Automated Color Clustering for Medieval Manuscript Analysis

Thumbnail Image
Date
2015
Authors
Yang, Ying
Pintus, Ruggero
Gobbetti, Enrico
Rushmeier, Holly
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Abstract
Given a color image of a medieval manuscript page, we propose a simple, yet efficient algorithm for automatically estimating the number of its color-based pixel groups, K. We formulate this estimation as a minimization problem, where the objective function assesses the quality of a candidate clustering. Rather than using all the features of the given image, we carefully select a subset of features to perform clustering. The proposed algorithm was extensively evaluated on a dataset of 2198 images (1099 original images and their 1099 variants produced by modifying both spatial and spectral resolutions of the originals) from the Yale's Institute for the Preservation of Cultural Heritage (IPCH). The experimental results show that it is able to yield satisfactory estimates of K for these test images.
Description

        
@inproceedings{
10.1109:DigitalHeritage.2015.7419462
,
booktitle = {
International Congress on Digital Heritage - Theme 3 - Analysis And Interpretation
},
editor = {
Gabriele Guidi  and Roberto Scopigno and Juan Barceló
},
title = {{
Automated Color Clustering for Medieval Manuscript Analysis
}},
author = {
Yang, Ying
 and 
Pintus, Ruggero
 and 
Gobbetti, Enrico
 and 
Rushmeier, Holly
},
year = {
2015
},
publisher = {
IEEE
},
ISBN = {
978-1-5090-0048-7
},
DOI = {
10.1109/DigitalHeritage.2015.7419462
}
}
Citation
URI
https://doi.org/10.1109/DigitalHeritage.2015.7419462
Collections
DH2015 - Track 3