Font and Size Independent OCR for Printed Kannada Documents using SVM Classifiers

The following topics were dealt with: document analysis and recognition; multimedia document processing; character recognition; document image processing; cheque processing; form processing; music processing; document segmentation; electronic documents; character classification; handwritten character recognition; information retrieval; postal automation; font recognition; Indian language OCR; handwriting recognition; performance evaluation; graphics recognition; oriental character recognition; and word recognition

Lexicon-free, novel segmentation of online handwritten indic words

Research in the field of recognizing unlimited vocabulary, online handwritten Indic words is still in its infancy. Most of the focus so far has been in the area of isolated character recognition. In the context of lexicon-free recognition of words, one of the primary issues to be addressed is that of segmentation. As a preliminary attempt, this paper proposes a novel script-independent, lexicon-free method for segmenting online handwritten words to their constituent symbols. Feedback strategies, inspired from neuroscience studies, are proposed for improving the segmentation. The segmentation strategy has been tested on an exhaustive set of 10000 Tamil words collected from a large number of writers. The results show that better segmentation improves the overall recognition performance of the handwriting system.

Deep learning review and its applications

Deep neural networks have recently gained popularity for improv- ing state-of-the-art machine learning algorithms in diverse areas such as speech recognition, computer vision and bioinformatics. Convolutional networks especially have shown prowess in visual recognition tasks such as object recognition and detection in which this work is focused on. Mod- ern award-winning architectures have systematically surpassed previous attempts at tackling computer vision problems and keep winning most current competitions. After a brief study of deep learning architectures and readily available frameworks and libraries, the LeNet handwriting digit recognition network study case is developed, and lastly a deep learn- ing network for playing simple videogames is reviewed.

Physiological modules for generating discrete and rhythmic movements: Component analysis of EMG signals

A central question in Neuroscience is that of how the nervous system generates the spatiotemporal commands needed to realize complex gestures, such as handwriting. A key postulate is that the central nervous system (CNS) builds up complex movements from a set of simpler motor primitives or control modules. In this study we examined the control modules underlying the generation of muscle activations when performing different types of movement: discrete, point-to-point movements in eight different directions and continuous figure-eight movements in both the normal, upright orientation and rotated 90 degrees. To test for the effects of biomechanical constraints, movements were performed in the frontal-parallel or sagittal planes, corresponding to two different nominal flexion/abduction postures of the shoulder. In all cases we measured limb kinematics and surface electromyographic activity (EMB) signals for seven different muscles acting around the shoulder. We first performed principal component analysis (PCA) of the EMG signals on a movement-by-movement basis. We found a surprisingly consistent pattern of muscle groupings across movement types and movement planes, although we could detect systematic differences between the PCs derived from movements performed in each sholder posture and between the principal components associated with the different orientations of the figure. Unexpectedly we found no systematic differences between the figute eights and the point-to-point movements. The first three principal components could be associated with a general co-contraction of all seven muscles plus two patterns of reciprocal activatoin. From these results, we surmise that both "discrete-rhythmic movements" such as the figure eight, and discrete point-to-point movement may be constructed from three different fundamental modules, one regulating the impedance of the limb over the time span of the movement and two others operating to generate movement, one aligned with the vertical and the other aligned with the horizontal.

Modelos caligráficos na escola brasileira : uma história do Renascimento aos nossos dias

Se a escrita pessoal precisa sobreviver como habilidade individual perante as novas técnicas de produção textual, parece-nos necessária uma análise da escrita manual sob uma nova perspectiva. Num universo regido pelas mídias tecnológicas, no qual o computador pode ser visto como uma verdadeira extensão do homem, qual o lugar da escrita manual na atualidade? E, ainda: acreditando que o design pode auxiliar o educador, de que forma o mesmo pode interferir na aquisição da escrita manual e na formação de uma escrita legível e funcional? O presente projeto de pesquisa procura lançar luzes sobre este tema a partir de uma síntese dos principais modelos de escrita adotados na educação fundamental no Brasil durante o século XX. Para tanto, vamos elencá-los e analisá-los buscando relações e pontos comuns entre esses modelos e apontando para uma reflexão futura, calcada no campo do design e, em especial, da tipografia, tendo a aquisição da escrita como pano de fundo.

