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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 101–110 of 1209 papers

Title	Date	Tasks	Status
Judge a Book by its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription	Feb 27, 2025	Handwritten Text RecognitionHTR	CodeCode Available
NusaAksara: A Multimodal and Multilingual Benchmark for Preserving Indonesian Indigenous Scripts	Feb 25, 2025	Image SegmentationLanguage Identification	—Unverified
Detecting Offensive Memes with Social Biases in Singapore Context Using Multimodal Large Language Models	Feb 25, 2025	Optical Character Recognition (OCR)	CodeCode Available
Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI	Feb 24, 2025	document understandingMultimodal Reasoning	—Unverified
MultiOCR-QA: Dataset for Evaluating Robustness of LLMs in Question Answering on Multilingual OCR Texts	Feb 24, 2025	Optical Character RecognitionOptical Character Recognition (OCR)	CodeCode Available
Visual Zero-Shot E-Commerce Product Attribute Value Extraction	Feb 21, 2025	Aspect ExtractionAttribute	—Unverified
KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding	Feb 20, 2025	document understandingOptical Character Recognition	—Unverified
Harnessing PDF Data for Improving Japanese Large Multimodal Models	Feb 20, 2025	Optical Character Recognition (OCR)	—Unverified
Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning	Feb 18, 2025	Optical Character Recognition (OCR)	—Unverified
Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language models	Feb 18, 2025	Image to textOptical Character Recognition	CodeCode Available

Show:10 25 50

← PrevPage 11 of 121Next →

All datasets Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study VideoDB's OCR Benchmark Public Collection FSNS - Test I2L-140K SUT im2latex-100k

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	DTrOCR	Accuracy (%)	89.6	—	Unverified
2	DTrOCR 105M	Accuracy (%)	89.6	—	Unverified
3	MaskOCR-L	Accuracy (%)	82.6	—	Unverified
4	TransOCR	Accuracy (%)	72.8	—	Unverified
5	SRN	Accuracy (%)	65	—	Unverified
6	MORAN	Accuracy (%)	64.3	—	Unverified
7	SEED	Accuracy (%)	61.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GPT-4o	Average Accuracy	76.22	—	Unverified
2	Gemini-1.5 Pro	Average Accuracy	76.13	—	Unverified
3	Claude-3 Sonnet	Average Accuracy	67.71	—	Unverified
4	RapidOCR	Average Accuracy	56.98	—	Unverified
5	EasyOCR	Average Accuracy	49.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	STREET	Sequence error	27.54	—	Unverified
2	SEE	Sequence error	22	—	Unverified
3	AttentionOCR_Inception-resnet-v2_Location	Sequence error	15.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	I2L-NOPOOL	BLEU	89.09	—	Unverified
2	I2L-STRIPS	BLEU	89	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Tesseract	Character Error Rate (CER)	0.08	—	Unverified
2	EasyOCR	Character Error Rate (CER)	0.07	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	I2L-STRIPS	BLEU	88.86	—	Unverified