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
MinerU: An Open-Source Solution for Precise Document Content ExtractionCode16
MiniCPM-V: A GPT-4V Level MLLM on Your PhoneCode12
SWIFT:A Scalable lightWeight Infrastructure for Fine-TuningCode11
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end ModelCode9
DeepSeek-VL: Towards Real-World Vision-Language UnderstandingCode7
SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language ModelsCode7
TextMonkey: An OCR-Free Large Multimodal Model for Understanding DocumentCode5
Kimi-VL Technical ReportCode5
Nougat: Neural Optical Understanding for Academic DocumentsCode5
Focus Anywhere for Fine-grained Multi-page Document UnderstandingCode5
MixTex: Unambiguous Recognition Should Not Rely Solely on Real DataCode5
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction ModelCode5
On Path to Multimodal Historical Reasoning: HistBench and HistAgentCode4
OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and ReasoningCode4
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding BenchmarkCode4
AnyText: Multilingual Visual Text Generation And EditingCode4
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text RecognitionCode4
PaliGemma 2: A Family of Versatile VLMs for TransferCode3
Image-to-Markup Generation with Coarse-to-Fine AttentionCode3
MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated CapabilitiesCode3
Vary: Scaling up the Vision Vocabulary for Large Vision-Language ModelsCode3
From Panels to Prose: Generating Literary Narratives from ComicsCode3
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth FusionCode3
OCR-free Document Understanding TransformerCode3
PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR SystemCode2
OCRBench: On the Hidden Mystery of OCR in Large Multimodal ModelsCode2
Real-time Scene Text Detection with Differentiable BinarizationCode2
2.5 Years in Class: A Multimodal Textbook for Vision-Language PretrainingCode2
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language UnderstandingCode2
PP-OCR: A Practical Ultra Lightweight OCR SystemCode2
NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document EnhancementCode2
Delivering Document Conversion as a Cloud Service with High Throughput and ResponsivenessCode2
OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented GenerationCode2
Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document RestorationCode2
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual ContextsCode2
Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Multi-modal Text RecognitionCode2
MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K CategoriesCode2
GUICourse: From General Vision Language Models to Versatile GUI AgentsCode2
IMKGA-SM: Interpretable Multimodal Knowledge Graph Answer Prediction via Sequence ModelingCode2
GlyphControl: Glyph Conditional Control for Visual Text GenerationCode2
GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image GenerationCode2
Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown ExtractionCode2
Institutional Books 1.0: A 242B token dataset from Harvard Library's collections, refined for accuracy and usabilityCode2
BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual QuestionsCode2
General Detection-based Text Line RecognitionCode2
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image UnderstandingCode2
An Empirical Study of Scaling Law for Scene Text RecognitionCode2
An Approach for Air Drawing Using Background Subtraction and Contour ExtractionCode2
MouSi: Poly-Visual-Expert Vision-Language ModelsCode2
A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document UnderstandingCode2
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
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