Erro de medicação: a visão do enfermeiro neonatologista

O manejo da terapia medicamentosa em unidade de terapia intensiva neonatal é complexo e agrega inúmeras drogas. Nesse sentido, manter a atenção ao preparar e administrar corretamente os medicamentos é fundamental em todo o período de assistência ao recém-nascido. Portanto, faz-se necessário que os enfermeiros tenham o entendimento acerca do conceito do erro com medicação, para que possa identificá-lo, bem como os fatores contribuintes para sua ocorrência. Diante do exposto, esta pesquisa teve como objetivos: analisar o entendimento dos enfermeiros neonatologistas sobre o conceito do erro de medicação em uma unidade de terapia intensiva neonatal; conhecer na visão destes enfermeiros quais os fatores contribuintes para a ocorrência desse erro e discutir a partir desta visão como estes fatores podem afetar a segurança do neonato. Metodologia: trata-se de uma pesquisa qualitativa, do tipo descritiva. O cenário do estudo foi uma unidade de terapia intensiva neonatal de um hospital universitário, situado no município do Rio de Janeiro. Os sujeitos foram 14 enfermeiros entre plantonistas e residentes que atuavam no manejo da terapia medicamentosa. Para a coleta dos dados utilizou-se a entrevista semiestruturada, que foram analisadas através da análise de conteúdo de Bardin, emergindo 04 categorias: Diversos conceitos sobre erros de medicação; Fatores humanos contribuintes ao erro de medicação; Fatores ambientais contribuintes ao erro de medicação e Conhecendo como os fatores contribuintes ao erro podem afetar a segurança do paciente. Para as enfermeiras o erro de medicação significa errar um dos cinco certos na administração de medicamentos (paciente, dose, via, horário e medicamento certo), e este pode acontecer em alguma parte do sistema de medicação. Neste sentido, elas entendem que uma pessoa não pode ser considerada a única responsável pela ocorrência de um erro medicamentoso. Quanto aos fatores contribuintes ao erro de medicação elencaram aqueles relacionados à prescrição medicamentosa (letra ilegível, prescrição da dose e via incorretas), ao próprio profissional de enfermagem (como sobrecarga de trabalho, número reduzido de profissionais e os múltiplos vínculos empregatícios) e ao ambiente de trabalho (ambiente inadequado e estressante; conversas paralelas com os colegas e os ruídos no setor). Na visão das enfermeiras, os fatores contribuintes ao erro podem afetar a segurança do recém-nascido, levando às situações de danos a sua saúde, podendo trazer consequências clínicas e risco de óbito. O estudo aponta a necessidade de se buscar sistemas de medicação mais confiáveis e seguros. Neste sentido, é imprescindível desenvolver e implementar programas de educação centrados nos princípios gerais da segurança do paciente. Além disso, é de suma importância que as políticas públicas de saúde, direcionem ações para o aprimoramento de medidas na segurança do RN, do sistema de medicação e da cultura de segurança.

Dasher

Dasher is an information-efficient text-entry interface, which can be driven by natural continuous pointing gestures or by pressing buttons. Dasher is a competitive text-entry system wherever a full-size keyboard cannot be used - for example, when operating a computer one-handed, by joystick, touchscreen, trackball, or mouse; when operating a computer with zero hands (i.e., by head-mouse or by eyetracker); on a palmtop computer; on a wearable computer. The gazetracking version of Dasher allows an experienced user to write text as fast as normal handwriting - 29 words per minute; using a mouse, experienced users can write at 39 words per minute. Dasher can be used to write efficiently in any language. Dasher is free software (distributed under the GPL) and is available for many computer platforms, including linux, windows, and android.

scenario-based interactive intention understanding in pen-based user interfaces

Interactive intention understanding is important for Pen-based User Interface (PUI). Many works on this topic are reported, and focus on handwriting or sketching recognition algorithms at the lexical layer. But these algorithms cannot totally solve the problem of intention understanding and can not provide the pen-based software with high usability. Hence, a scenario-based interactive intention understanding framework is presented in this paper, and is used to simulate human cognitive mechanisms and cognitive habits. By providing the understanding environment supporting the framework, we can apply the framework to the practical PUI system. The evaluation of the Scientific Training Management System for the Chinese National Diving Team shows that the framework is effective in improving the usability and enhancing the intention understanding capacity of this system.

一种连续手写中文的演化分割方法

在连续手写中文中,有偏旁部首离得较远的单字,单字之间可能会存在粘连、重叠。针对这种情况给出了一种基于识别得分提取单字的演化方法。对行笔划序列进行二进制编码,采用改进的遗传算法实现演化过程。染色体中连续0或1对应的笔划组成候选单字。用汉王手写单字识别器获取它们的识别得分,以单字个数较少和总的识别得分较大为优化目标。遗传算法中的变异概率和交叉概率自适应生成。测试结果表明该方法对连续手写中文具有较好的分割效果。

