|
|
|
| Image Saliency Detection Based on Global and Local Information Fusion |
| BAO Lei, LU Jian-Jiang, LI Yang, SHI Yan-Wei |
| College of Command Information Systems, PLA University of Science and Technology, Nanjing 210007 |
|
|
|
|
Abstract Visual Attention System is an important part of computer vision receiving more and more attention. In this paper, an image saliency detection model is presented based on global and local information fusion. The model firstly makes discrete shearlet decomposition on input image to obtain shearlet and scaling coefficients. As the shearlet coefficients contain most details of an image, a feature map is reconstructed on each decomposition level by performing inverse shearlet transform on these coefficients. Based on the feature maps, global and local contrasts are derived. On one hand, feature vectors are obtained by using all the feature maps to describe the detected image, and the global probability density distribution is calculated to obtain the global saliency value. After that, a global saliency map is obtained. On the other hand, the local entropy is calculated to measure the geometric distribution complexity of local areas on each feature map. After the local saliency value is obtained for every decomposition level, the local saliency map is built. By properly fusing global and local saliency maps, the total saliency map is obtained. The experimental results show that the proposed saliency detection model performs better than current models do.
|
|
Received: 08 November 2013
|
|
|
|
|
|
[1] Chen Z L. Research on Region of Interest Extraction. Ph.D Dissertation. Changsha, China: Central South University, 2012 (in Chinese)
(陈再良.图像感兴趣区域提取方法研究.博士学位论文.长沙:中南大学, 2012)
[2] Itti L, Koch C, Niebur E. A Model of Saliency-Based Visual Attention for Rapid Scene Analysis. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259
[3] Itti L. Models of Bottom-Up and Top-Down Visual Attention. Ph.D Dissertation. Pasadena, USA: California Institute of Technology, 2000
[4] Liu Q, Han T, Sun Y T, et al. A Two Step Salient Objects Extraction Framework Based on Image Segmentation and Saliency Detection. Multimedia Tools and Applications, 2013, 67(1): 231-247
[5] Duncan K, Sarkar S. Relational Entropy-Based Saliency Detection in Images and Videos // Proc of the 19th IEEE International Confe-rence on Image Processing. Orlando, USA, 2012: 1093-1096
[6] Guo C L, Zhang L M. A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression. IEEE Trans on Image Processing, 2010, 19(1): 185-198
[7] Li J, Levine M D, An X J, et al. Visual Saliency Based on Scale-Space Analysis in the Frequency Domain. IEEE Trans on Pattern Analysis and Machine Intelligence, 2013, 35(4): 996-1010
[8] Chen Z X. The Curvelet Transform and Its Application to Information Extraction for Potential Data. Ph.D Dissertation. Beijing, China: China University of Geosciences, 2012 (in Chinese)
(陈召曦.位场数据的曲波变换与信息提取应用.博士学位论文.北京:中国地质大学, 2012)
[9] Ma J W, Plonka G. The Curvelet Transform. IEEE Signal Processing Magazine, 2010, 27(2): 118-133
[10] Ngau C W H, Ang L M, Seng K P. Bottom-Up Visual Saliency Map Using Wavelet Transform Domain // Proc of the 3rd IEEE International Conference on Computer Science and Information Technology. Chengdu, China, 2010, I: 692-695
[11] Li Z Q, Fang T, Huo H. A Saliency Model Based on Wavelet Transform and Visual Attention. SCIENCE CHINA Information Sciences, 2010, 53(4): 738-751
[12] Imamoglu N, Lin W S, Fang Y M. A Saliency Detection Model Using Low-Level Features Based on Wavelet Transform. IEEE Trans on Multimedia, 2013, 15(1): 96-105
[13] Guo K H, Labate D. Optimally Sparse Multidimensional Representation Using Shearlet. SIAM Journal on Mathematical Analysis, 2007, 39(1): 298-318
[14] Guo Q. Research on Shearlet-Based Statistical Model for Images and Its Applications. Ph.D Dissertation. Shanghai, China: Shanghai University, 2010 (in Chinese)
(郭 强.基于剪切波变换的图像统计模型及其应用研究.博士学位论文.上海:上海大学, 2010)
[15] Kutyniok G, Labate D. Shearlet: Multiscale Analysis for Multiva-riate Data. Basel, Switzerland: Birkhauser, 2012: 22-59
[16] Donoho D L. De-noising by Soft-Thresholding. IEEE Trans on Information Theory, 1995, 41(3): 613-627
[17] Goferman S, Zelnik-Manor L, Tal A. Context-Aware Saliency Detection. IEEE Trans on Pattern Analysis and Machine Intelligence, 2012, 34(10): 1915-1926
[18] Murray N, Vanrell M, Otazu X, et al. Saliency Estimation Using a Non-parametric Low-Level Vision Model // Proc of the 24th IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2011: 433-440
[19] Liu T, Yuan Z J, Sun J, et al. Learning to Detect a Salient Object. IEEE Trans on Pattern Analysis and Machine Intelligence, 2010, 33(2): 353-367 |
|
|
|
2015, Vol. 28 
