Automatic Handwriting Recognition Research Articles

Sharing Cultural Heritage—The Case of the Lodovico Media Library

The article aims to reflect on the Lodovico media library, a digital repository preserving the digitised cultural heritage of the Emilia-Romagna region. The first part covers the project’s history and the challenges encountered during its setup phase, and we also explore the co-creation approach employed in defining the metadata architecture. The discussion extends by outlining the key features of shared metadata, illustrating their application to diverse digital objects within the Lodovico media library. Following a concise examination of the methodology for collecting/creating data and the initial research findings, the article concludes by highlighting the project’s potential in the realm of automatic handwriting recognition processes.

AI-ASSISTED DIGITALISATION OF HISTORICAL DOCUMENTS

Abstract. Preserving historical archival heritage involves not only physical measures to safeguard these valuable texts but also providing for their digital preservation. However, merely digitising manuscripts and codexes is not enough. A further step is needed: the digitalisation of their content, i.e. the verbatim transcription of scanned texts. This process enables the accurate preservation of their textual content, making it easier to search for information and conduct further analyses. With the help of artificial intelligence, particularly Deep Neural Networks (DNNs), automatic handwriting recognition can be performed. In this study, we employed a Convolutional Recurrent Neural Network (CRNN), an established type of DNN, to determine the minimum amount of labelled data required to automatically transcribe five different historical datasets that vary in language and time period. The results show that a Character Error Rate (CER) lower than 10% can be achieved with just a few hundred labelled text lines in almost all cases.

Application of optimized convolutional neural networks for early aided diagnosis of essential tremor: Automatic handwriting recognition and feature analysis.

Essential tremor (ET) is one of the most common neurological disorders, and its mainly clinical symptoms, including patient hand's kinetic tremor, dystonia, ataxia, etc., would influence the daily life of patients inordinately. Current ET diagnosis highly replies on the clinical evaluation and neurological examination, so the objective measurement indicators are particularly important in the auxiliary diagnosis of ET. In this research, the Archimedes spiral line freehand sketching samples without template assistance is collected and the Convolutional Neural Network (CNN) model of optimized structure is adopted to fully analyze the tremor, spacing of turns, shape, etc. shown in the handwriting samples of patients with ET, including the following main process: characteristics extraction, model visualization and subregional relevance evaluation. Dropout is used as a regularization technique in the network structure. The test group consisted of 50 patients with confirmed ET and the control group consisted of 40 healthy individuals. The main research objectives of this paper comprise two points: on the one hand, to achieve effective automatic classification of patients with ET and healthy controls using a scheme combining deep learning and simple hand mapping for the purpose of primary disease screening; on the other hand, to design sub-regional automatic classification experiments to demonstrate that Archimedean spiral hand drawings of patients with ET do have distinct local features, and to lay the experimental foundation for future hand drawing-based automatic aid for the identification of a variety of neurodegenerative diseases. Our model's average accuracy rate in test set reaches 89.3%, and average AUC is 0.972, with favorable stability and generalization performance. Besides, subregional characteristics recognition proofs that the spiral line samples of most of the patients with ET show more category-related characteristics in the local area of upper right, which provides evidences and theory update for predecessors' medical research.

Towards Accurate Children’s Arabic Handwriting Recognition via Deep Learning

Automatic handwriting recognition has received considerable attention over the past three decades. Handwriting recognition systems are useful for a wide range of applications. Much research has been conducted to address the problem in Latin languages. However, less research has focused on the Arabic language, especially concerning recognizing children’s Arabic handwriting. This task is essential as the demand for educational applications to practice writing and spelling Arabic letters is increasing. Thus, the development of Arabic handwriting recognition systems and applications for children is important. In this paper, we propose two deep learning-based models for the recognition of children’s Arabic handwriting. The proposed models, a convolutional neural network (CNN) and a pre-trained CNN (VGG-16) were trained using Hijja, a recent dataset of Arabic children’s handwriting collected in Saudi Arabia. We also train and test our proposed models using the Arabic Handwritten Character Dataset (AHCD). We compare the performance of the proposed models with similar models from the literature. The results indicate that our proposed CNN outperforms the pre-trained CNN (VGG-16) and the other compared models from the literature. Moreover, we developed Mutqin, a prototype to help children practice Arabic handwriting. The prototype was evaluated by target users, and the results are reported.

Генерация изображений рукописного текста на русском языке

Automatic handwriting recognition is an important component in the process of electronic documents analysis, but its solution is still far from ideal. One of the main reasons for the complexity of Russian handwriting recognition is the insufficient amount of data used to train recognition models. Moreover, for the Russian language the problem is more acute and is exacerbated by a large variety of complex handwriting. This paper explores the impact of various methods of generating additional training datasets on the quality of recognition models: the method based on handwritten fonts, the StackMix method of gluing words from symbols, and the use of a generative adversarial network. A font-based method for creating images of handwritten text in Russian has been developed and described in this work. In addition, an algorithm for the formation of a new Cyrillic handwritten font based on the existing images of handwritten characters is proposed. The effectiveness of the developed method was tested using experiments that were carried out on two publicly available Cyrillic datasets using two different recognition models. The results of the experiments showed that the developed method for generating images made it possible to increase the accuracy of handwriting recognition by an average of 6%, which is comparable to the results of other more complex methods. The source code of the experiments, the proposed method, as well as the datasets generated during the experiments are posted in the public domain and are ready for download.

Kannada Text Recognition

Abstract: The task of automatic handwriting recognition is critical. This can be a difficult subject, and it has gotten a lot of attention in recent years. In the realm of picture grouping, handwritten character recognition is a problem. Handwritten characters are difficult to decipher since various people have distinct handwriting styles. For decades, researchers have been focusing on character identification in Latin handwriting. Kannada has had fewer studies conducted on it. Our "Kannada Text Recognition" research and effort attempts to classify and recognize characters written in Kannada, a south Indian language. The characters are taken from written documents, preprocessed with numpy and OpenCV, and then run through a CNN.

Arabic handwriting recognition system using convolutional neural network

Automatic handwriting recognition is an important component for many applications in various fields. It is a challenging problem that has received a lot of attention in the past three decades. Research has focused on the recognition of Latin languages’ handwriting. Fewer studies have been done for the Arabic language. In this paper, we present a new dataset of Arabic letters written exclusively by children aged 7–12 which we call Hijja. Our dataset contains 47,434 characters written by 591 participants. In addition, we propose an automatic handwriting recognition model based on convolutional neural networks (CNN). We train our model on Hijja, as well as the Arabic Handwritten Character Dataset (AHCD) dataset. Results show that our model’s performance is promising, achieving accuracies of 97% and 88% on the AHCD dataset and the Hijja dataset, respectively, outperforming other models in the literature.

HDSR-Flor: A Robust End-to-End System to Solve the Handwritten Digit String Recognition Problem in Real Complex Scenarios

Automatic handwriting recognition systems are of interest for academic research fields and for commercial applications. Recent advances in deep learning techniques have shown dramatic improvement in relation to classic computer vision problems, especially in Handwritten Text Recognition (HTR). However, several approaches try to solve the problem of deep learning applied to Handwritten Digit String Recognition (HDSR), where it has to deal with the low number of trainable data, while learning to ignore any writing symbol around the digits (noise). In this context, we present a new optical model architecture (Gated-CNN-BGRU), based on HTR workflow, applied to HDSR. The International Conference on Frontiers of Handwriting Recognition (ICFHR) 2014 competition on HDSR were used as baselines to evaluate the effectiveness of our proposal, whose metrics, datasets and recognition methods were adopted for fair comparison. Furthermore, we also use a private dataset (Brazilian Bank Check - Courtesy Amount Recognition), and 11 different approaches from the state-of-the-art in HDSR, as well as 2 optical models from the state-of-the-art in HTR. Finally, the proposed optical model demonstrated robustness even with low data volume (126 trainable data, for example), surpassing the results of existing methods with an average precision of 96.50%, which is equivalent to an average percentage of improvement of 3.74 points compared to the state-of-the-art in HDSR. In addition, the result stands out in the competition’s CVL HDS set, where the proposed optical model achieved a precision of 93.54%, while the best result so far had been from Beijing group (from the competition itself), with 85.29%.

Correction des données : retour d’expérience sur la plate-forme RECITAL de transcription participative

Crowdsourcing have been widely deployed to cover some challenges in digital humanities, like in the transcription of old handwritten documents. Such approach is especially useful to tackle existing limits in automatic handwriting recognition techniques. Crowdsourcing allows workers to help experts in extraction and classification of information, when the workload is daunting. Yet, it yields some specific challenges related to the quality of produced data. In this paper, we discuss data quality in a research project called CIRESFI which aims at transcribing Italian Comedy financial archives through the RECITAL web platform. We finally propose some leads to tackle these issues.

Keep calm and carry on? De toekomst van de sociaal-economische geschiedenis in de Lage Landen

This contribution offers a series of thoughts on new directions which social and economic history in the Low Countries might take. The field faces important challenges: source digitization, automatic handwriting recognition and digital methods of analysis. Somewhat ironically, social and economic history has received renewed interest after the 2008 financial and economic crisis. This crisis has fuelled research into inequality and capitalism and has forced economics as a discipline to question itself. One answer to the crisis of economics is to include more economic history. This essay emphasizes the fact that social and economic history is a house with many rooms and explicitly encourages social and economic historians to be inspired by other scholars, whether they be other historians or social scientists. One way to go forward might be the inclusion of insights from behavioral economics and the history of emotions which could lead to a fuller and more realistic analysis of the decisions individual historical actors took.

Clock Drawing Test Digit Recognition Using Static and Dynamic Features

The clock drawing test (CDT) is a standard neurological test for detection of cognitive impairment. A computerised version of the test promises to improve the accessibility of the test in addition to obtaining more detailed data about the subject's performance. Automatic handwriting recognition is one of the first stages in the analysis of the computerised test, which produces a set of recognized digits and symbols together with their positions on the clock face. Subsequently, these are used in the test scoring. This is a challenging problem because the average CDT taker has a high likelihood of cognitive impairment, and writing is one of the first functional activities to be affected. Current handwritten digit recognition system perform less well on this kind of data due to its unintelligibility. In this paper, a new system for numeral handwriting recognition in the CDT is proposed. The system is based on two complementary sources of data, namely static and dynamic features extracted from handwritten data. The main novelty of this paper is the new handwriting digit recognition system, which combines two classifiers—fuzzy k-nearest neighbour for dynamic stroke-based features and convolutional neural network for static image- based features, which can take advantage of both static and dynamic data. The proposed digit recognition system is tested on two sets of data: first, Pendigits online handwriting digits; and second, digits from the actual CDTs. The latter data set came from 65 drawings made by healthy people and 100 drawings reproduced from the drawings by dementia patients. The test on both data sets shows that the proposed combination system can outperform each classifier individually in terms of recognition accuracy, especially when assessing the handwriting of people with dementia.

The ESPOSALLES database: An ancient marriage license corpus for off-line handwriting recognition

Historical records of daily activities provide intriguing insights into the life of our ancestors, useful for demography studies and genealogical research. Automatic processing of historical documents, however, has mostly been focused on single works of literature and less on social records, which tend to have a distinct layout, structure, and vocabulary. Such information is usually collected by expert demographers that devote a lot of time to manually transcribe them. This paper presents a new database, compiled from a marriage license books collection, to support research in automatic handwriting recognition for historical documents containing social records. Marriage license books are documents that were used for centuries by ecclesiastical institutions to register marriage licenses. Books from this collection are handwritten and span nearly half a millennium until the beginning of the 20th century. In addition, a study is presented about the capability of state-of-the-art handwritten text recognition systems, when applied to the presented database. Baseline results are reported for reference in future studies.

