A pragmatic convolutional bagging ensemble learning for recognition of Farsi handwritten digits

Recognition of handwritten digits is one of the most important and challenging issues in recent decades in the field of computer science. Its cursive nature, the right to left writing styles of words and characters as well as various digits shapes have imposed curiosity among numerous researchers to impose a lot of efforts on the recognition of handwritten Farsi numbers. In order to improve the recognition accuracy of Farsi handwritten digit recognition, the pragmatic CBWME network structure model based on convolution bagging weighted majority ensemble learning is developed by integrating the convolution neural network (CNN) and bagging weighted majority ensemble learning. For base classifiers, we applied the VGG16, ResNet18, and Xception architectures and explored the bagging weighted majority ensemble learning in combining the base classifiers results, which are later used in identifying Farsi handwritten digits. The performance of the CNN models (VGG16, ResNet18, and Xception) and CBWME model was evaluated by comparing their results. From the experimental result analysis, it was observed that the proposed CBWME model achieved the best average recognition accuracy (97.65%), followed by the Xception model (95.9%), ResNet18 model (93.75%), and VGG16 model (90.26%) in HODA dataset. The accuracy orders were the same as in IFHCDB and CENPARMI datasets. The CSE model attained the best result with rate of (99.876%) compared with the other studies.

[1]  Deepak Chaudhary,et al.  Hindi Handwritten Character Recognition using Deep Convolution Neural Network , 2019, 2019 6th International Conference on Computing for Sustainable Global Development (INDIACom).

[2]  Azam Bastanfard,et al.  Pattern Separation Network Based on the Hippocampus Activity for Handwritten Recognition , 2020, IEEE Access.

[3]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[4]  Mohammad Shojafar,et al.  Mobile Cloud Computing: Challenges and Future Research Directions , 2017, 2017 10th International Conference on Developments in eSystems Engineering (DeSE).

[5]  Samaher AlJanabi,et al.  A Novel Software to Improve Healthcare Base on Predictive Analytics and Mobile Services for Cloud Data Centers , 2019, Big Data and Networks Technologies.

[6]  H. Agahi.  Handwritten Digits Recognition Using an Ensemble Technique based on the Firefly Algorithm , 2019 .

[7]  Lambert Schomaker,et al.  A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification , 2019, Neural Computing and Applications.

[8]  Sunghwan Kim,et al.  Handwritten Arabic Optical Character Recognition Approach Based on Hybrid Whale Optimization Algorithm With Neighborhood Rough Set , 2020, IEEE Access.

[9]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[10]  Harold Mouchère,et al.  Transfer Learning for Handwriting Recognition on Historical Documents , 2018, ICPRAM.

[11]  Hamid Parvin,et al.  A New Divide and Conquer Based Classification for OCR , 2010 .

[12]  Samad Roohi,et al.  Persian handwritten character recognition using convolutional neural network , 2017, 2017 10th Iranian Conference on Machine Vision and Image Processing (MVIP).

[13]  Youssfi Elkettani,et al.  Towards Directing Convolutional Neural Networks Using Computational Geometry Algorithms: Application to Handwritten Arabic Character Recognition , 2020 .

[14]  Mohammad Parseh,et al.  Persian Handwritten Digit Recognition Using Combination of Convolutional Neural Network and Support Vector Machine Methods , 2020, Int. Arab J. Inf. Technol..

[15]  Samaher Al-Janabi,et al.  An Innovative synthesis of deep learning techniques (DCapsNet & DCOM) for generation electrical renewable energy from wind energy , 2020, Soft Computing.

[16]  Mohsen Soryani,et al.  Improving persian digit recognition by combining data augmentation and AlexNet , 2017, 2017 10th Iranian Conference on Machine Vision and Image Processing (MVIP).

[17]  Samaher Al-Janabi,et al.  Evaluation prediction techniques to achievement an optimal biomedical analysis , 2019, Int. J. Grid Util. Comput..

[18]  Mohammad Mosleh,et al.  Persian Handwritten Digit Recognition Using Ensemble Classifiers , 2015 .

[19]  Vahid Ghods,et al.  Farsi handwritten phone number recognition using deep learning , 2020, SN Applied Sciences.

[20]  Amit Gupta,et al.  Comparative analysis of machine learning algorithms in OCR , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[21]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Samaher Al-Janabi,et al.  A nifty collaborative analysis to predicting a novel tool (DRFLLS) for missing values estimation , 2019, Soft Computing.

[23]  Farbod Razzazi,et al.  Recognition of Handwritten Persian Two-digit Numerals Using a Novel Hybrid SVM/HMM algorithm , 2016 .

[24]  Samaher Al-Janabi,et al.  Evaluation prediction techniques to achievement an optimal biomedical analysis , 2019 .

[25]  Bongjin Oh,et al.  A case study on scene recognition using an ensemble convolution neural network , 2018, 2018 20th International Conference on Advanced Communication Technology (ICACT).

[26]  Hedieh Sajedi,et al.  Persian Handwritten Number Recognition Using Adapted Framing Feature and Support Vector Machines , 2016, Int. J. Comput. Intell. Appl..

[27]  Vahid Ghods,et al.  Farsi Handwriting Digit Recognition Based on Convolutional Neural Networks , 2018, 2018 6th International Symposium on Computational and Business Intelligence (ISCBI).

[28]  Mohamed Yousuff Caffiyar,et al.  A Novel Deep Convolutional Neural Network Architecture Based on Transfer Learning for Handwritten Urdu Character Recognition , 2020 .

[29]  Najla Al-Nabhan,et al.  Analysis and comparison of machine learning classifiers and deep neural networks techniques for recognition of Farsi handwritten digits , 2020, The Journal of Supercomputing.

[30]  Samaher Al-Janabi,et al.  A new method for prediction of air pollution based on intelligent computation , 2020, Soft Comput..

[31]  Ghazanfar Latif,et al.  Deep Convolutional Neural Network for Recognition of Unified Multi-Language Handwritten Numerals , 2018, 2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR).

[32]  Andrew Zisserman,et al.  Deep Structured Output Learning for Unconstrained Text Recognition , 2014, ICLR.

[33]  N. Shobha Rani,et al.  Deep Learning Network Architecture based Kannada Handwritten Character Recognition , 2020, 2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA).

[34]  Kalpdrum Passi,et al.  Real Time Static Gesture Detection Using Deep Learning , 2019, BDA.

[35]  Jon Hoffman.  Cramnet: Layer-wise Deep Neural Network Compression with Knowledge Transfer from a Teacher Network , 2019, ArXiv.

[36]  Cheng-Fa Tsai,et al.  Enhancement of Deep Learning in Image Classification Performance Using Xception with the Swish Activation Function for Colorectal Polyp Preliminary Screening , 2019 .

[37]  Vahid Mohammadi Safarzadeh,et al.  Offline Persian Handwriting Recognition with CNN and RNN-CTC , 2020, 2020 25th International Computer Conference, Computer Society of Iran (CSICC).

[38]  Yunhao Liu,et al.  Face Recognition Method Based on Convolutional Neural Network , 2019, CSPS.

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