Image Saliency Detection Based on Local and Regional Features
-
摘要: 提出了一种基于颜色空间的Local特征和Regional特征的自然图像显著性检测方法. 该方法将图像分成8×8的子块, 计算多个尺度下每一个子块的Local特征和Regional特征, 并将其加权组合来确定子块的显著程度, 从而得到整个图像的显著特征. 此外, 通过计算4个颜色通道上的色度对比度, 获得显著物体的边缘. 将图像的显著特征与显著物体的边缘综合后得到图像中的显著目标. 实验结果显示, 本文提出的方法能够快速、清晰而准确地提取出图像中的显著性目标.
-
关键词:
- 显著性检测 /
- Local特征 /
- Regional特征 /
- 多尺度
Abstract: This paper proposes a model of salient region detection based on local and regional features in color space. Firstly, the image is divided into 8×8 sub-blocks, in each sub-block, then the multi-scale local and regional features are calculated and combined by weighted summation as the sub-block's salient value; secondly, the salient edge is calculated by the color contrast of the four color channels; finally, the salient map can be extracted by combining the salient features and salient edge together. The experiment results show that our model can extract salient objects in images fast and exactly.-
Key words:
- Saliency detection /
- local feature /
- regional feature /
- multi-scale
-
[1] Jian M W, Dong J Y, Ma J. Image retrieval using wavelet-based salient regions. The Imaging Science Journal, 2011, 59(4): 219-231 [2] Hua Shun-Gang, Chen Guo-Peng, Shi Shu-Sheng. Image resizing algorithm based on similarity criterion. Computer Engineering, 2012, 38(4): 191-193(华顺刚, 陈国鹏, 时树胜. 基于相似性判据的图像尺寸调整算法. 计算机工程, 2012, 38(4): 191-193) [3] Gupta R, Chaudhury S. A scheme for attentional video compression. Pattern Recognition and Machine Intelligence, 2011, 6744: 458-465 [4] Kim W, Kim C. A novel image importance model for content-aware image resizing. In: Proceedings of the 18th IEEE International Conference on Image. Brussels, Belgium: IEEE, 2011. 2469-2472 [5] Shen Lan-Sun, Zhang Jing, Li Xiao-Guang. Image Retrieval and Compressed Domain Processing. Beijing: Posts and Telecom Press, 2008. 102-103(沈兰荪, 张菁, 李晓光. 图像检索与压缩域处理技术的研究. 北京: 人民邮电出版社, 2008. 102-103) [6] Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259 [7] Zhang X L, Li Z P, Zhou T G, Fang F. Neural activities in V1 create a bottom-up saliency map. Neuron, 2012, 73(1): 183-192 [8] Sun J Y, Chen R F, He J. A modified GBVS method with entropy for extracting bottom-up attention information. Lecture Notes in Electrical Engineering, 2012, 121: 765-770 [9] Hansen L K, Karadogan S, Marchegiani L. What to measure next to improve decision making? On top-down task driven feature saliency. In: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain. Paris, France: IEEE. 2011. 86-87 [10] Baluch F, Itti L. Mechanisms of top-down attention. Trends in Neurosciences, 2011, 34(4): 210-224 [11] Itti L, Koch C. A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research, 2000, 40(6): 1489-1506 [12] Itti L, Koch C. Computational modelling of visual attention. Nature Reviews Neuroscience, 2001, 2(3): 194-230 [13] Jiao W, Peng Q M, Lv W X, Huang W J. Multiscale detection of salient regions. In: Proceedings of the 4th IEEE Conference on Industrial Electronics and Applications. Xi'an, China: IEEE, 2009. 2408-2411 [14] Zhang J, Sun J D, Liu J, Yang C X, Yan H. Visual attention model based on multi-scale local contrast of low-level features. In: Proceedings of the 10th IEEE International Conference on Signal Processing (ICSP). Beijing, China, 2010. 902-905 [15] Zhang Qiao-Rong, Gu Guo-Chang, Liu Hai-Bo, Xiao Hui-Min. Salient region detection using multi-scale analysis in the frequency domain. Journal of Harbin Engineering University, 2010, 31(3): 361-365 (张巧荣, 顾国昌, 刘海波, 肖会敏. 利用多尺度频域分析的图像显著区域检测. 哈尔滨工程大学学报, 2010, 31(3): 361-365) [16] Liu T, Yuan Z J, Sun J, Wang J D, Zheng N N, Tang X O, Shun H Y. Learning to detect a salient object. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(2): 353-367 [17] Achanta R, Hemami S, Estrada F, Süsstrunk S. Frequency-tuned salient region detection. In: Prceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Miami Beach, Florida: IEEE, 2009. 1579-1604 [18] Yao Jun-Cai. Color image compression technology based on chromatic aberration. Chinese Journal of Liquid Crystal and Displays, 2012, 27(3): 391-395 (姚军财. 基于颜色色差的彩色图像压缩技术研究. 液晶与显示, 2012, 27(3): 391-395) [19] Wang Xiang-Yang, Yang Hong-Ying, Zheng Hong-Liang, Wu Jun-Feng. A color block-histogram image retrieval based on visual weight. Acta Automatica Sinica, 2010, 36(10): 1489-1492 (王向阳, 杨红颖, 郑宏亮, 吴俊峰. 基于视觉权值的分块颜色直方图图像检索算法. 自动化学报, 2010, 36(10): 1489-1492) [20] Goferman S, Zelnik-Manor L, Tal A. Context-aware saliency detection. In: Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco, CA: IEEE, 2010. 2376-2383 [21] Walther D, Koch C. Modeling attention to salient proto-objects. Neural Networks, 2006, 19(9): 1395-1407 [22] Ma Y F, Zhang H J. Contrast-based image attention analysis by using fuzzy growing. In: Proceedings of the 11th ACM International Conference on Multimedia. New York: ACM, 2003. 374-381 [23] Harel J, Koch C, Perona P. Graph-based visual saliency. Advances in Neural Information Processing Systems, 2007, 19: 545-552 [24] Hou X D, Zhang L Q. Saliency detection: a spectral residual approach. In: Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN: IEEE, 2007. 1-8 [25] Achanta R, Estrada F, Wils P, Süsstrunk S. Salient region detection and segmentation. In: Proceedings of the 6th International Conference on Computer Vision Systems. Berlin, Heidelberg: Springer-Verlag, 2008, 5008: 66-75
点击查看大图
计量
- 文章访问数: 3084
- HTML全文浏览量: 144
- PDF下载量: 3819
- 被引次数: 0