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 1126–1150 of 1209 papers

TitleStatusHype
How many faces can be recognized? Performance extrapolation for multi-class classification—0
How Much Data Do You Need? About the Creation of a Ground Truth for Black Letter and the Effectiveness of Neural OCR—0
ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction—0
ICDAR 2023 Competition on Reading the Seal Title—0
Ice hockey player identification via transformers and weakly supervised learning—0
Identifying OCRs in cfDNA WGS Data by Correlation Clustering—0
Image-based Natural Language Understanding Using 2D Convolutional Neural Networks—0
Image preprocessing and modified adaptive thresholding for improving OCR—0
Image Processing Based Scene-Text Detection and Recognition with Tesseract—0
Implementation of a Workflow Management System for Non-Expert Users—0
Important New Developments in Arabographic Optical Character Recognition (OCR)—0
Improve CAPTCHA's Security Using Gaussian Blur Filter—0
Improved Typesetting Models for Historical OCR—0
Improvement in Semantic Address Matching using Natural Language Processing—0
Improve Sentence Alignment by Divide-and-conquer—0
Improving Amharic Handwritten Word Recognition Using Auxiliary Task—0
Improving Document Clustering by Removing Unnatural Language—0
Improving Handwritten OCR with Training Samples Generated by Glyph Conditional Denoising Diffusion Probabilistic Model—0
Improving Inference Performance of Machine Learning with the Divide-and-Conquer Principle—0
Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory—0
Improving OCR-Based Image Captioning by Incorporating Geometrical Relationship—0
Improving OCR Quality in 19th Century Historical Documents Using a Combined Machine Learning Based Approach—0
Improving Optical Character Recognition of Finnish Historical Newspapers with a Combination of Fraktur \& Antiqua Models and Image Preprocessing—0
Improving Text Generation on Images with Synthetic Captions—0
IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection—0
Show:102550
← PrevPage 46 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