Urdu Character Research Articles

Comprehensive robustness evaluation of an automatic writer identification system using convolutional neural networks

<p>This research paper presents a convolutional neural network (CNN) model for identifying handwritten Urdu characters. A dataset of 38 fundamental Urdu characters from 100 different writers in the Kashmir valley was manually collected. The developed system was trained on a training dataset of 30,400 samples and verified on a test dataset of 7600 samples, and it outperformed previously proposed AI based writer identification systems in Urdu language with an identification rate of 91.44 percent for 38 classes. This study highlights the effectiveness of deep learning techniques in solving the challenging task of the Urdu writer identification. The findings demonstrate the potential of the developed CNN model for real-world applications in handwritten character recognition and verification systems. Future work involves expanding the dataset to include numerals and isolated characters for improved system performance.</p>

Review on Isolated Urdu Character Recognition: Offline Handwritten Approach

Abstract: This paper summarizes a system for recognizing isolated Urdu characters using advanced machine learning algorithms. The system analyzes visual features of Urdu characters, like strokes and curves, to train models such as CNN, SVM, ANN, and MLP. With a large dataset, the system can accurately predict unseen characters. It can be integrated into various applications for real-time character recognition tasks like OCR (Optical Character Recognition) and handwriting recognition. This literature survey explores research papers focused on character recognition in languages like Urdu, Arabic, Persian, and Sindhi, proposing various techniques like feature extraction, deep learning, and machine learning to enhance character recognition technology. The survey highlights specific studies with high accuracy and discusses recognition systems for Arabic characters as well.

An Enhanced Prototypical Network Architecture for Few-Shot Handwritten Urdu Character Recognition

Few shot models have started to gain a lot of popularity in the past few years. This is mostly because these models grant the ability to structure the representation space (classes) using a very less amount of examples for each class. Such models are usually trained on a wide range of different classes and their examples, which allows them to form and learn a decision-based metric in the process. Non-Latin languages, especially languages such as Urdu, have a bi-linear direction of writing and are context-sensitive in nature, and are hard to recognize. Also, unlike traditional English, there is a very small amount of clean, collated, and usable data that is available for the Urdu language. In this paper, we explore a prototypical network for k-shot classification on handwritten Urdu characters. The prototypical network learns the Euclidean embeddings of the provided images and uses clusters to classify newer examples. Our improved method is able to outperform other methods of few-shot learning and is able to accurately classify both Urdu characters as well as numerals using a minimal number of examples. After comprehensive qualitative and quantitative evaluation and comparison of our proposed approach with other methods to classify handwritten text in few-shot settings, we found out that our proposed approach was typically able to beat other methods by a margin of 1% – 2% while relying on a small training set.

Recognition of offline handwritten Urdu characters using RNN and LSTM models

Recognition of offline handwritten Urdu characters using RNN and LSTM models

Handwritten Urdu Characters and Digits Recognition Using Transfer Learning and Augmentation With AlexNet

Automated recognition of handwritten characters and digits is a challenging task. Although a significant amount of literature exists for automatic recognition of handwritten characters of English and other major languages in the world, there exists a wide research gap due to lack of research for recognition of Urdu language. The variations in writing style, shape and size of individual characters and similarities with other characters add to the complexity for accurate classification of handwritten characters. Deep neural networks have emerged as a powerful technology for automated classification of character patters and object images. Although deep networks are known to provide remarkable results on large-scale datasets with millions of images, however the use of deep networks for small image datasets is still challenging. The purpose of this research is to present a classification framework for automatic recognition of handwritten Urdu character and digits with higher recognition accuracy by utilizing theory of transfer learning and pre-trained Convolution Neural Networks (CNN). The performance of transfer learning is evaluated in different ways: by using pre-trained AlexNet CNN model with Support Vector Machine (SVM) classifier, and fine-tuned AlexNet for extracting features and classification. We have fine-tuned AlexNet hyper-parameters to achieve higher accuracy and data augmentation is performed to avoid over-fitting. Experimental results and the quantitative comparisons demonstrate the effectiveness of the proposed research for recognition of handwritten characters and digits using fine-tuned AlexNet. The proposed research based on fine-tuned AlexNet outperforms the related state-of-the-art research thereby achieving a classification accuracy of 97.08%, 98.21%, 94.92% for urdu characters, digits and hybrid datasets respectively. The presented methods can be applied for research on Urdu characters and in diverse domains such as handwritten text image retrieval, reading postal addresses, bank’s cheque processing, preserving and digitization of manuscripts from old ages.

