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 451–500 of 1209 papers

TitleStatusHype
DocFormerv2: Local Features for Document UnderstandingCode1
Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question AnsweringCode1
Improving Handwritten OCR with Training Samples Generated by Glyph Conditional Denoising Diffusion Probabilistic Model—0
A template-independent approach for information extraction in real estate documentsCode0
DuoSearch: A Novel Search Engine for Bulgarian Historical DocumentsCode0
GlyphControl: Glyph Conditional Control for Visual Text GenerationCode2
FuseCap: Leveraging Large Language Models for Enriched Fused Image CaptionsCode1
Exploring Better Text Image Translation with Multimodal CodebookCode1
Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution LayersCode1
People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts—0
MRN: Multiplexed Routing Network for Incremental Multilingual Text RecognitionCode1
Quantifying Character Similarity with Vision TransformersCode0
DUBLIN -- Document Understanding By Language-Image Network—0
Measuring Intersectional Biases in Historical DocumentsCode0
XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented LanguagesCode1
TextDiffuser: Diffusion Models as Text Painters—0
Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding—0
Mobile User Interface Element Detection Via Adaptively Prompt TuningCode0
OCRBench: On the Hidden Mystery of OCR in Large Multimodal ModelsCode2
Visual Information Extraction in the Wild: Practical Dataset and End-to-end SolutionCode1
Combining OCR Models for Reading Early Modern Printed BooksCode0
TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text RecognitionCode1
E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine TranslationCode0
Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentation—0
Evaluating BERT-based Scientific Relation Classifiers for Scholarly Knowledge Graph Construction on Digital Library Collections—0
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction ModelCode5
DocParser: End-to-end OCR-free Information Extraction from Visually Rich DocumentsCode1
ICDAR 2023 Competition on Reading the Seal Title—0
Multimodal Short Video Rumor Detection System Based on Contrastive Learning—0
TransDocs: Optical Character Recognition with word to word translationCode0
Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts—0
Linking Representations with Multimodal Contrastive Learning—0
TagGPT: Large Language Models are Zero-shot Multimodal TaggersCode1
ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic RulesCode1
Efficient OCR for Building a Diverse Digital HistoryCode1
GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image GenerationCode2
A semi-automatic method for document classification in the shipping industry—0
OVeNet: Offset Vector Network for Semantic SegmentationCode0
Optical Character Recognition and Transcription of Berber Signs from Images in a Low-Resource Language Amazigh—0
CLIP-ReIdent: Contrastive Training for Player Re-Identification—0
The System Description of dun_oscar team for The ICPR MSR Challenge—0
BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis DatasetCode0
Meme Sentiment Analysis Enhanced with Multimodal Spatial Encoding and Facial Embedding—0
StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-trainingCode0
Language Is Not All You Need: Aligning Perception with Language Models—0
User-Centric Evaluation of OCR Systems for Kwak'wala—0
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image ClassificationCode1
An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning—0
SPARLING: Learning Latent Representations with Extremely Sparse Activations—0
DEVICE: DEpth and VIsual ConcEpts Aware Transformer for TextCaps—0
Show:102550
← PrevPage 10 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