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 926–950 of 1209 papers

TitleStatusHype
Deep Learning Approach for Receipt Recognition—0
A Cost Efficient Approach to Correct OCR Errors in Large Document Collections—0
FUNSD: A Dataset for Form Understanding in Noisy Scanned DocumentsCode1
Integration of Text-maps in Convolutional Neural Networks for Region Detection among Different Textual Categories—0
Stroke extraction for offline handwritten mathematical expression recognitionCode0
Enhancing Cross-task Transferability of Adversarial Examples with Dispersion ReductionCode0
Object detection deep learning networks for Optical Character RecognitionCode0
Producing Corpora of Medieval and Premodern Occitan—0
A Scalable Handwritten Text Recognition System—0
An Ensemble of Neural Networks for Non-Linear Segmentation of Overlapped Cursive Script—0
Diversified Hidden Markov Models for Sequential Labeling—0
Shape Robust Text Detection with Progressive Scale Expansion NetworkCode1
Automatic Classification of Pathology Reports using TF-IDF Features—0
Convolutional Neural Networks for Automatic Meter Reading—0
OCR evaluation tools for the 21st century—0
Multikernel activation functions: formulation and a case study—0
SAML-QC: a Stochastic Assessment and Machine Learning based QC technique for Industrial Printing—0
A Multi-Object Rectified Attention Network for Scene Text RecognitionCode0
Lipi Gnani - A Versatile OCR for Documents in any Language Printed in Kannada Script—0
An OCR system for the Unified Northern AlphabetCode0
Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural NetworksCode1
TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network—0
Dynamic Programming Approach to Template-based OCR—0
Pay Voice: Point of Sale Recognition for Visually Impaired People—0
Deep Reader: Information extraction from Document images via relation extraction and Natural Language—0
Show:102550
← PrevPage 38 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