Handwritten Digit Recognition (HDR) is one of the most challenging tasks in the domain of Optical Character Recognition (OCR). Irrespective of language, there are some inherent challenges of HDR, which mostly arise due to the variations in writing styles across individuals, writing medium and environment, inability to maintain the same strokes while writing any digit repeatedly, etc. In addition to that, the structural complexities of the digits of a particular language may lead to ambiguous scenarios of HDR. Over the years, researchers have developed numerous offline and online HDR pipelines, where different image processing techniques are combined with traditional Machine Learning (ML)-based and/or Deep Learning (DL)-based architectures. Although evidence of extensive review studies on HDR exists in the literature for languages, such as English, Arabic, Indian, Farsi, Chinese, etc., few surveys on Bengali HDR (BHDR) can be found, which lack a comprehensive analysis of the challenges, the underlying recognition process, and possible future directions. In this paper, the characteristics and inherent ambiguities of Bengali handwritten digits along with a comprehensive insight of two decades of state-of-the-art datasets and approaches towards offline BHDR have been analyzed. Furthermore, several real-life application-specific studies, which involve BHDR, have also been discussed in detail. This paper will also serve as a compendium for researchers interested in the science behind offline BHDR, instigating the exploration of newer avenues of relevant research that may further lead to better offline recognition of Bengali handwritten digits in different application areas.

https://ieeexplore.ieee.org/ielx7/6287639/6514899/09869842.pdf

Two Decades of Bengali Handwritten Digit Recognition: A Survey

Handwritten Digit Recognition (HDR) is one of the most challenging tasks in the domain of Optical Character Recognition (OCR). Irrespective of language, there are some inherent challenges of HDR, which mostly arise due to the variations in writing styles across individuals, writing medium and environment, inability to maintain the same strokes while writing any digit repeatedly, etc. In addition to that, the structural complexities of the digits of a particular language may lead to ambiguous scenarios of HDR. Over the years, researchers have developed numerous offline and online HDR pipelines, where different image processing techniques are combined with traditional Machine Learning (ML)-based and/or Deep Learning (DL)-based architectures. Although evidence of extensive review studies on HDR exists in the literature for languages, such as English, Arabic, Indian, Farsi, Chinese, etc., few surveys on Bengali HDR (BHDR) can be found, which lack a comprehensive analysis of the challenges, the underlying recognition process, and possible future directions. In this paper, the characteristics and inherent ambiguities of Bengali handwritten digits along with a comprehensive insight of two decades of the state-of-the-art datasets and approaches towards offline BHDR have been analyzed. Furthermore, several real-life application-specific studies, which involve BHDR, have also been discussed in detail. This paper will also serve as a compendium for researchers interested in the science behind offline BHDR, instigating the exploration of newer avenues of relevant research that may further lead to better offline recognition of Bengali handwritten digits in different application areas. 

/pdf/two-decades-of-bengali-handwritten-digit-recognition-a-7jcj0924.pdf

Classifying handwritten digits is one of the most trending topics of research in the study of the automated text recognition system. The problem is more challenging in the case of Bengali digits due to additional complexities arising from similarity among various digits along with a wide variety of styles of hand-writings. In this paper, an end-to-end deep convolutional neural network, named as DeepBanglaNet, is proposed to classify Bengali handwritten digits. The proposed network utilizes various state-of-the-art optimization algorithms for eliminating vanishing/exploding gradient problems while extracting the global features effectively required for proper recognition of handwritten digits. This results in a very efficient model providing state-of-the-art accuracy of 99.43% on the NumtaDB database and outperforms all other existing models in all traditional evaluation metrics.

DeepBanglaNet: A Deep Convolutional Neural Network to Recognize Bengali Handwritten Digits

The recognition of Bangla handwritten numerals (BHNR) has recently emerged as a very interesting area for machine learning and pattern recognition research. Recently, the technology for character or object recognition has also advanced. Bangla handwritten number recognition can serve as a foundation for creating an Optical Character Recognition (OCR) in the Bangla language. However, the lack of a sizable and accurate dataset makes Bangla's handwritten numeral recognition study insufficient in contrast to that of other well-known languages. Similar to MNIST for English digits, NumtaDB is by far the largest dataset collection for handwritten digits in the Bangla language. The most used datasets for the recognition of Bangla handwritten numerals in the past were NumtaDB, CMATERdb, and ISI. The majority of approaches now in use rely on feature extraction and a few outdated machine learning algorithms. Although some approaches operate quickly enough to meet practical demands, they are not always accurate. Even while certain techniques work quite well for languages other than Bangla, they still require improvement. Convolutional Neural Networks (CNN), in particular, are demonstrating excellent achievements in this discipline with higher accuracy. In this work, we’ve used custom CNN architectures to build our model to recognize digits using all the existing datasets with a high degree of accuracy. Our CNN model shows an average of 98% accuracy recognizing Bangla numeric in respect of above datasets. We have cross verified our model with mixed datasets and the result is also promising.

/pdf/bangla-handwritten-numeral-recognition-using-deep-2pqr4xfg.pdf

Bangla handwritten numeral recognition using deep convolutional neural network

Despite being one of the major languages in the world, research regarding Bengali handwritten numeral recognition (BHNR) isn't enough in comparison with the other prominent languages. Existing methods mostly rely on feature extraction and some older machine learning algorithms. Recent bloom in machine learning due to deep neural network especially using Convolutional Neural Network (CNN) showing promising results in this field with better accuracy. Some recent works show very good accuracy only in recognizing plain simple digits but perform poor in challenging scenario because of lack of large and versatile training dataset. In this work, we propose a method where our proposed CNN model which recognizes numerals with high degree of accuracy beyond 96%, even in most challenging noisy conditions. Initially 72000+ specimens were used from NumtaDB (85000+) dataset for training and 1700+ specimens were used as test dataset. The improvement in performance in challenging scenarios is observed, when training specimens are augmented to create a training dataset of size about 114000 specimens. The performance of our proposed model also compared with other existing works and presented here. These findings are based on Computer Vision Challenge on Bengali HandWritten Digit Recognition (2018) competition submissions.

Chaity Saha

Papers

A Deep Convolutional Neural Network for Bangla Handwritten Numeral Recognition