Handwritten Recognition Research Articles

Magnetic field-free stochastic computing based on the voltage-controlled magnetic tunnel junction

The stochastic computing (SC) has been proven to be an energy-efficient way to perform neural network. In this study, we propose a field-free voltage-controlled spintronics SC system based on the magnetic tunnel junction (MTJ). We observe a stochastic switching behavior of the MTJ and that it could be controlled by the voltage applied on the device. The voltage-controlled stochastic switching behavior is used to encode numbers ranging from 0 to 1 into a series of random bit-streams in the SC system. Furthermore, the handwritten recognition task is performed on the MTJ-based SC system, achieving a 95% maximum accuracy, which is comparable with the floating-point based neural network. Our work provides inspiration for the energy-efficient neural network systems.

An Effective Deep Learning Approach For Handwritten Ol-Chiki Character Recognition

In this paper, we propose a deep convolution neural network approach to recognize Ol-Chiki handwritten characters. Here we describe recognition of handwritten basic characters of Ol-Chiki script, used by more than 10 million tribal people in India mostly from Assam, Bengal, Bihar, Odisha and Jharkhand. There are 30 basic characters and 10 numeral digits in Ol-Chiki. We have used a dataset of 10000 handwritten isolated character samples written by 100 persons. Convolution Neural Network (CNN) architecture has been used for the recognition of handwritten isolated Ol-Chiki characters. Our system has been tested on Ol-Chiki isolated dataset and we have achieved 92% accuracy on almost on all Ol-Chiki characters.

ET-Network: A novel efficient transformer deep learning model for automated Urdu handwritten text recognition.

Automatic Urdu handwritten text recognition is a challenging task in the OCR industry. Unlike printed text, Urdu handwriting lacks a uniform font and structure. This lack of uniformity causes data inconsistencies and recognition issues. Different writing styles, cursive scripts, and limited data make Urdu text recognition a complicated task. Major languages, such as English, have experienced advances in automated recognition, whereas low-resource languages, such as Urdu, still lag. Transformer-based models are promising for automated recognition in high- and low-resource languages such as Urdu. This paper presents a transformer-based method called ET-Network that integrates self-attention into EfficientNet for feature extraction and a transformer for language modeling. The use of self-attention layers in EfficientNet helps to extract global and local features that capture long-range dependencies. These features proceeded into a vanilla transformer to generate text, and a prefix beam search is used for the finest outcome. NUST-UHWR, UPTI2.0, and MMU-OCR-21 are three datasets used to train and test the ET Network for a handwritten Urdu script. The ET-Network improved the character error rate by 4% and the word error rate by 1.55%, while establishing a new state-of-the-art character error rate of 5.27% and a word error rate of 19.09% for Urdu handwritten text.

Albanian Handwritten Text Recognition using Synthetic Datasets and Pre-Trained Models

Handwritten Text Recognition (HTR) has continuously attracted the focus of researchers to enable the integration of technology into our daily lives. Handwritten text recognition (HTR), a technology of considerable importance, takes a leading role in the analysis and digitization of various documents. This technology is important in facilitating the efficient use of handwritten documents, especially within academic, historical, and cultural contexts. The use of artificial intelligence in handwriting recognition offers a very good opportunity to achieve satisfactory results in this field, but to achieve good results a large dataset is needed. Creating a large dataset to train different AI models is a challenge for languages with limited resources such as the Albanian language. This paper aims to present a novel approach to the development of an HTR system for the Albanian language using an attention-based encoder-decoder architecture. The dataset used in the experiments is a synthetic dataset generated using deep learning techniques based on the English language dataset as they are both variants of the Latin alphabet. We enhanced the dataset with two letters specific to Albanian, (“ë” and “ç”). The usage of pre-trained English models for handwriting recognition improved our model’s performance. The results of the experiments are very promising and prove that our approach is efficient in recognizing handwriting in the Albanian language. This shows that the attention-based encoder-decoder architecture can be adopted for different languages with limited resources.

