Handwritten Character Dataset Research Articles

Generative innovations for paleography: enhancing character image synthesis through unconditional single image models

Data scarcity in paleographic image datasets poses a significant challenge to researchers and scholars in the field. Unlike modern printed texts, historical manuscripts and documents are often scarce and fragile, making them difficult to digitize and create comprehensive datasets. Recently many innovations have been arrived on single image generative models for natural images but none of them are focused on paleographic character images and other handwritten datasets. In paleographic images like stone inscription characters, maintaining exact shape and structure of character is important unlike natural images. In this paper we propose an unconditional single image generative model, CharGAN for isolated paleographic character images. In the proposed system, augmented images are generated from a single image using generative adversarial networks, while maintaining their structure. Specifically, an external augmentation inducer is used to create higher-level augmentations in the generated images. In addition, the input to the generator is replaced with dynamic sampling from a Gaussian mixture model to make changes to the low-level features. From our experimental results, we infer that these two enhancements make single-image generative models suitable not only for natural images, but also for paleographic character images and other handwritten character datasets, the AHCD dataset, and EMNIST, where the global structure is important. Both the qualitative and quantitative results show that our approach is effective and superior in single-image generative tasks, particularly in isolated character image generation.

Chronological Evolution: Development and Identification of a Marathi Handwritten Character Dataset Using Deep Learning

Chronological Evolution: Development and Identification of a Marathi Handwritten Character Dataset Using Deep Learning

Chronological Evolution: Development and Identification of an Odia Handwritten Character Dataset Using Deep Learning

Chronological Evolution: Development and Identification of an Odia Handwritten Character Dataset Using Deep Learning

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.

Recognizing Off-line Devanagari Handwritten Characters Using Modified Lenet-5 Deep Neural Network

Recognizing specific characters from a large set of handwritten characters is called off-line character recognition. Devanagari, the reading and writing script, is widely used in a broad region of India. This paper proposes using the modified LeNet-5 architecture for recognizing Devanagari off-line handwritten characters using the Devanagari Handwritten Character Dataset (DHCD). The dataset comprises 46 distinct character classes, each with 2000 images. The proposed modified Lenet-5 Base Architecture (MLCNN8) uses more filters and kernels of small sizes with batch normalization. The proposed modified Lenet-5 Base Architecture (MLCNN8) outperformed the Lenet-5 Base Architecture (LCNN) with an accuracy of 99.21% in 53 epochs, whereas LCNN achieved an accuracy of 94.50% in 48 epochs. Hence, the proposed modified Lenet-5 architecture outperforms the Lenet-5 Base Architecture. The proposed model's results were compared with other state-of-the-art and found that it also has an edge for recognizing the Devanagari handwritten characters.

Comparing the Performance of Deep Denoising Sparse Autoencoder with Other Defense Methods Against Adversarial Attacks for Arabic letters

The aim of this paper is to compare how effectively the Deep Denoising Sparse Autoencoder (DDSA) method performs compared to other defense strategies - like adversarial training, defensive distillation and feature squeezing - in dealing with adversarial attacks for Arabic letters. We strive to evaluate both the accuracy and robustness as well as efficiency of these methods by examining a test set from the Arabic Handwritten Characters Dataset while considering adversarial attacks. Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and Carlini and Wagner (C&W) are all part of this. Our research findings demonstrate that DDSA surpasses the rest of the defense methods in terms of classification accuracy and robustness. This exceptional performance is due to the distinctive attributes of DDSA, which concentrate on acquiring distinguishing features and integrating spatial information to improve defense against adversarial perturbations. While it necessitates more computational resources, DDSA's superior performance validates the additional expenses, particularly in critical applications where misclassification may have severe implications.

An algorithm for extracting similar segments of moving target trajectories based on shape matching

Trajectory similarity analysis of moving target is the foundation for mining high-value and regular behavioral information such as motion preferences, activity hotspots and frequent paths. Unlike most trajectory similarity analysis methods aimed at discovering correlations of target activities in time, space or spatio-temporal domains, this paper focuses on the shape matching of target trajectories. If some specific shapes frequently appear in historical trajectories, extracting these local shapes would be beneficial for analyzing the target motion templates and behavior modes. Trajectory segments with similar shapes may not have spatio-temporal correlation, and the shapes also have geometric transformation characteristics such as rotation, scaling and translation. Since the existing trajectory similarity analysis methods cannot be directly applied, an algorithm for extracting similar segments based on shape matching is proposed. First, a new shape descriptor based on signed barycenter distance (SBD) is established. It describes a trajectory as a one-dimensional shape feature sequence, which has the advantage of low computational complexity. Then, the distributed nearest neighbor search strategy is used in the particle swarm optimization (PSO) method, which aims to accelerate the retrieval of trajectory segments with similar shapes and improve the matching accuracy. Experiments on MPEG-7, handwritten character and maneuvering target simulation trajectory data sets show that compared with the existing typical shape descriptors, SBD shape descriptor has advantages in accuracy and noise insensitivity, and the improved PSO method can efficiently and accurately obtain the local shape matching results.

Ranjana Script Handwritten Character Recognition using CNN

This paper proposes a public image database for Ranjana script Handwritten Character Datasets (RHCD), publicly available for Ranjana script researchers or anyone interested in the subject. To the best of our knowledge, the Ranjana script Handwritten Character Dataset (RHCD) is the first publicly available database for Ranjana script researchers. Ranjana script descended from the Brahmi script, consists of 36 consonant letters, 16 vowel letters, and 10 numerical letters. The focus of this research is three-fold: the first is to create a new database for Ranjana script Handwritten Character Recognition; the second is to test the character recognition accuracy of the created RHCD using existing CNN algorithms like LeNET-5, AlexNET, and ZFNET algorithm; the third is to propose a model by investigating different hyper-tuning parameters to improve the recognition accuracy of the created RHCD. The research method applied in this study is dataset collection, digitization & cropping, pre-processing, dataset splitting, data augmentation, and finally, implementing the CNN model (existing and proposed). Performance evaluation is based on the test accuracy, precision, recall, and F1-score. The experiment result shows that our model ranks first, with a testing accuracy of 99.73% for 64x64 pixels resolution with precision, recall, and F1-score value 1. Creation and recognition of Ranjana script characters, vowel modifiers, and compound characters can be the next milestone to be achieved. Segmentation of words and sentences into characters and recognizing each character individually can be the next research domain.

HDevChaRNet: A deep learning-based model for recognizing offline handwritten devanagari characters

<p>Optical character recognition (OCR) converts text images into machine-readable text. Due to the non-availability of several standard datasets of Devanagari characters, researchers have used many techniques for developing an OCR system with varying recognition rates using their own created datasets. The main objective of our proposed study is to improve the recognition rate by analyzing the effect of using batch normalization (BN) instead of dropout in convolutional neural network (CNN) architecture. So, a CNN-based model HDevChaRNet (Handwritten Devanagari Character Recognition Network) is proposed in this study for same to recognize offline handwritten Devanagari characters using a dataset named Devanagari handwritten character dataset (DHCD). DHCD comprises a total of 46 classes of characters, out of which 36 are consonants, and 10 are numerals. The proposed models based on convolutional neural network (CNN) with BN for recognizing the Devanagari characters showed an improved accuracy of 98.75%, 99.70%, and 99.17% for 36, 10, and 46 classes, respectively.</p>

Development of a Benchmark Odia Handwritten Character Database for an Efficient Offline Handwritten Character Recognition with a Chronological Survey

A good benchmark dataset is a primary requirement in the offline handwritten character recognition (HCR) process. Only three handwritten numerals and alphabet datasets from Odia are publicly accessible for study, although many writers have used several datasets in their experiments. In this article, two tasks are done to address this issue. Those are the following: First, an extensive survey focused on various datasets is provided with the methodologies used in chronological order. The second factor is a solution to the lack of publicly available handwritten characters and numeral datasets. A new dataset of handwritten Odia characters with numerals has been developed. Anyone can access this dataset by sending an email to the authors of the article. This dataset was created with the help of 150 volunteers of various age groups, races, and qualifications. Some homogeneous experiments are conducted using deep learning models to evaluate the consistency of the dataset. One heterogeneous trial has also been performed to estimate the complexities of the characters present in the dataset by comparing them with the existing benchmark datasets.

Handwritten Arabic Character Recognition for Children Writing Using Convolutional Neural Network and Stroke Identification

Automatic Arabic handwritten recognition is one of the recently studied problems in the field of Machine Learning. Unlike Latin languages, Arabic is a Semitic language that forms a harder challenge, especially with the variability of patterns caused by factors such as the writer’s age. Most studies have focused on adults, with only one recent study on children. Moreover, many recent machine-learning methods have focused on using Convolutional Neural Networks (CNNs), a powerful class of neural networks that can extract complex features from images. In this paper, we propose a convolutional neural network (CNN) model that recognizes children’s handwriting with an accuracy of 91% on the Hijja dataset, a recent dataset built by collecting images of Arabic characters written by children, and 97% on the Arabic Handwritten Character Dataset. The results showed a good improvement over the proposed model from the Hijja dataset authors, yet it revealed a bigger challenge to solve for children’s Arabic handwritten character recognition. Moreover, we proposed a new approach using multiple models instead of a single model based on the number of strokes in a character and merged Hijja with AHCD, which achieved an average prediction accuracy of 96%.

Handwritten Multi-Scale Chinese Character Detector with Blended Region Attention Features and Light-Weighted Learning.

Character-level detection in historical manuscripts is one of the challenging and valuable tasks in the computer vision field, related directly and effectively to the recognition task. Most of the existing techniques, though promising, seem not powerful and insufficiently accurate to locate characters precisely. In this paper, we present a novel algorithm called free-candidate multiscale Chinese character detection FC-MSCCD, which is based on lateral and fusion connections between multiple feature layers, to successfully predict Chinese characters of different sizes more accurately in old documents. Moreover, cheap training is exploited using cheaper parameters by incorporating a free-candidate detection technique. A bottom-up architecture with connections and concatenations between various dimension feature maps is employed to attain high-quality information that satisfies the positioning criteria of characters, and the implementation of a proposal-free algorithm presents a computation-friendly model. Owing to a lack of handwritten Chinese character datasets from old documents, experiments on newly collected benchmark train and validate FC-MSCCD to show that the proposed detection approach outperforms roughly all other SOTA detection algorithms.

Offline handwritten Tai Le character recognition using wavelet deep convolution features and ensemble deep variationally sparse Gaussian processes

Handwriting recognition is an important application in pattern recognition. Because handwritten Tai Le has similar characters and the proportion of characters with similar shapes is relatively high, this paper proposes a wavelet deep convolution (WDC) feature combined with an ensemble deep variational sparse Gaussian process (EDVSGP) offline handwritten Tai Le recognition method. A Tai Le recognition sample database is constructed, 2 and 3 levels of wavelet decomposition prior features are extracted, and then, the wavelet a priori feature is transformed into a WDC feature. To avoid the dimensional disaster caused by feature fusion, a dimensionality reduction method combining LDA and PCA is used to reducing the dimensionality of the fused features without reducing the accuracy rate. Moreover, to better recognize handwritten Tai Le characters, 6 deep variationally sparse Gaussian process (DVSGP) models are integrated as an EDVSGP classification model. Using the handwritten Tai Le character database, the proposed method is superior to the existing methods, with an accuracy, recall and F1-score of 94.15%, 94.15%, and 94.15%, respectively. The universality of the method is verified on a dataset of handwritten Chinese characters with similar shapes (HCFC2021.4) and the Devanagari dataset.

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.

