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 201–225 of 1209 papers

TitleStatusHype
Fused Text Recogniser and Deep Embeddings Improve Word Recognition and RetrievalCode1
FuseCap: Leveraging Large Language Models for Enriched Fused Image CaptionsCode1
Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text ImagesCode1
Lights, Camera, Action! A Framework to Improve NLP Accuracy over OCR documentsCode1
GenKIE: Robust Generative Multimodal Document Key Information ExtractionCode1
TagGPT: Large Language Models are Zero-shot Multimodal TaggersCode1
Large Scale Font Independent Urdu Text Recognition SystemCode1
LAMBERT: Layout-Aware (Language) Modeling for information extractionCode1
LaTr: Layout-Aware Transformer for Scene-Text VQACode1
ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic RulesCode1
A Deep Learning Approach to Geographical Candidate Selection through Toponym MatchingCode1
CORU: Comprehensive Post-OCR Parsing and Receipt Understanding DatasetCode1
Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question AnsweringCode1
OCR Post Correction for Endangered Language TextsCode1
Structured Multimodal Attentions for TextVQACode1
Image-based table recognition: data, model, and evaluationCode1
HAPI: A Large-scale Longitudinal Dataset of Commercial ML API PredictionsCode1
Tokenization Repair in the Presence of Spelling ErrorsCode1
Hespi: A pipeline for automatically detecting information from hebarium specimen sheetsCode1
TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text RecognitionCode1
It Takes Two to Tango: Combining Visual and Textual Information for Detecting Duplicate Video-Based Bug ReportsCode0
Optimal Projections for Discriminative Dictionary Learning using the JL-lemmaCode0
AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video UnderstandingCode0
Investigating OCR-Sensitive Neurons to Improve Entity Recognition in Historical DocumentsCode0
Jochre 3 and the Yiddish OCR corpusCode0
Show:102550
← PrevPage 9 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