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 101–125 of 1209 papers

TitleStatusHype
hmBERT: Historical Multilingual Language Models for Named Entity RecognitionCode1
Image-based table recognition: data, model, and evaluationCode1
FuseCap: Leveraging Large Language Models for Enriched Fused Image CaptionsCode1
An Unsupervised method for OCR Post-Correction and Spelling Normalisation for FinnishCode1
Implicit Feature Alignment: Learn to Convert Text Recognizer to Text SpotterCode1
Improving accuracy and speeding up Document Image Classification through parallel systemsCode1
Generating Synthetic Handwritten Historical Documents With OCR Constrained GANsCode1
Data Generation for Post-OCR correction of Cyrillic handwritingCode1
FlowLearn: Evaluating Large Vision-Language Models on Flowchart UnderstandingCode1
LAMBERT: Layout-Aware (Language) Modeling for information extractionCode1
Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text RetrievalCode1
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual PromptsCode1
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from DocumentsCode1
Lights, Camera, Action! A Framework to Improve NLP Accuracy over OCR documentsCode1
An Empirical Study of Scaling Law for OCRCode1
Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth EvaluationCode1
CLEval: Character-Level Evaluation for Text Detection and Recognition TasksCode1
ARB: A Comprehensive Arabic Multimodal Reasoning BenchmarkCode1
FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) SystemsCode1
From Text to Pixel: Advancing Long-Context Understanding in MLLMsCode1
MathReader : Text-to-Speech for Mathematical DocumentsCode1
Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of ExpertsCode1
Efficient OCR for Building a Diverse Digital HistoryCode1
Detection of Furigana Text in ImagesCode1
End-to-End Information Extraction by Character-Level Embedding and Multi-Stage Attentional U-NetCode1
Show:102550
← PrevPage 5 of 49Next →
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