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 151–200 of 1209 papers

TitleStatusHype
AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited TranscriptionsCode1
Neural OCR Post-Hoc Correction of Historical CorporaCode1
Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural NetworksCode1
Data Generation for Post-OCR correction of Cyrillic handwritingCode1
Lexically Aware Semi-Supervised Learning for OCR Post-CorrectionCode1
Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical DocumentsCode1
ClusterTabNet: Supervised clustering method for table detection and table structure recognitionCode1
Deep Relational Reasoning Graph Network for Arbitrary Shape Text DetectionCode1
Lights, Camera, Action! A Framework to Improve NLP Accuracy over OCR documentsCode1
CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing ModelsCode1
CLEval: Character-Level Evaluation for Text Detection and Recognition TasksCode1
Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of ExpertsCode1
ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper PagesCode1
DiT: Self-supervised Pre-training for Document Image TransformerCode1
A Multiplexed Network for End-to-End, Multilingual OCRCode1
Digitizing Historical Balance Sheet Data: A Practitioner's GuideCode1
Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question AnsweringCode1
Large Scale Font Independent Urdu Text Recognition SystemCode1
bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali DocumentsCode1
DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document UnderstandingCode1
DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point PredictionCode1
DocParser: End-to-end OCR-free Information Extraction from Visually Rich DocumentsCode1
Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video EnvironmentsCode1
DocScanner: Robust Document Image Rectification with Progressive LearningCode1
LaTr: Layout-Aware Transformer for Scene-Text VQACode1
Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text ImagesCode1
Intrinsic Decomposition of Document Images In-the-WildCode1
Indian Licence Plate Dataset in the wildCode1
Iranis: A Large-scale Dataset of Farsi License Plate CharactersCode1
ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic RulesCode1
One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP TasksCode1
PM4Bench: A Parallel Multilingual Multi-Modal Multi-task Benchmark for Large Vision Language ModelCode1
Improving accuracy and speeding up Document Image Classification through parallel systemsCode1
Privacy-Aware Document Visual Question AnsweringCode1
Image-text matching for large-scale book collectionsCode1
EAST: An Efficient and Accurate Scene Text DetectorCode1
Combining Morphological and Histogram based Text Line Segmentation in the OCR ContextCode1
Rerunning OCR: A Machine Learning Approach to Quality Assessment and Enhancement PredictionCode1
Efficient OCR for Building a Diverse Digital HistoryCode1
Robust Learning for Text Classification with Multi-source Noise Simulation and Hard Example MiningCode1
A Deep Learning Approach to Geographical Candidate Selection through Toponym MatchingCode1
Image-based table recognition: data, model, and evaluationCode1
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual PromptsCode1
From Text to Pixel: Advancing Long-Context Understanding in MLLMsCode1
Exploring Cross-Image Pixel Contrast for Semantic SegmentationCode1
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from DocumentsCode1
Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth EvaluationCode1
Show, Attend and Read: A Simple and Strong Baseline for Irregular Text RecognitionCode1
Implicit Feature Alignment: Learn to Convert Text Recognizer to Text SpotterCode1
LAMBERT: Layout-Aware (Language) Modeling for information extractionCode1
Show:102550
← PrevPage 4 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