Urdu Natural Scene Character Recognition using Convolutional Neural Networks

Ali, Asghar; Pickering, Mark; Shafi, Kamran

doi:10.1109/asar.2018.8480202

Cited by 24 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the proposed network is compared with sequential CNN and HoG networks. The experimental results show that the proposed model outperforms the methods proposed in [29] and [30] without data augmentation. Furthermore, the proposed model is evaluated on the Chars74K [33] and ICDAR03 [34] datasets, where our method outperforms on the Chars74K dataset and achieves competitive results on the ICDAR03 dataset.…”

Section: Introductionmentioning

confidence: 90%

“…It is a type of cursive language, written in the right-to-left direction, and is derived from the Arabic and Persian scripts. To the best of our knowledge, no research has been conducted for the Urdu language, except our previous works [29]- [31].…”

Section: Introductionmentioning

confidence: 99%

“…However, deep learning-based methods have the capability to extract high-level spatial features from natural scenes automatically. In our previous work, the model proposed in [29] implemented a sequential CNN without analyzing the effect of multi-scale and multi-level feature fusion. Similarly, the model proposed in [30] implemented a histogram of oriented gradients (HoG) method.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

2020

View full text Add to dashboard Cite

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 multiscale 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. INDEX TERMS Cursive text recognition, natural scene Urdu character recognition, multi-scale feature aggregation, multi-level feature fusion, convolutional neural network (CNN)

show abstract

Section: Introductionmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

2020

View full text Add to dashboard Cite

show abstract

“…DNN has the ability to provide robust solution in end to end text recognition in videos. In this regard, Faster R-CNN [88], CNN [89,90], LSTM based method [91] have shown comparatively better performance on scene text recognition. In general, temporal redundancy can be used in tracking for text detection and recognition from complex videos [92].…”

Section: Text Recognitionmentioning

confidence: 99%

An analytical study of information extraction from unstructured and multidimensional big data

2019

View full text Add to dashboard Cite

IntroductionInformation extraction (IE) process extracts useful structured information from the unstructured data in the form of entities, relations, objects, events and many other types. The extracted information from unstructured data is used to prepare data for analysis. Therefore, the efficient and accurate transformation of unstructured data in the IE process improves the data analysis. Numerous techniques have been introduced for different data types i.e. text, image, audio, and video.The advancement in technology promoted the rapid growth of data volume in recent years. The volume, variety (structured, unstructured, and semi-structured data) and velocity of big data have also changed the paradigm of computational capabilities of the systems. IBM estimated that more than 2.5 quintillion bytes of data are generated every Abstract Process of information extraction (IE) is used to extract useful information from unstructured or semi-structured data. Big data arise new challenges for IE techniques with the rapid growth of multifaceted also called as multidimensional unstructured data. Traditional IE systems are inefficient to deal with this huge deluge of unstructured big data. The volume and variety of big data demand to improve the computational capabilities of these IE systems. It is necessary to understand the competency and limitations of the existing IE techniques related to data pre-processing, data extraction and transformation, and representations for huge volumes of multidimensional unstructured data. Numerous studies have been conducted on IE, addressing the challenges and issues for different data types such as text, image, audio and video. Very limited consolidated research work have been conducted to investigate the task-dependent and task-independent limitations of IE covering all data types in a single study. This research work address this limitation and present a systematic literature review of state-of-the-art techniques for a variety of big data, consolidating all data types. Recent challenges of IE are also identified and summarized. Potential solutions are proposed giving future research directions in big data IE. The research is significant in terms of recent trends and challenges related to big data analytics. The outcome of the research and recommendations will help to improve the big data analytics by making it more productive. which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. Adnan and Akbar J Big Data (2019) 6:91 Malaysia Adnan and Akbar J Big Data (2019) 6:91 RESEARCHday. Among these statistics, it was also predicted that unstructured data from diverse sources will grow up to 90% in few years. IDC estimated that unstructured data will be 95% of the global data in 2020 with estimated 65% annual growth rate [1]. The common characteristics of unstructured data are, (i) it comes in multiple formats...

show abstract

“…For pure outdoor Urdu-text detection, we were only able to find one relevant study [16]. Chandio et al [11] and Ali et al [28] used manually cropped Urdu characters from natural outdoor scenes for recognition of Urdu-characters, while in [16] Asghar et al used custom annotated Urdu images with ICDAR2017-MLT Arabic text for detection purpose, they used a combination of their custom collection of Urdu images and Arabic images from ICDAR 2017-MLT [7], They have dealt with Urdu and Arabic text at the word level. A similar kind of study is done by Ahmed et al [29] and Oulladji et al [30] for Arabic outdoor text.…”

Section: Introductionmentioning

confidence: 99%

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

Arafat

Iqbal

2020

IEEE Access

View full text Add to dashboard Cite

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 × 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. INDEX TERMS BLSTM, deep neural network, FasterRCNN, image classification, Nastalique, optical character recognition (OCR), regression residual neural network (RRNN), synthetic urdu text, text detection, two stream deep neural network (TSDNN).

show abstract

Urdu Natural Scene Character Recognition using Convolutional Neural Networks

Cited by 24 publications

References 7 publications

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

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

An analytical study of information extraction from unstructured and multidimensional big data

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

Contact Info

Product

Resources

About