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 51–100 of 1209 papers

TitleStatusHype
Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?Code1
The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting—0
Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents—0
LogicOCR: Do Your Large Multimodal Models Excel at Logical Reasoning on Text-Rich Images?Code1
Object-Centric Representations Improve Policy Generalization in Robot Manipulation—0
An agentic system with reinforcement-learned subsystem improvements for parsing form-like documentsCode0
Low-Resource Language Processing: An OCR-Driven Summarization and Translation PipelineCode0
Analyzing Patterns and Influence of Advertising in Print Newspapers—0
Towards Self-Improvement of Diffusion Models via Group Preference Optimization—0
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 Court—0
Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late InteractionCode0
Gameplay Highlights Generation—0
Development of a WAZOBIA-Named Entity Recognition System—0
Arrow-Guided VLM: Enhancing Flowchart Understanding via Arrow Direction EncodingCode0
Toward Advancing License Plate Super-Resolution in Real-World Scenarios: A Dataset and BenchmarkCode0
Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval—0
GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing—0
ChemRxivQuest: A Curated Chemistry Question-Answer Database Extracted from ChemRxiv Preprints—0
DOTA: Deformable Optimized Transformer Architecture for End-to-End Text Recognition with Retrieval-Augmented Generation—0
SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration—0
Automated Parsing of Engineering Drawings for Structured Information Extraction Using a Fine-tuned Document Understanding Transformer—0
Entropy Heat-Mapping: Localizing GPT-Based OCR Errors with Sliding-Window Shannon Analysis—0
Tiger200K: Manually Curated High Visual Quality Video Dataset from UGC Platform—0
Guidelines for External Disturbance Factors in the Use of OCR in Real-World Environments—0
Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language ModelsCode0
Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR—0
Relation-Rich Visual Document Generator for Visual Information ExtractionCode0
NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding—0
Kimi-VL Technical ReportCode5
Towards Calibration Enhanced Network by Inverse Adversarial Attack—0
Towards Visual Text Grounding of Multimodal Large Language Model—0
VISTA-OCR: Towards generative and interactive end to end OCR models—0
QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding—0
Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical DocumentsCode1
Context-Independent OCR with Multimodal LLMs: Effects of Image Resolution and Visual Complexity—0
From Panels to Prose: Generating Literary Narratives from ComicsCode3
BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata ExtractionCode0
TFIC: End-to-End Text-Focused Image Compression for Coding for Machines—0
PM4Bench: A Parallel Multilingual Multi-Modal Multi-task Benchmark for Large Vision Language ModelCode1
Slide2Text: Leveraging LLMs for Personalized Textbook Generation from PowerPoint Presentations—0
KL3M Tokenizers: A Family of Domain-Specific and Character-Level Tokenizers for Legal, Financial, and Preprocessing ApplicationsCode0
A Data-driven Investigation of Euphemistic Language: Comparing the usage of "slave" and "servant" in 19th century US newspapersCode0
LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents—0
KAP: MLLM-assisted OCR Text Enhancement for Hybrid Retrieval in Chinese Non-Narrative DocumentsCode0
Revisiting Noise in Natural Language Processing for Computational Social Science—0
CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model—0
PP-DocBee: Improving Multimodal Document Understanding Through a Bag of TricksCode0
AI-Driven Multi-Stage Computer Vision System for Defect Detection in Laser-Engraved Industrial Nameplates—0
An Approach for Air Drawing Using Background Subtraction and Contour ExtractionCode2
Show:102550
← PrevPage 2 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