基于结构理解的笔迹智能编辑

随着人机界面朝着自然高效的方向发展,手写笔迹的结构分析和智能编辑越来越被人们所关注。给出了一种基于多层次相互作用的结构理解的笔迹智能编辑方法。该方法先自下而上初步提取单字、行、段,然后自上而下利用整体信息对组成信息进行精确分割,提取的信息表示成一个多层次的结构。基于笔迹的结构,用户可以使用笔手势对笔迹进行编辑。实验评估表明,该方法对笔迹的智能编辑具有较好的效果。

基于多通道融合的连续手写识别纠错方法

在基于识别的界面中,用户的满意度不但由识别准确度决定,而且还受识别错误的纠正过程的影响.提出一种基于多通道融合的连续手写笔迹识别错误的纠正方法.该方法允许用户通过口述书写内容纠正手写识别中的字符提取和识别的错误.该纠错方法的核心是一种多通道融合算法.该算法通过利用语音输入约束最优手写识别结果的搜索,可纠正手写字符的切分错和识别错.实验评估结果表明,该融合算法能够有效纠正错误,计算效率高.与另外两种手写识别错误纠正方法相比,该方法具有更高的纠错效率.

基于感知的多方向在线手写笔迹文本行提取

提出一种多方向手写笔迹文本行的提取方法.该方法以视觉感知理论为基础,采取自底向上的策略,先将笔画组合成类比字符的笔画块,然后基于这些笔画块建立链接模型,最后采用分支限界搜索算法从链接模型中找出最优行排列.实验结果表明,该方法能有效地提取多方向笔迹行结构,并适用于弯曲文本行的提取.

基于数学形态学的联机手写字符识别去噪方法

手写输入时由于笔尖抖动等原因产生了大量噪声,有效地去除噪声是手写识别的前提和关键。根据联机手写识别中手写体字符形态的特性,分析了手写时由于各种原因而产生的噪声,运用数学形态学中膨胀、腐蚀、细化等基本运算,提出了一种将数学形态学应用于联机手写识别预处理的方法,该方法可以有效地消除大量的冗余信息。测试结果表明,提出的方法可行,具有很好的鲁棒性,可以配合其他方案应用于各种联机手写字符识别中。

计算机离线签名鉴定系统研究

介绍了基于VC++开发的离线签名笔迹计算机鉴定系统,能够较好地实现签名笔迹图像多种处理效果,以满足特征提取的不同需要。他可以从复杂签名图像背景下提取出不同颜色签名笔迹,具有方便、快捷、失真小的特点。通过将笔划宽度斜度特征α加入系统进行鉴别,可有效降低识别的错误率,获得了相对较好的鉴别效果。

手持通信设备的多通道文本输入研究

Recently，Handheld Communication Devices is developing very fast, extending in users and spreading in application fields, and has an promising future. This study investigated the acceptance of the multimodal text entry method and the behavioral characteristics when using it. Based on the general information process model of a bimodal system and the human factor studies about the multimodal map system, the present study mainly focused on the hand-speech bimodal text entry method. For acceptance, the study investigated the subjective perception of the accuracy of speech recognition by Wizard of Oz (WOz) experiment and a questionnaire. Results showed that there was a linear relationship between the speech recognition accuracy and the subjective accuracy. Furthermore, as the familiarity increasing, the difference between the acceptable accuracy and the subjective accuracy gradually decreased. In addition, the similarity of meaning between the outcome of speech recognition and the correct sentences was an important referential criterion. The second study investigated three aspects of the bimodal text entry method, including input, error recovery and modal shifts. The first experiment aimed to find the behavioral characteristics of user when doing error recovery task. Results indicated that participants preferred to correct the error by handwriting, which had no relationship with the input modality. The second experiment aimed to discover the behavioral characteristics of users when doing text entry in various types of text. Results showed that users preferred to speech input in both words and sentences conditions, which was highly consistent among individuals, while no significant difference was found between handwriting and speech input in the character condition. Participants used more direct strategy than jumping strategy to deal with mixed text, especially for the Chinese-English mixed type. The third experiment examined the cognitive load in the different modal shifts, results suggesting that there were significant differences between different shifts. Moreover, relevant little time was needed in the Shift from speech input to hand input. Based on the main findings, implications were discussed as follows: Firstly, when evaluating a speech recognition system, attention should be paid to the fact that the speech recognition accuracy was not equal to the subjective accuracy. Secondly, in order to make a speech input system more acceptable, a good method is to train and supply the feedback for the accuracy in training, which improving the familiarity and sensitivity to the system. Thirdly, both the universal and individual behavioral patterns were taken into consideration to improve the error recovery method. Fourthly, easing the study and the use of speech input, the operations of speech input should be simpler. Fifthly, more convenient text input method for non-Chinese text entry should be provided. Finally, the shifting time between hand input and speech input provides an important parameter for the design of automatic-evoked speech recognition system.