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 876–900 of 1209 papers

TitleStatusHype
MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding—0
MMR: Evaluating Reading Ability of Large Multimodal Models—0
Morphological annotation of Old and Middle Hungarian corpora—0
mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding—0
mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding—0
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding—0
MT^3: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning—0
MultiCoNER v2: a Large Multilingual dataset for Fine-grained and Noisy Named Entity Recognition—0
MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation—0
Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition—0
Multi-Input Attention for Unsupervised OCR Correction—0
Multikernel activation functions: formulation and a case study—0
Multilingual Named Entity Recognition for Medieval Charters Using Stacked Embeddings and Bert-based Models.—0
Multimodal Sentiment Analysis: Perceived vs Induced Sentiments—0
Multimodal Short Video Rumor Detection System Based on Contrastive Learning—0
Multimodal Transformer for Comics Text-Cloze—0
Multi-modular domain-tailored OCR post-correction—0
Multiple-Question Multiple-Answer Text-VQA—0
Multistage Curvilinear Coordinate Transform Based Document Image Dewarping using a Novel Quality Estimator—0
Multistep Automated Data Labelling Procedure (MADLaP) for Thyroid Nodules on Ultrasound: An Artificial Intelligence Approach for Automating Image Annotation—0
Multi-Task Learning for Improved Discriminative Training in SMT—0
Named Entity Recognition and Correction in OCRized Corpora (D\'etection et correction automatique d'entit\'es nomm\'ees dans des corpus OCRis\'es) [in French]—0
Named Entity Recognition in Historic Legal Text: A Transformer and State Machine Ensemble Method—0
Named Entity Recognition in the Legal Domain using a Pointer Generator Network—0
NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts—0
Show:102550
← PrevPage 36 of 49Next →
All datasetsBenchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical StudyVideoDB's OCR Benchmark Public CollectionFSNS - TestI2L-140KSUTim2latex-100k

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DTrOCR 105MAccuracy (%)89.6—Unverified
2DTrOCRAccuracy (%)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