ABSTRACT
This paper presents a novel clustering-based approach for computing a salient object. The key idea of the proposed method is that saliency is detected by using multiple color models with different Gaussian filters to derive various segmentation results. The proposed method consists of two main processes: mean-shift based saliency (MS) and Bayesian based saliency (BS). First, three different models for the input image are created using different Gaussian filters. Then, the MS process categorizes all of the pixels, and the categorized results are utilized to extract saliency using centroid weight map (CWM) and foreground estimation (FE). For the BS method, saliency is detected in a similar manner, but the difference between MS and BS is that the BS categorizes all of the pixels using the prior knowledge from mean-shift results. In the experimental results, the scheme achieved superior detection accuracy in the MSRA-ASD benchmark database with both a higher precision and better recall than state-of-the-art saliency detection methods.
- Berengolts, A. Lindenbaum, M. 2006. "On the distribute of saliency," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, 973--1990. Google ScholarDigital Library
- Koch, C. Ullman, S. 1985. Shifts in selective visual attention: towards the underlying neural circuitry," Human Neurobiology, vol. 4, no. 4, 19--227.Google Scholar
- Ye Luo, Yuan Jun Song, 2013. "Salient object detection in video by optimal spatio-temporal path discovery," Proceedings of the 21st ACM international conference on Multimedia, 509--512. Google ScholarDigital Library
- Khuwuthyakorn, P. Robles-Kelly, A. Zhou, J. 2010. "Object of interest detection by Saliency Learning," Proceedings of the 11th European Conference on Computer Vision: part 2, vol. 6312, 636--649. Google ScholarDigital Library
- Bonaiuto, J. Itti, L. 2005. "Combining attention and recognition for rapid scene analysis," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition---Workshops, 90--97. Google ScholarDigital Library
- Li, Z. Qin, S. and Itti, L. 2011. "Visual attention guided bit allocation in video compression," Image and Video Computing, vol. 29, no. 1, 1--14. Google ScholarDigital Library
- R. Achanta, S. Susstrunk, "Saliency detection using maximum symmetric surround," Proceedings of the IEEE International Conference on Image Processing, 2010, 2653--2656.Google Scholar
- Kootstra, G. de Boer, B. Schomaker, L. 2011. "Predicting eye fixations on complex visual stimuli using local symmetry," Cognitive Computation, vol 3, no 1, 223--240.Google ScholarDigital Library
- Rosin, P. L. 2009. "A simple method for detecting salient regions," Pattern Recognition 42, 2363--2371. Google ScholarDigital Library
- Greenspan, H. Belongie, S. Goodman, R. Perona, P. Rakshit, S. and Anderson, C. H. 1994. "Overcomplete steerable pyramid filters and rotation invariance," Proc. IEEE Computer Vision and Pattern Recognition, 222--228.Google Scholar
- Avraham, T. Lindenbaum, M. 2010. "Esaliency (extended saliency): meaningful attention using stochastic image modeling," IEEE Transactions on Pattern Analysis and Machine Intelligence 32, 693--708. Google ScholarDigital Library
- Achanta, R. Hemami, S. Estrada, F. Susstrunk, S. 2009. "Frequency-tuned salient region detection," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1597--1604.Google Scholar
- X. Hou, L. Zhang, "Dynamic visual attention: Searching for coding length increments," Proceedings of the 21th Annual Conference on Neural Information Processing Systems (NIPS'08), 2008, 681--688.Google Scholar
- X. D. Hou, J. Harel, C. Koch, "Image signature: highlighting sparse salient regions," IEEE Trans. Pattern Anal. Mach, vol. 34, no. 1, 2012, 194--201. Google ScholarDigital Library
- Yang, W. Tang, Y. Fang, B. Shang, Z. Lin, Y. 2013. "Visual saliency detection with center shift." Neurocomputing, vol. 103 no. 1, 63--74. Google ScholarDigital Library
- Yanulevskaya, V. Geusebroek, J. M. 2009. "Significance of the Weibull distribution and its sub-models in natural image statistics," Proceedings of the International Conference on Computer Vision Theory and Applications, 355--362.Google Scholar
- Torralba, A. Oliva, M. S. Castelhano, and Henderson, J. M. 2006. "Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search," Psychol. Rev. vol. 113 no. 4, 766--786.Google ScholarCross Ref
- Alexe, B. Deselaers, T. Ferrari, V. "What is an object?," Proceedings of CVPR, 2010, 73--80.Google Scholar
- KangHan Oh, SooHyung Kim and InSeop Na, 2014. "Saliency detection using Centroid Weight Map," Proc. Int. Conf. Ubiquitous Information Management and Communication 2014(CD-Pub), Aticle No. 107. Google ScholarDigital Library
- HsinHo Yeh, KengHao Liu, ChuSong Chen, 2014. "Salient object detection via local saliency estimation and global homogeneity refinement. Pattern Recognition," vol. 44, 1740--1750. Google ScholarDigital Library
- E. Rahtu, J. Kannala, M. Salo, "Segmenting salient objects from images and videos," in: ECCV, 2010, 366--379. Google ScholarDigital Library
- Klein, D. Frintrop, S. 2011. "Center-surround divergence of features tatistics for salient object detection," ICCV, 2214--2219. Google ScholarDigital Library
- Comaniciu, D. and Meer, P. 2002. "Mean shift: A robust approach toward feature space analysis," IEEE Trans. Pattern Anal. Machine vol. 24, 603--619. Google ScholarDigital Library
- Harel, J. Koch, C. and Perona, P. 2006. "Graph-based visual saliency." Advances in neural information processing systems, 545--552.Google Scholar
- Perazzi, F. Krahenbuhl, P. Pritch, Y. Hornung, A.2012. "Saliency filters: contrast-based filtering for salient region detection," CVPR, 733--740. Google ScholarDigital Library
- Yuan, Y. B. Vorburger, T. V. Song, J. F. Renegar, T. B. 2000. "A Simplified Realization for the Gaussian Filter in Surface Metrology", International Colloquium on Surfaces, Chemnitz (Germany).Google Scholar
- Itti, L. Koch, C. and Niebur, E. 1998. "A model of saliency-based visual attention for rapid scene analysis," IEEE TPAMI, vol. 20, no. 11, 1254--1259. Google ScholarDigital Library
- Colby, C. L. Goldberg, M. E. 1999. "Space and attention in parietal cortex," Proceedings of the Annual Review of Neuroscience, vol. 22, 319--349.Google ScholarCross Ref
- Kienzle, W. Wichmann, F. A. 2007. "Franz, A nonparametric approach to bottom-up visual saliency," Advances in Neural Information Processing Systems, 689--696.Google Scholar
- Liu, Z. Xue, Y. Shen, L. and Zhang, Z. 2010."Nonparametric saliency detection using kernel density estimation," Proceedings of the IEEE International Conference on Image Processing, 253--256.Google Scholar
- Liu, T. Sun, J. Zheng, N.-N. Tang, X. 2007. "Shum Learning to detect a salient object," IEEE Conference on Computer Vision and Pattern Recognition, 1--8.Google Scholar
- Achanta, R. Estrada, F. Wils, P. and Susstrunk, S. 2008. "Salient region detection and segmentation." International Conference on Computer Vision Systems (ICVS '08), Vol. 5008, Springer Lecture Notes in Computer Science, 66--75. Google ScholarDigital Library
- Ma, Y.-F. and Zhang, H.-J. 2003. "Contrast-based image attention analysis by using fuzzy growing," ACM Multimedia, 374--381. Google ScholarDigital Library
Index Terms
- Salient object detection by combining multiple color clustering
Recommendations
A color saliency model for salient objects detection in natural scenes
MMM'10: Proceedings of the 16th international conference on Advances in Multimedia ModelingDetection of salient objects is very useful for object recognition, content-based image/video retrieval, scene analysis and image/video compression. In this paper, we propose a color saliency model for salient objects detection in natural scenes. In our ...
Exploiting contrast cues for salient region detection
Visual saliency detection is an important cue used in human visual system, which can offer efficient solutions for both biological and artificial vision systems. Although there are many saliency detection models that can achieve good results on public ...
Visual saliency detection based on region descriptors and prior knowledge
Visual saliency detection not only plays a significant role, but it is also a challenging task in computer vision. In this paper we propose a new method for saliency detection. It incorporates visual features and spatial information with a guidance of ...
Comments