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 251–300 of 1209 papers

TitleStatusHype
ChatSchema: A pipeline of extracting structured information with Large Multimodal Models based on schema—0
VILA^2: VILA Augmented VILA—0
PLayerTV: Advanced Player Tracking and Identification for Automatic Soccer Highlight Clips—0
Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction—0
Braille-to-Speech Generator: Audio Generation Based on Joint Fine-Tuning of CLIP and Fastspeech2—0
Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition—0
VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document UnderstandingCode1
Spanish TrOCR: Leveraging Transfer Learning for Language AdaptationCode0
Resolving Sentiment Discrepancy for Multimodal Sentiment Detection via Semantics Completion and Decomposition—0
High-Throughput Phenotyping using Computer Vision and Machine LearningCode0
Semantic Segmentation for Real-World and Synthetic Vehicle's Forward-Facing Camera Images—0
FlowLearn: Evaluating Large Vision-Language Models on Flowchart UnderstandingCode1
Optimizing Nepali PDF Extraction: A Comparative Study of Parser and OCR TechnologiesCode0
Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge—0
Historical Ink: 19th Century Latin American Spanish Newspaper Corpus with LLM OCR CorrectionCode0
Proposal Report for the 2nd SciCAP Competition 2024—0
A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document UnderstandingCode2
MMLongBench-Doc: Benchmarking Long-context Document Understanding with VisualizationsCode2
Mind the Gap: Analyzing Lacunae with Transformer-Based Transcription—0
DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document AnnotationCode0
MixTex: Unambiguous Recognition Should Not Rely Solely on Real DataCode5
News Deja Vu: Connecting Past and Present with Semantic Search—0
GUI Action Narrator: Where and When Did That Action Take Place?—0
Unifying Multimodal Retrieval via Document Screenshot Embedding—0
GUICourse: From General Vision Language Models to Versatile GUI AgentsCode2
OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst—0
Enhancing Question Answering on Charts Through Effective Pre-training Tasks—0
M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine TranslationCode0
Fetch-A-Set: A Large-Scale OCR-Free Benchmark for Historical Document Retrieval—0
Scaling Automatic Extraction of Pseudocode—0
CORU: Comprehensive Post-OCR Parsing and Receipt Understanding DatasetCode1
Improving Text Generation on Images with Synthetic Captions—0
Towards Unified Multi-granularity Text Detection with Interactive Attention—0
RealitySummary: Exploring On-Demand Mixed Reality Text Summarization and Question Answering using Large Language Models—0
Notes on Applicability of GPT-4 to Document Understanding—0
Vision Language Models for Spreadsheet Understanding: Challenges and Opportunities—0
Focus Anywhere for Fine-grained Multi-page Document UnderstandingCode5
Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Multi-modal Text RecognitionCode2
From Text to Pixel: Advancing Long-Context Understanding in MLLMsCode1
Transfer Learning Approach for Railway Technical Map (RTM) Component Identification—0
GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document UnderstandingCode0
Callico: a Versatile Open-Source Document Image Annotation Platform—0
CREPE: Coordinate-Aware End-to-End Document Parser—0
DELINE8K: A Synthetic Data Pipeline for the Semantic Segmentation of Historical DocumentsCode0
Multi-Page Document Visual Question Answering using Self-Attention Scoring MechanismCode0
ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in ImagesCode1
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites—0
Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer—0
Improvement in Semantic Address Matching using Natural Language Processing—0
MathWriting: A Dataset For Handwritten Mathematical Expression Recognition—0
Show:102550
← PrevPage 6 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