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 151–200 of 1209 papers

TitleStatusHype
RoundTripOCR: A Data Generation Technique for Enhancing Post-OCR Error Correction in Low-Resource Devanagari LanguagesCode0
Advancing Vehicle Plate Recognition: Multitasking Visual Language Models with VehiclePaliGemma—0
Enhancement of text recognition for hanja handwritten documents of Ancient Korea—0
One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environments—0
AI Adoption to Combat Financial Crime: Study on Natural Language Processing in Adverse Media Screening of Financial Services in English and Bangla multilingual interpretation—0
DocVLM: Make Your VLM an Efficient Reader—0
DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization—0
TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-ActionCode2
Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models—0
Aligned Music Notation and Lyrics TranscriptionCode0
Text Change Detection in Multilingual Documents Using Image Comparison—0
SynFinTabs: A Dataset of Synthetic Financial Tables for Information and Table ExtractionCode0
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth FusionCode3
PaliGemma 2: A Family of Versatile VLMs for TransferCode3
CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy—0
OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented GenerationCode2
Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection—0
TextSSR: Diffusion-based Data Synthesis for Scene Text RecognitionCode2
DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and TrustworthinessCode0
VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models—0
Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs—0
SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text RecognitionCode0
Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown ExtractionCode2
Towards Accessible Learning: Deep Learning-Based Potential Dysgraphia Detection and OCR for Potentially Dysgraphic Handwriting—0
Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of ExpertsCode1
DriveThru: a Document Extraction Platform and Benchmark Datasets for Indonesian Local Language ArchivesCode0
Is Cognition consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding—0
Veri-Car: Towards Open-world Vehicle Information Retrieval—0
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding—0
NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts—0
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding—0
TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models—0
Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learning—0
HIP: Hierarchical Point Modeling and Pre-training for Visual Information Extraction—0
Handwriting Recognition in Historical Documents with Multimodal LLM—0
Toxicity of the Commons: Curating Open-Source Pre-Training DataCode1
Are VLMs Really BlindCode0
Structured Analysis and Comparison of Alphabets in Historical Handwritten Ciphers—0
MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding—0
Towards Visual Text Design Transfer Across Languages—0
Harnessing Webpage UIs for Text-Rich Visual Understanding—0
Reference-Based Post-OCR Processing with LLM for Diacritic Languages—0
LEGAL-UQA: A Low-Resource Urdu-English Dataset for Legal Question AnsweringCode0
Comparison of Image Preprocessing Techniques for Vehicle License Plate Recognition Using OCR: Performance and Accuracy Evaluation—0
Enhancing Assamese NLP Capabilities: Introducing a Centralized Dataset RepositoryCode0
ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training—0
TextMaster: Universal Controllable Text Edit—0
Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text RecognitionCode1
MIRAGE: Multimodal Identification and Recognition of Annotations in Indian General Prescriptions—0
Unraveling Movie Genres through Cross-Attention Fusion of Bi-Modal Synergy of Poster—0
Show:102550
← PrevPage 4 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