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 201–250 of 1209 papers

TitleStatusHype
DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document UnderstandingCode1
Rerunning OCR: A Machine Learning Approach to Quality Assessment and Enhancement PredictionCode1
RUArt: A Novel Text-Centered Solution for Text-Based Visual Question AnsweringCode1
Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic LanguagesCode1
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text RecognitionCode1
DE-GAN: A Conditional Generative Adversarial Network for Document EnhancementCode1
CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing ModelsCode1
A Deep Learning Approach to Geographical Candidate Selection through Toponym MatchingCode1
An Unsupervised method for OCR Post-Correction and Spelling Normalisation for FinnishCode1
Structured Multimodal Attentions for TextVQACode1
Symmetrical Linguistic Feature Distillation with CLIP for Scene Text RecognitionCode1
TableFormer: Table Structure Understanding with TransformersCode1
Deep Relational Reasoning Graph Network for Arbitrary Shape Text DetectionCode1
TagGPT: Large Language Models are Zero-shot Multimodal TaggersCode1
Detection of Furigana Text in ImagesCode1
DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document UnderstandingCode1
Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven ApproachCode1
On the Cross-dataset Generalization in License Plate RecognitionCode1
TLGAN: document Text Localization using Generative Adversarial NetsCode1
Tokenization Repair in the Presence of Spelling ErrorsCode1
A semi-automatic method for document classification in the shipping industry—0
A second-order orientation-contrast stimulus for population-receptive-field-based retinotopic mapping—0
Amazigh Verb Conjugator—0
A Maximum Entropy Approach to Chinese Spelling Check—0
Artificial neural networks and fuzzy logic for recognizing alphabet characters and mathematical symbols—0
DECDM: Document Enhancement using Cycle-Consistent Diffusion Models—0
Decoding Anagrammed Texts Written in an Unknown Language and Script—0
Artificial Eye for the Blind—0
Classroom Slide Narration System—0
Data Cleaning for XML Electronic Dictionaries via Statistical Anomaly Detection—0
Classification of Contract-Amendment Relationships—0
Chunk-based Chinese Spelling Check with Global Optimization—0
DanProof: Pedagogical Spell and Grammar Checking for Danish—0
DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding—0
Deductron -- A Recurrent Neural Network—0
CHISPA on the GO: A mobile Chinese-Spanish translation service for travellers in trouble—0
CREPE: Coordinate-Aware End-to-End Document Parser—0
Chinese/English mixed Character Segmentation as Semantic Segmentation—0
A random forest system combination approach for error detection in digital dictionaries—0
A Linked Data Model for Multimodal Sentiment and Emotion Analysis—0
Crowdsourcing an OCR Gold Standard for a German and French Heritage Corpus—0
Classification of Documents Extracted from Images with Optical Character Recognition Methods—0
ChemRxivQuest: A Curated Chemistry Question-Answer Database Extracted from ChemRxiv Preprints—0
A Masked Bounding-Box Selection Based ResNet Predictor for Text Rotation Prediction—0
Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts—0
Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection—0
CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR—0
CLIP-ReIdent: Contrastive Training for Player Re-Identification—0
A Scalable Handwritten Text Recognition System—0
Chaurah: A Smart Raspberry Pi based Parking System—0
Show:102550
← PrevPage 5 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