Graph Laplacian for Spectral Clustering and Seeded Image Segmentation
Wallace Casaca$^{1}$
$^{1}$University of Sao Paulo. São Carlos-SP Brazil
email: wallace@icmc.usp.br

Schedule:Thu 22st@11:15, Room: A

Image segmentation is an indispensable tool to enhance the ability of computer systems to perform elementary cognitive tasks such as detection, recognition and tracking. In particular, interactive algorithms have gained much attention lately, specially due to their good performance in segmenting complex images and easy utilization. However, most interactive segmentation methods rely on sophisticated mathematical tools whose effectiveness strongly depends on the kind of image to be processed. In fact, sharp adherence to the contours of image segments, uniqueness of solution, high computational burden, and extensive user intervention are some of the weaknesses of most existing techniques. In this work we proposed two novel interactive image segmentation techniques that sort out the issues discussed above. The proposed methods rely on Laplace operators, spectral graph theory, and optimization approaches towards enabling highly accurate segmentation tools which demand a reduced amount of user interaction while still being mathematically simple and computationally efficient. The good performance of our segmentation algorithms is attested by a comprehensive set of comparisons against representative stateof-the-art methods. Indeed, qualitative and quantitative results obtained from well-known image benchmarks show that our methodologies outperform others. As additional contribution, we have also proposed two new algorithms for image inpainting and photo colorization, both of which rely on the accuracy of our segmentation apparatus.

BibTex

@InProceedings{CLEI-2015:144096,
	author 		= {Wallace Casaca},
	title 		= {Graph Laplacian for Spectral Clustering and Seeded Image Segmentation},
	booktitle 	= {2015 XLI Latin American Computing Conference (CLEI), Special Edition},
	pages 		= {167--186},
	year 		= {2015},
	editor 		= {Universidad Católica San Pablo},
	address 	= {Arequipa-Peru},
	month 		= {October},
	organization 	= {CLEI},
	publisher 	= {CLEI},
	url 		= {http://clei.org/clei2015/144096},
	isbn 		= {978-9972-825-91-0},
	}