Highlight and Shading Invariant Color Image Segmentation Using Simulated Annealing

Authors:
Paul W. Fieguth;Slawo Wesolkowski
Affiliations:
-;-
Venue:
EMMCVPR '01 Proceedings of the Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
Year:
2001

Citing 8
Cited 1

On the color image segmentation algorithm based on the thresholding and the fuzzy C-means techniques

Pattern Recognition
A physical approach to color image understanding

International Journal of Computer Vision
Surface Identification Using the Dichromatic Reflection Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern recognition: statistical, structural and neural approaches

Pattern recognition: statistical, structural and neural approaches
Markov Random Field Models for Unsupervised Segmentation of Textured Color Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised Image Segmentation Using Markov Random Field Models

EMMCVPR '97 Proceedings of the First International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
A region growing and merging algorithm to color segmentation

Pattern Recognition
Automatic watershed segmentation of randomly textured color images

IEEE Transactions on Image Processing

Removing shadows

Pattern Recognition Letters - Special issue: In memoriam Azriel Rosenfeld

Quantified Score

Hi-index	0.00

Visualization

Abstract

Color constancy in color image segmentation is an important research issue. In this paper we develop a framework, based on the Dichromatic Reflection Model for asserting the color highlight and shading invariance, and based on a Markov Random Field approach for segmentation. A given RGB image is transformed into a R'G'B' space to remove any highlight components, and only the vector-angle component, representing color hue but not intensity, is preserved to remove shading effects. Due to the arbitrariness of vector angles for low R'G'B' values, we perform a Monte-Carlo sensitivity analysis to determine pixel-dependent weights for the MRF segmentation. Results are presented and analyzed.