Handwritten Character Recognition: A Comparative Study

Handwriting recognition is a technique used to interpret intelligible handwritten input and convert it into digital text using Machine Learning tools. This research paper provides a comparison of the application of CRNN and CNN for handwriting recognition, using a dataset containing about 370,000 handwritten names. Our experiments demonstrate that the CRNN hybrid model produces the highest accuracy compared to the CNN model. This paper summarises contributions reported on the A-Z Handwritten Alphabets in .csv format dataset for handwritten character recognition. This dataset has been extensively used to validate novel techniques in computer vision. This paper makes a distinction between those works using some kind of data augmentation and works using the original dataset

An STS analysis of a digital humanities collaboration: trading zones, boundary objects, and interactional expertise in the DECRYPT project

A widely shared recognition over the past decade is that the methodology and the basic concepts of science and technology studies (STS) can be used to analyze collaborations in the cross-disciplinary field of digital humanities (DH). The concepts of trading zones (Galison, 2010), boundary objects (Star and Griesemer, 1989), and interactional expertise (Collins and Evans, 2007) are particularly fruitful for describing projects in which researchers from massively different epistemic cultures (Knorr Cetina, 1999) are trying to develop a common language. The literature, however, primarily concentrates on examples where only two parties, historians and IT experts, work together. More exciting perspectives open up for analysis when more than two, more nuanced and different epistemic cultures seek a common language and common research goals. In the DECRYPT project funded by the Swedish Research Council, computational linguists, historians, computer scientists and AI experts, cryptologists, computer vision specialists, historical linguists, archivists, and philologists collaborate with strikingly different methodologies, publication patterns, and approaches. They develop and use common resources (including a database and a large collection of European historical texts) and tools (among others a code-breaking software, a hand-written text recognition tool for transcription), researching partly overlapping topics (handwritten historical ciphers and keys) to reach common goals. In this article, we aim to show how the STS concepts are illuminating when describing the mechanisms of the DECRYPT collaboration and shed some light on the best practices and challenges of a truly cross-disciplinary DH project.

Intelligent Human-Computer Interaction: Combined Wrist and Forearm Myoelectric Signals for Handwriting Recognition.

Recent studies have highlighted the possibility of using surface electromyographic (EMG) signals to develop human-computer interfaces that are also able to recognize complex motor tasks involving the hand as the handwriting of digits. However, the automatic recognition of words from EMG information has not yet been studied. The aim of this study is to investigate the feasibility of using combined forearm and wrist EMG probes for solving the handwriting recognition problem of 30 words with consolidated machine-learning techniques and aggregating state-of-the-art features extracted in the time and frequency domains. Six healthy subjects, three females and three males aged between 25 and 40 years, were recruited for the study. Two tests in pattern recognition were conducted to assess the possibility of classifying fine hand movements through EMG signals. The first test was designed to assess the feasibility of using consolidated myoelectric control technology with shallow machine-learning methods in the field of handwriting detection. The second test was implemented to assess if specific feature extraction schemes can guarantee high performances with limited complexity of the processing pipeline. Among support vector machine, linear discriminant analysis, and K-nearest neighbours (KNN), the last one showed the best classification performances in the 30-word classification problem, with a mean accuracy of 95% and 85% when using all the features and a specific feature set known as TDAR, respectively. The obtained results confirmed the validity of using combined wrist and forearm EMG data for intelligent handwriting recognition through pattern recognition approaches in real scenarios.

OHSCR: Benchmarks Dataset for Offline Handwritten Sindhi Character Recognition

This research work presents a unique dataset for offline handwritten Sindhi character recognition. It has 7800 character images in total, divided into multiple categories by 150 writers of various ages, genders, and professional backgrounds. Each writer writes the 52 Sindhi characters in the designed form. With a high-quality scanner, all of the written samples were scanned. After that, all the handwritten Sindhi characters were cropped from the collected designed form, and the cropped images were saved in ‘.png’ format. For the benefit of the Sindhi research community, this work suggests an image dataset for character recognition in handwritten Sindhi. The dataset will be made publically available. For the Sindhi language, this dataset can be used to create and test handwritten character recognition systems and provide helpful insights through writer identification. The dataset has been divided into the training set and the test set, with 80% for training and 20% for testing. The different preprocessing techniques used to remove noise from scanned images to create a clean dataset. The dataset created as a result of this research is the world's first openly accessible dataset for handwritten research, and it can be useful for writer identification systems and handwriting recognition systems.

