KL Divergence Based Agglomerative Clustering for Automated Vitiligo Grading

Mithun Das Gupta, Srinidhi Srinivasa, Madhukara J., Meryl Antony; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 2700-2709

Abstract


In this paper we present a symmetric KL divergence based agglomerative clustering framework to segment multiple levels of depigmentation in Vitiligo images. The proposed framework starts with a simple merge cost based on symmetric KL divergence. We extend the recent body of work related to Bregman divergence based agglomerative clustering and prove that the symmetric KL divergence is an upper-bound for uni-modal Gaussian distributions. This leads to a very simple yet elegant method for bottomup agglomerative clustering. We introduce albedo and reflectance fields as features for the distance computations. We compare against other established methods to bring out possible pros and cons of the proposed method.

Related Material


[pdf]
[bibtex]
@InProceedings{Gupta_2015_CVPR,
author = {Das Gupta, Mithun and Srinivasa, Srinidhi and J., Madhukara and Antony, Meryl},
title = {KL Divergence Based Agglomerative Clustering for Automated Vitiligo Grading},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}