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 801–850 of 1209 papers

TitleStatusHype
Vulnerability Analysis of Transformer-based Optical Character Recognition to Adversarial Attacks—0
Weakly Supervised Construction of ASR Systems with Massive Video Data—0
Weakly supervised information extraction from inscrutable handwritten document images—0
We Live in a Motorized Civilization: Robert Moses Replies to Robert Caro—0
Training BERT Models to Carry Over a Coding System Developed on One Corpus to Another—0
What Large Language Models Bring to Text-rich VQA?—0
What Machines See Is Not What They Get: Fooling Scene Text Recognition Models With Adversarial Text Images—0
What Media Frames Reveal About Stance: A Dataset and Study about Memes in Climate Change Discourse—0
Words as Geometric Features: Estimating Homography using Optical Character Recognition as Compressed Image Representation—0
Word Searching in Scene Image and Video Frame in Multi-Script Scenario using Dynamic Shape Coding—0
Word Segmentation from Unconstrained Handwritten Bangla Document Images using Distance Transform—0
You’ve translated it, now what?—0
An Ensemble of Neural Networks for Non-Linear Segmentation of Overlapped Cursive Script—0
JoyType: A Robust Design for Multilingual Visual Text Creation—0
K-Algorithm A Modified Technique for Noise Removal in Handwritten Documents—0
Key Information Extraction in Purchase Documents using Deep Learning and Rule-based Corrections—0
Khattat: Enhancing Readability and Concept Representation of Semantic Typography—0
KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding—0
Knowledge Discovery in Optical Music Recognition: Enhancing Information Retrieval with Instance Segmentation—0
Language Classification and Segmentation of Noisy Documents in Hebrew Scripts—0
Language Independent Single Document Image Super-Resolution using CNN for improved recognition—0
Language Is Not All You Need: Aligning Perception with Language Models—0
Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting—0
Large Language Models for Page Stream Segmentation—0
Large Language Models for Simultaneous Named Entity Extraction and Spelling Correction—0
LayoutReader: Pre-training of Text and Layout for Reading Order Detection—0
Learning Adaptive Value of Information for Structured Prediction—0
Learning Ensembles of Structured Prediction Rules—0
Learning Multiple Tasks in Parallel with a Shared Annotator—0
Learning UI Navigation through Demonstrations composed of Macro Actions—0
Legal Entity Extraction using a Pointer Generator Network—0
Lesan -- Machine Translation for Low Resource Languages—0
Leveraging Statistical Transliteration for Dictionary-Based English-Bengali CLIR of OCR`d Text—0
Leveraging Text Repetitions and Denoising Autoencoders in OCR Post-correction—0
License Plate Recognition System Based on Color Coding Of License Plates—0
Linear-Time Sequence Classification using Restricted Boltzmann Machines—0
Linguistic Resources for Handwriting Recognition and Translation Evaluation—0
Linking Representations with Multimodal Contrastive Learning—0
Lipi Gnani - A Versatile OCR for Documents in any Language Printed in Kannada Script—0
Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling—0
Local String Transduction as Sequence Labeling—0
LOCR: Location-Guided Transformer for Optical Character Recognition—0
Logios : An open source Greek Polytonic Optical Character Recognition system—0
Look, Read and Ask: Learning to Ask Questions by Reading Text in Images—0
Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval—0
Low-resource OCR error detection and correction in French Clinical Texts—0
Low-resource Post Processing of Noisy OCR Output for Historical Corpus Digitisation—0
LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents—0
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding—0
Making Old Kurdish Publications Processable by Augmenting Available Optical Character Recognition Engines—0
Show:102550
← PrevPage 17 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