论文:2013,Vol:31,Issue(2):206-209
引用本文:
张艳邦, 韩军伟, 郭雷, 许明. 利用稀疏表达检测多幅图像协同显著性目标[J]. 西北工业大学
Zhang Yanbang, Han Junwei, Guo Lei, Xu Ming. A New Algorithm for Detecting Co-Saliency in Multiple Images through Sparse Coding Representation[J]. Northwestern polytechnical university

利用稀疏表达检测多幅图像协同显著性目标
张艳邦, 韩军伟, 郭雷, 许明
西北工业大学 自动化学院, 陕西 西安 710072
摘要:
提出了一种利用稀疏表达检测多幅图像中协同显著目标的方法。首先用独立变量分析方法训练得到自然图像一组稀疏基,接着求出检测图像的稀疏表达,然后定义了多变量K-L散度度量它们之间的相似性,最后,根据K-L散度性质找出散度下降明显的地方,检测出多幅图像的共同显著性目标。实验结果表明,该方法正确有效,具有和人类视觉特性相符合的显著性目标检测效果。
关键词:    算法    图像处理    独立变量分析    协同显著性    稀疏表达    K-L散度   
A New Algorithm for Detecting Co-Saliency in Multiple Images through Sparse Coding Representation
Zhang Yanbang, Han Junwei, Guo Lei, Xu Ming
Department of Automatic Control,Northwestern Polytechnical University,Xi'an 710072,China
Abstract:
We propose what we believe to be a new algorithm for detecting the co-saliency in multiple images.First,we use the independent component analysis to learn and obtain a set of sparse bases of a natural imagethrough filtering the input image and then use them to work out the sparse coding representation of the image to bedetected. Second,we define the multi-variable Kullback-Leibler (K-L) divergence to measure the similarity amongmultiple images. Third,according to the properties of the K-L divergence,we detect the region where the diver-gence decreases significantly,or the similarity of the image,thus detecting the co-saliency in multiple images. Toverify the effectiveness of our algorithm,we test the image co-saliency detection effect with the photos we took. Thetest results,given in Fig. 3,and their analysis show preliminarily that the image co-saliency detection effect of ournew algorithm is the same as that of human visual characteristics.
Key words:    algorithm    image processing    independent component analysis;co-saliency    sparse coding representa-tion    Kullback-Leibler divergence   
收稿日期: 2012-05-15     修回日期:
DOI:
基金项目: 国家自然科学基金(61273362);西北工业大学基础研究基金(NPU-FFR-JC201041)资助
通讯作者:     Email:
作者简介: 张艳邦(1980-),西北工业大学博士研究生,主要从事计算机视觉及模式识别等研究。
相关功能
PDF(484KB) Free
打印本文
把本文推荐给朋友
作者相关文章
张艳邦  在本刊中的所有文章
韩军伟  在本刊中的所有文章
郭雷  在本刊中的所有文章
许明  在本刊中的所有文章

参考文献:
[1] Achanta R,Hemami S,Estrada F,Susstrunk S. Frequency-Tuned Salient Region Detection. Proceedings of IEEE Conferenceon Computer Vision and Pattern Recognition (CVPR), 2011, 1597-1604
[2] Cheng M,Zhang G,Mitra N J,et al. