Browse > Article
http://dx.doi.org/10.4218/etrij.2018-0039

Image saliency detection based on geodesic-like and boundary contrast maps  

Guo, Yingchun (School of Artificial Intelligence, Hebei University of Technology)
Liu, Yi (School of Artificial Intelligence, Hebei University of Technology)
Ma, Runxin (Beijing Xinwei Group Co., Ltd)
Publication Information
ETRI Journal / v.41, no.6, 2019 , pp. 797-810 More about this Journal
Abstract
Image saliency detection is the basis of perceptual image processing, which is significant to subsequent image processing methods. Most saliency detection methods can detect only a single object with a high-contrast background, but they have no effect on the extraction of a salient object from images with complex low-contrast backgrounds. With the prior knowledge, this paper proposes a method for detecting salient objects by combining the boundary contrast map and the geodesics-like maps. This method can highlight the foreground uniformly and extract the salient objects efficiently in images with low-contrast backgrounds. The classical receiver operating characteristics (ROC) curve, which compares the salient map with the ground truth map, does not reflect the human perception. An ROC curve with distance (distance receiver operating characteristic, DROC) is proposed in this paper, which takes the ROC curve closer to the human subjective perception. Experiments on three benchmark datasets and three low-contrast image datasets, with four evaluation methods including DROC, show that on comparing the eight state-of-the-art approaches, the proposed approach performs well.
Keywords
boundary contrast map; geodesics-like map; image saliency detection; ROC with distance;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Y. Wei et al., Geodesic saliency using background priors, in Proc. Euro. Conf. Computer Vision, Florence, Italy, Oct. 7-13, 2012, pp. 29-42.
2 S. Goferman, L. Zelnik-Manor, and A. Tal, Context-aware saliency detection, IEEE Trans. Pattern Anal. Mach. Intell. 34 (2012), no. 10, 1915-1926.   DOI
3 C. Zhang et al., Saliency detection via graph-based manifold ranking, in Proc. IEEE Conf, Comput. Vision Pattern Recogn., Portland, OR, USA, June 23-28, pp. 2013, pp. 3166-3173.
4 P. Neubert, N. Sunderhauf, and P. Protzel, Superpixel-based appearance change prediction for long-term navigation across seasons, Rob Auton. Syst. 69 (2015), 15-27.   DOI
5 R. Achanta et al., Slic superpixels compared to state-of-the-art superpixel methods, IEEE Trans. Pattern Anal. Mach. Intell. 34 (2012), no. 11, 2274-2282.   DOI
6 Z. Bylinskii et al., What do different evaluation metrics tell us about saliency models? ArXiv: arXiv:1604.03605v2, 2017.
7 A. Jimenez-Valverde, Insights into the area under the receiver operating characteristic curve (AUC) as a discrimination measure in species distribution modelling, Glob. Ecol. Biogeogr. 21 (2012), 498-507.   DOI
8 H. Jiang et al., Automatic salient object segmentation based on context and shape prior, in Proc. British Mach. Vision Conf., Dundee, UK, Aug. 29-Sept. 2, 2011, pp. 1-12.
9 Y. Xie, H. Lu, and M. H. Yang, Bayesian saliency via low and mid level cues, IEEE Trans. Image Process. 22 (2013), no. 5, 1689-1698.   DOI
10 M. M. Cheng et al., Efficient salient region detection with soft image abstraction, in Proc. Int. IEEE Conf. Computer Vision, Sydney, Australia, Dec. 1-8, 2013, pp. 1529-1536.
11 D. Sen and M. Kankanhalli, A bio-inspired center-surround model for salience computation in images, J. Vis. Commun. Imag. Represent. 30 (2015), 277-288.   DOI
12 Microsoft Research, Available online: Accessed Oct. 20, 2016. http://research.Microsoft.com/enus/um/people/jiansun/salientobject/salient_object.htm.
