Call For Paper Volume:4 Issue:8 Aug'2017 |

OSS Optimized Superpixel Segmentation

Publication Date : 30/09/2015

Author(s) :

Rintu Chacko , Divya M Moni.

Volume/Issue :
Volume 2
Issue 9
(09 - 2015)

Abstract :

Optimized superpixel segmentation is an approach using lazy random walk and an energy optimization algorithm. The first step is to initializing the seed positions and runs the lazy random walk algorithm on the input to obtain the probabilities of each pixel. The initial superpixels are iteratively optimized by the new optimization function, which is defined based on the texture measurement LBP.  Lazy random walk algorithm has the advantage of segmenting the weak boundaries and complicated texture regions by the global probability maps. The superpixel performance is improved by relocating the seed positions of superpixels and splitting the large superpixels into small ones with the optimization algorithm and for foreground object separation use combination of these two methods.

No. of Downloads :



Web Design MymensinghPremium WordPress ThemesWeb Development

OSS Optimized Superpixel Segmentation

September 29, 2015