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 101–150 of 1209 papers

TitleStatusHype
LAMBERT: Layout-Aware (Language) Modeling for information extractionCode1
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image ClassificationCode1
Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text ImagesCode1
An Unsupervised method for OCR Post-Correction and Spelling Normalisation for FinnishCode1
Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the WildCode1
DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point PredictionCode1
Indian Licence Plate Dataset in the wildCode1
DocParser: End-to-end OCR-free Information Extraction from Visually Rich DocumentsCode1
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
Improving accuracy and speeding up Document Image Classification through parallel systemsCode1
DocTr: Document Image Transformer for Geometric Unwarping and Illumination CorrectionCode1
NAT: Noise-Aware Training for Robust Neural Sequence LabelingCode1
Document Dewarping with Control PointsCode1
Intrinsic Decomposition of Document Images In-the-WildCode1
Confidence-aware Non-repetitive Multimodal Transformers for TextCapsCode1
Implicit Feature Alignment: Learn to Convert Text Recognizer to Text SpotterCode1
Iranis: A Large-scale Dataset of Farsi License Plate CharactersCode1
An Empirical Study of Scaling Law for OCRCode1
Deep Relational Reasoning Graph Network for Arbitrary Shape Text DetectionCode1
OCR-IDL: OCR Annotations for Industry Document Library DatasetCode1
OCR Post Correction for Endangered Language TextsCode1
Combining Morphological and Histogram based Text Line Segmentation in the OCR ContextCode1
DSG: An End-to-End Document Structure GeneratorCode1
CORU: Comprehensive Post-OCR Parsing and Receipt Understanding DatasetCode1
MathReader : Text-to-Speech for Mathematical DocumentsCode1
HAPI: A Large-scale Longitudinal Dataset of Commercial ML API PredictionsCode1
ClusterTabNet: Supervised clustering method for table detection and table structure recognitionCode1
Hespi: A pipeline for automatically detecting information from hebarium specimen sheetsCode1
Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural NetworksCode1
An Automatic Approach for Generating Rich, Linked Geo-Metadata from Historical Map ImagesCode1
CLEval: Character-Level Evaluation for Text Detection and Recognition TasksCode1
hmBERT: Historical Multilingual Language Models for Named Entity RecognitionCode1
ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper PagesCode1
Graph Neural Networks and Representation Embedding for Table Extraction in PDF DocumentsCode1
German Parliamentary Corpus (GerParCor)Code1
ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic RulesCode1
AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited TranscriptionsCode1
CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing ModelsCode1
Image-based table recognition: data, model, and evaluationCode1
Fused Text Recogniser and Deep Embeddings Improve Word Recognition and RetrievalCode1
From Text to Pixel: Advancing Long-Context Understanding in MLLMsCode1
FuseCap: Leveraging Large Language Models for Enriched Fused Image CaptionsCode1
Generating Synthetic Handwritten Historical Documents With OCR Constrained GANsCode1
Attack of the Tails: Yes, You Really Can Backdoor Federated LearningCode1
Geometry Restoration and Dewarping of Camera-Captured Document ImagesCode1
FlowLearn: Evaluating Large Vision-Language Models on Flowchart UnderstandingCode1
A Two-Step Approach for Automatic OCR Post-CorrectionCode1
A Multiplexed Network for End-to-End, Multilingual OCRCode1
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from DocumentsCode1
Show:102550
← PrevPage 3 of 25Next →
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