Co-segmentation of multiple similar images using saliency detection and region merging
- Author(s): Chongbo Zhou 1, 2 and Chuancai Liu 1
-
-
View affiliations
-
Affiliations:
1:
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, People's Republic of China;
2: School of Physics and Engineering, Qufu Normal University, Qufu, Shandong 273165, People's Republic of China
-
Affiliations:
1:
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, People's Republic of China;
- Source:
Volume 8, Issue 3,
June 2014,
p.
254 – 261
DOI: 10.1049/iet-cvi.2012.0266 , Print ISSN 1751-9632, Online ISSN 1751-9640
- « Previous Article
- Table of contents
- Next Article »
The aim of co-segmentation is to simultaneously segment multiple images depicting an identical or similar object. In this study, a co-segmentation method using saliency detection and region merging is proposed. The saliency detection results using different detection methods on different types of colour space are combined to produce seed regions for each image in the image group. The initial seed regions of all the images are refined by eliminating the dissimilar ones to ensure accurate seed regions for each images as possible. Region merging is performed on each image individually in order to allow our method to be applied to large image groups. The maximal similarity measurement and nearest similarity measurement are defined as merging rules. The deliberately designed merging strategy aims to merge two regions using the maximal similarity rule and label two regions as the same class but not merge them using the nearest similarity rule. The proposed method has been compared with some state-of-the-art methods on three datasets, and the experimental results show its effectiveness.
Inspec keywords: image segmentation
Other keywords: nearest similarity measurement; saliency detection; region merging; multiple similar images cosegmentation; maximal similarity measurement
Subjects: Computer vision and image processing techniques; Optical, image and video signal processing
References
-
-
1)
-
20. Calderero, F., Marques, F.: ‘Region merging techniques using information theory statistical measures’, IEEE Trans. Image Process., 2010, 19, (6), pp. 1567–1586 (doi: 10.1109/TIP.2010.2043008).
-
-
2)
- P.F. Felzenszwalb , D.P. Huttenlocher . Efficient graph-based image segmentation. Int. J. Comput. Vision , 2 , 167 - 181
-
3)
- D. Comaniciu , P. Meer . Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. , 5 , 603 - 619
-
4)
- L. Vincent , P. Soille . Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Trans. Pattern Anal. Mach. Intell. , 6 , 583 - 598
-
5)
-
21. Meng, F., Li, H., Liu, G., Ngan, K.N.: ‘Object co-segmentation based on shortest path algorithm and saliency model’, IEEE Trans. Multimedia, 2012, 14, (5), pp. 1429–1441 (doi: 10.1109/TMM.2012.2197741).
-
-
6)
-
6. Liu, G., Lin, Z., Yu, Y., Tang, X.: ‘Unsupervised object segmentation with a hybrid graph model’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (5), pp. 910–924 (doi: 10.1109/TPAMI.2009.40).
-
-
7)
-
3. Lee, Y., Grauman, K.: ‘Object-graphs for context-aware visual category discovery’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (2), pp. 346–358 (doi: 10.1109/TPAMI.2011.122).
-
-
8)
-
15. Chai, Y., Lempitsky, V., Zisserman, A.: ‘BiCoS: a bi-level co-segmentation method for image classification’. Proc. Int. Conf. Computer Vision, Barcelona, Spain, 2011, pp. 2579–2586.
-
-
9)
-
29. Kumar, A., Singh, U.P.: ‘Image segmentation using graphical models: a survey’, Int. J. Emerging Technol. Adv. Eng., 2012, 2, (3), pp. 290–294.
-
-
10)
-
21. Meng, F., Li, H., Liu, G., Ngan, K.N.: ‘Object co-segmentation based on shortest path algorithm and saliency model’, IEEE Trans. Multimedia, 2012, 14, (5), pp. 1429–1441 (doi: 10.1109/TMM.2012.2197741).
-
-
11)
-
12. Hochbaum, D., Singh, V.: ‘An efficient algorithm for co-segmentation’. Proc. Int. Conf. Computer Vision, Kyoto, Japan, 2009, pp. 269–276.
-
-
12)
-
27. Nilsback, M., Zisserman, A.: ‘A visual vocabulary for flower classification’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, New York, USA, 2006, pp. 1447–1454.
-
-
13)
-
28. Shotton, J., Winn, J., Rother, C., Criminisi, A.: ‘Textonboost: joint appearance, shape and context modeling for multi-class object recognition and segmentation’. Proc. European Conf. Computer Vision, Graz, Austria, 2006, pp. 1–15.
-
-
14)
-
10. Batra, D., Kowdle, A., Parikh, D., Luo, J., Chen, T.: ‘iCoseg: interactive co-segmentation with intelligent scribble guidance’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Francisco, USA, 2010, pp. 3169–3176.
-
-
15)
-
13. Long, Y., Huang, Y.: ‘Image based source camera identification using demosaicking’. Proc. IEEE Eighth Workshop on Multimedia Signal Processing, Victoria, Canada, 2006, pp. 419–424.
