記錄 3 之 13
Record:   Prev Next
作者 Padalkar, Milind G., author
書名 Digital heritage reconstruction using super-resolution and inpainting / Milind G. Padalkar, Manjunath V. Joshi, Nilay L. Khatri
出版項 [San Rafael, California] : Morgan & Claypool, 2017
國際標準書號 9781627056168 ebook
9781627059213 print
國際標準號碼 10.2200/S00740ED1V01Y201611VCP026 doi
book jacket
說明 1 online resource (xviii, 150 pages) : illustrations
text rdacontent
electronic isbdmedia
online resource rdacarrier
系列 Synthesis lectures on visual computing, 2469-4223 ; # 26
Synthesis digital library of engineering and computer science
Synthesis lectures on visual computing ; # 26. 2469-4223
附註 Part of: Synthesis digital library of engineering and computer science
Includes bibliographical references (pages 135-147)
1. Introduction -- 1.1 What is super-resolution? -- 1.2 What is inpainting? -- 1.3 Applying super-resolution and inpainting in digital heritage images: challenges and solutions -- 1.4 A tour of the book --
2. Image super-resolution: self-learning, sparsity and Gabor prior -- 2.1 Single-image SR: a unified framework -- 2.1.1 Classical (within-scale) super-resolution -- 2.1.2 Exampled-based (across-scale) super-resolution -- 2.1.3 Unifying classical and example-based SR -- 2.2 Self-learning and degradation estimation -- 2.3 Gabor prior and regularization -- 2.4 Performance evaluation -- 2.4.1 Qualitative evaluation -- 2.4.2 Quantitative evaluation -- 2.5 Conclusion --
3. Self-learning: faster, smarter, simpler -- 3.1 Efficient self-learning -- 3.1.1 Improved self-learning for super-resolution -- 3.2 Performance evaluation -- 3.2.1 Perceptual and quantitative evaluation -- 3.2.2 Improvements and extensions -- 3.3 Conclusion --
4. An exemplar-based inpainting using an autoregressive model -- 4.1 Limitation of existing approaches -- 4.2 Proposed approach -- 4.3 Experimental results -- 4.4 Conclusion --
5. Attempts to improve inpainting -- 5.1 A modified exemplar-based multi-resolution approach -- 5.1.1 Refinement by matching a larger region -- 5.1.2 Refinement using the patch-neighborhood relationship -- 5.1.3 Refinement using compressive sensing framework -- 5.2 Curvature-based approach for inpainting -- 5.3 Observations and conclusion --
6. Simultaneous inpainting and super-resolution -- 6.1 Need for patch comparison at finer resolution -- 6.2 Proposed approach -- 6.2.1 Constructing image-representative LR-HR dictionaries -- 6.2.2 Estimation of HR patches -- 6.2.3 Simultaneous inpainting and SR of missing pixels -- 6.3 Experimental results -- 6.4 Conclusion --
7. Detecting and inpainting damaged regions in facial images of statues -- 7.1 Preprocessing -- 7.2 Extraction of eye, nose and lip regions -- 7.3 Classification -- 7.4 Inpainting -- 7.5 Experimental results -- 7.6 Conclusion --
8. Auto-inpainting cracks in heritage scenes -- 8.1 A simple method for detecting and inpainting cracks -- 8.1.1 Order-statistics-based filtering -- 8.1.2 Scan-line peak difference detection -- 8.1.3 Density-based filtering -- 8.1.4 Refinement -- 8.1.5 Experimental results -- 8.2 Singular value decomposition-based crack detection and inpainting -- 8.2.1 SVD and patch analysis -- 8.2.2 Thresholding -- 8.2.3 Experimental results -- 8.3 Crack detection using tolerant edit distance and inpainting -- 8.3.1 Preprocessing -- 8.3.2 Patch comparison using tolerant edit distance -- 8.3.3 Edge strength calculation -- 8.3.4 Thresholding -- 8.3.5 Refinement -- 8.3.6 Experimental results -- 8.4 Extension to auto-inpaint cracks in videos -- 8.4.1 Homography estimation -- 8.4.2 Reference frame detection -- 8.4.3 Tracking and inpainting cracked regions across frames -- 8.4.4 Experimental results -- 8.5 Conclusion --
9. Challenges and future directions -- Bibliography -- Authors' biographies
Abstract freely available; full-text restricted to subscribers or individual document purchasers
Compendex
INSPEC
Google scholar
Google book search
Mode of access: World Wide Web
System requirements: Adobe Acrobat Reader
Heritage sites across the world have witnessed a number of natural calamities, sabotage and damage from visitors, resulting in their present ruined condition. Many sites are now restricted to reduce the risk of further damage. Yet these masterpieces are significant cultural icons and critical markers of past civilizations that future generations need to see. A digitally reconstructed heritage site could diminish further harm by using immersive navigation or walkthrough systems for virtual environments. An exciting key element for the viewer is observing fine details of the historic work and viewing monuments in their undamaged form. This book presents image superresolution methods and techniques for automatically detecting and inpainting damaged regions in heritage monuments, in order to provide an enhanced visual experience. The book presents techniques to obtain higher resolution photographs of the digitally reconstructed monuments, and the resulting images can serve as input to immersive walkthrough systems. It begins with the discussion of two novel techniques for image super-resolution and an approach for inpainting a user-supplied region in the given image, followed by a technique to simultaneously perform super-resolution and inpainting of given missing regions. It then introduces a method for automatically detecting and repairing the damage to dominant facial regions in statues, followed by a few approaches for automatic crack repair in images of heritage scenes. This book is a giant step toward ensuring that the iconic sites of our past are always available, and will never be truly lost
Also available in print
Title from PDF title page (viewed on January 24, 2017)
鏈接 Print version: 9781627059213
主題 Image reconstruction
Image processing -- Digital techniques
Historic sites -- Conservation and restoration
Statues -- Conservation and restoration
Inpainting
super-resolution
inpainting
cultural heritage
crack detection
digital reconstruction
Alt Author Joshi, Manjunath V., author
Khatri, Nilay L., author
記錄 3 之 13
Record:   Prev Next