Multi-Domain Deep Convolutional Neural Network for Ancient Urdu Text Recognition System

Deep learning has achieved magnificent success in the field of pattern recognition. In recent years Urdu character recognition system has significantly benefited from the effectiveness of the deep convolutional neural network. Majority of the research on Urdu text recognition are concentrated on formal handwritten and printed Urdu text document. In this paper, we experimented the Challenging issue of text recognition in Urdu ancient literature documents. Due to its cursiveness, complex word formation (ligatures), and context-sensitivity, and inadequate benchmark dataset, recognition of Urdu text from the literature document is very difficult to process compared to the formal Urdu text document. In this work, first, we generated a dataset by extracting the recurrent ligatures from an ancient Urdu fatawa book. Secondly, we categorized and augment the ligatures to generate batches of augmented images that improvise the training efficiency and classification accuracy. Finally, we proposed a multi-domain deep Convolutional Neural Network which integrates a spatial domain and a frequency domain CNN to learn the modular relations between features originating from the two different domain networks to train and improvise the classification accuracy. The experimental results show that the proposed network with the augmented dataset achieves an averaged accuracy of 97.8% which outperforms the other CNN models in this class. The experimental results also show that for the recognition of ancient Urdu literature, well-known benchmark datasets are not appropriate which is also verified with our prepared dataset.

Urdu Handwritten Characters Data Visualization and Recognition Using Distributed Stochastic Neighborhood Embedding and Deep Network

In this paper, we make use of the 2-dimensional data obtained through t-Stochastic Neighborhood Embedding (t-SNE) when applied on high-dimensional data of Urdu handwritten characters and numerals. The instances of the dataset used for experimental work are classified in multiple classes depending on the shape similarity. We performed three tasks in a disciplined order; namely, (i) we generated a state-of-the-art dataset of both the Urdu handwritten characters and numerals by inviting a number of native Urdu participants from different social and academic groups, since there is no publicly available dataset of such type till date, then (ii) applied classical approaches of dimensionality reduction and data visualization like Principal Component Analysis (PCA), Autoencoders (AE) in comparison with t-Stochastic Neighborhood Embedding (t-SNE), and (iii) used the reduced dimensions obtained through PCA, AE, and t-SNE for recognition of Urdu handwritten characters and numerals using a deep network like Convolution Neural Network (CNN). The accuracy achieved in recognition of Urdu characters and numerals among the approaches for the same task is found to be much better. The novelty lies in the fact that the resulting reduced dimensions are used for the first time for the recognition of Urdu handwritten text at the character level instead of using the whole multidimensional data. This results in consuming less computation time with the same accuracy when compared with processing time consumed by recognition approaches applied to other datasets for the same task using the whole data.

Template Matching Based Probabilistic Optical Character Recognition for Urdu Nastaliq Script

This paper presents a technique for optical recognition of Urdu characters using template matching based on a probabilistic N-Gram language model. Dataset used has the collection of both printed and typed text. This model is able to perform three types of segmentations including line, ligature and character using horizontal projection, connected component labeling, corners and pointers techniques, respectively. A separate stochastic lexicon is built from a collected corpus, which contains the probability values of grams. By using template matching and the N-Gram language model, our study predicts complete segmented words with the promising result, particularly in case of bigrams. It outperforms three out of four existing models with an accuracy rate of 97.33%. Results achieved on our test dataset are encouraging in one perspective but provide direction to work for further improvement in this model.

UrduDeepNet: offline handwritten Urdu character recognition using deep neural network

UrduDeepNet: offline handwritten Urdu character recognition using deep neural network

Urdu character recognition: a systematic literature review

Urdu character recognition: a systematic literature review

Urdu character recognition: a systematic literature review

The cursive nature of the Urdu text, where a particular character concatenated in different words forms different shapes, makes it a complicated language for automatic character recognition. This p...

Machine Learning Empowered Urdu Characters Recognition Mechanism

Machine Learning Empowered Urdu Characters Recognition Mechanism

A Novel Deep Convolutional Neural Network Architecture Based on Transfer Learning for Handwritten Urdu Character Recognition

A Novel Deep Convolutional Neural Network Architecture Based on Transfer Learning for Handwritten Urdu Character Recognition

Cursive-Text: A Comprehensive Dataset for End-to-End Urdu Text Recognition in Natural Scene Images.

