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

Showing 5175 of 1209 papers

TitleStatusHype
The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting0
Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?Code1
Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents0
LogicOCR: Do Your Large Multimodal Models Excel at Logical Reasoning on Text-Rich Images?Code1
An agentic system with reinforcement-learned subsystem improvements for parsing form-like documentsCode0
Object-Centric Representations Improve Policy Generalization in Robot Manipulation0
Low-Resource Language Processing: An OCR-Driven Summarization and Translation PipelineCode0
Towards Self-Improvement of Diffusion Models via Group Preference Optimization0
Analyzing Patterns and Influence of Advertising in Print Newspapers0
PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto LanguageCode0
A document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court0
Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late InteractionCode0
Gameplay Highlights Generation0
Development of a WAZOBIA-Named Entity Recognition System0
Arrow-Guided VLM: Enhancing Flowchart Understanding via Arrow Direction EncodingCode0
Toward Advancing License Plate Super-Resolution in Real-World Scenarios: A Dataset and BenchmarkCode0
GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing0
Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval0
ChemRxivQuest: A Curated Chemistry Question-Answer Database Extracted from ChemRxiv Preprints0
DOTA: Deformable Optimized Transformer Architecture for End-to-End Text Recognition with Retrieval-Augmented Generation0
SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration0
Automated Parsing of Engineering Drawings for Structured Information Extraction Using a Fine-tuned Document Understanding Transformer0
Entropy Heat-Mapping: Localizing GPT-Based OCR Errors with Sliding-Window Shannon Analysis0
Tiger200K: Manually Curated High Visual Quality Video Dataset from UGC Platform0
Guidelines for External Disturbance Factors in the Use of OCR in Real-World Environments0
Show:102550
← PrevPage 3 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DTrOCR 105MAccuracy (%)89.6Unverified
2DTrOCRAccuracy (%)89.6Unverified
3MaskOCR-LAccuracy (%)82.6Unverified
4TransOCRAccuracy (%)72.8Unverified
5SRNAccuracy (%)65Unverified
6MORANAccuracy (%)64.3Unverified
7SEEDAccuracy (%)61.2Unverified
#ModelMetricClaimedVerifiedStatus
1GPT-4oAverage Accuracy76.22Unverified
2Gemini-1.5 ProAverage Accuracy76.13Unverified
3Claude-3 SonnetAverage Accuracy67.71Unverified
4RapidOCRAverage Accuracy56.98Unverified
5EasyOCRAverage Accuracy49.3Unverified
#ModelMetricClaimedVerifiedStatus
1STREETSequence error27.54Unverified
2SEESequence error22Unverified
3AttentionOCR_Inception-resnet-v2_LocationSequence error15.8Unverified
#ModelMetricClaimedVerifiedStatus
1I2L-NOPOOLBLEU89.09Unverified
2I2L-STRIPSBLEU89Unverified
#ModelMetricClaimedVerifiedStatus
1TesseractCharacter Error Rate (CER)0.08Unverified
2EasyOCRCharacter Error Rate (CER)0.07Unverified
#ModelMetricClaimedVerifiedStatus
1I2L-STRIPSBLEU88.86Unverified