File(s) under permanent embargo
Class-driven color transformation for semantic labeling
conference contribution
posted on 2015-01-01, 00:00 authored by Arash Shahriari, Jose M Alvarez, Antonio Robles-KellyAntonio Robles-KellyWe propose a novel class-driven color transformation aimed at semantic labeling. In contrast with other approaches elsewhere in the literature, our approach is a supervised one employing class information to learn a color transformation. Our method maps image color to a target space with maximum pairwise distances between classes and minimum scattering within each of them. To compute the color transformation, we pose the problem in terms of a composition of two mappings. The first mapping employs a pairwise discriminant cost function minimized through a steepest descent optimization to map the image color data onto a space spanned by the class set. It targets better separability between distinct classes as well as less scattering within each individual class. The second mapping corresponds to subspace projection of this class data to a target space with same dimensionality of image color data. To preserve distances attained by the first of the mappings, this subspace projection is effected making use of metric multi-dimensional scaling. We report our experiments on MSRC-21 and SBD datasets, where our method consistently improves overall and average performances of well-known publicly available TextonBoost and DARWIN multiclass segmentation frameworks at a negligible computational cost. These results confirms our contribution towards reflection of higher distinction in color space by imposing better separability in a novel representation which is learned from class information of the dataset under consideration.
History
Event
Computer Vision. Asian Conference (12th : 2014 : Singapore)Volume
9005Series
Lecture Notes in Computer SciencePagination
436 - 451Publisher
SpringerLocation
SingaporePlace of publication
Cham, SwitzerlandPublisher DOI
Start date
2014-11-01End date
2014-11-05ISBN-13
9783319168111Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
2015, Springer International PublishingEditor/Contributor(s)
D Cremers, I Reid, H Saito, M YangTitle of proceedings
ACCV 2014 : Asian Conference on Computer VisionUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC