SOTAVerified

Optical Character Recognition (OCR)

Optical Character Recognition or Optical Character Reader (OCR) is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo (for example the text on signs and billboards in a landscape photo, license plates in cars...) or from subtitle text superimposed on an image (for example: from a television broadcast)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1101–1150 of 1209 papers

TitleStatusHype
GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document UnderstandingCode0
Gated Recurrent Convolution Neural Network for OCRCode0
SPAN: a Simple Predict & Align Network for Handwritten Paragraph RecognitionCode0
Spanish TrOCR: Leveraging Transfer Learning for Language AdaptationCode0
Mobile User Interface Element Detection Via Adaptively Prompt TuningCode0
DDI-100: Dataset for Text Detection and RecognitionCode0
From Videos to URLs: A Multi-Browser Guide To Extract User's Behavior with Optical Character RecognitionCode0
AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational ApplicationsCode0
A Tool for Facilitating OCR Postediting in Historical DocumentsCode0
ChemScraper: Leveraging PDF Graphics Instructions for Molecular Diagram ParsingCode0
From the Paft to the Fiiture: a Fully Automatic NMT and Word Embeddings Method for OCR Post-CorrectionCode0
MRZ code extraction from visa and passport documents using convolutional neural networksCode0
Word-Level Alignment of Paper Documents with their Electronic Full-Text CounterpartsCode0
ChemGrapher: Optical Graph Recognition of Chemical Compounds by Deep LearningCode0
A template-independent approach for information extraction in real estate documentsCode0
Multi-Granularity Prediction for Scene Text RecognitionCode0
PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto LanguageCode0
A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling CheckCode0
State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source EnginesCode0
FINN-L: Library Extensions and Design Trade-off Analysis for Variable Precision LSTM Networks on FPGAsCode0
TF-LM: TensorFlow-based Language Modeling ToolkitCode0
Multimodal deep networks for text and image-based document classificationCode0
FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text SpottingCode0
FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo EmbeddingsCode0
Multi-modal Page Stream Segmentation with Convolutional Neural NetworksCode0
Quantifying Character Similarity with Vision TransformersCode0
Low-Resource Language Processing: An OCR-Driven Summarization and Translation PipelineCode0
Are VLMs Really BlindCode0
DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense UnderstandingCode0
MultiOCR-QA: Dataset for Evaluating Robustness of LLMs in Question Answering on Multilingual OCR TextsCode0
Multi-Page Document Visual Question Answering using Self-Attention Scoring MechanismCode0
STEP -- Towards Structured Scene-Text SpottingCode0
Reading Between the Mud: A Challenging Motorcycle Racer Number DatasetCode0
AON: Towards Arbitrarily-Oriented Text RecognitionCode0
Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language modelsCode0
Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language ModelsCode0
Enhancing Assamese NLP Capabilities: Introducing a Centralized Dataset RepositoryCode0
STN-OCR: A single Neural Network for Text Detection and Text RecognitionCode0
Character decomposition to resolve class imbalance problem in Hangul OCRCode0
Upcycle Your OCR: Reusing OCRs for Post-OCR Text Correction in Romanised SanskritCode0
NASS-AI: Towards Digitization of Parliamentary Bills using Document Level Embedding and Bidirectional Long Short-Term MemoryCode0
End-to-End Optical Character Recognition for Bengali Handwritten WordsCode0
Data-Driven Spelling Correction using Weighted Finite-State MethodsCode0
Data Centric Domain Adaptation for Historical Text with OCR ErrorsCode0
End-to-End Interpretation of the French Street Name Signs DatasetCode0
Empirical Error Modeling Improves Robustness of Noisy Neural Sequence LabelingCode0
Stroke extraction for offline handwritten mathematical expression recognitionCode0
StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-trainingCode0
Noisy Parallel Data AlignmentCode0
Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal CluesCode0
Show:102550
← PrevPage 23 of 25Next →
All datasetsBenchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical StudyVideoDB's OCR Benchmark Public CollectionFSNS - TestI2L-140KSUTim2latex-100k

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DTrOCRAccuracy (%)89.6—Unverified
2DTrOCR 105MAccuracy (%)89.6—Unverified
3MaskOCR-LAccuracy (%)82.6—Unverified
4TransOCRAccuracy (%)72.8—Unverified
5SRNAccuracy (%)65—Unverified
6MORANAccuracy (%)64.3—Unverified
7SEEDAccuracy (%)61.2—Unverified
#ModelMetricClaimedVerifiedStatus
1GPT-4oAverage Accuracy76.22—Unverified
2Gemini-1.5 ProAverage Accuracy76.13—Unverified
3Claude-3 SonnetAverage Accuracy67.71—Unverified
4RapidOCRAverage Accuracy56.98—Unverified
5EasyOCRAverage Accuracy49.3—Unverified
#ModelMetricClaimedVerifiedStatus
1STREETSequence error27.54—Unverified
2SEESequence error22—Unverified
3AttentionOCR_Inception-resnet-v2_LocationSequence error15.8—Unverified
#ModelMetricClaimedVerifiedStatus
1I2L-NOPOOLBLEU89.09—Unverified
2I2L-STRIPSBLEU89—Unverified
#ModelMetricClaimedVerifiedStatus
1TesseractCharacter Error Rate (CER)0.08—Unverified
2EasyOCRCharacter Error Rate (CER)0.07—Unverified
#ModelMetricClaimedVerifiedStatus
1I2L-STRIPSBLEU88.86—Unverified