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 726–750 of 1209 papers

TitleStatusHype
Tablext: A Combined Neural Network And Heuristic Based Table Extractor—0
Operationalizing a National Digital Library: The Case for a Norwegian Transformer ModelCode1
TeLCoS: OnDevice Text Localization with Clustering of Script—0
Open data for Moroccan license plates for OCR applications : data collection, labeling, and model construction—0
Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic LanguagesCode1
PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering NetworkCode0
Video-aided Unsupervised Grammar InductionCode1
Document Layout Analysis via Dynamic Residual Feature Fusion—0
A Multiplexed Network for End-to-End, Multilingual OCRCode1
We Live in a Motorized Civilization: Robert Moses Replies to Robert Caro—0
ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction—0
Interpretable Distance Metric Learning for Handwritten Chinese Character Recognition—0
Combining Morphological and Histogram based Text Line Segmentation in the OCR ContextCode1
Generating Synthetic Handwritten Historical Documents With OCR Constrained GANsCode1
uTHCD: A New Benchmarking for Tamil Handwritten OCR—0
TS-Net: OCR Trained to Switch Between Text Transcription Styles—0
Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question AnsweringCode0
Deep Structured Feature Networks for Table Detection and Tabular Data Extraction from Scanned Financial Document Images—0
Efficient Online ML API Selection for Multi-Label Classification Tasks—0
SPAN: a Simple Predict & Align Network for Handwritten Paragraph RecognitionCode0
Neural OCR Post-Hoc Correction of Historical CorporaCode1
Post-OCR Paragraph Recognition by Graph Convolutional Networks—0
Exploring Cross-Image Pixel Contrast for Semantic SegmentationCode1
It Takes Two to Tango: Combining Visual and Textual Information for Detecting Duplicate Video-Based Bug ReportsCode0
An Unsupervised Normalization Algorithm for Noisy Text: A Case Study for Information Retrieval and Stance DetectionCode0
Show:102550
← PrevPage 30 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