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 651–700 of 1209 papers

TitleStatusHype
Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting—0
DEXTER: An end-to-end system to extract table contents from electronic medical health documents—0
GMN: Generative Multi-modal Network for Practical Document Information Extraction—0
Towards Multimodal Vision-Language Models Generating Non-Generic Text—0
BusiNet -- a Light and Fast Text Detection Network for Business Documents—0
Sequence-aware multimodal page classification of Brazilian legal documentsCode0
Challenging America: Modeling language in longer time scales—0
Multistep Automated Data Labelling Procedure (MADLaP) for Thyroid Nodules on Ultrasound: An Artificial Intelligence Approach for Automating Image Annotation—0
iExam: A Novel Online Exam Monitoring and Analysis System Based on Face Detection and RecognitionCode0
Broken News: Making Newspapers Accessible to Print-Impaired—0
Towards Optimizing OCR for Accessibility—0
RDU: A Region-based Approach to Form-style Document Understanding—0
An Evaluation of OCR on Egocentric DataCode0
Transformer based Urdu Handwritten Text Optical Character Reader—0
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System—0
Contrastive Graph Multimodal Model for Text Classification in Videos—0
Two Decades of Bengali Handwritten Digit Recognition: A Survey—0
Introducing One Sided Margin Loss for Solving Classification Problems in Deep Networks—0
A Language Modelling Approach to Quality Assessment of OCR’ed Historical Text—0
MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining—0
Simulation d’erreurs d’OCR dans les systèmes de TAL pour le traitement de données anachroniques (Simulation of OCR errors in NLP systems for processing anachronistic data)—0
An Open Source Contractual Language Understanding Application Using Machine LearningCode0
Handwritten Character Generation using Y-Autoencoder for Character Recognition Model Training—0
CAMIO: A Corpus for OCR in Multiple Languages—0
Multilingual Named Entity Recognition for Medieval Charters Using Stacked Embeddings and Bert-based Models.—0
Optical character recognition quality affects perceived usefulness of historical newspaper clippings—0
Toolbox : une chaîne de traitement de corpus pour les humanités numériques (Toolbox : a corpus processing pipeline for digital humanities)—0
Reconnaissance d’entités nommées sur des sorties OCR bruitées : des pistes pour la désambiguïsation morphologique automatique (Resolution of entity linking issues on noisy OCR output : automatic disambiguation tracks)—0
Between History and Natural Language Processing: Study, Enrichment and Online Publication of French Parliamentary Debates of the Early Third Republic (1881-1899)—0
Generating Monolingual Dataset for Low Resource Language Bodo from old books using Google Keep—0
DisinfoMeme: A Multimodal Dataset for Detecting Meme Intentionally Spreading Out Disinformation—0
LILA-BOTI : Leveraging Isolated Letter Accumulations By Ordering Teacher Insights for Bangla Handwriting RecognitionCode0
Detection Masking for Improved OCR on Noisy Documents—0
Towards Deployable OCR models for Indic languages—0
Text Detection on Technical Drawings for the Digitization of Brown-field Processes—0
OCR Synthetic Benchmark Dataset for Indic Languages—0
Explainable Publication Year Prediction of Eighteenth Century Texts with the BERT Model—0
A Hybrid Defense Method against Adversarial Attacks on Traffic Sign Classifiers in Autonomous Vehicles—0
Unitail: Detecting, Reading, and Matching in Retail Scene—0
Benchmarking Algorithms for Automatic License Plate Recognition—0
Plagiarism Detection in the Bengali Language: A Text Similarity-Based Approach—0
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering—0
Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting—0
OCR quality affects perceived usefulness of historical newspaper clippings -- a user study—0
OCR Improves Machine Translation for Low-Resource Languages—0
Improving Amharic Handwritten Word Recognition Using Auxiliary Task—0
Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching—0
Identifying OCRs in cfDNA WGS Data by Correlation Clustering—0
BLPnet: A new DNN model and Bengali OCR engine for Automatic License Plate Recognition—0
Omnifont Persian OCR System Using Primitives—0
Show:102550
← PrevPage 14 of 25Next →
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