Interpreting Doctor Notes using Handwriting Recognition

Abstract: Handwriting recognition of medical prescriptions has been a challenging problem over the recent years with constant research in providing possible accurate solutions. Indecipherable handwritten prescription and inefficiency of Pharmacist to understand the medical prescription can lead to serious and harmful effect to the patients. Even in the recognition of handwriting, mainly doctors notes, they are very difficult for everyone to understand and it takes time for a person to analyse it. So, this idea mainly focused on interpreting doctor’s notes using handwritten recognition and deep learning techniques. The handwritten or printed document pictures are transformed into their electronic counterparts using an optical character recognition (OCR) system. Due to individuals' inconsistent writing styles, dealing with handwritten texts is significantly more difficult than dealing with printed ones. Handwritten text recognition could be done by Image processing, Machine Learning or Deep Learning Techniques. Out of these Deep Learning remains to be the most popular and prominent. Some of the Deep Learning techniques includes Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs). This gives a review of the various recognition methodologies used for interpreting handwritten texts. It includes the most important algorithms that could be used for detecting the handwritten word/text/character by using various approaches for the recognition process. In the end we are thus comparing the accuracies provided by these systems.

Comparison and Analysis of Chinese and English Handwriting Recognition Algorithms in Deep Learning

Handwriting recognition is an important topic of current research on image recognition. This technology provides convenience for production and life, as well as guarantees for us in some aspects of safety. The author hopes to help people get a preliminary understanding of English handwriting recognition by summarizing and comparing two commonly used models in deep learning. This paper focuses on two models of widely used English handwriting recognition, which are the simple Recurrent Neural Network (RNN) model and the Long Short-Term Memory (LSTM) model. Firstly, the principles of the two models are introduced, and then gradient problems, fitting problems, training difficulty, and accuracy, as well as the reasons for these problems are all discussed and compared within the two models. Nowadays, the accuracy rate of English handwriting recognition is relatively high using deep learning methods and models. With the development of deep learning models, if more accurate string segmentation can be achieved, the accuracy rate of handwriting recognition can also be further improved.

Advancements and Trends in CNN-Based Handwritten Text Recognition: A Comprehensive Survey

Handwritten Text Recognition (HTR) is pivotal in transforming handwritten documents into digital format, enabling efficient search, storage, and information retrieval. In this project, we explore the application of Convolutional Neural Networks (CNNs) for HTR tasks. We comprehensively analyzed existing literature surveys to understand the current state-of-the-art techniques, methodologies, and challenges in HTR using CNNs. The survey encompassed various aspects including network architectures, dataset compositions, preprocessing techniques, and evaluation metrics. Our findings reveal the evolution of CNN-based HTR systems and highlight key trends in research, such as the integration of attention mechanisms and recurrent neural networks to enhance recognition accuracy and contextual understanding. Through this analysis, we provide insights into the advancements and future directions in CNN-based HTR methodologies.

DeepAHR: a deep neural network approach for recognizing Arabic handwritten recognition

DeepAHR: a deep neural network approach for recognizing Arabic handwritten recognition

The implications of handwritten text recognition for accessing the past at scale

PurposeThis paper focuses on image-to-text manuscript processing through Handwritten Text Recognition (HTR), a Machine Learning (ML) approach enabled by Artificial Intelligence (AI). With HTR now achieving high levels of accuracy, we consider its potential impact on our near-future information environment and knowledge of the past.Design/methodology/approachIn undertaking a more constructivist analysis, we identified gaps in the current literature through a Grounded Theory Method (GTM). This guided an iterative process of concept mapping through writing sprints in workshop settings. We identified, explored and confirmed themes through group discussion and a further interrogation of relevant literature, until reaching saturation.FindingsCatalogued as part of our GTM, 120 published texts underpin this paper. We found that HTR facilitates accurate transcription and dataset cleaning, while facilitating access to a variety of historical material. HTR contributes to a virtuous cycle of dataset production and can inform the development of online cataloguing. However, current limitations include dependency on digitisation pipelines, potential archival history omission and entrenchment of bias. We also cite near-future HTR considerations. These include encouraging open access, integrating advanced AI processes and metadata extraction; legal and moral issues surrounding copyright and data ethics; crediting individuals’ transcription contributions and HTR’s environmental costs.Originality/valueOur research produces a set of best practice recommendations for researchers, data providers and memory institutions, surrounding HTR use. This forms an initial, though not comprehensive, blueprint for directing future HTR research. In pursuing this, the narrative that HTR’s speed and efficiency will simply transform scholarship in archives is deconstructed.

