Convolutional neural network-based ensemble methods to recognize Bangla handwritten character

In this era of advancements in deep learning, an autonomous system that recognizes handwritten characters and texts can be eventually integrated with the software to provide better user experience. Like other languages, Bangla handwritten text extraction also has various applications such as post-office automation, signboard recognition, and many more. A large-scale and efficient isolated Bangla handwritten character classifier can be the first building block to create such a system. This study aims to classify the handwritten Bangla characters. The proposed methods of this study are divided into three phases. In the first phase, seven convolutional neural networks i.e., CNN-based architectures are created. After that, the best performing CNN model is identified, and it is used as a feature extractor. Classifiers are then obtained by using shallow machine learning algorithms. In the last phase, five ensemble methods have been used to achieve better performance in the classification task. To systematically assess the outcomes of this study, a comparative analysis of the performances has also been carried out. Among all the methods, the stacked generalization ensemble method has achieved better performance than the other implemented methods. It has obtained accuracy, precision, and recall of 98.68%, 98.69%, and 98.68%, respectively on the Ekush dataset. Moreover, the use of CNN architectures and ensemble methods in large-scale Bangla handwritten character recognition has also been justified by obtaining consistent results on the BanglaLekha-Isolated dataset. Such efficient systems can move the handwritten recognition to the next level so that the handwriting can easily be automated.

[1]  Javier Gomez-Pilar,et al.  Adaptive Stacked Generalization for Multiclass Motor Imagery-Based Brain Computer Interfaces , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[2]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[3]  Tetsushi Wakabayashi,et al.  Handwritten Bangla Compound Character Recognition Using Gradient Feature , 2007, 10th International Conference on Information Technology (ICIT 2007).

[4]  Karl Rihaczek,et al.  1. WHAT IS DATA MINING? , 2019, Data Mining for the Social Sciences.

[5]  Torsten Hothorn,et al.  Double-Bagging: Combining Classifiers by Bootstrap Aggregation , 2002, Pattern Recognit..

[6]  Samuel Manoharan.  A SMART IMAGE PROCESSING ALGORITHM FOR TEXT RECOGNITION, INFORMATION EXTRACTION AND VOCALIZATION FOR THE VISUALLY CHALLENGED , 2019 .

[7]  Muhammad Abul Hasan,et al.  Isolated Bangla handwritten character recognition with convolutional neural network , 2017, 2017 20th International Conference of Computer and Information Technology (ICCIT).

[8]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[9]  Khawza I. Ahmed,et al.  Handwritten Bangla digit recognition using Sparse Representation Classifier , 2014, 2014 International Conference on Informatics, Electronics & Vision (ICIEV).

[10]  Marc'Aurelio Ranzato,et al.  Efficient Learning of Sparse Representations with an Energy-Based Model , 2006, NIPS.

[11]  George R. Thoma,et al.  A novel stacked generalization of models for improved TB detection in chest radiographs , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[12]  Chiranjibi Sitaula,et al.  Vector representation based on a supervised codebook for Nepali documents classification , 2021, PeerJ Comput. Sci..

[13]  L. Vinet,et al.  A ‘missing’ family of classical orthogonal polynomials , 2010, 1011.1669.

[14]  Rafiqul Islam,et al.  BanglaLekha-Isolated: A multi-purpose comprehensive dataset of Handwritten Bangla Isolated characters , 2017, Data in brief.

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Eduardo Fidalgo,et al.  Boosting image classification through semantic attention filtering strategies , 2018, Pattern Recognit. Lett..

[17]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[18]  Syed Akhter Hossain,et al.  Ekush: A Multipurpose and Multitype Comprehensive Database for Online Off-Line Bangla Handwritten Characters , 2018, RTIP2R.

[19]  Sheikh Abujar,et al.  EkushNet: Using Convolutional Neural Network for Bangla Handwritten Recognition , 2018 .

[20]  D. Opitz,et al.  Popular Ensemble Methods: An Empirical Study , 1999, J. Artif. Intell. Res..

[21]  E. Sreenivasa Reddy,et al.  Role of Offline Handwritten Character Recognition System in Various Applications , 2016 .

[22]  Ujjwal Bhattacharya,et al.  An End-to-End System for Bangla Online Handwriting Recognition , 2016, 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[23]  Sudipta Roy,et al.  Bengali Handwritten Character Classification Using Transfer Learning on Deep Convolutional Network , 2019, IHCI.

[24]  Subhadip Basu,et al.  A benchmark image database of isolated Bangla handwritten compound characters , 2014, International Journal on Document Analysis and Recognition (IJDAR).

[25]  Hujun Yin,et al.  Markov Random Field Based Convolutional Neural Networks for Image Classification , 2017, IDEAL.

[26]  Charu C. Aggarwal,et al.  Data Mining , 2015, Springer International Publishing.

[27]  Kazuyuki Murase,et al.  Bangla handwritten character recognition using deep belief network , 2014, 2013 International Conference on Electrical Information and Communication Technology (EICT).

[28]  Sakib Reza,et al.  Basic to Compound: A Novel Transfer Learning Approach for Bengali Handwritten Character Recognition , 2019, 2019 International Conference on Bangla Speech and Language Processing (ICBSLP).

[29]  Bidyut B. Chaudhuri.  A Complete Handwritten Numeral Database of Bangla – A Major Indic Script , 2006 .

[30]  Petra Perner,et al.  Data Mining - Concepts and Techniques , 2002, Künstliche Intell..

[31]  Nafees Mansoor,et al.  A hybrid deep model with HOG features for Bangla handwritten numeral classification , 2016, 2016 9th International Conference on Electrical and Computer Engineering (ICECE).

[32]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[33]  Mamunur Rahaman Mamun,et al.  Bangla Handwritten Digit Recognition Approach with an Ensemble of Deep Residual Networks , 2018, 2018 International Conference on Bangla Speech and Language Processing (ICBSLP).

[34]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[35]  Nibaran Das,et al.  An enhanced harmony search method for Bangla handwritten character recognition using region sampling , 2015, 2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS).

[36]  Subhadip Basu,et al.  CMATERdb1: a database of unconstrained handwritten Bangla and Bangla–English mixed script document image , 2011, International Journal on Document Analysis and Recognition (IJDAR).

[37]  Mohammad Shahadat Hossain,et al.  Bangla Handwritten Character Recognition using Convolutional Neural Network with Data Augmentation , 2019, 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR).

[38]  Vijayan K. Asari,et al.  Handwritten Bangla Character Recognition Using the State-of-the-Art Deep Convolutional Neural Networks , 2017, Comput. Intell. Neurosci..

[39]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Johannes R. Sveinsson,et al.  Random Forests for land cover classification , 2006, Pattern Recognit. Lett..

[41]  Ujjwal Bhattacharya,et al.  Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[42]  Yago Saez,et al.  A Survey of Handwritten Character Recognition with MNIST and EMNIST , 2019, Applied Sciences.

[43]  Mark J. van der Laan,et al.  The relative performance of ensemble methods with deep convolutional neural networks for image classification , 2017, Journal of applied statistics.

[44]  Shamim H. Ripon,et al.  Stacked Generalization Ensemble Method to Classify Bangla Handwritten Character , 2021 .

[45]  Kang Huang,et al.  Robust Handwriting Recognition with Limited and Noisy Data , 2020, 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[46]  Luca Maria Gambardella,et al.  Convolutional Neural Network Committees for Handwritten Character Classification , 2011, 2011 International Conference on Document Analysis and Recognition.

[47]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[48]  Samiul Alam,et al.  NumtaDB - Assembled Bengali Handwritten Digits , 2018, ArXiv.

[49]  Chih-Fong Tsai,et al.  Training support vector machines based on stacked generalization for image classification , 2005, Neurocomputing.

[50]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[51]  Md Saiful Islam,et al.  Bengali handwritten character recognition using deep convolutional neural network , 2017, 2017 20th International Conference of Computer and Information Technology (ICCIT).

[52]  M. M. Hafizur Rahman,et al.  Bangla Handwritten Character Recognition using Convolutional Neural Network , 2015 .

[53]  Gregory Shakhnarovich,et al.  FractalNet: Ultra-Deep Neural Networks without Residuals , 2016, ICLR.

[54]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[55]  Jihad El-Sana,et al.  Evolution maps and applications , 2016, PeerJ Comput. Sci..

[56]  Md Shopon,et al.  Bangla handwritten digit recognition using autoencoder and deep convolutional neural network , 2016, 2016 International Workshop on Computational Intelligence (IWCI).