Abstract
In this paper, a bottom-up salient object detection method is proposed by modeling image as a random graph. The proposed method starts with portioning input image into superpixels and extracting color and spatial features for each superpixel. Then, a complete graph is constructed by employing superpixels as nodes. A high edge weight is assigned into a pair of superpixels if they have high similarity. Next, a random walk prior on nodes is assumed to generate the probability distribution on edges. On the other hand, a complete directed graph is created that each edge weight represents the probability for transmitting random walker from current node to next node. By considering a threshold and eliminating edges with higher probability than the threshold, a random graph is created to model input image. The inbound degree vector of a random graph is computed to determine the most salient nodes (regions). Finally, a propagation technique is used to form saliency map. Experimental results on two challenging datasets: MSRA10K and SED2 demonstrate the efficiency of the proposed unsupervised RG method in comparison with the state-of-the-art unsupervised methods.
Similar content being viewed by others
References
Achanta R, Estrada F, Wils P, Süsstrunk S (2008) Salient region detection and segmentation, in: Comput. Vis. Syst., Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 66–75
Achanta R, Hemami S, Estrada F, Susstrunk S (2009) Frequency-tuned salient region detection. In: 2009 I.E. Conf. Comput. Vis. Pattern Recognit, IEEE, pp 1597–1604
Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2012) SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34:2274–2281
Alpert S, Galun M, Basri R, Brandt A (2007) Image segmentation by probabilistic bottom-up aggregation and cue integration. In: 2007 I.E. Conf. Comput. Vis. Pattern Recognit, IEEE, pp 1–8
Borji A (2015) What is a salient object ? A dataset and a baseline model for salient object detection. IEEE Trans Pattern Anal Mach Intell 24:742–756
Borji A, Cheng M-M, Jiang H, Li J (2015) Salient object detection: a benchmark. IEEE Trans Image Process 24:5706–5722
Buso V, Benois-Pineau J, Domenger J-P (2015) Geometrical cues in visual saliency models for active object recognition in egocentric videos. Multimed. Tools Appl. 74:10077–10095
Chakraborty S, Mitra P (2016) A dense subgraph based algorithm for compact salient image region detection. Comput Vis Image Underst 145:1–14
Cheng M-M, Mitra NJ, Huang X, Torr PHS, Hu S-M (2015) Global contrast based salient region detection. IEEE Trans Pattern Anal Mach Intell 37:569–582
Elazary L, Itti L, Bayesian A (2010) Model for efficient visual search and recognition. Vis Res 50:1338–1352
Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph based image segmentation. Int Conf Comput Vis:167–181
Fu K, Gu IYH, Yun Y, Gong C, Yang J (2014) Graph construction for salient object detection in videos, 2014. In: 22nd Int. Conf. Pattern Recognit, pp 2371–2376
Gilbert EN (1959) Random graphs. Ann Math Stat 30(4):1141–1144
Gopalakrishnan V, Hu Y, Rajan D (2010) Random walks on graphs for salient object detection in images. IEEE Trans Image Process 19:3232–3242
Harel J, Koch C, Perona P (2007) Graph-based visual saliency. In: Advances in neural information processing systems. MIT Press, Cambridge, pp 545–552
Huang S, Wang W, Zhang H (2014) Retrieving images using saliency detection and graph matching. In: 2014 I.E. Int. Conf. Image Process, IEEE, pp 3087–3091
Jiang B, Zhang L (2013) H. Lu, C. Yang, M.-H. Yang, saliency detection via absorbing Markov chain. In: Comput. Vis. (ICCV), 2013 I.E. Int. Conf, pp 1665–1672