Reading text in natural scene images is an active research area in the fields of computer vision and pattern recognition as text detection, text recognition and script identification are required. In this data article, a comprehensive dataset for Urdu text detection and recognition in natural scene images is presented and analysed. To develop the dataset, more than 2500 natural scene images were captured using a digital camera and a built-in mobile phone camera. Three separate datasets for isolated Urdu character images, cropped word images and end-to-end text spotting were developed. The isolated Urdu character and cropped word images dataset contain a much larger number of samples than existing Arabic natural scene text datasets. The Urdu text spotting dataset contains images with Urdu, English and Sindhi text instances. However, the focus has been given to the Urdu text instances. The ground truths for each image in the isolated character, cropped word or text spotting datasets are provided separately. The proposed datasets can be used to perform Urdu text detection and recognition or end-to-end recognition in natural scenes. These datasets can also be helpful to develop Arabic and Persian natural scene text detection and recognition systems, as Urdu is a derived language of these scripts and has many similar letters. The datasets can also be helpful to develop multi-language translation systems, which can facilitate foreign tourists to read and translate multilingual text in natural scene images. To evaluate the datasets, state-of-the-art machine learning and deep neural networks were used to build the text detection and recognition models, where the best classification accuracies are achieved. To the best of the authors’ knowledge, this is the first dataset proposed for Urdu text detection, recognition or end-to-end text recognition in natural scene images. The aim of this data article is to present a benchmark work in the field of document analysis and recognition.Computer ScienceComputer Vision and Pattern RecognitionTablesFiguresImagesText FilesUsing a digital camera with a 20 megapixels (MP) sensor, an iPhone with a 12 MP back camera and a Samsung mobile with a 16MP back camera.RawAnalyzedEnvironmental factors such as illuminations, blurring and lighting conditions were considered while capturing images. The focus was given to the text within an image.The images in the dataset were obtained from the advertisement banners, sign-boards along the road side and streets, shop name boards, text written on the passing vehicles and walls.The images provided in this dataset were collected in different cities of Sindh, Pakistan.Summarized data are hosted with the article.The datasets and their related files are hosted in a Mendeley public data repository.DOI: https://data.mendeley.com/datasets/k5fz57zd9z/1URL: http://dx.doi.org/10.17632/k5fz57zd9z.1

Handwritten Urdu character recognition via images using different machine learning and deep learning techniques

Objectives: This research presents a model for Urdu Handwritten Character Recognition via images using various Machine Learning and Deep Learning Techniques. The main objective of this research is to provide comparative study on Urdu Handwritten Characters from images dataset. Methods/Statistical analysis: In this research paper, Support Vector Machine (SVM), K-Nearest Neighbor (K-NN) algorithm, Multi-Layer Perceptron (MLP), Concurrent Neural Network (CNN), Recurrent Neural Network (RNN) and Random Forest Algorithm (RF) have been implemented in order to evaluate most suitable technique for Urdu Handwritten Characters Recognition via images. Findings: Ample amount of research work has been carried out on English Language but it is clearly shown through the conducted literature review that very lesser amount of work has been done on Urdu Handwritten Characters Recognition using images. Furthermore, It has been analyzed from this research that CNN models are most efficient compared to RF, SVM and MLP as to produce reliable results in terms of optimal accuracy. Therefore, using the CNN model is a viable choice to recognize Urdu handwritten characters from the images. And proposed study provides significant contribution in automatic learning of Urdu handwritten Characters. Keywords: Urdu Handwritten Characters; Machine Learning; Deep Learning; Urdu Character Recognition

Cursive Character Recognition in Natural Scene Images Using a Multilevel Convolutional Neural Network Fusion

The accuracy of current natural scene text recognition algorithms is limited by the poor performance of character recognition methods for these images. The complex backgrounds, variations in the writing, text size, orientations, low resolution and multi-language text make recognition of text in natural images a complex and challenging task. Conventional machine learning and deep learning-based methods have been developed that have achieved satisfactory results, but character recognition for cursive text such as Arabic and Urdu scripts in natural images is still an open research problem. The characters in the cursive text are connected and are difficult to segment for recognition. Variations in the shape of a character due to its different positions within a word make the recognition task more challenging than non-cursive text. Optical character recognition (OCR) techniques proposed for Arabic and Urdu scanned documents perform very poorly when applied to character recognition in natural images. In this paper, we propose a multi-scale feature aggregation (MSFA) and a multi-level feature fusion (MLFF) network architecture to recognize isolated Urdu characters in natural images. The network first aggregates multi-scale features of the convolutional layers by up-sampling and addition operations and then combines them with the high-level features. Finally, the outputs of the MSFA and MLFF networks are fused together to create more robust and powerful features. A comprehensive dataset of segmented Urdu characters is developed for the evaluation of the proposed network models. Synthetic text on the patches of images with real natural scene backgrounds is generated to increase the samples of infrequently used characters. The proposed model is evaluated on the Chars74K and ICDAR03 datasets. To validate the proposed model on the new Urdu character image dataset, we compare its performance with the histogram of oriented gradients (HoG) method. The experimental results show that the aggregation of multi-scale and multilevel features and their fusion is more effective, and outperforms other methods on the Urdu character image and Chars74K datasets.