Combination of machine learning algorithms and Resnet50 for Arabic Handwritten Classification

The recognition or classification of Arabic handwritten characters is extremely crucial in many applications and, at the same time, one of the biggest challenges that machine learning faces. The emergence of deep learning, particularly Convolutional Neural Networks (CNN), is considered a suitable technique to face these challenges. In this research paper, an investigation model is proposed to make recognition for Arabic handwriting utilizing one of CNN architectures: ResNet50 architecture, after replacing the last layer with one of two types of machine learning algorithms, Support Vector Machine (SVM) and Random Forest (RF), to reduce training time and increase overall accuracy. Our experimental work was performed on three data sets: Arabic Handwritten Character Dataset (AHCD), Alexa Isolated Alphabet Dataset (AIA9K), and Hijja Dataset. Experimental results show that combining ResNet50 with random forest produces more accurate and consistent results than the ResNet50 model produces by itself. Finally, the comparison with the other methods across all data sets demonstrates the robustness and effectiveness of the combination of random forest with the ResNet50 approach. Where the modified ResNet50 architecture has achieved a rate of 92.37%, 98.39%, and 91.64%, while the combination architecture has achieved 95%, 99%, and 92.4% for AIA9K, AHCD, and Hijja datasets, respectively.

A Tree-Structure Analysis Network on Handwritten Chinese Character Error Correction

Existing researches on handwritten Chinese characters are mainly based on recognition network designed to solve the complex structure and numerous amount characteristics of Chinese characters. In this paper, we investigate Chinese characters from the perspective of error correction, which is to diagnose a handwritten character to be right or wrong and provide a feedback on error analysis. For this handwritten Chinese character error correction task, we define a benchmark by unifying both the evaluation metrics and data splits for the first time. Then we design a diagnosis system that includes decomposition, judgement and correction stages. Specifically, a novel tree-structure analysis network (TAN) is proposed to model a Chinese character as a tree layout. Using the predicted tree layout for judgement, if the character is wrongly written, correction operation is needed for error analysis. The correction stage mainly consists of three steps: fetch the ideal character, correct the errors and locate the errors. Computing the distance between the model output and all candidate characters can generate ideal characters. With the decomposition ability of TAN, edit distance computing between predicted tree and ideal tree can lead to correction operations. By using attention visualization, we can even provide the approximate error location. Through quantitative analysis, we prove that TAN captures more accurate spatial position information than regular encoder-decoder models. Additionally, we propose a novel bucketing mining strategy to apply triplet loss at radical level to alleviate feature dispersion. Experiments on handwritten character dataset demonstrate that our proposed TAN shows great superiority on all three metrics comparing with other state-of-the-art models.

An intelligent approach for Arabic handwritten letter recognition using convolutional neural network.

Currently, digital transformation has occurred in most countries in the world to varying degrees, but digitizing business processes are complex in terms of understanding the various aspects of manual documentation. The use of digital devices and intelligent systems is vital in the digital transformation of manual documentation from hardcopy to digital formats. The transformation of handwritten documents into electronic files is one of the principal aspects of digitization and represents a common need shared by today’s businesses. Generally, handwriting recognition poses a complex digitization challenge, and Arabic handwriting recognition, specifically, proves inordinately challenging due to the nature of Arabic scripts and the excessive diversity in human handwriting. This study presents an intelligent approach for recognizing handwritten Arabic letters. In this approach, a convolution neural network (CNN) model is proposed to recognize handwritten Arabic letters. The model is regularized using batch normalization and dropout operations. Moreover, the model was tested with and without dropout, resulting in a significant difference in the performance. Hence, the model overfitting has been prevented using dropout regularization. The proposed model was applied to the prominent, publicly-available Arabic handwritten characters (AHCD) dataset with 16,800 letters, and the performance was measured using several evaluation measures. The experimental results show the best fit of the proposed model in terms of higher accuracy results that reached 96.78%; additionally, other evaluation measures compared to popular domain-relevant approaches in the literature.

DeblurGAN-CNN: Effective Image Denoising and Recognition for Noisy Handwritten Characters

