Camera-Based Document Analysis and Recognition

Name: Camera-Based Document Analysis and Recognition | 4th International Workshop, CBDAR 2011, Beijing, China, September 22, 2011, Revised Selected Papers
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

4th International Workshop, CBDAR 2011, Beijing, China, September 22, 2011, Revised Selected Papers

Masakazu Iwamura Faisal Shafait(Herausgeber*in)

Springer (Verlag)

Erschienen am 12. April 2012

VIII, 173 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-642-29364-1 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Title
Preface
Table of Contents
Text Detection and Recognition in Scene Images
Multi-script and Multi-oriented Text Localization from Scene Images
Introduction
Review of Text Detection
Color Text Segmentation
Feature Extraction for Text Classification
Experiments and Results
Estimation of Word Bounding Boxes
Conclusions
References
Assistive Text Reading from Complex Background for Blind Persons
Introduction
Previous Work in Text Localization
System and Algorithm Overview
Automatic Text Localization
Text Stroke Orientation
Distributions of Edge Pixels
Adaboost Learning of Features of Text
Text Region Localization
Text Recognition and Audio Output
Experiments
Datasets
Results and Discussions
Conclusion
References
A Head-Mounted Device for Recognizing Text in Natural Scenes
Introduction
Hardware Design
Proposed System
Image Segmentation
Region Filtering
Perceptual Text Grouping
Results
Conclusion
References
Text Detection of Two Major Indian Scripts in Natural Scene Images
Introduction
Devanagari and Bangla Script Characteristics
Proposed Approach to Text Detection
Preprocessing and Connected Components
Extraction of Strokes of Near-Uniform Thickness
General Rules Based on the Geometry of Text Regions
Detection of Headline of Bangla and Devanagari Texts
Use of ``Similarity Measures" for Detecting Missed-Out Text Regions
Experimental Results and Discussions
Conclusions
References
An Algorithm for Colour-Based Natural Scene Text Segmentation
Introduction
Introduction of Selective Metric-Based Clustering
The Proposed Method
Modification of Validation Measure
Proposed Segmentation Evaluation Method
Experimental Results
Conclusion
References
Recognizing Natural Scene Characters by Convolutional Neural Network and Bimodal Image Enhancement
Introduction
Natural Scene Character Recognition
Framework
Maximum Separability Color-to-Gray Conversion
Grayscale Distribution Normalization
Shape Holding Grayscale Character Image Normalization
Convolutional Neural Network
Experiment Result
Discussions and Conclusions
References
Camera-Based Systems
PaperUI
Introduction
PaperUI Overview
Emerging Technologies for Realizing the PaperUI Concept
Barcode
Micro Optical Patterns
Encode Hidden Information
Paper Fingerprint
Character/Word Recognition
RFID-Based Document Recognition
PaperUI Applications
Digital Pen Based Applications
Barcode Based Applications
RFID Based Applications
Character/Word Recognition Based Applications
Encoding Hidden Information Based Applications
Original Document Feature Based Applications
Fine-Grained Phone-Paper Interactions
Concluding Remarks
References
Decapod: A Flexible, Low Cost Digitization Solution for Small and Medium Archives
Introduction
System Architecture
Document Capture
Dewarping
Preprocessing / Layout Analysis
Tokenization
Font Reconstruction
PDF Generation
Project Status
Conclusion
References
A Method for Camera-Based InteractiveWhiteboard Reading
Introduction
Related Work
Whiteboard Reading System
Image Acquisition and Camera-Projector Calibration
Image Segmentation
Layout Analysis
Word Detection
Word Recognition
The Mindmap Manager
Interaction with the Whiteboard
Experiments
Data Description
Results
Summary
References
Border Noise Removal of Camera-Captured Document Images Using Page Frame Detection
Introduction
Page Frame Detection Method
Preprocessing
Text-Line Detection
Page Frame Detection
Experiments and Results
Discussion
References
Datasets and Evaluation
An Image Based Performance Evaluation Method for Page Dewarping Algorithms Using SIFT Features
Introduction
Image Based Performance Evaluation
Ground-Truth Dewarped Images
Performance Evaluation Methodology
Experiment and Results
Conclusion
References
NEOCR: A Configurable Dataset for Natural Image Text Recognition
Introduction
Dataset
Global Image Metadata
Textfield Metadata
Summary
Related Work
Conclusion
References
The IUPR Dataset of Camera-Captured Document Images
Introduction
The IUPR Dataset
Ground-Truth
Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken