DocumentCode :
3639282
Title :
Efficient graph-based image segmentation via speeded-up turbo pixels
Author :
Cevahir Çığla;A. Aydın Alatan
Author_Institution :
Department of Electrical and Electronics Engineering M.E.T.U, Turkey
fYear :
2010
Firstpage :
3013
Lastpage :
3016
Abstract :
An efficient graph based image segmentation algorithm exploiting a novel and fast turbo pixel extraction method is introduced. The images are modeled as weighted graphs whose nodes correspond to super pixels; and normalized cuts are utilized to obtain final segmentation. Utilizing super pixels provides an efficient and compact representation; the graph complexity decreases by hundreds in terms of node number. Connected K-means with convexity constraint is the key tool for the proposed super pixel extraction. Once the pixels are grouped into super pixels, iterative bi-partitioning of the weighted graph, as introduced in normalized cuts, is performed to obtain segmentation map. Supported by various experiments, the proposed two stage segmentation scheme can be considered to be one of the most efficient graph based segmentation algorithms providing high quality results.
Keywords :
"Pixel","Image segmentation","Algorithm design and analysis","MATLAB","Pattern analysis","Conferences","Computational complexity"
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2010 17th IEEE International Conference on
ISSN :
1522-4880
Print_ISBN :
978-1-4244-7992-4
Type :
conf
DOI :
10.1109/ICIP.2010.5653963
Filename :
5653963
Link To Document :
بازگشت