Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/161099
Title: Novel Techniques for Auto inpainting in Heritage Reconstruction
Researcher: Padalkar, Milind Gajanan
Guide(s): Joshi, manjunath V.
Keywords: Inpainting
cultural heritage
super-resolution
textons
digital reconstruction
detection
homography
video quality
University: Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT)
Completed Date: 2016
Abstract: Digital reconstruction of ruined historic monuments and heritage sites can help in visualizing how these may have existed in the past. Also, such a process requires no physical alteration to the existing monuments. This facilitates in avoiding their further accidental damage. A digitally reconstructed heritage site in the form of an immersive walkthrough can serve as a delightful tool for both educational and entertainment purpose.This thesis presents novel approaches for auto-inpainting that involves image inpainting as well as automatic detection of cracks and other damaged regions for newlineinpainting in heritage monuments. As a by-product of one of our inpainting techniques, we are also able to perform resolution enhancement i.e. super-resolution.The purpose is to obtain the digitally reconstructed monuments having enhanced resolution, where the digital reconstruction is performed by automatically detecting and inpainting the damaged regions. The resulting images can serve as an input to immersive walkthrough systems. In our first inpainting approach, newlinewe propose an iterative exemplar based method that fills the missing pixels by making use of parameters of an autoregressive (AR) model. These parameters represent the pixel-neighborhood relationship. Considering a set of candidate exemplars, we estimate the parameters of the AR model using the non-negatively constrained least squares (NNLS) method. newlineIn our second inpainting approach, we propose a unified framework to perform simultaneous inpainting and super-resolution. Here, we construct dictionaries of image-representative low and high resolution patch pairs from the known newlineregions in the test image and its coarser resolution. Inpainting of the missing pixels is performed using exemplars found by comparing patch details at a finer resolution, where self-learning is used to obtain the finer resolution patches by newlinemaking use of the constructed dictionaries. The obtained finer resolution patches represent the super-resolved patches in the missing regions.
Pagination: xx, 149 p.
URI: http://hdl.handle.net/10603/161099
Appears in Departments:Department of Information and Communication Technology

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File84.31 kBAdobe PDFView/Open
02_declaration and certificate.pdf76.97 kBAdobe PDFView/Open
03_acknowledgements.pdf82.1 kBAdobe PDFView/Open
04_contents.pdf81.95 kBAdobe PDFView/Open
05_abstract.pdf58.99 kBAdobe PDFView/Open
06_list of tables.pdf63.24 kBAdobe PDFView/Open
07_list of figures.pdf214.28 kBAdobe PDFView/Open
08_chapter 1.pdf119.13 kBAdobe PDFView/Open
09_chapter 2.pdf125.75 kBAdobe PDFView/Open
10_chapter 3.pdf1.2 MBAdobe PDFView/Open
11_chapter 4.pdf6.05 MBAdobe PDFView/Open
12_chapter 5.pdf1.58 MBAdobe PDFView/Open
13_chapter 6.pdf7.17 MBAdobe PDFView/Open
14_chapter 7.pdf20.83 MBAdobe PDFView/Open
15_chapter 8.pdf102.03 kBAdobe PDFView/Open
16_refference.pdf178.81 kBAdobe PDFView/Open
17_list of publication.pdf95.24 kBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.