Color Restoration of Scanned Archaeological Artifacts with Repetitive Patterns

dc.contributor.authorGilad-Glickman, Daniten_US
dc.contributor.authorShimshoni, Ilanen_US
dc.contributor.editorChiara Eva Catalano and Livio De Lucaen_US
dc.date.accessioned2016-10-05T06:27:42Z
dc.date.available2016-10-05T06:27:42Z
dc.date.issued2016
dc.description.abstractOur work addresses the problem of virtually restoring archaeological artifacts. Virtual restoration is the process of creating a noise-free model of a degraded object, to visualize its original appearance. Our work focuses on restoring the coloring of the object. We considered both 2D and 3D objects, including scans of ancient texts and 3D models of decorated pottery. Our denoising method exploits typical characteristics of archaeological artifacts, such as repetitive decoration motifs and a limited palette of colors. Our classification method is based on minimization of an energy function, which includes a correspondence term, to encourage consistent labeling of similar regions. The energy function is minimized using the Graph-Cuts algorithm.en_US
dc.description.sectionheadersAnalysis and Interpretation
dc.description.seriesinformationEurographics Workshop on Graphics and Cultural Heritage
dc.identifier.doi10.2312/gch.20161392
dc.identifier.isbn978-3-03868-011-6
dc.identifier.issn2312-6124
dc.identifier.pages105-108
dc.identifier.urihttps://doi.org/10.2312/gch.20161392
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/gch20161392
dc.publisherThe Eurographics Associationen_US
dc.subjectI.3.7 [Computer Graphics]
dc.subjectThree Dimensional Graphics and Realism
dc.subjectColor
dc.subjectshading
dc.subjectshadowing
dc.subjectand texture
dc.subjectI.4.6 [Image Processing and Computer Vision]
dc.subjectSegmentation
dc.subjectPixel classification
dc.subjectI.5.3 [Pattern Recognition]
dc.subjectClustering
dc.subjectSimilarity measures
dc.titleColor Restoration of Scanned Archaeological Artifacts with Repetitive Patternsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
105-108.pdf
Size:
1.46 MB
Format:
Adobe Portable Document Format