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 401–425 of 1209 papers

TitleStatusHype
NVLM: Open Frontier-Class Multimodal LLMs—0
Computer Vision Intelligence Test Modeling and Generation: A Case Study on Smart OCR—0
PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction—0
UNIT: Unifying Image and Text Recognition in One Vision Encoder—0
Confidence-Aware Document OCR Error Detection—0
mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding—0
Post-OCR Text Correction for Bulgarian Historical DocumentsCode0
CLOCR-C: Context Leveraging OCR Correction with Pre-trained Language ModelsCode0
ChartEye: A Deep Learning Framework for Chart Information Extraction—0
Can Visual Language Models Replace OCR-Based Visual Question Answering Pipelines in Production? A Case Study in Retail—0
Platypus: A Generalized Specialist Model for Reading Text in Various Forms—0
Knowledge Discovery in Optical Music Recognition: Enhancing Information Retrieval with Instance Segmentation—0
FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text SpottingCode0
A Permuted Autoregressive Approach to Word-Level Recognition for Urdu Digital Text—0
MMR: Evaluating Reading Ability of Large Multimodal Models—0
Ancient but Digitized: Developing Handwritten Optical Character Recognition for East Syriac Script Through Creating KHAMIS Dataset—0
Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese—0
Large Language Models for Page Stream Segmentation—0
Handwritten Code Recognition for Pen-and-Paper CS EducationCode0
Advancing Post-OCR Correction: A Comparative Study of Synthetic DataCode0
PIXELMOD: Improving Soft Moderation of Visual Misleading Information on TwitterCode0
ChatSchema: A pipeline of extracting structured information with Large Multimodal Models based on schema—0
VILA^2: VILA Augmented VILA—0
Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction—0
PLayerTV: Advanced Player Tracking and Identification for Automatic Soccer Highlight Clips—0
Show:102550
← PrevPage 17 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