Close
Metadata

%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2015/06.12.04.07
%2 sid.inpe.br/sibgrapi/2015/06.12.04.07.28
%T IFT-SLIC: A general framework for superpixel generation based on simple linear iterative clustering and image foresting transform
%D 2015
%A Alexandre, Eduardo Barreto,
%A Chowdhury, Ananda Shankar,
%A Falcão, Alexandre Xavier,
%A Miranda, Paulo A. Vechiatto,
%@affiliation Institute of Mathematics and Statistics (IME), Dept. of Computer Science, University of São Paulo (USP)
%@affiliation Dept. of Electronics and Telecommunication Engineering, Jadavpur University, Kolkata, India
%@affiliation Institute of Computing, Dept. of Information Systems, University of Campinas
%@affiliation Institute of Mathematics and Statistics (IME), Dept. of Computer Science, University of São Paulo (USP)
%E Papa, João Paulo,
%E Sander, Pedro Vieira,
%E Marroquim, Ricardo Guerra,
%E Farrell, Ryan,
%B Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)
%C Salvador
%8 Aug. 26-29, 2015
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%K Simple Linear Iterative Clustering, Image Foresting Transform, Superpixel, unsupervised segmentation.
%X Image representation based on superpixels has become indispensable for improving efficiency in Computer Vision systems. Object recognition, segmentation, depth estimation, and body model estimation are some important problems where superpixels can be applied. However, superpixels can influence the efficacy of the system in positive or negative manner, depending on how well they respect the object boundaries in the image. In this paper, we improve superpixel generation by extending a popular algorithm - Simple Linear Iterative Clustering (SLIC) - to consider minimum path costs between pixel and cluster centers rather than their direct distances. This creates a new Image Foresting Transform (IFT) operator that naturally defines superpixels as regions of strongly connected pixels by choice of the most suitable path-cost function for a given application. Non-smooth connectivity functions are also explored in our IFT-SLIC approach leading to improved performance. Experimental results indicate better superpixel extraction using the proposed approach as compared to that of SLIC.
%@language en
%3 00078.pdf


Close