Many problems can reduce handwritten character recognition performance, such as image degradation, light conditions, low-resolution images, and even the quality of the capture devices. However, in this research, we have focused on the noise in the character images that could decrease the accuracy of handwritten character recognition. Many types of noise penalties influence the recognition performance, for example, low resolution, Gaussian noise, low contrast, and blur. First, this research proposes a method that learns from the noisy handwritten character images and synthesizes clean character images using the robust deblur generative adversarial network (DeblurGAN). Second, we combine the DeblurGAN architecture with a convolutional neural network (CNN), called DeblurGAN-CNN. Subsequently, two state-of-the-art CNN architectures are combined with DeblurGAN, namely DeblurGAN-DenseNet121 and DeblurGAN-MobileNetV2, to address many noise problems and enhance the recognition performance of the handwritten character images. Finally, the DeblurGAN-CNN could transform the noisy characters to the new clean characters and recognize clean characters simultaneously. We have evaluated and compared the experimental results of the proposed DeblurGAN-CNN architectures with the existing methods on four handwritten character datasets: n-THI-C68, n-MNIST, THI-C68, and THCC-67. For the n-THI-C68 dataset, the DeblurGAN-CNN achieved above 98% and outperformed the other existing methods. For the n-MNIST, the proposed DeblurGAN-CNN achieved an accuracy of 97.59% when the AWGN+Contrast noise method was applied to the handwritten digits. We have evaluated the DeblurGAN-CNN on the THCC-67 dataset. The result showed that the proposed DeblurGAN-CNN achieved an accuracy of 80.68%, which is significantly higher than the existing method, approximately 10%.

CArDIS: A Swedish Historical Handwritten Character and Word Dataset

This paper introduces a new publicly available image-based Swedish historical handwritten character and word dataset named Character Arkiv Digital Sweden (CArDIS) (https://cardisdataset.github. io/CARDIS/). The samples in CArDIS are collected from 64,084 Swedish historical documents written by several anonymous priests between 1800 and 1900. The dataset contains 116,000 Swedish alphabet images in RGB color space with 29 classes, whereas the word dataset contains 30,000 image samples of ten popular Swedish names as well as 1,000 region names in Sweden. To examine the performance of different machine learning classifiers on CArDIS dataset, three different experiments are conducted. In the first experiment, classifiers such as Support Vector Machine (SVM), Artificial Neural Networks (ANN), k-Nearest Neighbor (k-NN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Random Forest (RF) are trained on existing character datasets which are Extended Modified National Institute of Standards and Technology (EMNIST), IAM and CVL and tested on CArDIS dataset. In the second and third experiments, the same classifiers as well as two pre-trained VGG-16 and VGG-19 classifiers are trained and tested on CArDIS character and word datasets. The experiments show that the machine learning methods trained on existing handwritten character datasets struggle to recognize characters efficiently on the CArDIS dataset, proving that characters in the CArDIS contain unique features and characteristics. Moreover, in the last two experiments, the deep learning-based classifiers provide the best recognition rates.

Query Pixel Guided Stroke Extraction with Model-Based Matching for Offline Handwritten Chinese Characters

Stroke extraction and matching are critical for structural interpretation based applications of handwritten Chinese characters, such as Chinese character education and calligraphy analysis. Stroke extraction from offline handwritten Chinese characters is difficult because of the missing of temporal information, the multi-stroke structures and the distortion of handwritten shapes. In this paper, we propose a comprehensive scheme for solving the stroke extraction problem for handwritten Chinese characters. The method consists of three main steps: (1) fully convolutional network (FCN) based skeletonization; (2) query pixel guided stroke extraction; (3) model-based stroke matching. Specifically, based on a recently proposed architecture of FCN, both the stroke skeletons and cross regions are firstly extracted from the character image by the proposed SkeNet and CrossNet, respectively. Stroke extraction is solved by simulating the human perception that once given a certain pixel from non-cross region of a stroke, the whole stroke containing the pixel can be traced. To realize this idea, we formulate stroke extraction as a problem of pairing and connecting skeleton-wise stroke segments which are adjacent to the same cross region, where the pairing consistency between stroke segments is measured using a PathNet [1]. To reduce the ambiguity of stroke extraction, the extracted candidate strokes are matched with a character model consisting of standard strokes by tree search to identify the correct strokes. For verifying the effectiveness of the proposed method, we train and test our models on character images with stroke segmentation annotations generated from the online handwriting datasets CASIA-OLHWDB and ICDAR13-Online, as well as a dataset of Regularly-Written online handwritten characters (RW-OLHWDB). The experimental results demonstrate the effectiveness of the proposed method and provide several benchmarks. Particularly, the precisions of stroke extraction for ICDAR13-Online and RW-OLHWDB are 89.0% and 94.9%, respectively.