-
-
16)
-
11. Mukherjee, L., Singh, V., Dyer, C.: ‘Half-integrality based algorithms for cosegmentation of images’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Miami, USA, 2009, pp. 2028–2035.
-
-
17)
-
30. Moore, A.P., Prince, S., Warrell, J., Mohammed, U., Jones, G.: ‘Superpixel lattices’. IEEE Proc. Computer Vision and Pattern Recognition, 2008, pp. 1–8.
-
-
18)
-
26. Calderero, F., Marques, F.: ‘Region merging techniques using information theory statistical measures’, IEEE Trans. Image Process., 2010, 19, (6), pp. 1567–1586 (doi: 10.1109/TIP.2010.2043008).
-
-
19)
-
14. Chang, K., Liu, T., Lai, S.: ‘From co-saliency to co-segmentation: an efficient and fully unsupervised energy minimization model’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Colorado Springs, USA, 2011, pp. 2129–2136.
-
-
20)
-
5. Carreira, J., Sminchisescu, C.: ‘Constrained parametric min-cuts for automatic object segmentation’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Francisco, USA, 2010, pp. 3241–3248.
-
-
21)
-
8. Joulin, A., Bach, F., Ponce, J.: ‘Discriminative clustering for image co-segmentation’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Francisco, USA, 2010, pp. 1943–1950.
-
-
22)
-
23. Felzenszwalb, P., Huttenlocher, D.: ‘Efficient graph-based image segmentation’, Int. J. Comput. Vis., 2004, 59, (2), pp. 167–181 (doi: 10.1023/B:VISI.0000022288.19776.77).
-
-
23)
-
7. Rother, C., Kolmogorov, V., Minka, T., Blake, A.: ‘Cosegmentation of image pairs by histogram matching – incorporating a global constraint into MRFs’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, New York, USA, 2006, pp. 993–1000.
-
-
24)
-
1. Kumar, M., Turki, H., Preston, D., Koller, D.: ‘Learning specific-class segmentation from diverse data’. Proc. Int. Conf. Computer Vision, Barcelona, Spain, 2011, pp. 1800–1807.
-
-
25)
-
25. Vincent, L., Soille, P.: ‘Watersheds in digital spaces: an efficient algorithm based on immersion simulations’, IEEE Trans. Pattern Anal. Mach. Intell., 1991, 13, (6), pp. 583–598 (doi: 10.1109/34.87344).
-
-
26)
-
16. Joulin, A., Bach, F., Ponce, J.: ‘Multi-class cosegmentation’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Providence, USA, 2012, pp. 542–549.
-
-
27)
-
9. Cheng, D., Figueiredo, M.: ‘Cosegmentation for image sequences’. Proc. Int. Conf. Image Analysis and Processing, Modena, Italy, 2007, pp. 635–640.
-
-
28)
-
24. Comaniciu, D., Meer, P.: ‘Mean shift: A robust approach toward feature space analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (5), pp. 603–619 (doi: 10.1109/34.1000236).
-
-
29)
-
20. Kim, G., Xing, E., Fei-Fei, L., Kanade, T.: ‘Distributed cosegmentation via submodular optimization on anisotropic diffusion’. Proc. Int. Conf. Computer Vision, Barcelona, Spain, 2011, pp. 169–176.
-
-
30)
-
18. Mukherjee, L., Singh, V., Peng, J.: ‘Scale invariant cosegmentation for image groups’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Colorado Springs, USA, 2011, pp. 1881–1888.
-
-
31)
-
17. Kim, E., Li, H., Huang, X.: ‘A hierarchical image clustering cosegmentation framework’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Providence, USA, 2012, pp. 686–693.
-
-
32)
-
19. Vicente, S., Rother, C., Kolmogorov, V.: ‘Object cosegmentation’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Colorado Springs, USA, 2011, pp. 2217–2224.
-
-
33)
-
2. Lee, Y., Grauman, K.: ‘Collect-cut: segmentation with top-down cues discovered in multi-object images’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Francisco, USA, 2010, pp. 3185–3192.
-
-
34)
-
4. Endres, I., Hoiem, D.: ‘Category independent object proposals’. Proc. European Conf. Computer Vision, Heraklion, Greece, 2010, pp. 575–588.
-
-
35)
-
22. Rubio, J., Serrat, J., Lopez, A., Paragios, N.: ‘Unsupervised co-segmentation through region matching’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Providence, USA, 2012, pp. 749–756.
-
-
36)
-
6. Liu, G., Lin, Z., Yu, Y., Tang, X.: ‘Unsupervised object segmentation with a hybrid graph model’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (5), pp. 910–924 (doi: 10.1109/TPAMI.2009.40).
-
-
37)
-
3. Lee, Y., Grauman, K.: ‘Object-graphs for context-aware visual category discovery’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (2), pp. 346–358 (doi: 10.1109/TPAMI.2011.122).
-
-
1)