BNVGLENET: Hypercomplex Bangla handwriting character recognition with hierarchical class expansion using Convolutional Neural Networks

Object recognition technology has made significant strides where recognizing handwritten Bangla characters including symbols, compounds form, etc. remains a challenging problem due to the prevalence of cursive writing and many ambiguous characters. The complexity and variability of the Bangla script, and individual’s unique handwriting styles make it difficult to achieve satisfactory performance for practical applications, and the best existing recognizers are far less effective than those developed for English alpha-numeric characters. In comparison to other major languages, there are limited options for recognizing handwritten Bangla characters. This study has the potential to improve the accuracy and effectiveness of handwriting recognition systems for the Bengali language, which is spoken by over 200 million people worldwide. This paper aims to investigate the application of Convolutional Neural Networks (CNNs) for recognizing Bangla handwritten characters, with a particular focus on enlarging the recognized character classes. To achieve this, a novel challenging dataset for handwriting recognition is introduced, which is collected from numerous students’ handwriting from two institutions. A novel convolutional neural network-based approach called BNVGLENET is proposed in this paper to recognize Bangla handwritten characters by modifying the LeNet-5 and combining it with the VGG architecture, which has the advantage of significantly identifying the characters from Bengali handwriting. This study systematically evaluated the performance of models not only on custom novel dataset but also on the publicly available Bangla handwritten character dataset called the Grapheme dataset. This research achieved a state-of-the-art recognition accuracy of 98.2% on our custom testing vowel-consonant class and 97.5% on the custom individual class. The improvements achieved in this study bridge a notable disparity between the practical needs and the actual performance of Bangla handwritten character recognition systems.

Enhancing Arabic Handwritten Recognition System-Based CNN-BLSTM Using Generative Adversarial Networks

Arabic Handwritten Recognition (AHR) presents unique challenges due to the complexity of Arabic script and the limited availability of training data. This paper proposes an approach that integrates generative adversarial networks (GANs) for data augmentation within a robust CNN-BLSTM architecture, aiming to significantly improve AHR performance. We employ a CNN-BLSTM network coupled with connectionist temporal classification (CTC) for accurate sequence modeling and recognition. To address data limitations, we incorporate a GANs based data augmentation module trained on the IFN-ENIT Arabic handwriting dataset to generate realistic and diverse synthetic samples, effectively augmenting the original training corpus. Extensive evaluations on the IFN-ENIT benchmark demonstrate the efficacy of adopted approach. We achieve a recognition rate of 95.23%, surpassing the baseline model by 3.54%. This research presents a promising approach to data augmentation in AHR and demonstrates a significant improvement in word recognition accuracy, paving the way for more robust and accurate AHR systems.

A Handwriting Recognition System With WiFi

Handwriting recognition systems are a convenient and alternative way of writing in the air with fingers rather than typing on keyboards. However, existing recognition systems are limited by their low accuracy and the requirement to wear dedicated devices. To address these issues, we propose WiWrite, an accurate contactless handwriting recognition system that allows users to write in the air without wearing any wearable devices. Specifically, we employ a novel <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CSI division scheme</i> to process the noisy raw WiFi channel state information (CSI), which stabilizes the CSI phase and reduces noise in CSI amplitude. To automatically retain low noise data for identification in the LOS scenario, we propose a self-paced dense convolutional network (SPDCN), which is a self-paced loss function based on a modified convolutional neural network coupled with a dense convolutional network. Furthermore, to achieve accurate handwriting recognition in the NLOS scenario, we combine ADOA and PCA algorithms to remove location-induced interference and extract action features. Comprehensive experiments show the merits of WiWrite, revealing that the recognition accuracy for the same-size input and different-size input are 93.6% and 89.0%, respectively. Moreover, WiWrite can achieve accurate recognition regardless of environment and target diversity in LOS and NLOS scenarios.

