Cursive Research Articles

Transcribing Handwritten Medical Prescription using Convolutional Neural Network AlexNet Architecture and Canny Edge Detection

Misinterpreted medical prescriptions had led to casualties due to the illegible cursive handwriting of medical practitioners. Many studies focused on this problem. However, the accuracy was unsatisfactory and needed improvement. The study evaluated the performance of the Canny edge detection with other preprocessing methods, including RGB to Grayscale Conversion, Binarization, and Inversion, which was used to process the images of cursive handwritten medical prescriptions using Alexnet Convolutional Recurrent Neural Network (ACoRNN). The CRNN model developed by previous researchers was used as the basis for comparison, and the researchers created a faster and more accurate model. The best combination of preprocessing methods for ACoRNN was with RGB to Grayscale Conversion, Binarization, Canny edge detection, and Inversion. The researchers’ model had faster preprocessing and testing time and achieved 90.76% average accuracy through five trials.

Value of Cursive Writing

Value of Cursive Writing

Hubungan Antara Menulis Huruf Tegak Bersambung pada Kemampuan Membaca Siswa Sekolah Dasar

In this digital era that is sophisticated and easy, writing by hand especially cursive writing becomes one of the topics of discussion why it is still learned in this era. Whereas cursive writing has many benefits for students. The purpose of this literature review is to provide an overview of the relationship between cursive writing and the reading ability of elementary school students. The method used in this study is the literature study or literature review method. The technique used is collecting, analyzing, and summarizing information related to the research topic. Based on the literature review conducted, cursive writing skills have many benefits including training visual-motor skills, visual spatial skills, spelling, cognitive skills, and understanding of writing so that students’ reading skills become better and faster to capture the content of the reading. Another result of this study is that cursive writing activates the synaptic network of students’ brains so that the information read by students can be remembered longer and also through this cursive writing activity students’ patience is also well honed. Therefore, cursive writing can be one of the strategies to improve students’ reading skills.
 Keywords: Writing, Reading, Cursive Writing.

Integration of Deep Direction Distribution Feature Extraction and Optimized Attention Based Double Hidden Layer GRNN Models for Robust Cursive Handwriting Recognition

Cursive handwriting recognition (CHWR) is an interesting area of research as it has a wide range of applications but lacks an accurate approach to provide better results due to its character shapes, the non-uniform spacing between words and within a word, diverse placements of dots, and diacritics, and very low inter-class variation among individual classes. A novel CHWR model is proposed to enhance the recognition accuracy with high global stability. The proposed model introduces three major phases: pre-processing, feature extraction and classification. In the pre-processing stage, the noise removal and binarization are adapted with the intrusion of improved adaptive wiener filtering (IAWF) and structural symmetric pixels. A hybrid deep direction distribution feature extraction (HDDDFE) approach is proposed to extract directional Local gradient histogram (LGH), column gradient histogram (CGH) features and a wavelet convolutional neural network with Block Attention Module (WCNN-BAM) is proposed to extract deep global features (GF), profile features (PF) and dynamic features (DF). A novel double hidden layer gated recurrent neural network with a feature attention mechanism (ODHL-GRNN-FAM) is proposed to offer handwritten classification results. The developed model is evaluated with the IAM database and attains an overall recognition accuracy of 98%, precision of 97%, f-measure of 97.99%, character error rate (CER) of 1.23%, word error rate (WER) of 4.8%, respectively.