13 H. Z. Fu, X. C. Cao, and Z. W. Tu, Cluster-based co-saliency detection, IEEE Trans. Image Process. 22 (2013), no. 10, 3766-3778.   DOI
14 Q. Yan et al., Hierarchical saliency detection, in Proc. IEEE Conf. Comput. Vision Pattern Recogn., Portland, OR, USA, June 23-28, 2013, pp. 1155-1162.
15 S. Alpert et al., Image segmentation by probabilistic bottom-up aggregation and cue integration, IEEE Trans. Pattern Anal. Mach. Intell. 34 (2012), 315-327.   DOI
16 J. Li et al., Image saliency estimation via random walk guided by informativeness and latent signal correlations, Image Commun. 38 (2015), 3-14.
17 X. C. Cao et al., Self-adaptively weighted co-saliency detection via rank constraint, IEEE Trans. Image Process. 23 (2014), no. 9, 4175-4186.   DOI
18 H. Jiang et al., Salient object detection: a discriminative regional feature integration approach, in Proc. IEEE Conf. Comput. Vision Pattern Recogn., Portland, OR, USA, June 23-28, 2013, pp. 2083-2090.
19 W. Zhu et al., Saliency optimization from robust background detection, in Proc. IEEE Conf. Comput. Vision Pattern Recogn., Columbus, OH, USA, June 23-28, 2014, pp. 2814-2821.
20 J. Kim et al., Salient region detection via high-dimensional color transform, in Proc. IEEE Conf. Comput. Vision Pattern Recogn., Columbus, OH, USA, June 23-28, 2014, pp. 883-890.
21 L. Yang et al., Balanced dual-band bandpass filter with multiple transmission zeros using doubly short-ended resonator coupled line, IEEE Trans. Microw. Theory Techn. 63 (2015), no. 7, 2225-2232.   DOI
22 S. Li et al., Closed-form optimization on saliency-guided image compression for HEVC-MSP, IEEE Trans. Multi. 20 (2018), no. 1, 155-170.   DOI
23 N. Jiang and L. Wang, Quantum image scaling using nearest neighbor interpolation, Quant. Inform. Process. 14 (2015), no. 2, 1559-1571.   DOI
24 Y. X. Xue et al., Multiple sensors based hand motion recognition using adaptive directed acyclic, Graph, Appli. Sci. 7 (2017), no. 4, 358:1-414.
25 M. Wan et al., Infrared small moving target detection via saliency histogram and geometrical invariability, Appl. Sci. 7 (2017), no. 6, 569:1-614.
26 B. Montrucchio, C. Celozzi, and P. Cerutti, Thresholds of vision of the human visual system: visual adaptation for monocular and binocular vision, IEEE Trans. Human-Mach. Syst. 45 (2015), no. 6, 739-749.   DOI
27 L. Itti, C. Koch, and E. Niebur, A model of saliency-based visual attention for rapid scene analysis, IEEE Trans. Pattern Anal. Mach. Intell. 20 (1998), no. 11, 1254-1259.   DOI
28 R. Achanta et al., Frequency-tuned salient region detection, in IEEE Conf. Comput. Vision Pattern Recogn., Miami, FL, USA, June 20-25, 2009, pp. 1597-1604.
29 H. Peng et al., Salient object detection via structured matrix decomposition, IEEE Trans. Patt. Anal. Mach. Intell. 39 (2017), no. 4, 818-832.   DOI
30 Y. Yuan et al., Reversion correction and regularized random walk ranking for saliency detection, IEEE Trans. Image Process. 27 (2018), no. 3, 1311-1322.   DOI
31 J. Liu and S. Wang, Salient region detection via simple local and global contrast representation, Neurocomput. 147 (2015), 435-443.   DOI
32 M. M. Cheng et al., Global contrast based salient region detection, in IEEE Conf. Comput. Vision Pattern Recogn, Colorado Springs, CO, USA, June 20-25, 2011, pp. 409-416.
33 R. Achanta et al., Salient region detection and segmentation, in Proc. Int. Conf. Comput. Vision Syst., Santorini, Greece, May 12-15, 2008, pp. 66-75.