OCR-Nets: Variants of Pre-trained CNN for Urdu Handwritten Character Recognition via Transfer Learning

Abstract Deep Convolutional neural networks (CNN) have been among the utmost competitive neural network architectures and have set the state-of-the-art in various fields of computer vision. In this paper, we present OCR-Nets, variants of (AlexNet & GoogleNet) for recognition of handwritten Urdu characters through transfer learning. Our proposed networks are experimented using an integrated dataset. To compare the recognition rate with traditional character recognition methods and to confirm the fairness of the experiment an additional Urdu character dataset is manually generated with different fonts and size. The experimental result shows that OCR-AlexNet and OCR-GoogleNet produce significant performance gains of 96.3% and 94.7% averaged success rate respectively.

A Comparative Analysis on Nastaliq Style Urdu Character Recognition

Optical Character Recognition (OCR) has emerged as an interesting research field. Lot of work has been declared in Urdu script based on various approaches and diverse methodologies have been put forward on Nastaliq font style to get the desired output. The paper presents a survey on different techniques of OCR and ends up with the comparative analysis of Urdu character recognition based on accuracy and other performance parameters. This exploration directly implies that the nonpresence of Urdu OCR has restricted the idea on advanced Urdu library and thus, drives a pathway for enormous research in this field.

Urdu-Text Detection and Recognition in Natural Scene Images Using Deep Learning

Urdu text is a cursive script and belongs to a non-Latin family of other cursive scripts like Arabic, Chinese, and Hindi. Urdu text poses a challenge for detection/localization from natural scene images, and consequently recognition of individual ligatures in scene images. In this paper, a methodology is proposed that covers detection, orientation prediction, and recognition of Urdu ligatures in outdoor images. As a first step, the custom FasterRCNN algorithm has been used in conjunction with well-known CNNs like Squeezenet, Googlenet, Resnet18, and Resnet50 for detection and localization purposes for images of size $320\times 240$ pixels. For ligature Orientation prediction, a custom Regression Residual Neural Network (RRNN) is trained/tested on datasets containing randomly oriented ligatures. Recognition of ligatures was done using Two Stream Deep Neural Network (TSDNN). In our experiments, five-set of datasets, containing 4.2K and 51K Urdu-text-embedded synthetic images were generated using the CLE annotation text to evaluate different tasks of detection, orientation prediction, and recognition of ligatures. These synthetic images contain 132, and 1600 unique ligatures corresponding to 4.2K and 51K images respectively, with 32 variations of each ligature (4-backgrounds and font 8-color variations). Also, 1094 real-world images containing more than 12k Urdu characters were used for TSDNN’s evaluation. Finally, all four detectors were evaluated and used to compare them for their ability to detect/localize Urdu-text using average-precision (AP). Resnet50 features based FasterRCNN was found to be the winner detector with AP of.98. While Squeeznet, Googlenet, Resnet18 based detectors had testing AP of.65,.88, and.87 respectively. RRNN achieved and accuracy of 79% and 99% for 4k and 51K images respectively. Similarly, for characters classification in ligatures, TSDNN attained a partial sequence recognition rate of 94.90% and 95.20% for 4k and 51K images respectively. Similarly, a partial sequence recognition rate of 76.60% attained for real world-images.

Dataset of Urduud1k from Natural Scenes

In latest years research has drawn attention on text analysis in natural scenes. Databases play a significant part in the efficiency assessment of the algorithm for text recognition. A data set of natural scene text images in six distinct languages have recently been released in an International Conference on Document Analysis and Recognition (ICDAR).This dataset is for multi-languages except Urdu. In the natural images of the Urdu scene, there is an absence of a conventional Urdu text database. This research therefore mainly aims to build a database for Urdu text in natural scenes. The dataset is very large because there are 10 distinct cameras with distinct resolution, distinct angles and distinct range requirements for each picture captured by distinct light zone. The dataset comprises of Urdu words, ligatures and characters in natural scenes. The dataset contains 16k images of words, 32k ligatures and characters images. This dataset contains 1kimagesincluding signboard, a name of the store, banners and so on. In addition, the Urdu dataset is contrasted with the current data set including ICRAR 2003, ARASTI, Chars 74k, etc. The dataset includes many images from the natural scene so it can be used in natural environments to identify Urdu text.