Multi-Saliency Detection via Instance Specific Element Homology

Saliency detection aims to find the useful and attractive regions from an image. In many situations, there may be multiple objects in the image, and these objects may have equal attractiveness. Moreover, the appearance of pixels in one object may demonstrate large difference, which could lead to lose the object integrality when detecting saliency. To this end, this paper proposes a multi-saliency detection model via Instance Specific Element Homology (ISEH), where the integrality of an object is also considered. The ISEH is mainly formulated as a belongingness probability computation of two elements (e.g., pixels or superpixels) relative to the same object, which exploits the linking of elements within certain proposal, as well as the objectness of the proposal simultaneously. This work takes ISEH into account in the foreground and background estimation and a final optimization, and generates a superior performance for multi-saliency detection than the state-of-the-arts.

[1]  Laurent Itti,et al.  Automatic foveation for video compression using a neurobiological model of visual attention , 2004, IEEE Transactions on Image Processing.

[2]  R. Venkatesh Babu,et al.  Salient object detection via objectness measure , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[3]  Lihi Zelnik-Manor,et al.  Context-Aware Saliency Detection , 2012, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Huchuan Lu,et al.  Saliency Detection via Graph-Based Manifold Ranking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Thomas Deselaers,et al.  Measuring the Objectness of Image Windows , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Yang Wang,et al.  Salient Object Segmentation via Effective Integration of Saliency and Objectness , 2017, IEEE Transactions on Multimedia.

[7]  Guo-Wei Wei,et al.  Object-oriented persistent homology , 2016, J. Comput. Phys..

[8]  Huchuan Lu,et al.  Ranking Saliency , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Jiajun Lin,et al.  Salient object detection via compactness and objectness cues , 2017, The Visual Computer.

[10]  Shi-Min Hu,et al.  Sketch2Photo: internet image montage , 2009, ACM Trans. Graph..

[11]  B. Schölkopf,et al.  Graph-Based Visual Saliency , 2007 .

[12]  Xing Zhang,et al.  Salient Region Detection Based on Color Uniqueness and Color Spatial Distribution , 2014, IEICE Trans. Inf. Syst..

[13]  Jianru Xue,et al.  Saliency detection via background invariance in scale space , 2017, J. Electronic Imaging.

[14]  Jian Sun,et al.  Geodesic Saliency Using Background Priors , 2012, ECCV.

[15]  Lihi Zelnik-Manor,et al.  What Makes a Patch Distinct? , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Junjie Cao,et al.  A generalized nonlocal mean framework with object-level cues for saliency detection , 2015, The Visual Computer.

[17]  C. Lawrence Zitnick,et al.  Edge Boxes: Locating Object Proposals from Edges , 2014, ECCV.

[18]  Yael Pritch,et al.  Saliency filters: Contrast based filtering for salient region detection , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Huchuan Lu,et al.  Saliency detection via Cellular Automata , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Qasim Zaidi,et al.  Salience of unique hues and implications for color theory. , 2015, Journal of vision.

[21]  Pietro Perona,et al.  Is bottom-up attention useful for object recognition? , 2004, CVPR 2004.

[22]  Frédo Durand,et al.  Defocus Magnification , 2007, Comput. Graph. Forum.

[23]  Shuyuan Yang,et al.  Object-level saliency detection with color attributes , 2016, Pattern Recognit..

[24]  Sabine Süsstrunk,et al.  Saliency detection using maximum symmetric surround , 2010, 2010 IEEE International Conference on Image Processing.

[25]  Terence Sim,et al.  Defocus map estimation from a single image , 2011, Pattern Recognit..

[26]  S. Süsstrunk,et al.  Frequency-tuned salient region detection , 2009, CVPR 2009.

[27]  Zhenjiang Miao,et al.  A Saliency Prior Context Model for Real-Time Object Tracking , 2017, IEEE Transactions on Multimedia.

[28]  Peng Jiang,et al.  Salient Region Detection by UFO: Uniqueness, Focusness and Objectness , 2013, 2013 IEEE International Conference on Computer Vision.

[29]  Shi-Min Hu,et al.  Global contrast based salient region detection , 2011, CVPR 2011.

[30]  Fabrice Urban,et al.  Image and Video Saliency Models Improvement by Blur Identification , 2012, ICCVG.

[31]  C. Lawrence Zitnick,et al.  Structured Forests for Fast Edge Detection , 2013, 2013 IEEE International Conference on Computer Vision.

[32]  Yan Yan,et al.  Visual saliency detection based on homology similarity and an experimental evaluation , 2016, J. Vis. Commun. Image Represent..

[33]  Jian Sun,et al.  Saliency Optimization from Robust Background Detection , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Li Si,et al.  Center-focus global contrast saliency detection , 2016, 2016 Chinese Control and Decision Conference (CCDC).

[35]  Tony Wang,et al.  Location and salience of unique features in human perceptual learning. , 2012, Journal of experimental psychology. Animal behavior processes.

[36]  Gabriela Csurka,et al.  A framework for visual saliency detection with applications to image thumbnailing , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[37]  Liqing Zhang,et al.  Saliency Detection: A Spectral Residual Approach , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[38]  Tim K Marks,et al.  SUN: A Bayesian framework for saliency using natural statistics. , 2008, Journal of vision.

[39]  Qi Wang,et al.  Online hash tracking with spatio-temporal saliency auxiliary , 2017, Comput. Vis. Image Underst..

[40]  C. Lawrence Zitnick,et al.  Fast Edge Detection Using Structured Forests , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.