WiRITE: General and Practical Wi-Fi Based Hand-Writing Recognition

Device-free hand-writing systems identify the content that a user writes by hand movement in the air, thus providing an intuitive human computer interface. In this paper, we propose WiRITE, a Wi-Fi hand-writing recognition system built with commodity Wi-Fi APs. Unlike most existing machine learning based hand-writing recognition systems, which are often subject to severe limitations in generality, e.g., high training overhead when adapted across hand-writing alphabets, environments, and users, WiRITE is designed with unique consideration of its generality when applied to practice—being application-transferable, environment-agnostic, and user-independent. With little training overhead, WiRITE behaves inclusively to different users, environments, and applications, stemming from a comprehensive design of signal processing that is built into its core machine learning model. Extensive evaluation is conducted with five users for three applications, i.e., recognizing Digits, English letters, and Chinese characters, in realistic office environment. The experiment results demonstrate that WiRITE provides at least 0.9 accuracy in various combinations of users and applications with 0.93 accuracy in average.

HANDWRITTEN CHARACTER RECOGNITION IN ASSYRIAN LANGUAGE USING CONVOLUTIONAL NEURAL NETWORK

Academics and researchers worldwide have paid close attention to biometric handwriting recognition using deep learning as much research has been proposed to enhance biometric recognition in the past and in recent years. Several solutions for character recognition systems in various languages, including Chinese, English, Japanese, Arabic, and Kurdish have been developed. Unfortunately, there has been minimal growth in the Assyrian language. There is still little research on Assyrian handwriting. In this paper, a new Assyrian language dataset was created as part of the procedure by distributing 500 forms consisting of 36 Assyrian characters to people between the ages of 13 and 60 of both genders. The preprocessing operation includes cleaning the noisy data and segmenting each image to 224x224 pixels. This effort resulted in the collection of 18,000 images of these characters to be trained 70% and tested 30% in four CNN models, VGG16, VGG19, MobileNet-V2, and ResNet-50, over 30 epochs to give an accuracy rate of 90.97%, 92.06%, 95.70%, and 94.97%., respectively.

SpaceGTN: A Time-Agnostic Graph Transformer Network for Handwritten Diagram Recognition and Segmentation

Online handwriting recognition is pivotal in domains like note-taking, education, healthcare, and office tasks. Existing diagram recognition algorithms mainly rely on the temporal information of strokes, resulting in a decline in recognition performance when dealing with notes that have been modified or have no temporal information. The current datasets are drawn based on templates and cannot reflect the real free-drawing situation. To address these challenges, we present SpaceGTN, a time-agnostic Graph Transformer Network, leveraging spatial integration and removing the need for temporal data. Extensive experiments on multiple datasets have demonstrated that our method consistently outperforms existing methods and achieves state-of-the-art performance. We also propose a pipeline that seamlessly connects offline and online handwritten diagrams. By integrating a stroke restoration technique with SpaceGTN, it enables intelligent editing of previously uneditable offline diagrams at the stroke level. In addition, we have also launched the first online handwritten diagram dataset, OHSD, which is collected using a free-drawing method and comes with modification annotations.

Direct Tensor Voting in line segmentation of handwritten documents

In the vast archives and libraries of the world, countless historical documents are tucked away, often difficult to access. Thankfully, the digitization process has made it easier to view these invaluable records. However, simply digitizing them is not enough – the real challenge lies in making them searchable and computer-readable. Many of these documents were handwritten, which means they need to undergo handwriting recognition. The first step in this process is to divide the document into lines. This article introduces a solution to this problem using tensor voting. The algorithm starts by conducting voting on the binary image itself. Then, using the local maxima found in the resulting tensor field, the lines of text are precisely tracked and labeled. To ensure its effectiveness, the algorithm’s performance was tested on the data-set delivered by the organizers of the ICDAR 2009 competition and evaluated using the criteria from this contest.