Abstract
Human visual system is endowed with an innate capability of distinguishing the salient regions of an image. It do so even in the presence of noise and other natural disturbances. Conventional8 computational saliency models in the literature assume that the input images are clean, though an explicit treatment of noise is missing. In this paper, we propose a coupled data-driven approach for estimating saliency map for a noisy input using Variational Mode Decomposition (VMD) and Dynamic Mode Decomposition(DMD. Variational Mode Decomposition (VMD) is a well received technique explored for denoising in the literature. VMD modes with high entropy (randomness) are removed and the residual modes are employed to generate a scalar valued saliency map. The proposed method is compared against seven state-of-the-art methods over a wide range of noise strengths. The submitted approach furnished comparable results with respect to state-of-the art methods for clean and noisy images in terms of various benchmark performance measures.
Similar content being viewed by others
References
Achanta R, Hemami S, Estrada F, Susstrunk S “Frequency-tuned salient region detection.” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2009). No. CONF. 2009.
Borji A, Cheng MM, Jiang H, Li J (2015) Salient object detection: A benchmark. IEEE Trans Image Process 24(12):5706
Borji A, Sihite DN, Itti L (2013) Quantitative analysis of human-model agreement in visual saliency modeling: A comparative study. IEEE Trans Image Process 22(1):55
Bruce ND, Tsotsos JK (2009) Saliency, attention, and visual search: An information theoretic approach. J Vision 9(3):5
Cheng MM, Mitra NJ, Huang X, Torr PH, Hu SM (2015) Global contrast based salient region detection. IEEE Trans Pattern Anal Machine Intell 37(3):569
Dragomiretskiy K, Zosso D (2015) Two-dimensional variational mode decomposition. In: International workshop on energy minimization methods in computer vision and pattern recognition. Springer, pp 197–208
Goferman S, Zelnik-Manor L, Tal A (2012) A. Tal, Context-aware saliency detection. IEEE Trans Pattern Anal machine Intell 34(10):1915
Grosek J (2013) Robust real-time image processing through dynamic mode decomposition. Ph.D. thesis
Guo C, Zhang L (2010) A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression. IEEE Trans Image Process 19(1):185
Hou X, Zhang L (2007) Saliency detection: A spectral residual approach. In: IEEE conference on computer vision and pattern recognition, 2007. CVPR’07. IEEE, pp 1–8
Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Machine Intell 20(11):1254
Jiang H, Wang J, Yuan Z, Wu Y, Zheng N, Li S (2013) Salient object detection: A discriminative regional feature integration approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2083–2090
Kim C, Milanfar P (2013) Visual saliency in noisy images. J Vision 13(4):5
Kutz JN, Grosek J, Brunton S, Fu X, Pendergrass S (2017) Using dynamic mode decomposition for real-time background/foreground separation in video. US Patent 9,674,406
Lahmiri S, Boukadoum M (2014) Biomedical image denoising using variational mode decomposition. In: Biomedical circuits and systems conference (BioCAS), 2014 IEEE. IEEE, pp 340–343
Le Meur O, Le Callet P, Barba D (2007) Predicting visual fixations on video based on low-level visual features. Vision Res 47(19):2483
Liu Y, Yang G, Li M, Yin H (2016) Variational mode decomposition denoising combined the detrended uctuation analysis. Signal Process 125:349
Mohan N, Kumar S, Poornachandran P, Soman K (2016) Modified variational mode decomposition for power line interference removal in ecg signals. Int J Elect Comput Eng 6(1):151
Murray N, Vanrell M, Otazu X, Parraga CA (2011) Saliency estimation using a nonparametric low-level vision model. In: 2011 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 433–440
Pankaj D, Kumar SS, Mohan N, Soman K (2016) Image fusion using variational mode decomposition. Indian J Sci Technol 9(45)
Perazzi F, Krähenbühl P, Pritch Y, Hornung A (2012) Saliency filters: Contrast based filtering for salient region detection. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 733–740
Peters RJ, Iyer A, Itti L, Koch C (2005) Components of bottom-up gaze allocation in natural images. Vision Res 45(18):2397
Rother C, Kolmogorov V, Blake A (2004) Grabcut: Interactive foreground extraction using iterated graph cuts. In: ACM transactions on graphics (TOG), vol 23. ACM, pp 309–314
Seo HJ, Milanfar P (2009) Static and space-time visual saliency detection by self-resemblance. J Vision 9(12):15
Sikha O, Kumar SS, Soman K (2017) Salient region detection and object segmentation in color images using dynamic mode decomposition. J Computational Sci
Sikha O, Soman K (2019) Multi-resolution dynamic mode decomposition-based salient region detection in noisy images. Signal Image Video Process :1–9
Tavakoli HR, Rahtu E, Heikkilä J (2011) Fast and efficient saliency detection using sparse sampling and kernel density estimation. In: Scandinavian conference on image analysis. Springer, pp 666–675
Wang J, Li S, Jiang H (2015) Salient object segmentation. US Patent 9,042,648
Wang YS, Tai CL, Sorkine O, Lee TY (2008) Optimized scale-and-stretch for image resizing. In: ACM transactions on graphics (TOG), vol 27. ACM, p 118
Yang C, Zhang L, Lu H, Ruan X, Yang MH (2013) Saliency detection via graph-based manifold ranking. In: 2013 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 3166–3173
Yang J, Yang MH (2012) Top-down visual saliency via joint crf and dictionary learning. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2296–2303
Zhang J, Malmberg F, Sclaroff S (2019) Unconstrained salient object detection. In: Visual saliency: from pixel-level to object-level analysis. Springer, pp 95–111
Zhang L, Tong MH, Marks TK, Shan H, Cottrell GW (2008) A bayesian framework for saliency using natural statistics. J Vision 8(7):32
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sikha, O.K., Soman, K.P. & Kumar, S.S. VMD-DMD coupled data-driven approach for visual saliency in noisy images. Multimed Tools Appl 79, 1951–1970 (2020). https://doi.org/10.1007/s11042-019-08297-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08297-3