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 1–50 of 1209 papers

TitleStatusHype
DeQA-Doc: Adapting DeQA-Score to Document Image Quality AssessmentCode0
VisionThink: Smart and Efficient Vision Language Model via Reinforcement LearningCode0
Seeing the Signs: A Survey of Edge-Deployable OCR Models for Billboard Visibility Analysis—0
A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends—0
Orchestrator-Agent Trust: A Modular Agentic AI Visual Classification System with Trust-Aware Orchestration and RAG-Based ReasoningCode0
Design and Implementation of an OCR-Powered Pipeline for Table Extraction from Invoices—0
TextPixs: Glyph-Conditioned Diffusion with Character-Aware Attention and OCR-Guided Supervision—0
PaddleOCR 3.0 Technical ReportCode0
Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document RestorationCode2
Logios : An open source Greek Polytonic Optical Character Recognition system—0
DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document ImagesCode0
Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation—0
Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models—0
Unfolding the Past: A Comprehensive Deep Learning Approach to Analyzing Incunabula Pages—0
An accurate and revised version of optical character recognition-based speech synthesis using LabVIEW—0
FormGym: Doing Paperwork with Agents—0
AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video UnderstandingCode0
Efficient Medical VIE via Reinforcement Learning—0
MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation—0
Intelligent Automation for FDI Facilitation: Optimizing Tariff Exemption Processes with OCR And Large Language Models—0
Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers—0
Institutional Books 1.0: A 242B token dataset from Harvard Library's collections, refined for accuracy and usabilityCode2
Reading in the Dark with Foveated Event Vision—0
The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing—0
A Survey on Vietnamese Document Analysis and Recognition: Challenges and Future Directions—0
MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K CategoriesCode2
Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document ParsingCode0
SARD: A Large-Scale Synthetic Arabic OCR Dataset for Book-Style Text Recognition—0
Predicting the Past: Estimating Historical Appraisals with OCR and Machine LearningCode0
Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression RecognitionCode1
ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering—0
TextSR: Diffusion Super-Resolution with Multilingual OCR Guidance—0
Synthetic Document Question Answering in HungarianCode0
VidText: Towards Comprehensive Evaluation for Video Text UnderstandingCode1
ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained KnowledgeCode1
E2E Process Automation Leveraging Generative AI and IDP-Based Automation Agent: A Case Study on Corporate Expense Processing—0
Unifying Multimodal Large Language Model Capabilities and Modalities via Model MergingCode1
On Path to Multimodal Historical Reasoning: HistBench and HistAgentCode4
MT^3: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning—0
TextDiffuser-RL: Efficient and Robust Text Layout Optimization for High-Fidelity Text-to-Image Synthesis—0
ReadBench: Measuring the Dense Text Visual Reading Ability of Vision-Language ModelsCode1
Words as Geometric Features: Estimating Homography using Optical Character Recognition as Compressed Image Representation—0
TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis—0
One RL to See Them All: Visual Triple Unified Reinforcement Learning—0
TokBench: Evaluating Your Visual Tokenizer before Visual Generation—0
OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image ReasoningCode0
ARB: A Comprehensive Arabic Multimodal Reasoning BenchmarkCode1
What Media Frames Reveal About Stance: A Dataset and Study about Memes in Climate Change Discourse—0
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads—0
Every Pixel Tells a Story: End-to-End Urdu Newspaper OCR—0
Show:102550
← PrevPage 1 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