Keeping the line in transition years: Comparison of preschoolers and nine graders

The study deals with the graphomotor difficulties of children at the beginning and the end of primary school. The aim is to describe and analyze the occurrence of two manifestations of graphomotor problems: tremor and line continuity. The results of the redrawing of seven graphics were compared. Fifty-one (51) preschoolers and 22 nine graders participated in the research. The tremor was detected at 1/5 to 4/5 of preschoolers and at 1/5 to 3/5 of ninth graders; the prevalence of the tremor decreases with age. Significant differences were found in the number of interruptions in most tasks. Contrary to expectations, more interruptions were found among 9th graders. The result is interpreted based on declining experience with writing and drawing images larger than interlinear differences, experience interference such as writing through discontinuous cursive handwriting, favored by the majority of adolescents, and intervening personality characteristics such as perfectionism, and laziness. Keywords: Adolescents; graphomotor skills; interruptions; preschool children; tremor

Peningkatan Keterampilan Menulis Tegak Bersambung Melalui Metode Pembelajaran Drill di Kelas II Sekolah Dasar

<em>The purpose of this research is to improve the cursive handwriting skill through drill learning method of the students in 2nd grade of SDN Soropadan No. 108 Surakarta. Classroom action research was used for this study, which was conducted over the course of two cycles. Every cycle had two meetings. Students in 2nd grade of SDN Soropadan No. 108 Surakarta was the subject of this research. They were 32 total students. The data was collected by observation, interview, test, and documentary. The data validity was using content validity, source triangulation and technique triangulation. The data analysis was using interactive analysis model. According to research results, the students in 2nd grade of SDN Soropadan No. 108 Surakarta saw an improvement in their cursive handwriting skills. When compared to the minimum guaranteed score of 75, the pre-action average for the cursive handwriting skills test was 57.03, with a classical completion rate of 16%, or as many as 5 out of 32 students. In the first cycle, the average value was 75.4, with a classical completion rate of 56%, or 18 out of 32 students, being successful. In the second cycle, the average value increased to 85.77, with classical completeness reached 84%, or 27 out of 32 students successfully completed. The conclusions in this research is cursive handwriting skill can be improved through drill learning method of the students in 2nd grade of SDN Soropadan No. 108 Surakarta.</em>

Research on cursive symbols and variants in Vietnamese manuscripts

The complexity of variants is more prominent because of the greater randomness of manuscripts. Symbolization is one of the essential characteristics of the spread and variation of Chinese characters in Vietnam. There are many types of symbols in the configuration of Vietnamese variants, and most of them are derived from cursive handwriting in China. Based on the Vietnamese symbolic variants and from the angle of combining the handwriting in calligraphy with the symbol theory in philology, the present article analyzes eight kinds of common symbols in variants in Vietnamese manuscripts and probes into their sources, hoping to encourage a preliminary discussion regarding their symbolic features’?

Concurrent and Predictive Validity of a Cycloid Loops Copy Task to Assess Handwriting Disorders in Children.

Handwriting disorders (HDs) are mainly assessed using script or cursive handwriting tasks. The most common is the scale for children's handwriting, with a French adaptation (BHK). The present study aims to assess the concurrent validity of a pre-scriptural task (copying a line of cycloid loops) with the BHK for the diagnosis of HDs. Thirty-five primary school children (7 females, 28 males) with HD aged 6-11 years were recruited and compared to 331 typically developing children (TDC). Spatial/temporal/kinematic measures were collected using a digital pen on a paper. Posture and inter-segmental writing arm coordination were video recorded. A logistic regression statistical method, including a receiver-operating characteristic curve, was used to assess the ability of the task to predict HD. Gestural patterns were significantly less mature in HDs than in TDC (p < 0.05), and associated with poorer quality, less fluid, and slower drawing (p < 0.001). Moreover, good correlations between temporal and kinematic measures and the BHK scale were found. Number of strokes, total drawing time, in-air pauses times, and number of velocity peaks showed very good sensitivity (88%) and specificity (74%) to diagnose HDs. Consequently, the cycloid loops task is an easy, robust, and predictive tool for clinicians to identify HDs before the alphabet is mastered.

Validation of the Concise Assessment Scale for Children's Handwriting (BHK) in an Italian Population.

