A saliency detection model using shearlet transform

详细信息    查看全文

• 作者：Lei Bao ; Jianjiang Lu ; Yang Li ; Yanwei Shi
• 关键词：Saliency detection ; Shearlet transform ; Feature map ; Entropy
• 刊名：Multimedia Tools and Applications
• 出版年：2015
• 出版时间：June 2015
• 年：2015
• 卷：74
• 期：11
• 页码：4045-4058
• 全文大小：1,922 KB
• 参考文献：1.Achanta R, Hemami S, Estrada F, Susstrunk S (2009) Frequency-tuned salient region detection. IEEE Conference on Computer Vision and Pattern Recognition
  2.Candes E, Donoho D (2004) New tight frames of curvelets and optimal representations of objects with piecewise singularities. Commun Pure Appl Math 57(2):219鈥?66View Article MATH MathSciNet
  3.Donoho DL (1995) De-noising by soft-thresholding. IEEE Trans Inf Theory 41(3):613鈥?27View Article MATH MathSciNet
  4.Duncan K, Sarkar S (2012) Relational entropy-based saliency detection in images and videos. IEEE International Conference on Image Processing, Orlando, FL, pp. 1093鈥?096
  5.Goferman S, Zelnik-Manor L, Technion AT (2012) Context-aware saliency detection. IEEE Trans Pattern Anal Mach Intell 34(10):1915鈥?926View Article
  6.Guo KH, Labate D (2007) Optimally sparse multidimensional representation using shearlet. SIAM J Math Anal 39(1):298鈥?18View Article MATH MathSciNet
  7.Guo CL, Zhang LM (2010) A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression. IEEE Trans Image Process 19(1):185鈥?98View Article MathSciNet
  8.Imamoglu N, Lin WS, Fang YM (2013) A saliency detection model using low-level features based on wavelet transform. IEEE Trans Multimedia 15(1):96鈥?05View Article
  9.Itti L (2000) Models of bottom-up and top-down visual attention. PhD thesis, California Institute of Technology
  10.Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell 20(11):1254鈥?259View Article
  11.Kutyniok G, Labate D (2012) Shearlet: multiscale analysis for multivariate data. Birkhauser, New York, pp 22鈥?9View Article
  12.Li ZQ, Fang T, Huo H (2010) A saliency model based on wavelet transform and visual attention. Sci China Inf Sci 53(4):738鈥?51View Article
  13.Li J, Levine MD, An XJ, Xu X, He HG (2013) Visual saliency based on scale-space analysis in the frequency domain. IEEE Trans Pattern Anal Mach Intell 35(4):996鈥?010View Article
  14.Liu Q, Han T, Sun YT, Chu Z (2013) A two step salient objects extraction framework based on image segmentation and saliency detection. Multimedia Tools Appl 67(1):231鈥?47View Article
  15.Liu T, Sun J, Zheng NN, Tang XO, Shum HY (2007) Learning to detect a salient object. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1鈥?
  16.Ma JW, Plonka G (2010) The curvelet transform. IEEE Signal Process Mag 27(2):118鈥?33View Article
  17.Ngau CWH, Ang LM, Seng KP (2010) Bottom-up visual saliency map using wavelet transform domain. IEEE Int Conf Comput Sci Inf Technol Chengdu 1:692鈥?95
  18.Oakes M, Abhayaratne C (2012) Visual saliency estimation for video. International Workshop on Image Analysis for Multimedia Interactive Services, Dublin, pp. 1鈥?
  
• 作者单位：Lei Bao (1)
  Jianjiang Lu (1)
  Yang Li (1)
  Yanwei Shi (2)
  
  1. College of Command Information Systems, PLA University of Science and Technology, Qingdao, 210000, China
  2. Training Command, PLA 91206 Troops, Qingdao, 266000, China
  
• 刊物类别：Computer Science
• 刊物主题：Multimedia Information Systems
  Computer Communication Networks
  Data Structures, Cryptology and Information Theory
  Special Purpose and Application-Based Systems
  
• 出版者：Springer Netherlands
• ISSN：1573-7721

文摘

Visual attention is a mechanism to derive possible locations of objects or regions from natural scenes, and many studies have tried to simulate this mechanism to build saliency detection models, which would accelerate the course of many applications, such as object location, detection and recognition, image segmentation, retrieval and so on. Recently, researchers have tried building the detection models in transform domains. In this paper, a novel saliency detection model using shearlet transform is presented. Firstly, multi-scale feature maps are created. The feature maps built on scaling coefficients are used to generate potential salient regions, which is further used to update the feature maps generated on shearlet coefficients. As these feature maps represent the details of image in multi scale, based on them global and local contrast is calculated to form global and local saliency maps. That is the proposed model obtains the global saliency based on global probability density distribution, and measures the local saliency by calculating the entropy of local areas. By combining the local and global saliency maps, the final saliency maps are obtained. The work of this paper is absolutely a new try to detect saliency regions in shearlet domain, and experimental results demonstrate the saliency detection performance of the novel proposed model.