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 901–950 of 1209 papers

TitleStatusHype
Books of Hours. the First Liturgical Data Set for Text Segmentation.—0
Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution—0
Boosting Optical Character Recognition: A Super-Resolution Approach—0
Bootstrapping a historical commodities lexicon with SKOS and DBpedia—0
BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations—0
Braille-to-Speech Generator: Audio Generation Based on Joint Fine-Tuning of CLIP and Fastspeech2—0
Broken News: Making Newspapers Accessible to Print-Impaired—0
BROS: A Pre-trained Language Model for Understanding Texts in Document—0
Budget-Optimal Task Allocation for Reliable Crowdsourcing Systems—0
Building a Corpus from Handwritten Picture Postcards: Transcription, Annotation and Part-of-Speech Tagging—0
Building A Handwritten Cuneiform Character Imageset—0
Building OCR/NER Test Collections—0
BusiNet -- a Light and Fast Text Detection Network for Business Documents—0
Bypassing Captcha By Machine A Proof For Passing The Turing Test—0
Callico: a Versatile Open-Source Document Image Annotation Platform—0
CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model—0
CAMIO: A Corpus for OCR in Multiple Languages—0
Can Visual Language Models Replace OCR-Based Visual Question Answering Pipelines in Production? A Case Study in Retail—0
Can You Read Me Now? Content Aware Rectification using Angle Supervision—0
Cascaded Detail-Preserving Networks for Super-Resolution of Document Images—0
Categorizing ancient documents—0
CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy—0
CG-DIQA: No-reference Document Image Quality Assessment Based on Character Gradient—0
Challenging America: Modeling language in longer time scales—0
Challenging America: Modeling language in longer time scales—0
Character Keypoint-based Homography Estimation in Scanned Documents for Efficient Information Extraction—0
Chargrid-OCR: End-to-end Trainable Optical Character Recognition for Printed Documents using Instance Segmentation—0
Chargrid-OCR: End-to-end trainable Optical Character Recognition through Semantic Segmentation and Object Detection—0
Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs—0
ChartEye: A Deep Learning Framework for Chart Information Extraction—0
ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering—0
ChartParser: Automatic Chart Parsing for Print-Impaired—0
Chart-RCNN: Efficient Line Chart Data Extraction from Camera Images—0
ChatSchema: A pipeline of extracting structured information with Large Multimodal Models based on schema—0
Chaurah: A Smart Raspberry Pi based Parking System—0
ChemRxivQuest: A Curated Chemistry Question-Answer Database Extracted from ChemRxiv Preprints—0
Chinese/English mixed Character Segmentation as Semantic Segmentation—0
CHISPA on the GO: A mobile Chinese-Spanish translation service for travellers in trouble—0
Chunk-based Chinese Spelling Check with Global Optimization—0
Classification of Contract-Amendment Relationships—0
Classification of Documents Extracted from Images with Optical Character Recognition Methods—0
Classroom Slide Narration System—0
Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts—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
Clustering-based Automatic Construction of Legal Entity Knowledge Base from Contracts—0
CMUQ@QALB-2014: An SMT-based System for Automatic Arabic Error Correction—0
CNN based Cuneiform Sign Detection Learned from Annotated 3D Renderings and Mapped Photographs with Illumination Augmentation—0
CodeSCAN: ScreenCast ANalysis for Video Programming Tutorials—0
Combining Human and Machine Transcriptions on the Zooniverse Platform—0
Show:102550
← PrevPage 19 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