANN in handling noisy digits. The ANN perfomance was also compared with the perfomance of other conventional techniques, achieving better results in many cases.