Convolutional ensembles for Arabic Handwritten Character and Digit Recognition.
Ontology highlight
ABSTRACT:
SUBMITTER: Palatnik de Sousa I
PROVIDER: S-EPMC7924465 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description: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.
| S-EPMC9202630 | biostudies-literature
Project description:Although there is a huge progress in complementary-metal-oxide-semiconductor (CMOS) technology, construction of an artificial neural network using CMOS technology to realize the functionality comparable with that of human cerebral cortex containing 1010-1011 neurons is still of great challenge. Recently, phase change memristor neuron has been proposed to realize a human-brain level neural network operating at a high speed while consuming a small amount of power and having a high integration density. Although memristor neuron can be scaled down to nanometer, integration of 1010-1011 neurons still faces many problems in circuit complexity, chip area, power consumption, etc. In this work, we propose a CMOS compatible HfO2 memristor neuron that can be well integrated with silicon circuits. A hybrid Convolutional Neural Network (CNN) based on the HfO2 memristor neuron is proposed and constructed. In the hybrid CNN, one memristive neuron can behave as multiple physical neurons based on the Time Division Multiplexing Access (TDMA) technique. Handwritten digit recognition is demonstrated in the hybrid CNN with a memristive neuron acting as 784 physical neurons. This work paves the way towards substantially shrinking the amount of neurons required in hardware and realization of more complex or even human cerebral cortex level memristive neural networks.
| S-EPMC6105732 | biostudies-literature
Project description:Author verification of handwritten text is required in several application domains and has drawn a lot of attention within the research community due to its importance. Though, several approaches have been proposed for the text-independent writer verification of handwritten text, none of these have addressed the problem domain where author verification is sought based on partially-damaged handwritten documents (e.g., during forensic analysis). In this paper, we propose an approach for offline text-independent writer verification of handwritten Arabic text based on individual character shapes (within the Arabic alphabet). The proposed approach enables writer verification for partially damaged documents where certain handwritten characters can still be extracted from the damaged document. We also provide a mechanism to identify which Arabic characters are more effective during the writer verification process. We have collected a new dataset, Arabic Handwritten Alphabet, Words and Paragraphs Per User (AHAWP), for this purpose in a classroom setting with 82 different users. The dataset consists of 53,199 user-written isolated Arabic characters, 8,144 Arabic words, 10,780 characters extracted from these words. Convolutional neural network (CNN) based models are developed for verification of writers based on individual characters with an accuracy of 94% for isolated character shapes and 90% for extracted character shapes. Our proposed approach provided up to 95% writer verification accuracy for partially damaged documents.
| S-EPMC9044228 | biostudies-literature
Project description:BackgroundHandwritten Chinese character recognition (HCCR) is a difficult problem in character recognition. Chinese characters are diverse and many of them are very similar. The HCCR model consumes a large number of computational resources during runtime, making it difficult to deploy to resource-limited development platforms.MethodsIn order to reduce the computational consumption and improve the operational efficiency of such models, an improved lightweight HCCR model is proposed in this article. We reconstructed the basic modules of the SqueezeNext network so that the model would be compatible with the introduced attention module and model compression techniques. The proposed Cross-stage Convolutional Block Attention Module (C-CBAM) redeploys the Spatial Attention Module (SAM) and the Channel Attention Module (CAM) according to the feature map characteristics of the deep and shallow layers of the model, targeting enhanced information interaction between the deep and shallow layers. The reformulated intra-stage convolutional kernel importance assessment criterion integrates the normalization nature of the weights and allows for structured pruning in equal proportions for each stage of the model. The quantization aware training is able to map the 32-bit floating-point weights in the pruned model to 8-bit fixed-point weights with minor loss.ResultsPruning with the new convolutional kernel importance evaluation criterion proposed in this article can achieve a pruning rate of 50.79% with little impact on the accuracy rate. The various optimization methods can compress the model to 1.06 MB and achieve an accuracy of 97.36% on the CASIA-HWDB dataset. Compared with the initial model, the volume is reduced by 87.15%, and the accuracy is improved by 1.71%. The model proposed in this article greatly reduces the running time and storage requirements of the model while maintaining accuracy.
| S-EPMC10496007 | biostudies-literature
Project description:The digitalization of traditional Palmyra manuscripts, such as Lontar, is the government's main focus in efforts to preserve Balinese culture. Digitization is done by acquiring Lontar manuscripts through photos or scans. To understand Lontar's contents, experts usually carry out transliteration. Automatic transliteration using computer vision is generally carried out in several stages: character detection, character recognition, syllable recognition, and word recognition. Many methods can be used for detection and recognition, but they need data to train and evaluate the resulting model. In compiling the dataset, the data needs to be processed and labelled. This paper presented data collection and building datasets for detection and recognition tasks. Lontar was collected from libraries at universities in Bali. Data generation was carried out to produce 400 augmented images from 200 Lontar original images to increase the variousness of data. Annotations were performed to label each character producing over 100,000 characters in 55 character classes. This dataset can be used to train and evaluate performance in character detection and syllable recognition of new manuscripts.
| S-EPMC9741579 | biostudies-literature
Project description:The Transformer shows good prospects in computer vision. However, the Swin Transformer model has the disadvantage of a large number of parameters and high computational effort. To effectively solve these problems of the model, a simplified Swin Transformer (S-Swin Transformer) model was proposed in this article for handwritten Chinese character recognition. The model simplifies the initial four hierarchical stages into three hierarchical stages. In addition, the new model increases the size of the window in the window attention; the number of patches in the window is larger; and the perceptual field of the window is increased. As the network model deepens, the size of patches becomes larger, and the perceived range of each patch increases. Meanwhile, the purpose of shifting the window's attention is to enhance the information interaction between the window and the window. Experimental results show that the verification accuracy improves slightly as the window becomes larger. The best validation accuracy of the simplified Swin Transformer model on the dataset reached 95.70%. The number of parameters is only 8.69 million, and FLOPs are 2.90G, which greatly reduces the number of parameters and computation of the model and proves the correctness and validity of the proposed model.
| S-EPMC9575930 | biostudies-literature
Project description:Document analysis tasks, as text recognition, word spotting, or segmentation, are highly dependent on comprehensive and suitable databases for training and validation. However their generation is expensive in sense of labor and time. As a matter of fact, there is a lack of such databases, which complicates research and development. This is especially true for the case of Arabic handwriting recognition, that involves different preprocessing, segmentation, and recognition methods, which have individual demands on samples and ground truth. To bypass this problem, we present an efficient system that automatically turns Arabic Unicode text into synthetic images of handwritten documents and detailed ground truth. Active Shape Models (ASMs) based on 28046 online samples were used for character synthesis and statistical properties were extracted from the IESK-arDB database to simulate baselines and word slant or skew. In the synthesis step ASM based representations are composed to words and text pages, smoothed by B-Spline interpolation and rendered considering writing speed and pen characteristics. Finally, we use the synthetic data to validate a segmentation method. An experimental comparison with the IESK-arDB database encourages to train and test document analysis related methods on synthetic samples, whenever no sufficient natural ground truthed data is available.
| S-EPMC4534626 | biostudies-other
Project description:This article presents a handwritten Arabic alphabets, words and paragraphs dataset (AHAWP). The dataset contains 65 different Arabic alphabets (with variations on begin, end, middle and regular alphabets), 10 different Arabic words (that encompass all Arabic alphabets) and 3 different paragraphs. The dataset was collected anonymously from 82 different users. Each user was asked to write each alphabet and word 10 times. A userid uniquely but anonymously identifies the writer of each alphabet, word and paragraph. In total, the dataset consists of 53199 alphabet images, 8144 words images and 241 paragraphs images. This dataset can be used for multiple purposes. It can be used for optical handwriting recognition of alphabets and words. It can also be used for writer identification (or verification) of handwritten Arabic text. It is also possible to evaluate difference in writing styles of isolated alphabets as compared to the same alphabet written as part of the word or in paragraph by the same user using this dataset. The dataset is publicly available at https://data.mendeley.com/datasets/2h76672znt/1.
| S-EPMC8866147 | biostudies-literature
Project description:Character recognition is an important research field of interest for many applications. In recent years, deep learning has made breakthroughs in image classification, especially for character recognition. However, convolutional neural networks (CNN) still deliver state-of-the-art results in this area. Motivated by the success of CNNs, this paper proposes a simple novel full depth stacked CNN architecture for Latin and Arabic handwritten alphanumeric characters that is also utilized for license plate (LP) characters recognition. The proposed architecture is constructed by four convolutional layers, two max-pooling layers, and one fully connected layer. This architecture is low-complex, fast, reliable and achieves very promising classification accuracy that may move the field forward in terms of low complexity, high accuracy and full feature extraction. The proposed approach is tested on four benchmarks for handwritten character datasets, Fashion-MNIST dataset, public LP character datasets and a newly introduced real LP isolated character dataset. The proposed approach tests report an error of only 0.28% for MNIST, 0.34% for MAHDB, 1.45% for AHCD, 3.81% for AIA9K, 5.00% for Fashion-MNIST, 0.26% for Saudi license plate character and 0.97% for Latin license plate characters datasets. The license plate characters include license plates from Turkey (TR), Europe (EU), USA, United Arab Emirates (UAE) and Kingdom of Saudi Arabia (KSA).
| S-EPMC8237323 | biostudies-literature
Project description:This article presents two massive datasets for central Kurdish handwriting digits and isolated characters named K-ZHMARA and K-PIT. The first dataset, named K-ZHMARA dataset, contains 70,000 images of Kurdish digits, 7000 images for each digit, and a printed A4 paper with a grid of 10 × 10 is used for data collection. Apart from digits, the K-PIT dataset includes 245,000 images of all Kurdish characters, 7000 images for each character; data was collected via a printed A4 paper with a grid of 12 × 10 for this dataset. Moreover, both datasets include 315,000 images. Python programming has been used to scan each piece of paper, segment, crop, resize, binarize, and invert the images via edge detection and image processing techniques.
| S-EPMC10018436 | biostudies-literature