MULTIMODAL COMPUTER-ASSISTED TRANSCRIPTION OF TEXT IMAGES AT CHARACTER-LEVEL INTERACTION

Currently, automatic handwriting recognition systems are ineffectual in unconstrained handwriting documents. Therefore, to obtain perfect transcriptions, heavy human intervention is required to validate and correct the results of such systems. Given that this post-editing process is inefficient and uncomfortable, a multimodal interactive approach has been proposed in previous works, which aims at obtaining correct transcriptions with the minimum human effort. In this approach, the user interacts with the system by means of an e-pen and/or more traditional methods such as keyboard or mouse. This user's feedback allows to improve system accuracy and multimodality increases system ergonomics and user acceptability. Until now, multimodal interaction has been considered only at whole-word level. In this work, multimodal interaction at character-level is studied, that may lead to more effective interactivity, since it is faster and easier to write only one character rather than a whole word. Here we study this kind of fine-grained multimodal interaction and present developments that allow taking advantage of interaction-derived context to significantly improve feedback decoding accuracy. Empirical tests on three cursive handwritten tasks suggest that, despite losing the deterministic accuracy of traditional peripherals, this approach can save significant amounts of user effort with respect to fully manual transcription as well as to noninteractive post-editing correction.

Multimodal interactive transcription of text images

To date, automatic handwriting recognition systems are far from being perfect and heavy human intervention is often required to check and correct the results of such systems. This “post-editing” process is both inefficient and uncomfortable to the user. An example is the transcription of historic documents: state-of-the-art handwritten text recognition technology is not suitable to perform this task automatically and expensive paleography expert work is needed to achieve correct transcriptions. As an alternative to fully manual transcription and post-editing, a multimodal interactive approach is proposed here where user feedback is provided by means of touchscreen pen strokes and/or more traditional keyboard and mouse operation. User's feedback directly allows to improve system accuracy, while multimodality increases system ergonomy and user acceptability. Multimodal interaction is approached in such a way that both the main and the feedback data streams help each-other to optimize overall performance and usability. Empirical tests on three cursive handwritten tasks suggest that, using this approach, considerable amounts of user effort can be saved with respect to both pure manual work and non-interactive, post-editing processing.

Palaeography and Image-Processing: Some Solutions and Problems

This paper considers the application of image-processing and data-mining to the analysis of scribal hands. The work of forensic document analysts on feature-extraction is considered, particularly the algorithms developed for automatic handwriting-recognition by Srihari, and by Bulacu and Schomaker. Automatic clustering is also considered using the AutoClass package. Preliminary results of the author’s own experiments with these approaches are presented, and some of the obstacles are outlined which must be overcome before a practical system can be developed for the automatic identification of medieval scribes.

On-line handwritten digit recognition based on trajectory and velocity modeling

The handwriting is one of the most familiar communication media. Pen based interface combined with automatic handwriting recognition offers a very easy and natural input method. The handwritten signal is on-line collected via a digitizing device, and it is classified as one pre-specified set of characters. The main techniques applied in our work include two fields of research. The first one consists of the modeling system of handwriting. In this area, we developed a novel method of the handwritten trajectory modeling based on elliptic and Beta representation. The second part of our work shows the implementation of a classifier consisting of the Multi-Layers Perception of Neural Networks (MLPNN) developed in a fuzzy concept. The training process of the recognition system is based on an association of the Self Organization Maps (SOM) with Fuzzy K-Nearest Neighbor Algorithms (FKNNA). To test the performance of our system we build 30,000 Arabic digits. The global recognition rate obtained by our recognition system is about 95.08%.

Classifiers combination and syntax analysis for Arabic literal amount recognition

Automatic handwriting recognition has a variety of applications in real world problems, such as mail sorting and check processing. Recently, it has been demonstrated that combining the decisions of several classifiers and integrating multiple information sources can lead to better recognition results. This article presents an approach for recognizing handwritten Arabic literal (legal) amounts. The proposed system uses a set of holistic structural features to describe the words. These features are presented to three classifiers: multilayer neural network, k nearest neighbor, and fuzzy k nearest neighbor. The classification results are then combined using several schemes; we retained the score summation one for this work. A syntactic post-classification process is then carried out to find the best match among the candidate words. The performance of this approach is superior to the system which ignores all contextual information and simply relies on the recognition scores of the recognizers.

Identification and decomposition of fast handwriting system

Systems for carrying out automatic handwriting recognition or writer verification based on real-time handwriting signals have as their basic function the separation and characterization of a muscular force function and a hand system impulse response. The problem is how to deconvolve the handwriting signal into two functions mentioned above. The problem assumes that the only datum available is the convolution itself; the handwriting signal. Limiting our discussions exclusively to the "fast" handwriting case, an approach to this class of blind deconvolution -is described based on the interaction of theory and experiments.