Proceedings ArticleDOI
A Deep Convolutional Neural Network for Bangla Handwritten Numeral Recognition
Kazi Mejbaul Islam,Rouhan Noor,Chaity Saha,Jakaria Rahimi +3 more
- Vol. 2018, pp 45-50
Reads0
Chats0
TLDR
This work proposes a method where the proposed CNN model which recognizes numerals with high degree of accuracy beyond 96%, even in most challenging noisy conditions is observed.Abstract:
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.read more
Citations
More filters
Journal ArticleDOI
Two Decades of Bengali Handwritten Digit Recognition: A Survey
A. B. M. Ashikur Rahman,Md. Bakhtiar Hasan,Shabbir Ahmed,Tasnim Ahmed,Md. Hamjajul Ashmafee,Mohammad Ridwan Kabir,Md. Hasanul Kabir +6 more
TL;DR: 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 and several real-life application-specific studies, which involve BH DR, have been discussed in detail.
Journal ArticleDOI
Two Decades of Bengali Handwritten Digit Recognition: A Survey
TL;DR: In this article , 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.
Proceedings ArticleDOI
DeepBanglaNet: A Deep Convolutional Neural Network to Recognize Bengali Handwritten Digits
TL;DR: An end-to-end deep convolutional neural network, named as DeepBanglaNet, is proposed to classify Bengali handwritten digits, providing state-of-the-art accuracy of 99.43% on the NumtaDB database and outperforms all other existing models in all traditional evaluation metrics.
Journal ArticleDOI
Bangla handwritten numeral recognition using deep convolutional neural network
TL;DR: In this paper , the authors used custom CNN architectures to build a model to recognize digits using all the existing datasets with a high degree of accuracy, achieving an average of 98% accuracy.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Proceedings Article
Regularization of Neural Networks using DropConnect
TL;DR: This work introduces DropConnect, a generalization of Dropout, for regularizing large fully-connected layers within neural networks, and derives a bound on the generalization performance of both Dropout and DropConnect.
Journal ArticleDOI
A genetic algorithm based region sampling for selection of local features in handwritten digit recognition application
TL;DR: A methodology where local regions of varying heights and widths are created dynamically and genetic algorithm (GA) is applied on these local regions to sample the optimal set of local regions from where an optimal feature set can be extracted that has the best discriminating features.
Journal ArticleDOI
Handwritten Bangla numeral recognition system and its application to postal automation
Ying Wen,Yue Lu,Pengfei Shi +2 more
TL;DR: It has been found that the recognition result achieved by the integrated system is more reliable than that by one method alone.