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 451–500 of 1209 papers

TitleStatusHype
Extraction of Line Word Character Segments Directly from Run Length Compressed Printed Text Documents—0
ExTTNet: A Deep Learning Algorithm for Extracting Table Texts from Invoice Images—0
Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation—0
ChartEye: A Deep Learning Framework for Chart Information Extraction—0
Digitizing 18th-Century French Literature: Comparing transcription methods for a critical edition text—0
Fast Search with Poor OCR—0
ChartParser: Automatic Chart Parsing for Print-Impaired—0
@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology—0
Fetch-A-Set: A Large-Scale OCR-Free Benchmark for Historical Document Retrieval—0
DEXTER: An end-to-end system to extract table contents from electronic medical health documents—0
An End-to-End OCR Framework for Robust Arabic-Handwriting Recognition using a Novel Transformers-based Model and an Innovative 270 Million-Words Multi-Font Corpus of Classical Arabic with Diacritics—0
Finding Names in Trove: Named Entity Recognition for Australian Historical Newspapers—0
Advancing Visual Specification of Code Requirements for Graphs—0
DEVICE: DEpth and VIsual ConcEpts Aware Transformer for TextCaps—0
Chaurah: A Smart Raspberry Pi based Parking System—0
FLELex: a graded lexical resource for French foreign learners—0
Development of a WAZOBIA-Named Entity Recognition System—0
BART for Post-Correction of OCR Newspaper Text—0
Development of a New Image-to-text Conversion System for Pashto, Farsi and Traditional Chinese—0
Detection of Text Reuse in French Medical Corpora—0
Font Identification in Historical Documents Using Active Learning—0
Fooling OCR Systems with Adversarial Text Images—0
FormGym: Doing Paperwork with Agents—0
Fraunhofer SIT at CheckThat! 2023: Mixing Single-Modal Classifiers to Estimate the Check-Worthiness of Multi-Modal Tweets—0
Bangla Text Recognition from Video Sequence: A New Focus—0
From Machine Learning to Machine Reasoning—0
An End-to-End Khmer Optical Character Recognition using Sequence-to-Sequence with Attention—0
An Ensemble of Neural Networks for Non-Linear Segmentation of Overlapped Cursive Script—0
Detection Masking for Improved OCR on Noisy Documents—0
Chunk-based Chinese Spelling Check with Global Optimization—0
Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning Based Methods—0
D\'etection d'erreurs dans des transcriptions OCR de documents historiques par r\'eseaux de neurones r\'ecurrents multi-niveau (Combining character level and word level RNNs for post-OCR error detection)—0
Bambara and Maninka Manding Languages Written Corpora Project (``Projet des corpus \'ecrits des langues manding : le bambara, le maninka'') [in French]—0
Detecting de minimis Code-Switching in Historical German Books—0
Classification of Documents Extracted from Images with Optical Character Recognition Methods—0
Design and Implementation of an OCR-Powered Pipeline for Table Extraction from Invoices—0
Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers—0
Generalizing Analytic Shrinkage for Arbitrary Covariance Structures—0
Balanced Korean Word Spacing with Structural SVM—0
Post-OCR Paragraph Recognition by Graph Convolutional Networks—0
Generating a Training Corpus for OCR Post-Correction Using Encoder-Decoder Model—0
Generating Monolingual Dataset for Low Resource Language Bodo from old books using Google Keep—0
Design and Development of a Framework For Stroke-Based Handwritten Gujarati Font Generation—0
Derivate-based Component-Trees for Multi-Channel Image Segmentation—0
Advancing Vehicle Plate Recognition: Multitasking Visual Language Models with VehiclePaliGemma—0
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding—0
Geometric Rectification of Creased Document Images based on Isometric Mapping—0
Delta vs. N-Gram Tracing: Evaluating the Robustness of Authorship Attribution Methods—0
Harnessing PDF Data for Improving Japanese Large Multimodal Models—0
Auto-ML Deep Learning for Rashi Scripts OCR—0
Show:102550
← PrevPage 10 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