Isolated Bangla Handwritten Character Classification using Transfer Learning

• URL: http://arxiv.org/abs/2509.03061v1
• Date: Wed, 03 Sep 2025 06:46:14 GMT
• Title: Isolated Bangla Handwritten Character Classification using Transfer Learning
• Authors: Abdul Karim, S M Rafiuddin, Jahidul Islam Razin, Tahira Alam,
• Abstract summary: This paper uses transfer learning to classify the basic, distinct, as well as compound Bangla handwritten characters.<n>Deep Neural Network techniques are applied to generate an end-to-end classification of all possible standard formations of handwritten characters.<n>The model achieved 99.82% accuracy on training data and 99.46% accuracy on test data.
• Score: 0.7299729677753102
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bangla language consists of fifty distinct characters and many compound characters. Several notable studies have been performed to recognize Bangla characters, both handwritten and optical. Our approach uses transfer learning to classify the basic, distinct, as well as compound Bangla handwritten characters while avoiding the vanishing gradient problem. Deep Neural Network techniques such as 3D Convolutional Neural Network (3DCNN), Residual Neural Network (ResNet), and MobileNet are applied to generate an end-to-end classification of all possible standard formations of handwritten characters in the Bangla language. The Bangla Lekha Isolated dataset, which contains 166,105 Bangla character image samples categorized into 84 distinct classes, is used for this classification model. The model achieved 99.82% accuracy on training data and 99.46% accuracy on test data. Comparisons with various state-of-the-art benchmarks of Bangla handwritten character classification show that the proposed model achieves better accuracy in classifying the data.

Related papers

• Performance Analysis of Few-Shot Learning Approaches for Bangla Handwritten Character and Digit Recognition [0.9895793818721335]
  This study investigates the performance of few-shot learning approaches in recognizing Bangla handwritten characters and numerals.<n>We introduce SynergiProtoNet, a hybrid network designed to improve the recognition accuracy of handwritten characters and digits.
  arXiv  Detail & Related papers  (2025-05-31T08:03:10Z)
• Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing [71.29488677105127]
  Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. We propose a contrastive learning-based STR framework by leveraging synthetic and real unlabeled data without any human cost. Our method achieves SOTA performance (94.7% and 70.9% average accuracy on common benchmarks and Union14M-Benchmark.
  arXiv  Detail & Related papers  (2024-11-23T15:24:47Z)
• Bukva: Russian Sign Language Alphabet [75.42794328290088]
  This paper investigates the recognition of the Russian fingerspelling alphabet, also known as the Russian Sign Language (RSL) dactyl. Dactyl is a component of sign languages where distinct hand movements represent individual letters of a written language. We provide Bukva, the first full-fledged open-source video dataset for RSL dactyl recognition.
  arXiv  Detail & Related papers  (2024-10-11T09:59:48Z)
• Language Models for Text Classification: Is In-Context Learning Enough? [54.869097980761595]
  Recent foundational language models have shown state-of-the-art performance in many NLP tasks in zero- and few-shot settings. An advantage of these models over more standard approaches is the ability to understand instructions written in natural language (prompts) This makes them suitable for addressing text classification problems for domains with limited amounts of annotated instances.
  arXiv  Detail & Related papers  (2024-03-26T12:47:39Z)
• BanglaNet: Bangla Handwritten Character Recognition using Ensembling of Convolutional Neural Network [0.0]
  This paper presents a classification model based on the ensembling of several Convolutional Neural Networks (CNN) Three different models based on the idea of state-of-the-art CNN models like Inception, ResNet, and DenseNet have been trained with both augmented and non-augmented inputs. Rigorous experimentation on three benchmark Bangla handwritten characters datasets, namely, CMATERdb, BanglaLekha-Isolated, and Ekush has exhibited significant recognition accuracies.
  arXiv  Detail & Related papers  (2024-01-16T01:08:19Z)
• BN-DRISHTI: Bangla Document Recognition through Instance-level Segmentation of Handwritten Text Images [0.0]
  This paper introduces a deep learning-based object detection framework (YOLO) with Hough and Affine transformation for skew correction. We present an extended version of the BN-HTRd dataset comprising 786 full-page handwritten Bangla document images. Evaluation on the test portion of our dataset resulted in an F-score of 99.97% for line and 98% for word segmentation.
  arXiv  Detail & Related papers  (2023-05-31T04:08:57Z)
• On Evaluation of Bangla Word Analogies [0.8658596218544772]
  This paper presents a high-quality dataset for evaluating the quality of Bangla word embeddings. Despite being the 7th most-spoken language in the world, Bangla is a low-resource language and popular NLP models fail to perform well.
  arXiv  Detail & Related papers  (2023-04-10T14:27:35Z)
• Bengali Handwritten Grapheme Classification: Deep Learning Approach [0.0]
  We participate in a Kaggle competition citek_link where the challenge is to classify three constituent elements of a Bengali grapheme in the image. We explore the performances of some existing neural network models such as Multi-Layer Perceptron (MLP) and state of the art ResNet50. We propose our own convolution neural network (CNN) model for Bengali grapheme classification with validation root accuracy 95.32%, vowel accuracy 98.61%, and consonant accuracy 98.76%.
  arXiv  Detail & Related papers  (2021-11-16T06:14:59Z)
• Sentiment analysis in tweets: an assessment study from classical to modern text representation models [59.107260266206445]
  Short texts published on Twitter have earned significant attention as a rich source of information. Their inherent characteristics, such as the informal, and noisy linguistic style, remain challenging to many natural language processing (NLP) tasks. This study fulfils an assessment of existing language models in distinguishing the sentiment expressed in tweets by using a rich collection of 22 datasets.
  arXiv  Detail & Related papers  (2021-05-29T21:05:28Z)
• Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification [52.69730591919885]
  We present a semi-supervised adversarial training process that minimizes the maximal loss for label-preserving input perturbations. We observe significant gains in effectiveness on document and intent classification for a diverse set of languages.
  arXiv  Detail & Related papers  (2020-07-29T19:38:35Z)
• Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild [103.51604161298512]
  We propose an adversarial learning framework for the generation and recognition of multiple characters in an image. Our framework can be integrated into recent recognition methods to achieve new state-of-the-art recognition accuracy.
  arXiv  Detail & Related papers  (2020-01-13T12:41:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.