Kim C, Kim J, Sim J (2014) Multiscale saliency detection using random walk with restart. IEEE Trans. Circuits Syst. Video Technol. 24:198–210
Li Y, Li Y (2016) A fast and efficient saliency detection model in video compressed-domain for human fixations prediction. Multimed. Tools Appl
Li X, Li Y, Shen C, Dick A, Van Den Hengel A (2013) Contextual hypergraph modeling for salient object detection. In: Proc. IEEE Int. Conf. Comput. Vis, pp 3328–3335
Liu T, Sun J, Zheng N, Tang X, Shum H-Y (2007) Learning to detect a salient object, in: 2007 I.E. Conf. Comput. Vis. Pattern Recognit. IEEE:1–8
Liu T, Yuan Z, Sun J, Wang J, Zheng N, Tang X, Shum HY (2011) Learning to detect a salient object. IEEE Trans Pattern Anal Mach Intell 33:353–367
Rasouli A, Tsotsos JK (2015) Integrating three mechanisms of visual attention for active visual search, in: 8th Int. Symp. Atten. Cogn. Syst, Hambg
Tsotsos J, Rothenstein A (2011) Computational models of visual attention. Scholarpedia 6:6201
Wang W, Wang Y, Huang Q, Gao W (2010) Measuring visual saliency by site entropy rate, in: proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.: pp. 2368–2375
Xie Y, Lu H, Yang M (2012) Bayesian saliency via low and mid level cues. IEEE Trans Image Process 22:1–1
Yan C, Zhang Y, Dai F, Li L (2013) Highly parallel framework for HEVC motion estimation on many-core platform, in: 2013 data compression Conf., IEEE: pp. 63–72
Yan C, Zhang Y, Xu J, Dai F, Li L, Dai Q, Wu F (2014) A highly parallel framework for HEVC coding unit partitioning tree decision on many-core processors. IEEE Signal Process Lett 21:573–576
Yan C, Zhang Y, Xu J, Dai F, Zhang J, Dai Q, Wu F (2014) Efficient parallel framework for HEVC motion estimation on many-Core processors. IEEE Trans Circuits Syst Video Technol 24:2077–2089
Yan C, Xie H, Liu S, Yin J, Zhang Y, Dai Q (2017) Effective Uyghur language text detection in complex background images for traffic prompt identification, IEEE trans. Intell Transp Syst 1–10
Yan C, Xie H, Yang D, Yin J, Zhang Y, Dai Q (2017) Supervised hash coding with deep neural network for environment perception of intelligent vehicles, IEEE trans. Intell. Transp. Syst. 1–12
Yang C, Zhang L, Lu H (2013) Graph-regularized saliency detection with convex-hull-based center prior. Signal Process Lett IEEE 20:637–640
Yang C, Zhang L, Lu H, Ruan X, Yang MH (2013) Saliency detection via graph-based manifold ranking, in: proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.: pp. 3166–3173
Yu J, Member S, Zhao J, Tian J, Tan Y (2014) Maximal entropy random walk for region-based visual saliency. IEEE Trans Cybern 44:1661–1672
Zhai Y, Wang D, Zhang M, Wang J, Guo F (2016) Fault detection of insulator based on saliency and adaptive morphology. Multimed Tools Appl
Zhang L, Yuan X (2015) Salient object detection with higher order potentials and learning affinity. IEEE Signal Process. Lett. 22:1396–1399
Zhang J, Zhang Y, Li L, Dai Q, Dai F, Yan C (2014) Efficient parallel HEVC intra-prediction on many-core processor. Electron Lett 50:805–806
Zhang Y, Wang X, Dai Q, Yan C, Dai F, Li L (2014) Parallel deblocking filter for HEVC on many-core processor. Electron Lett 50:367–368
Zhou D, Huang J, Schölkopf B (2006) Learning with hypergraphs: clustering, classification, and embedding, Adv. Neural Inf. Process, Syst
Acknowledgements
This work was supported by the Cognitive Science and Technology Council (CSTC) of Iran under the grant number 3232.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nouri, F., Kazemi, K. & Danyali, H. Salient object detection method using random graph. Multimed Tools Appl 77, 24681–24699 (2018). https://doi.org/10.1007/s11042-018-5668-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-5668-3