Handwriting difficulties represent a common complaint among children and may cause a significant delay in motor skills achievement. The Concise Assessment Scale for Children's Handwriting (BHK) assesses handwriting skill in clinical and experimental settings, providing a quick evaluation of handwriting quality and speed through a copying text. The aim of the present study was to validate the Italian adaptation of the BHK in a representative primary school population. Overall, 562 children aged 7-11 from 16 public primary schools of Rome were included and asked to copy a text in 5 min using cursive handwriting. Handwriting quality and copying speed were measured. The included population followed a normal distribution for the BHK quality scores. Sex influenced the total quality scores, whereas school level influenced the copying speed. The BHK quality score was higher in girls (p < 0.05) and resulted as a stable parameter along the school years, without significant variations with regard to the years spent in handwriting exercise (p = 0.76). The handwriting speed was influenced by school level, and significant differences were found for each of the grades from the second to the fifth (p < 0.05), but not for gender (p = 0.47). Both BHK measures represent a helpful tool for the characterization and assessment of children with handwriting difficulties. The present study confirms that sex influences total BHK quality score, while school level influences handwriting speed.

A Robust Residual Shrinkage Balanced Network for Image Recognition from Japanese Historical Documents

Kuzushiji, as characters written in a cursive style, had been continuously used for both publishing and handwriting in Japan before the end of the 19th century. However, well into the twentieth century, most modern Japanese lost the ability to read Kuzushiji due to changes in writing systems. Therefore, how to develop advanced machine learning algorithms to identify Japanese historical characters has great significance in preserving cultural knowledge and promoting sustainable development in urban living. Unlike traditional digit image recognition, Kuzushiji image recognition is a more challenging task due to the complex script for cursive handwriting, multiple variations between characters, and imbalanced data. To address such issues, a novel deep learning‐based character recognition method called residual shrinkage balanced network (RSBN) is developed for classifying Japanese historical characters. A novel residual shrinkage structure with a soft threshold function is constructed to reduce redundant features using specially designed skip‐connected subnetworks. Then, multiple residual shrinkage modules are stacked together to learn hierarchical features from raw input. Furthermore, a novel class rebalancing strategy is further designed to improve learning performance from imbalanced data. The experiments are conducted on Japanese classical literature datasets. The results demonstrate that the proposed method obtains more than 89.01% testing accuracy on Kuzushiji‐MNIST dataset, which outperforms the existing deep learning‐based character image recognition methods. Moreover, without additional data augmentation techniques, the proposed approach also achieves 97.16% balanced accuracy on Kuzushiji‐49 dataset, which is the best one compared with existing published results. When considering the computational performance, the number of trainable parameters of the proposed method is competitive with that of the typical ResNet‐18.

Handwriting Speeds of 4th–8th Grade Students

For the effective expression of feelings and thoughts, handwriting should be produced fluently at a certain speed. The aim of this study was to examine the development of handwriting speeds in 4th–8th grade primary and secondary school students in terms of somevariables. In line with this aim, answers were sought to the question, “Do 4th–8th grade primary and secondary school students’ handwriting speeds differ significantly depending on their grade, gender, hand preference, and handwriting style?” The study was designed inthe survey method, and the study group consisted of 322 students attending the 4th, 5th, 6th, 7th, and 8th grades of primary and secondary school. A form developed by the researchers for all grade levels was usedas the data collection tool in the study. In the data collection process, the students were required to copy a given text within one minute. The research results revealed that while the primary and secondary school students’ handwriting speeds differed significantly according to their grade level, gender, and handwriting style, they did not differ significantly according to their hand preferences. As the grade level increased, mean handwriting speeds also increased. Female students wrote faster than male students. Students using the manuscript handwriting style wrote faster than students who used the cursive handwriting style.

Development of Cursive Writing Learning Textbooks for Lower-Grade Elementary School Students

This study aims to produce cursive writing skills learning textbook for lower-grade students in elementary school that is valid, practical, and effective. This type of research uses research and development with a borg and gall design. This study will focus on improving the cursive writing skills of lower-grade students in four elementary schools in the Karanganyar sub-district. Researchers collect data using observation techniques, interviews, questionnaires, and tests to determine the needs of teachers and students and determine the quality of the products that have been developed. The collected data were then analyzed using qualitative descriptive and statistical analysis techniques. The results of the statistical analysis were converted into qualitative values. The data on the cursive writing skills test results will go through N-gain, normality, and homogeneity. The results of this study indicate that the product developed gets a proper category based on the validation of experts and the responses of students and teachers. There is an increase in students' cursive writing skills after using soft writing learning textbooks.

Efficient feature descriptor selection for improved Arabic handwritten words recognition

&lt;span lang="EN-US"&gt;Arabic handwritten text recognition has long been a difficult subject, owing to the similarity of its characters and the wide range of writing styles. However, due to the intricacy of Arabic handwriting morphology, solving the challenge of cursive handwriting recognition remains difficult. In this paper, we propose a new efficient based image processing approach that combines three image descriptors for the feature extraction phase. To prepare the training and testing datasets, we applied a series of preprocessing techniques to 100 classes selected from the handwritten Arabic database of the &lt;/span&gt;&lt;em&gt;&lt;span lang="EN-US"&gt;Institut Für Nachrichtentechnik/Ecole Nationale d'Ingénieurs de Tunis&lt;/span&gt;&lt;/em&gt;&lt;span lang="EN-US"&gt; (IFN/ENIT). Then, we trained the k-nearest neighbor’s algorithm (k-NN) algorithm to generate the best model for each feature extraction descriptor. The best k-NN model, according to common performance evaluation metrics, is used to classify Arabic handwritten images according to their classes. Based on the performance evaluation results of the three k-NN generated models, the majority-voting algorithm is used to combine the prediction results. A high recognition rate of up to 99.88% is achieved, far exceeding the state-of-the-art results using the IFN/ENIT dataset. The obtained results highlight the reliability of the proposed system for the recognition of handwritten Arabic words.&lt;/span&gt;

A Review of Pattern Recognition Using Statistics

Abstract: Pattern recognition's primary objective is supervised or classification techniques. The statistical method has been the most intensively researched and implemented in practice among the various frameworks in which classification technique has typically been developed. In recent times, neural network techniques and methods based on statistical learning theory have gotten a lot of attention. The following issues must be carefully considered when designing a recognition system: pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design, learning, training, test sample selection, and performance evaluation. The overall challenge of detecting intricate forms with modifiable direction, position, and size has not been addressed despite just Fifty years of intensive research. Data mining, web browsing, recovery of multimedia content, face recognition, and cursive handwriting recognition are just a couple of minor new and emerging applications that require strong and fast pattern recognition methods. The intention of this review paper is to summarize and analyze some of the adopted approaches in various phases of a recognition system, as well as to identify areas of research and applications that are at the forefront of innovation in this exciting and challenging field.

Evaluating Handwriting Skills through Human-Machine Interaction: A New Digitalized System for Parameters Extraction.

Handwriting is an important component of academic curricula and grapho-motor skills (GMS) support learning, reading, memory and self-confidence. Teachers and clinicians report increase in children experiencing problems with acquiring fluid and legible handwriting. To date gold-standard tests evaluating children's GMS, mostly rely on pen and paper tests, requiring extensive coding time and subject to high inter-rater variability. This work presents preliminary data on a new digital platform for Grapho-motor Handwriting Evaluation & Exercise (GHEE), attempting to overcome limitations of available digitalized methods for GMS evalution. In fact, contrary to previous systems, GHEE design originated from comparisons among multiple standardized tests and was based on a human-machine interaction approach. GHEE hardware and software is presented as well as data on preliminary testing. Cursive handwriting data from six adult volunteers was analyzed according to six parameters of relevance, both automatically (i.e., using GHEE software) and manually (i.e., by a human coder). Comparisons among machine and human data sets allowed parsing out parameters to be extracted automatically and parameters requiring human-machine interaction. Results confirmed platform efficacy and feasibility of the proposed approach.

