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 301–325 of 1209 papers

TitleStatusHype
KAP: MLLM-assisted OCR Text Enhancement for Hybrid Retrieval in Chinese Non-Narrative DocumentsCode0
Optimal Projections for Discriminative Dictionary Learning using the JL-lemmaCode0
Jochre 3 and the Yiddish OCR corpusCode0
Latent Tree Language ModelCode0
InstructOCR: Instruction Boosting Scene Text SpottingCode0
Indiscapes: Instance Segmentation Networks for Layout Parsing of Historical Indic ManuscriptsCode0
Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question AnsweringCode0
Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document ParsingCode0
Investigating OCR-Sensitive Neurons to Improve Entity Recognition in Historical DocumentsCode0
Improving OCR Accuracy on Early Printed Books by utilizing Cross Fold Training and VotingCode0
Improving patch-based scene text script identification with ensembles of conjoined networksCode0
Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active LearningCode0
Low-Resource Language Processing: An OCR-Driven Summarization and Translation PipelineCode0
Improving OCR Accuracy on Early Printed Books using Deep Convolutional NetworksCode0
BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis DatasetCode0
Advancing Multilingual Handwritten Numeral Recognition with Attention-driven Transfer LearningCode0
Implicit Language Model in LSTM for OCRCode0
DELINE8K: A Synthetic Data Pipeline for the Semantic Segmentation of Historical DocumentsCode0
An efficient way for segmentation of Bangla characters in printed document using curved scanningCode0
Automatic Recognition of Learning Resource Category in a Digital LibraryCode0
Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and DissertationsCode0
It Takes Two to Tango: Combining Visual and Textual Information for Detecting Duplicate Video-Based Bug ReportsCode0
Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural NetworkCode0
HENet: Forcing a Network to Think More for Font RecognitionCode0
Handwriting Classification for the Analysis of Art-Historical DocumentsCode0
Show:102550
← PrevPage 13 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