Kernel fitting for image segmentation

Previously, a classifier called Kernel-based Nonlinear Representor (KNR) was proposed for pattern classification. In this paper KNR is changed to curve fitting for image segmentation applications. For each gray level, a curve is estimated by KNR and separated from that of a higher gray level by a th...

Full description

Saved in:
Bibliographic Details
Published in2008 International Conference on Machine Learning and Cybernetics Vol. 5; pp. 2914 - 2917
Main Authors Ben-Yong Liu, Wen-Yue Wu, Xiao-Wei Chen
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2008
Subjects
Algorithm design and analysis
Curve fitting
Histograms
Image segmentation
Kernel
Kernel method
Kernel-based nonlinear representor (KNR)
Machine learning
Machine learning algorithms
Thresholding
Online AccessGet full text

Cover

More Information
Summary:Previously, a classifier called Kernel-based Nonlinear Representor (KNR) was proposed for pattern classification. In this paper KNR is changed to curve fitting for image segmentation applications. For each gray level, a curve is estimated by KNR and separated from that of a higher gray level by a threshold obtained from Newman-Pearson criterion. The thresholds are then merged into a few representative ones, with an ideal high-pass filtering approach, for image segmentation. Feasibility of the presented method in image segmentation is illustrated by some experimental results.
ISBN:1424420954
9781424420957
ISSN:2160-133X
DOI:10.1109/ICMLC.2008.4620906