The Implementation of Artificial Neural Network (ANN) on Offline Cursive Handwriting Image Recognition

Identifying a writing is an easy thing to do for human, but this does not apply to computers, in particular if it is handwriting. Handwriting recognition, especially cursive handwriting is a research in the area of image processing and pattern matching that is challenging to complete, following the different characteristics of each person's cursive handwriting style. In this study, the use of the ANN model will be implemented in performing offline handwriting image recognition. The cursive handwriting image that has been obtained is then preprocessed and segmented using bounding box rectangle and contour techniques. Evaluation of system performance using global performance metrics in this study resulted in a percentage of 93% where the bounding box and contour succeeded in determining the segmentation point correctly, so that the ANN model worked optimally.

Visualization of Customized Convolutional Neural Network for Natural Language Recognition.

For analytical approach-based word recognition techniques, the task of segmenting the word into individual characters is a big challenge, specifically for cursive handwriting. For this, a holistic approach can be a better option, wherein the entire word is passed to an appropriate recognizer. Gurumukhi script is a complex script for which a holistic approach can be proposed for offline handwritten word recognition. In this paper, the authors propose a Convolutional Neural Network-based architecture for recognition of the Gurumukhi month names. The architecture is designed with five convolutional layers and three pooling layers. The authors also prepared a dataset of 24,000 images, each with a size of 50 × 50. The dataset was collected from 500 distinct writers of different age groups and professions. The proposed method achieved training and validation accuracies of about 97.03% and 99.50%, respectively for the proposed dataset.

Многообразието на кирилицата в обучението по български като чужд

The focus of this article are the issues of teaching and acquiring Cyrillic alphabet. In the first part of the text a contrastive analysis of the Cyrillic and Latin alphabet is made. The second and third part are dealing respectively with reading and writing (manuscript and cursive handwriting and keyboarding).

Marianne Moore’s Ghost Revisions

The Rosenbach Museum and Library contains The Marianne Moore Library (MML), the largest collection of Marianne Moore’s personal objects and literary papers. Among these objects and papers are the poet’s personal copies of each of her published books. One of the first observations to be made about Moore’s revising method is her habit of revising on copies of her books from her first publication, Poems (1921), through her final publication, Complete Poems (1967), often neatly writing in an updated word or phrase in small cursive handwriting. Indeed, her lifelong habit of using published texts as sites of revision began with Poems (1921) not long after it was published. To date, I have not found a study that addresses these revisions made upon her own copies of her books, especially Poems (1921) and both editions of Observations (1924 and 1925). In order to better understand Moore’s revision process in her early years before becoming editor of The Dial, their curious presence becomes a prerequisite for reading and positing a chronology to the revisions on her manuscripts and typed scripts of her other early poetry. This essay intends to explore the revisions that Moore made on her two copies of Poems (1921) and on Observations (1924).&#x0D; &#x0D;

Segmentation Free FragNet and GRRNN for Writer-Identification in Cursive Handwriting

Writer identification is a method in which a handwritten sample is assigned to the corresponding author of that sample. Since handwriting is a behavioral biometric application like the signature, writer identification will also confirm the authenticity of the document. Major applications of the writer identification process come in forensics, banking, and paleography which is a study of historical books and writings. Different writers have their own style of handwriting which has different characteristics, so they require different handling. Due to this difference, it is difficult to identify the author of the manuscript. Slant, curvature, orientations, etc may vary. The writer identification task predicts the writer by identifying various features involved in the handwrit- ten sample. The proposed method identifies the writer of a handwritten sample by combining both local and global features. This is accomplished by a combination of FragNet and Global Recurrent Neural Network. FragNet captures local features and to make them spatially correct, global features are captured from local features by Global Residual Recurrent Neural Network. A segmentation-free method is used so that writers of cursive handwriting can also be identified.