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 176–200 of 1209 papers

TitleStatusHype
ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic RulesCode1
A Multiplexed Network for End-to-End, Multilingual OCRCode1
DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point PredictionCode1
DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document UnderstandingCode1
DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document UnderstandingCode1
DocScanner: Robust Document Image Rectification with Progressive LearningCode1
Easter2.0: Improving convolutional models for handwritten text recognitionCode1
Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical DocumentsCode1
Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)Code1
Digitizing Historical Balance Sheet Data: A Practitioner's GuideCode1
Detection of Furigana Text in ImagesCode1
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision ResearchCode1
DiT: Self-supervised Pre-training for Document Image TransformerCode1
DE-GAN: A Conditional Generative Adversarial Network for Document EnhancementCode1
One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP TasksCode1
Fully Unsupervised Diversity Denoising with Convolutional Variational AutoencodersCode1
Data Generation for Post-OCR correction of Cyrillic handwritingCode1
Operationalizing a National Digital Library: The Case for a Norwegian Transformer ModelCode1
CORU: Comprehensive Post-OCR Parsing and Receipt Understanding DatasetCode1
Deep Relational Reasoning Graph Network for Arbitrary Shape Text DetectionCode1
Combining Morphological and Histogram based Text Line Segmentation in the OCR ContextCode1
A Deep Learning Approach to Geographical Candidate Selection through Toponym MatchingCode1
Post-OCR Document Correction with large Ensembles of Character Sequence-to-Sequence ModelsCode1
A Comprehensive Gold Standard and Benchmark for Comics Text Detection and RecognitionCode1
Confidence-aware Non-repetitive Multimodal Transformers for TextCapsCode1
Show:102550
← PrevPage 8 of 49Next →
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