{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bengali-handwritten-character-classification","title":"Bengali Handwritten Character Classification using Transfer Learning on Deep Convolutional Neural Network","arxiv_id":"1902.11133","date":"2019-02-25","proceeding":null,"authors":["Swagato Chatterjee","Rwik Kumar Dutta","Debayan Ganguly","Kingshuk Chatterjee","Sudipta Roy"],"abstract":"In this paper, we propose a solution which uses state-of-the-art techniques\nin Deep Learning to tackle the problem of Bengali Handwritten Character\nRecognition ( HCR ). Our method uses lesser iterations to train than most other\ncomparable methods. We employ Transfer Learning on ResNet 50, a\nstate-of-the-art deep Convolutional Neural Network Model, pretrained on\nImageNet dataset. We also use other techniques like a modified version of One\nCycle Policy, varying the input image sizes etc. to ensure that our training\noccurs fast. We use the BanglaLekha-Isolated Dataset for evaluation of our\ntechnique which consists of 84 classes (50 Basic, 10 Numerals and 24 Compound\nCharacters). We are able to achieve 96.12% accuracy in just 47 epochs on\nBanglaLekha-Isolated dataset. When comparing our method with that of other\nresearchers, considering number of classes and without using Ensemble Learning,\nthe proposed solution achieves state of the art result for Handwritten Bengali\nCharacter Recognition. Code and weight files are available at\nhttps://github.com/swagato-c/bangla-hwcr-present.","url_abs":"http://arxiv.org/abs/1902.11133v1","url_pdf":"http://arxiv.org/pdf/1902.11133v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bengali-handwritten-character-classification","repo_url":"https://github.com/swagato-c/bangla-hwcr-present","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"ensemble-learning","task_name":"Ensemble Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}