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 1–25 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
SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language ModelsCode7
DeepSeek-VL: Towards Real-World Vision-Language UnderstandingCode7
TextMonkey: An OCR-Free Large Multimodal Model for Understanding DocumentCode5
MixTex: Unambiguous Recognition Should Not Rely Solely on Real DataCode5
Focus Anywhere for Fine-grained Multi-page Document UnderstandingCode5
Nougat: Neural Optical Understanding for Academic DocumentsCode5
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction ModelCode5
Kimi-VL Technical ReportCode5
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text RecognitionCode4
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
On Path to Multimodal Historical Reasoning: HistBench and HistAgentCode4
AnyText: Multilingual Visual Text Generation And EditingCode4
From Panels to Prose: Generating Literary Narratives from ComicsCode3
PaliGemma 2: A Family of Versatile VLMs for TransferCode3
Vary: Scaling up the Vision Vocabulary for Large Vision-Language ModelsCode3
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth FusionCode3
MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated CapabilitiesCode3
Image-to-Markup Generation with Coarse-to-Fine AttentionCode3
OCR-free Document Understanding TransformerCode3
GIT: A Generative Image-to-text Transformer for Vision and LanguageCode2
Show:102550
← PrevPage 1 of 49Next →
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