DocumentCode :
144612
Title :
Matching based image co-segmentation
Author :
Ding-Jie Chen ; Chi-Yun Liu ; Long-Wen Chang
Author_Institution :
Dept. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Volume :
2
fYear :
2014
fDate :
26-28 April 2014
Firstpage :
818
Lastpage :
822
Abstract :
The goal of image co-segmentation is to segment the same or similar objects from a set of images. Unlike traditional methods, we propose a matching based algorithm to achieve this goal. Our method contains two phases. In the first phase, we use a matching algorithm to jointly estimate initial foreground labels of the input images. In the next phase, the labels of each image are used to extract its foreground regions via graph cuts. In contrast to other co-segmentation algorithms, our approach decomposes the co-segmentation problem into the two simpler phases, thus preventing the need to construct a complicated co-segmentation graph model which may cause troublesome optimization. The experimental results show the competitive performance of the proposed method in comparison with other famous image co-segmentation techniques on the CMU-Cornell iCoseg dataset that has variability in object deformations and poses.
Keywords :
graph theory; image matching; image segmentation; CMU-Cornell iCoseg dataset; co-segmentation algorithm; co-segmentation graph model; foreground labels; foreground regions; graph cuts; image co-segmentation; matching algorithm; matching based algorithm; object deformations; troublesome optimization; Accuracy; Feature extraction; Histograms; Image color analysis; Image segmentation; Minimization; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Science, Electronics and Electrical Engineering (ISEEE), 2014 International Conference on
Conference_Location :
Sapporo
Print_ISBN :
978-1-4799-3196-5
Type :
conf
DOI :
10.1109/InfoSEEE.2014.6947781
Filename :
6947781
Link To Document :
بازگشت