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 101–125 of 1209 papers

TitleStatusHype
Confidence-aware Non-repetitive Multimodal Transformers for TextCapsCode1
Geometry Restoration and Dewarping of Camera-Captured Document ImagesCode1
ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic RulesCode1
An Unsupervised method for OCR Post-Correction and Spelling Normalisation for FinnishCode1
Generating Synthetic Handwritten Historical Documents With OCR Constrained GANsCode1
Iranis: A Large-scale Dataset of Farsi License Plate CharactersCode1
GenKIE: Robust Generative Multimodal Document Key Information ExtractionCode1
Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text RetrievalCode1
Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question AnsweringCode1
Data Generation for Post-OCR correction of Cyrillic handwritingCode1
From Text to Pixel: Advancing Long-Context Understanding in MLLMsCode1
FlowLearn: Evaluating Large Vision-Language Models on Flowchart UnderstandingCode1
FuseCap: Leveraging Large Language Models for Enriched Fused Image CaptionsCode1
An Empirical Study of Scaling Law for OCRCode1
FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) SystemsCode1
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from DocumentsCode1
Detection of Furigana Text in ImagesCode1
ARB: A Comprehensive Arabic Multimodal Reasoning BenchmarkCode1
Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth EvaluationCode1
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual PromptsCode1
DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document UnderstandingCode1
Fused Text Recogniser and Deep Embeddings Improve Word Recognition and RetrievalCode1
Graph Neural Networks and Representation Embedding for Table Extraction in PDF DocumentsCode1
DiT: Self-supervised Pre-training for Document Image TransformerCode1
bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali DocumentsCode1
Show:102550
← PrevPage 5 of 49Next →
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