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 1076–1100 of 1209 papers

TitleStatusHype
DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression NetworksCode0
Single Classifier-based Passive System for Source Printer Classification using Local Texture FeaturesCode0
Measuring Intersectional Biases in Historical DocumentsCode0
Detecting Offensive Memes with Social Biases in Singapore Context Using Multimodal Large Language ModelsCode0
Handwritten Code Recognition for Pen-and-Paper CS EducationCode0
PIXELMOD: Improving Soft Moderation of Visual Misleading Information on TwitterCode0
An Evaluation of OCR on Egocentric DataCode0
Attention-based Extraction of Structured Information from Street View ImageryCode0
An Evaluation of DNN Architectures for Page Segmentation of Historical NewspapersCode0
Chinese Text in the WildCode0
Handwriting Classification for the Analysis of Art-Historical DocumentsCode0
MIDV-2019: Challenges of the modern mobile-based document OCRCode0
DeQA-Doc: Adapting DeQA-Score to Document Image Quality AssessmentCode0
Aligned Music Notation and Lyrics TranscriptionCode0
Analyzing Green View Index and Green View Index best path using Google Street View and deep learningCode0
PopEval: A Character-Level Approach to End-To-End Evaluation Compatible with Word-Level Benchmark DatasetCode0
Mining Spatio-temporal Data on Industrialization from Historical RegistriesCode0
DELINE8K: A Synthetic Data Pipeline for the Semantic Segmentation of Historical DocumentsCode0
Post-OCR parsing: building simple and robust parser via BIO taggingCode0
Post-OCR Text Correction for Bulgarian Historical DocumentsCode0
An efficient way for segmentation of Bangla characters in printed document using curved scanningCode0
DeepErase: Weakly Supervised Ink Artifact Removal in Document Text ImagesCode0
Deciphering the Underserved: Benchmarking LLM OCR for Low-Resource ScriptsCode0
When Vision Fails: Text Attacks Against ViT and OCRCode0
Predicting the Past: Estimating Historical Appraisals with OCR and Machine LearningCode0
Show:102550
← PrevPage 44 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