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 501–550 of 1209 papers

TitleStatusHype
Advancements and Challenges in Arabic Optical Character Recognition: A Comprehensive Survey—0
TDeLTA: A Light-weight and Robust Table Detection Method based on Learning Text Arrangement—0
Information Extraction from Unstructured data using Augmented-AI and Computer Vision—0
Polar-Doc: One-Stage Document Dewarping with Multi-Scope Constraints under Polar Representation—0
Multimodal Sentiment Analysis: Perceived vs Induced Sentiments—0
UPOCR: Towards Unified Pixel-Level OCR Interface—0
Enhancing Vehicle Entrance and Parking Management: Deep Learning Solutions for Efficiency and Security—0
Pipeline Enabling Zero-shot Classification for Bangla Handwritten Grapheme—0
Vulnerability Analysis of Transformer-based Optical Character Recognition to Adversarial Attacks—0
Automatic Recognition of Learning Resource Category in a Digital LibraryCode0
Optimization of Image Processing Algorithms for Character Recognition in Cultural Typewritten DocumentsCode0
SUT: a new multi-purpose synthetic dataset for Farsi document image analysisCode0
Similar Document Template Matching Algorithm—0
ChemScraper: Leveraging PDF Graphics Instructions for Molecular Diagram ParsingCode0
DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding—0
Efficient End-to-End Visual Document Understanding with Rationale Distillation—0
DECDM: Document Enhancement using Cycle-Consistent Diffusion Models—0
Multiple-Question Multiple-Answer Text-VQA—0
Reading Between the Mud: A Challenging Motorcycle Racer Number DatasetCode0
What Large Language Models Bring to Text-rich VQA?—0
DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency—0
On Manipulating Scene Text in the Wild with Diffusion ModelsCode0
DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense UnderstandingCode0
PHD: Pixel-Based Language Modeling of Historical DocumentsCode0
MultiCoNER v2: a Large Multilingual dataset for Fine-grained and Noisy Named Entity Recognition—0
DocXChain: A Powerful Open-Source Toolchain for Document Parsing and Beyond—0
EfficientOCR: An Extensible, Open-Source Package for Efficiently Digitizing World Knowledge—0
Towards reducing hallucination in extracting information from financial reports using Large Language Models—0
Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA—0
Invisible Threats: Backdoor Attack in OCR Systems—0
Solution for SMART-101 Challenge of ICCV Multi-modal Algorithmic Reasoning Task 2023—0
Constructing Image-Text Pair Dataset from Books—0
Comprehensive Overview of Named Entity Recognition: Models, Domain-Specific Applications and Challenges—0
Order-preserving Consistency Regularization for Domain Adaptation and GeneralizationCode0
STEP -- Towards Structured Scene-Text SpottingCode0
Bengali Document Layout Analysis -- A YOLOV8 Based Ensembling Approach—0
Separate and Locate: Rethink the Text in Text-based Visual Question AnsweringCode0
Enhancing OCR Performance through Post-OCR Models: Adopting Glyph Embedding for Improved Correction—0
Vision Grid Transformer for Document Layout Analysis—0
Optimal Projections for Discriminative Dictionary Learning using the JL-lemmaCode0
Bengali Document Layout Analysis with Detectron2—0
DISGO: Automatic End-to-End Evaluation for Scene Text OCR—0
American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers—0
CNN based Cuneiform Sign Detection Learned from Annotated 3D Renderings and Mapped Photographs with Illumination Augmentation—0
OCR Language Models with Custom Vocabularies—0
FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo EmbeddingsCode0
Training BERT Models to Carry Over a Coding System Developed on One Corpus to Another—0
Making the V in Text-VQA Matter—0
Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotations—0
Optimizing the Neural Network Training for OCR Error Correction of Historical Hebrew Texts—0
Show:102550
← PrevPage 11 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