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 1101–1150 of 1209 papers

TitleStatusHype
OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited—0
Measuring Lexical Quality of a Historical Finnish Newspaper Collection ― Analysis of Garbled OCR Data with Basic Language Technology Tools and Means—0
Crowdsourcing an OCR Gold Standard for a German and French Heritage Corpus—0
Training \& Quality Assessment of an Optical Character Recognition Model for Northern Haida—0
OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles—0
OCR Error Correction Using Character Correction and Feature-Based Word Classification—0
Overlay Text Extraction From TV News Broadcast—0
Robust Scene Text Recognition with Automatic RectificationCode0
Recursive Recurrent Nets with Attention Modeling for OCR in the Wild—0
Resource Constrained Structured Prediction—0
Data Cleaning for XML Electronic Dictionaries via Statistical Anomaly Detection—0
Improving patch-based scene text script identification with ensembles of conjoined networksCode0
Font Identification in Historical Documents Using Active Learning—0
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural ImagesCode0
Decoding Anagrammed Texts Written in an Unknown Language and Script—0
Comparison of Visual and Logical Character Segmentation in Tesseract OCR Language Data for Indic Writing Scripts—0
Finding Names in Trove: Named Entity Recognition for Australian Historical Newspapers—0
Calibrated Structured PredictionCode0
Sequence to Sequence Learning for Optical Character Recognition—0
Directional Global Three-part Image Decomposition—0
Telugu OCR Framework using Deep Learning—0
OCR accuracy improvement on document images through a novel pre-processing approach—0
Statistical Machine Translation Improvement based on Phrase Selection—0
DanProof: Pedagogical Spell and Grammar Checking for Danish—0
Is it possible to recover personal health information from an automatically de-identified corpus of French EHRs?—0
Topic Stability over Noisy Sources—0
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text RecognitionCode4
SAHSOH@QALB-2015 Shared Task: A Rule-Based Correction Method of Common Arabic Native and Non-Native Speakers' Errors—0
A Linked Data Model for Multimodal Sentiment and Emotion Analysis—0
A preliminary study on similarity-preserving digital book identifiers—0
TECHLIMED@QALB-Shared Task 2015: a hybrid Arabic Error Correction System—0
License Plate Recognition System Based on Color Coding Of License Plates—0
Boosting Optical Character Recognition: A Super-Resolution Approach—0
Automated Translation of a Literary Work: A Pilot Study—0
Unsupervised Code-Switching for Multilingual Historical Document Transcription—0
Squibs: Spelling Error Patterns in Brazilian Portuguese—0
Regularization and Kernelization of the Maximin Correlation Approach—0
A survey of modern optical character recognition techniques—0
A Study of Sindhi Related and Arabic Script Adapted languages Recognition—0
Learning Multiple Tasks in Parallel with a Shared Annotator—0
Efficient Media Retrieval from Non-Cooperative Queries—0
Optical Character Recognition, Using K-Nearest Neighbors—0
OCR and Automated Translation for the Navigation of non-English Handsets: A Feasibility Study with Arabic—0
A random forest system combination approach for error detection in digital dictionaries—0
Improve CAPTCHA's Security Using Gaussian Blur Filter—0
CMUQ@QALB-2014: An SMT-based System for Automatic Arabic Error Correction—0
TECHLIMED system description for the Shared Task on Automatic Arabic Error Correction—0
Autocorrection of arabic common errors for large text corpus—0
Balanced Korean Word Spacing with Structural SVM—0
Bypassing Captcha By Machine A Proof For Passing The Turing Test—0
Show:102550
← PrevPage 23 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