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 151–175 of 1209 papers

TitleStatusHype
An Automatic Approach for Generating Rich, Linked Geo-Metadata from Historical Map ImagesCode1
Confidence-aware Non-repetitive Multimodal Transformers for TextCapsCode1
Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural NetworksCode1
LaTr: Layout-Aware Transformer for Scene-Text VQACode1
hmBERT: Historical Multilingual Language Models for Named Entity RecognitionCode1
Lexically Aware Semi-Supervised Learning for OCR Post-CorrectionCode1
ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper PagesCode1
Image-based table recognition: data, model, and evaluationCode1
HAPI: A Large-scale Longitudinal Dataset of Commercial ML API PredictionsCode1
Hespi: A pipeline for automatically detecting information from hebarium specimen sheetsCode1
Image-text matching for large-scale book collectionsCode1
A Multiplexed Network for End-to-End, Multilingual OCRCode1
ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic RulesCode1
CLEval: Character-Level Evaluation for Text Detection and Recognition TasksCode1
Graph Neural Networks and Representation Embedding for Table Extraction in PDF DocumentsCode1
GenPlot: Increasing the Scale and Diversity of Chart Derendering DataCode1
Fully Unsupervised Diversity Denoising with Convolutional Variational AutoencodersCode1
Detection of Furigana Text in ImagesCode1
bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali DocumentsCode1
Digitizing Historical Balance Sheet Data: A Practitioner's GuideCode1
DocFormerv2: Local Features for Document UnderstandingCode1
A Large Multi-Target Dataset of Common Bengali Handwritten GraphemesCode1
Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video EnvironmentsCode1
DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document UnderstandingCode1
GenKIE: Robust Generative Multimodal Document Key Information ExtractionCode1
Show:102550
← PrevPage 7 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