Handwritten Script Research Articles

Machine Learning Approach for Arabic Handwritten Recognition

Text recognition is an important area of the pattern recognition field. Natural language processing (NLP) and pattern recognition have been utilized efficiently in script recognition. Much research has been conducted on handwritten script recognition. However, the research on the Arabic language for handwritten text recognition received little attention compared with other languages. Therefore, it is crucial to develop a new model that can recognize Arabic handwritten text. Most of the existing models used to acknowledge Arabic text are based on traditional machine learning techniques. Therefore, we implemented a new model using deep machine learning techniques by integrating two deep neural networks. In the new model, the architecture of the Residual Network (ResNet) model is used to extract features from raw images. Then, the Bidirectional Long Short-Term Memory (BiLSTM) and connectionist temporal classification (CTC) are used for sequence modeling. Our system improved the recognition rate of Arabic handwritten text compared to other models of a similar type with a character error rate of 13.2% and word error rate of 27.31%. In conclusion, the domain of Arabic handwritten recognition is advancing swiftly with the use of sophisticated deep learning methods.

Digitization Of Tulu Handwritten Scripts- A Literature Survey

Applications for handwritten script digitization include automated form processing, archival preservation, document digitization, handwriting recognition software, and historical document research. The performance of the recognition algorithms, the complex nature of the script, and the handwriting quality all affect how accurate the digitization is. Significant research on handwritten text recognition in scripts like Latin, Chinese, Arabic, and Japanese is reported. Still in its infancy, the work described on handwritten Indic scripts necessitates extensive research in this area. This thorough analysis offers an open view of different feature extraction and classification methods for the offline and online identification of handwritten Indic scripts.The primary objective of this paper is to explore the accuracy and efficiency of recognition systems by analyzing several state-of-the-art studies and comparing and evaluating various techniques for Tulu script handwritten character recognition. This paper aims to describe various advancements reported over the last few decades in the field of handwritten scripts recognition.

Application of Computer Vision and Mobile Systems in Education: A Systematic Review

The computer vision industry has experienced a significant surge in growth, resulting in numerous promising breakthroughs in computer intelligence. The present review paper outlines the advantages and potential future implications of utilizing this technology in education. A total of 84 research publications have been thoroughly scrutinized and analyzed. The study revealed that computer vision technology integrated with a mobile application is exceptionally useful in monitoring students’ perceptions and mitigating academic dishonesty. Additionally, it facilitates the digitization of handwritten scripts for plagiarism detection and automates attendance tracking to optimize valuable classroom time. Furthermore, several potential applications of computer vision technology for educational institutions have been proposed to enhance students’ learning processes in various faculties, such as engineering, medical science, and others. Moreover, the technology can also aid in creating a safer campus environment by automatically detecting abnormal activities such as ragging, bullying, and harassment.

Intelligent Character Recognition Framework for Kannada Scripts via Long Short Term Memory with Thresholding-based Segmentation

Various opinions were made by the researchers to develop an automatic network for Optical Character Recognition (OCR). Still, character recognition in handwritten scripts is an unsolved task. In this paper, two efficient techniques are developed an effective character recognition technique for the handwritten Kannada scripts. The Kannada Character Recognition (KCR) techniques faced several challenges due to the different writing styles of people and the absence of fixed spacing among alphabets, words and lines. Another complication in the KCR model is the absence of large datasets to train the network, and it isn’t easy to write the Kannada script by combining the Kannada alphabets. Therefore, a new handwritten KCR approach is developed to identify the characters from the ancient Kannada scripts. The required Kannada script images are gathered from various online databases. The garnered images are preprocessed and segmented using morphological operation and thresholding. The relevant features from the images are achieved by the geometric feature extraction method. Finally, the characters are recognized by utilizing the Long Short Term Memory (LSTM) network, and the experimental results will be analyzed over the traditional optimization strategies and baseline works to evaluate the efficiency of the proposed network.

Integrated multi-layer perceptron neural network and novel feature extraction for handwritten Arabic recognition

Arabic handwritten script recognition presents an energetic area of study. These types of recognitions face several obstacles, such as vast open databases, boundless diversity in individuals' penmanship, and freestyle writing. Thus, Arabic handwriting requires effective techniques to achieve better recognition results. On the other hand, Multilayer Perceptron (MLP) is one of the most common Artificial Neural Networks (ANNs) which deals with various problems efficiently. Therefore, this study introduces a new technique called Block Density and Location Feature (BDLF) with MLP, namely BDLF-MLP, which aims to extract novel features from letter images and estimate the letter's pixel density and its location for each equal-sized block in the image. In other words, BDLF-MLP can deal with various styles of Arabic handwritten, such as overlapping letters. The BDLF-MLP starts with the Block Feature Extraction (BFE) of the image by dividing the image into sixteen parts. After that, it calculates the density and location of each block (i.e., BDLF) by finding the sum of all values inside blocks. Finally, it determines the position of the greatest pixel density to obtain better recognition accuracy. The dataset containing 720 images is used to evaluate the efficiency of the proposed technique. Also, 1440 letters are used for training and testing divided evenly between them. The experiment results illustrate that BDLF-MLP outperformed the other algorithms in the literature with an accuracy of 97.26 %.

Handwritten Odia Digit Recognition using Learning Systems: A Comparison of Neural Networks and Support Vector Machine Models

The Odia language is one of the many regional languages spoken in India. It is the official language of Odisha, a State in eastern India. The Odia language carries a 1500-year-old history and worldwide is spoken by more than 50 million people. The Odia digits are complex due to the presence of many curves in each character. Handwritten scripts are even more complex due to free-style writing. However, the development of an innovative machine learning model is essential because Odia scripts consist of a huge number of historical documents of more than 1000 years old. A robust automation method will help in converting historical documents into digital form and will help to preserve the documents. This will solve a big problem in society. This work experiments with handwritten Odia numerals by implementing two different classifiers. The first one is the implementation of a Convolutional Neural Network (CNN) and the second experiment implements a Support Vector Machine (SVM). Finally, results from both experiments have been compared. The dataset has been generated through software by writing the digits on MS Paint. Both CNN and SVM models have been implemented through Python programming to recognize the inputs into a particular class. Both training and testing of the models have been done using this dataset. The accuracy from the CNN Model is obtained to be 94.999% which is ≈95% and for SVM, the model accuracy is 86%. Comparing both results, it is concluded that the CNN model is comparatively better than the SVM classifier in the case of the proposed work.

DIFFERENT APPROACHES OF HANDWRITTEN BENGALI CHARACTER RECOGNITION FROM DOCUMENT IMAGE

Handwritten character recognition from a document image is no-doubt a challenging task and active research filed of interest because of its several application domain. It becomes more challenging in pattern recognition domain because of variability of human writing style, skew and orientation. Noises, smears and faded ink makes it more complicated. OCR research success has limited to very few scripts like Roman, English and Chinese. Among Indian script, Bengali Handwritten Script identification is still an open and active research area. In this paper some popular approach are discussed to indentify the handwritten Bengali character recognition process.

A Survey on Approaches for Recognition of Dravidian Tulu Script

Handwritten script recognition is a interesting task that has been widely researched in the arena of computer vision and image processing. Tulu language is a Dravidian language spoken in coastal regions of Southern part of India. Recognition of Tulu handwritten scripts is important for preserving cultural heritage, historical documents, and facilitating communication among native speakers. This survey paper provides an overview of the existing tactics for recognition of Tulu scripts. We present a comprehensive review of the literature on various methods such as feature extraction, segmentation, classification, and deep learning techniques used for Tulu script recognition. The paper also discusses the challenges associated with Tulu script recognition and highlights the future research directions in this area. Key Words: Tulu, Handwritten script recognition, Feature extraction, Segmentation, Classification, Deep learning

An intelligent system for handwriting biometric forgery detection – communication from the research project implementation

The aim of this study is to discuss the main assumptions and goals of the “Rękopis” project, as well as to present the achieved results in the current phase of its implementation. The study is divided into two parts. The first part introduces the issue of handwriting in terms of its biometric properties and evaluates the possibilities of utilizing both classical methods and more advanced technologies in the analysis of original manuscripts to determine the technique of their application to a document surface, either manually or mechanically using a CNC device. In the second part, the applied research procedures and techniques will be presented, along with the obtained results of utilizing the characteristics of handwritten script, with particular emphasis on its biometric properties, in achieving the project goal mentioned above. Project “Rękopis” with the number DOB-SZAFIR/06/A/042/01/2020 titled “Intelligent System for Handwriting Biometric Forgery Detection” is funded by the National Centre for Research and Development (NCBR), within the framework of the SZAFIR program, Competition No. 1/SZAFIR/2020. The project is carried out by a consortium composed of the Central Forensic Laboratory of the Police (leader), the Criminalistics Institute of the Polish Forensic Association Ltd., and JAS Technologies Ltd. The project implementation is planned for 48 months from 2020 to 2024.

Recognition of Kannada Character Scripts Using Hybrid Feature Extraction and Ensemble Learning Approaches

An automated handwritten script identification system seeks more attention in the academic research field and commercial applications. Recognizing the handwritten Kannada scripts in recent years is an active research area. But, it is a much more challenging one in the pattern recognition field owing to the complexity of structural hierarchy, huge vocabulary count, and distinct people’s diverse handwriting styles. Therefore, this paper aims to develop Kannada handwritten script recognition framework by ensemble methods. Initially, the essential Kannada handwritten text images are collected. These collected images are used for pre-processing with the CLAHE and filtering techniques and followed by segmentation with the active contour approach. The segmented images are utilized using the Adaptive Local Tetra Pattern with freeman chain code histogram techniques. Here, the parameters in the LTrP are tuned with Hybrid Honey Badger Henry Gas Solubility Optimization. Finally, the handwritten recognition is performed by Hybrid Feature Extraction with Ensemble Deep Learning (HFE-EDH). Further, the recognition rate is elevated with the parameter optimization in deep learning approaches using the HGSO + HBA algorithm. Throughout the result analysis, the accuracy of the designed method attains 96%. Thus, the proposed method reveals better performance regarding various performance measures.

Online handwritten scripts classification using fuzzy attributed relational graphs

Online handwritten scripts classification using fuzzy attributed relational graphs

Handwritten Script Detection and Translation

Handwritten Script Detection and Translation

Dzongkha Handwritten Digit Recognition using Machine Learning Techniques

Handwritten digit recognition has recently gained importance, attracting many researchers due to its use in various machine learning and computer vision applications. As technology and science progressing, there is a need for a system to recognize the handwritten script in several real-time applications to reduce human effort. There a lot of work has been done on the recognition and generation of handwritten digits of high-resource languages such as English. However, insufficient work has been done on Dzongkha digits recognition, as Dzongkha digits are low-resource and more complex than English patterns. This paper aims to perform handwritten character recognition of Dzongkha digit using several machine learning techniques. The unavailability of the Dzongkha handwritten digit dataset is the prime motivation behind this work. To facilitates the recognition of Dzongkha handwritten digit, we have collected the data of Dzongkha handwritten digit from indigenous and non-indigenous people of Bhutan and provided the dataset for further research. Moreover, we have used several machine algorithms, including a support vector machine, K-nearest neighbor, and decision tree. Among these algorithms, the support vector machine classification algorithm has achieved a remarkable result with an accuracy of 98.29%.

Technology alone does not achieve error reduction - a study of handwritten, tick-sheet, ink stamp and electronic medical prescriptions

Technology in the form of electronic record systems and prescriptions have been touted as a potential solution to human error. In South Africa, a middle-income country where health facilities have large variations in technological capacity, prescription errors can be complex and varied. We evaluated different prescribing methods to find if the increased use of technology in prescriptions will assist in reducing error rates. A retrospective, non-randomised study compared prescriptions, error rates and types in four hospitals with different prescribing methods: these were handwritten, ink stamp, tick-sheet and electronic prescriptions. A modern human error theory data collection tool was designed which included patient complexity. Cataract surgery was chosen as the single common procedure. One thousand six hundred and sixty-one individual scripts had 1 307 prescription errors. Increasing patient complexity was not an indicator of error rate. Handwritten and tick-sheet prescriptions had the fewest errors (49% and 51%, respectively). Electronic (96%) and ink stamp scripts (101%) had almost twice as many errors as handwritten scripts (p < 0.001) mainly due to systemic inbuilt errors. The application of increasing degrees of technological complexity does not automatically reduce error rate. This is especially apparent when technology is not integrated into human factors engineering and persistent critical assessment.

Do products branded with handwritten scripts suffer more amid product-harm crises?

PurposeThis paper aims to explore whether products branded with handwritten scripts suffer more from the effects of product-harm crises than other brands. Most studies on handwritten scripts focus on their positive effects, such as humanizing a product or creating an emotional tie with consumers. However, seldom have researchers investigated the negative effects of handwritten scripts. This paper goes some way to filling this gap.Design/methodology/approachFive experimental studies were conducted to test three hypotheses. These experiments provide evidence of the negative effects of handwritten scripts. In addition, they reveal the mechanisms that lead to these outcomes and outline the boundary conditions of the negative effects.FindingsFramed by attribution theory, three conclusions can be drawn from the experiments: when a product-harm crisis occurs, consumers react with greater negativity toward the brand using handwritten scripts than to those using machine typefaces. The negative effect is explained by a serial mediation process that follows the pattern: typeface → perceived humanization → brand responsibility → brand attitude. The negative effect decreases when the crisis is perceived to be an accident.Originality/valueThis paper enriches the theory of marketing in terms of both handwritten scripts and product-harm crises, providing valuable guidance for enterprises that use handwritten scripts in their marketing activities.

DHCR_SmartNet: A smart Devanagari Handwritten Character Recognition using Level-wised CNN Architecture

Handwritten Script Recognition is a vital application of Machine Learning domain. Applications like automatic number plate detection, pin code detection and managing historical documents increasing more attention towards handwritten script recognition. English is the most widely spoken language, hence there has been a lot of research into identifying a script using a machine. Devanagari is popular script used by a huge number of people in the Indian Subcontinent. In this paper, level-wised efficient transfer learning approach presented on VGG16 model of Convolutional Neural Network (CNN) for identification of Devanagari isolated handwritten characters. In this work a new dataset of Devanagari characters is presented and made accessible publicly. Newly created dataset comprises 5800 samples for 12 vowels, 36 consonants and 10 digits. Initially simple CNN is implemented and trained on this new small dataset. In next stage transfer learning approach is implemented on VGG16 model and in last stage fine-tuned efficient VGG16 model is implemented. The training and testing accuracy of fine-tuned model are obtained as 98.16% and 96.47% respectively.

Handwriting quality analysis using online-offline models

This work is part of an innovative e-learning project allowing the development of an advanced digital educational tool that provides feedback during the process of learning handwriting for young school children (three to eight years old). In this paper, we describe a new method for children handwriting quality analysis. It automatically detects mistakes, gives real-time on-line feedback for children’s writing, and helps teachers comprehend and evaluate children’s writing skills. The proposed method adjudges five main criteria: shape, direction, stroke order, position respect to the reference lines, and kinematics of the trace. It analyzes the handwriting quality and automatically gives feedback based on the combination of three extracted models: Beta-Elliptic Model (BEM) using similarity detection (SD) and dissimilarity distance (DD) measure, Fourier Descriptor Model (FDM), and perceptive Convolutional Neural Network (CNN) with Support Vector Machine (SVM) comparison engine. The originality of our work lies partly in the system architecture which apprehends complementary dynamic, geometric, and visual representation of the examined handwritten scripts and in the efficient selected features adapted to various handwriting styles and multiple script languages such as Arabic, Latin, digits, and symbol drawing. The application offers two interactive interfaces respectively dedicated to learners, educators, experts or teachers and allows them to adapt it easily to the specificity of their disciples. The evaluation of our framework is enhanced by a database collected in Tunisia primary school with 400 children. Experimental results show the efficiency and robustness of our suggested framework that helps teachers and children by offering positive feedback throughout the handwriting learning process using tactile digital devices.

Digital Assyriology—Advances in Visual Cuneiform Analysis

Cuneiform tablets appertain to the oldest textual artifacts used for more than three millennia and are comparable in amount and relevance to texts written in Latin or ancient Greek. These tablets are typically found in the Middle East and were written by imprinting wedge-shaped impressions into wet clay. There is an increasing demand in the Digital Humanities domain for handwriting recognition, i.e., machine reading of handwritten script, focusing on historic documents. Current practice in text analysis of cuneiform script relies heavily on transliteration and translation, which are incomplete and influenced by the knowledge and experience of the expert that created them. The development of computational tools for cuneiform analysis presents many opportunities. An efficient and accurate sign spotting enables cross-referencing and statistical analyzes that are infeasible to perform manually. Furthermore, a wedge constellation spotting tool, provides experts with a significantly broader base of references to create more accurate and less time consuming transliterations and translations. Yet, cuneiform script has since resisted efforts to computational processing on basis of its basic constituents, its 3D wedge-shaped impressions and their free-form arrangements into signs. In this work, we review the literature on computational processing and recognition in the domain of cuneiform script. We introduce the different heterogeneous sources of cuneiform script, namely, manual ink-on-paper drawings, digital vector graphics drawings, photographs, and 3D scans of tablets. We describe the development of methods, beginning with the first computational classification using a hybrid manual encoding and computational comparison, to the latest methods making use of Generative Adversarial Neural Networks to recognize characters automatically. Finally, we give an overview of applications of these methods that enable quantitative mining in the small, e.g., patterns of wedge constellations, and in the large, e.g., networks of economic activity.

Classification of North and South Indian Handwritten Scripts using Gabor Wavelet Features

Objectives: Handwritten script identification plays a vital role in processing handwritten data electronically. Most of the methods fail to provide accuracy due to variation in handwriting, hence the classification of the Indic script before providing it to OCR is crucial. The anticipated work helps increase the accuracy by categorizing the handwritten documents as north or South Indic script before further classification. Methods: This study has proposed a method, using Gabor filters to extract features from the text image for recognizing the kind of script, and seven widely used Indian scripts were considered for this experiment. The handwritten documents were collected from distinct individuals on request, under supervision. The database was manually created by extracting portions of lines from the scanned document images. Findings: A recognition accuracy of 100% was obtained for classifying North and South scripts while an average accuracy of 92% was obtained for biscript classification using KNN classifier at a portion of the line level. Novelty: The proposed method improves the accuracy by acting as a pre-processor to the OCR system by classifying the script according to North Indian script or South Indian Script. Further, it can be processed to find out the script type within the North or South Indian Scripts. Keywords: Handwritten Script; Gabor Filter; KNN Classifier; OCR; Indic Script

Word Segmentation by Component Tracing and Association (CTA) Technique

Word-level segmentation is a very important step in many document analysis systems. This is because word is the most important unit in any language systems. Word segmentation of handwritten documents is a very challenging task due to cursive nature of handwriting, overlap, touching and crossing of adjacent words, non-straight baselines, and cluttering among many others. Of these challenges, crossing is the most difficult challenge to deal with. This paper proposes a novel offline word-level segmentation technique for handwritten documents that addresses the challenges of touching and crossing of words. The main contribution of the paper is junction branch association (JBA) method that specifically handles touching and crossing words where many other proposed methods fail. The proposed method has been evaluated with ICDAR2009 and ICDAR2013 benchmark datasets of handwritten scripts. Also, crossing words extracted from FireMaker dataset of handwritten documents have been used to specifically evaluate performance of JBA method in segmenting crossing words.