首页/论文/1908.08674

arXiv 1908.086742019-08-23cs.CVcs.CLcs.LG

A BLSTM Network for Printed Bengali OCR System with High Accuracy

Society for Natural Language Technology Research（自然语言技术研究协会）；Techno India University（Techno印度大学）

Debabrata Paul, Bidyut Baran Chaudhuri

备注：: 6 pages, 6 figures, This OCR system is available online at https://banglaocr.nltr.org

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

This paper presents a printed Bengali and English text OCR system developed by us using a single hidden BLSTM-CTC architecture having 128 units. Here, we did not use any peephole connection and dropout in the BLSTM, which helped us in getting better accuracy. This architecture was trained by 47,720 text lines that include English words also. When tested over 20 different Bengali fonts, it has produced character level accuracy of 99.32% and word level accuracy of 96.65%. A good Indic multi script OCR system is also developed by Google. It sometimes recognizes a character of Bengali into the same character of a non-Bengali script, especially Assamese, which has no distinction from Bengali, except for a few characters. For example, Bengali character for 'RA' is sometimes recognized as that of Assamese, mainly in conjunct consonant forms. Our OCR is free from such errors. This OCR system is available online at https://banglaocr.nltr.org

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

bbOCR：面向孟加拉语文档的开源多领域OCR流水线

bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali Documents

Brac University（布拉卡大学）；Apsis Solutions Limited（阿普西斯解决方案有限公司）

针对孟加拉语等低资源语言OCR工具与数据集匮乏的问题，研究团队提出开源多领域OCR系统bbOCR，依托新型识别模型与合成数据集实现文档结构化数字化，性能优于现有同类系统。

2023-08-22cs.CV

BanglaWild：面向OCR和视觉-语言模型的野外孟加拉语场景文本识别基准

BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models

研究发现现有孟加拉语场景文本识别基准的不足，推出含2535张图像的BanglaWild基准，评估15个VLMs和3个OCR系统等，揭示视觉误识别为主要错误来源等结论，代码数据将公开。

2026-08-05cs.CLcs.CV

Bengali Handwritten Digit Recognition using CNN with Explainable AI

Ahsanullah University of Science and Technology（阿萨努拉科技大学）；Brac University（布拉克大学）

Handwritten character recognition is a hot topic for research nowadays. If we can convert a handwritten piece of paper into a text-searchable document using the Optical Character Recognition (OCR) technique, we can easily understand the content and do not need to read the handwritten document. OCR in the English language is very common, but in the Bengali language, it is very hard to find a good quality OCR application. If we can merge machine learning and deep learning with OCR, it could be a huge contribution to this field. Various researchers have proposed a number of strategies for recogni…

2022-12-23cs.CVcs.LG

End-to-End Optical Character Recognition for Bengali Handwritten Words

Bangladesh University of Business & Technology（孟加拉商业与技术大学）；King Abdulaziz University（阿卜杜勒阿齐兹国王大学）

Optical character recognition (OCR) is a process of converting analogue documents into digital using document images. Currently, many commercial and non-commercial OCR systems exist for both handwritten and printed copies for different languages. Despite this, very few works are available in case of recognising Bengali words. Among them, most of the works focused on OCR of printed Bengali characters. This paper introduces an end-to-end OCR system for Bengali language. The proposed architecture implements an end to end strategy that recognises handwritten Bengali words from handwritten word ima…

2021-05-09cs.CVcs.IR

通过专用模型和先进技术增强孟加拉语OCR以应对多种文档类型

Enhancement of Bengali OCR by Specialized Models and Advanced Techniques for Diverse Document Types

Apurba Technologies（阿普尔巴科技公司）；The University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）

该研究提出一种先进的孟加拉语OCR系统，通过专用分词模型和多种技术，实现多类型文档的准确文本提取与分析。

2024-02-07cs.AIcs.CVcs.LG

BLPnet: A new DNN model and Bengali OCR engine for Automatic License Plate Recognition

Military Institute of Science and Technology（军事科学技术研究院）

The development of the Automatic License Plate Recognition (ALPR) system has received much attention for the English license plate. However, despite being the sixth largest population around the world, no significant progress can be tracked in the Bengali language countries or states for the ALPR system addressing their more alarming traffic management with inadequate road-safety measures. This paper reports a computationally efficient and reasonably accurate Automatic License Plate Recognition (ALPR) system for Bengali characters with a new end-to-end DNN model that we call Bengali License Pl…

2022-02-18cs.AIcs.CVcs.NE

更多相关论文收起更多论文

基于Detectron2的孟加拉语文档布局分析

Bengali Document Layout Analysis with Detectron2

Shahjalal University of Science and Technology（沙赫贾拉尔科技大学）

针对孟加拉语DLA数据集匮乏、相关模型准确率不足的问题，研究人员基于Detectron2库的Mask R-CNN系列模型，在BaDLAD数据集上验证了不同变体及PubLayNet预训练权重的效果，拓展了该类模型在孟加拉语文档场景的适用性。

2023-08-26cs.CVcs.LG

孟加拉语文档布局分析——一种基于 YOLOv8 的集成方法

Bengali Document Layout Analysis -- A YOLOV8 Based Ensembling Approach

针对孟加拉语文档布局分析难题，本文提出基于 YOLOv8 的两阶段集成与后处理方法，结合数据增强和全量微调，在 BaDLAD 上优于单一基础模型。

2025-09-29cs.CVcs.LG

Topographic Feature Extraction for Bengali and Hindi Character Images

Indian Institute of Technology, Kharagpur（印度理工学院克勒格布尔分校）

Feature selection and extraction plays an important role in different classification based problems such as face recognition, signature verification, optical character recognition (OCR) etc. The performance of OCR highly depends on the proper selection and extraction of feature set. In this paper, we present novel features based on the topography of a character as visible from different viewing directions on a 2D plane. By topography of a character we mean the structural features of the strokes and their spatial relations. In this work we develop topographic features of strokes visible with re…

2011-07-14cs.CV

BaDLAD：一个大型多领域孟加拉语文档布局分析数据集

BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset

Shahjalal University of Science and Technology（沙赫贾拉尔科技大学）；BRAC University（BRAC大学）；Vanderbilt University（范德堡大学）；Rice University（莱斯大学）；RPI（伦斯勒理工学院）

针对孟加拉语DLA数据集缺失、现有规则系统鲁棒性不足的问题，该研究发布了含6个领域33695份样本、71万标注的BaDLAD数据集，并通过基准实验验证其可有效支撑孟加拉语文档数字化模型训练。

2023-05-05cs.CV

二十年来的孟加拉语手写数字识别：一项综述

Two Decades of Bengali Handwritten Digit Recognition: A Survey

Islamic University of Technology（伊斯兰科技大学）

本文综述二十年来离线孟加拉语手写数字识别的数据集、方法、挑战与现实应用，为后续研究提供参考。

2022-09-25cs.CV

Handwritten Arabic Numeral Recognition using a Multi Layer Perceptron

Techno India（泰克诺印度学院）；Jadavpur University（贾达普大学）

Handwritten numeral recognition is in general a benchmark problem of Pattern Recognition and Artificial Intelligence. Compared to the problem of printed numeral recognition, the problem of handwritten numeral recognition is compounded due to variations in shapes and sizes of handwritten characters. Considering all these, the problem of handwritten numeral recognition is addressed under the present work in respect to handwritten Arabic numerals. Arabic is spoken throughout the Arab World and the fifth most popular language in the world slightly before Portuguese and Bengali. For the present wor…

2010-03-09cs.CV

A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes

Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）；Apurba Technologies Inc.（阿普尔巴技术公司）；Independent University, Bangladesh（孟加拉国独立大学）

Latin has historically led the state-of-the-art in handwritten optical character recognition (OCR) research. Adapting existing systems from Latin to alpha-syllabary languages is particularly challenging due to a sharp contrast between their orthographies. The segmentation of graphical constituents corresponding to characters becomes significantly hard due to a cursive writing system and frequent use of diacritics in the alpha-syllabary family of languages. We propose a labeling scheme based on graphemes (linguistic segments of word formation) that makes segmentation in-side alpha-syllabary wor…

2021-01-13cs.CLcs.CVcs.LG

Extraction of Line Word Character Segments Directly from Run Length Compressed Printed Text Documents

University of Mysore（迈索尔大学）；Indian Statistical Institute（印度统计研究所）

Segmentation of a text-document into lines, words and characters, which is considered to be the crucial pre-processing stage in Optical Character Recognition (OCR) is traditionally carried out on uncompressed documents, although most of the documents in real life are available in compressed form, for the reasons such as transmission and storage efficiency. However, this implies that the compressed image should be decompressed, which indents additional computing resources. This limitation has motivated us to take up research in document image analysis using compressed documents. In this paper, …

2014-03-30cs.CV

Word Searching in Scene Image and Video Frame in Multi-Script Scenario using Dynamic Shape Coding

Indian Institute of Technology Roorkee（印度理工学院鲁尔基分校）；Institute of Engineering & Management（工程与管理学院）；Indian Statistical Institute（印度统计研究所）

Retrieval of text information from natural scene images and video frames is a challenging task due to its inherent problems like complex character shapes, low resolution, background noise, etc. Available OCR systems often fail to retrieve such information in scene/video frames. Keyword spotting, an alternative way to retrieve information, performs efficient text searching in such scenarios. However, current word spotting techniques in scene/video images are script-specific and they are mainly developed for Latin script. This paper presents a novel word spotting framework using dynamic shape co…

2018-07-30cs.CVcs.IR

用于多模态情感解释的令牌-区域引导交叉注意力融合

Token-Region Guided Cross-Attention Fusion for Multimodal Affect Interpretation

针对孟加拉语模因政治意图检测难题，引入多模态交叉注意力融合框架，利用视觉语言模型提取文本，经跨模态多头注意力机制合成特征，还整合政治词汇表，实验表明该方法显著优于基线，Macro-F1达0.94，有效实现文本语义基于视觉证据。

2026-07-28cs.AIcs.CV