Location

Science Center Auditorium, University of Dayton

Start Date

23-4-2016 1:50 PM

Description

We explore the use of extended pixel representation for color based image segmentation using the K-means clustering algorithm. Various extended pixel representations have been implemented in this paper and their results have been compared. By extending the representation of pixels an image is mapped to a higher dimensional space. Unlike other approaches, where data is mapped into an implicit features space of higher dimension (kernel methods), in the approach considered here, the higher dimensions are defined explicitly. Preliminary experimental results which illustrate the proposed approach are promising.

Comments

Copyright © 2016 by the authors. This paper was presented at the 2016 Modern Artificial Intelligence and Cognitive Science Conference, held at the University of Dayton April 22-23, 2016.

 
Apr 23rd, 1:50 PM

Extended Pixel Representation for Image Segmentation

Science Center Auditorium, University of Dayton

We explore the use of extended pixel representation for color based image segmentation using the K-means clustering algorithm. Various extended pixel representations have been implemented in this paper and their results have been compared. By extending the representation of pixels an image is mapped to a higher dimensional space. Unlike other approaches, where data is mapped into an implicit features space of higher dimension (kernel methods), in the approach considered here, the higher dimensions are defined explicitly. Preliminary experimental results which illustrate the proposed approach are promising.