Tasks/OCR & Document Understanding
OCR & Document Understanding
লিখন শনাক্তকরণ ও নথি বিশ্লেষণRecognising printed and handwritten Bangla text at word, line, document and scene level, and extracting information from document images. Isolated character and digit classification is out of scope — see TODO-data.md.
0 datasets·44 papers
| Dataset | Size | License | Year ▾ | Source paper | Link |
|---|---|---|---|---|---|
| No datasets curated for this task yet — add one via PR. | |||||
No leaderboard curated yet — contribute via PR.
2026BornoDrishti: Leveraging Vision Encoders and Domain-Adaptive Learning for Bangla OCR on Diverse DocumentsIslam et al.EACL2026BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language ModelsShiper et al.arXiv2026Asegmentation based optical character recognition system for Bangla printed textMahbub et al.TELKOMNIKA (Telecommunication Computing Electronics and Control)2025GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only TransformerHasan et al.EMNLP2025A CNN-Transformer Approach for Bengali Handwritten Word RecognitionSaha et al.Journal of The Institution of Engineers (India) Series B2025A hybrid approach to Bangla handwritten OCR: combining YOLO and an advanced CNNMaung et al.Discover Artificial Intelligence2025Bilingual Bangla OCR for Rural Empowerment: Detecting Handwritten Queries and Agricultural AssistanceAlam et al.IEEE Open Journal of the Computer Society2025Multilingual scene text recognition: A faster R-CNN approach for Bengali and English scriptsDutta et al.Expert Systems with Applications2024Optical Text Recognition in Nepali and Bengali: A Transformer-based ApproachHasan et al.arXiv2024Enhancement of Bengali OCR by Specialized Models and Advanced Techniques for Diverse Document TypesRabby et al.arXiv2024Bangla handwritten word recognition using YOLO V5Hossain et al.Bulletin of Electrical Engineering and Informatics2024Development of a Lightweight Model for Handwritten Dataset Recognition: Bangladeshi City Names in Bangla ScriptTusher et al.Computers, materials & continua/Computers, materials & continua (Print)2023Gold Standard Bangla OCR Dataset: An In-Depth Look at Data Preprocessing and Annotation ProcessesAli et al.EMNLP2023SynthNID: Synthetic Data to Improve End-to-end Bangla Document Key Information ExtractionMonsur et al.BLP @ EMNLP2023bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali DocumentsZulkarnain et al.arXiv2023A multifaceted evaluation of representation of graphemes for practically effective Bangla OCRRoy et al.International Journal on Document Analysis and Recognition (IJDAR)2023BWordDeepNet: a novel deep learning architecture for the recognition of online handwritten Bangla wordsBhattacharyya et al.Multimedia Tools and Applications2023Newspaper text recognition in Bengali script using support vector machineGhoshMultimedia Tools and Applications2022A Deep OCR for Degraded Bangla DocumentsChaudhury et al.ACM Transactions on Asian and Low-Resource Language Information Processing2022Character spotting and autonomous tagging: offline handwriting recognition for Bangla, Korean and other alphabetic scriptsMajid et al.International Journal on Document Analysis and Recognition (IJDAR)2022BN-HTRd: A Benchmark Dataset for Document Level Offline Bangla Handwritten Text Recognition (HTR) and Line SegmentationRahman et al.arXiv2021End-to-End Optical Character Recognition for Bengali Handwritten WordsSafir et al.arXiv2021BYANJON: A Ground Truth Preparation System for Online Handwritten Bangla DocumentsSen et al.ACM Transactions on Asian and Low-Resource Language Information Processing2021Handwritten Bangla city name word recognition using CNN-based transfer learning and FCNPramanik et al.Neural Computing and Applications2020Word Segmentation from Unconstrained Handwritten Bangla Document Images using Distance TransformSingh et al.arXiv2020An image database of handwritten Bangla words with automatic benchmarking facilities for character segmentation algorithmsMalakar et al.Neural Computing and Applications2020Bangla Optical Character Recognition and Text-to-Speech Conversion using Raspberry PiRajbongshi et al.International Journal of Advanced Computer Science and Applications2020NN-based analytic approach to symbol level recognition for degraded Bengali printed documentsMukherjee et al.Sadhana2020Segmentation‐based recognition system for handwritten Bangla and Devanagari words using conventional classification and transfer learningPramanik et al.IET Image Processing2019A BLSTM Network for Printed Bengali OCR System with High AccuracyPaul et al.arXiv2019Automatic rectification of warped Bangla document imagesGarai et al.IET Image Processing2019Online Bangla handwritten word recognition using HMM and language modelSen et al.Neural Computing and Applications2019RNN based online handwritten word recognition in Devanagari and Bengali scripts using horizontal zoningGhosh et al.Pattern Recognition2019Segmentation-free word spotting in historical Bangla handwritten document using Wave Kernel SignatureDas et al.Pattern Analysis and Applications2018A novel segmentation technique for online handwritten Bangla wordsSen et al.Pattern Recognition Letters2018Off-line Bangla handwritten word recognition: a holistic approachBhowmik et al.Neural Computing and Applications2017Benchmark databases of handwritten Bangla-Roman and Devanagari-Roman mixed-script document imagesSingh et al.Multimedia Tools and Applications2017Cleaning of Online Bangla Free-form Handwritten TextBhattacharya et al.ACM Transactions on Asian and Low-Resource Language Information Processing2014Bangla Text Recognition from Video Sequence: A New FocusBhowmick et al.arXiv2013A survey on optical character recognition for Bangla and Devanagari scriptsBag et al.Sadhana2012Segmentation of Offline Handwritten Bengali ScriptBasu et al.arXiv2011CMATERdb1: a database of unconstrained handwritten Bangla and Bangla–English mixed script document imageSarkar et al.International Journal on Document Analysis and Recognition (IJDAR)2010Multi-oriented Bangla and Devnagari text recognitionPal et al.Pattern Recognition1998A complete printed Bangla OCR systemChaudhuri et al.Pattern Recognition
No models catalogued for this task yet — add one via PR.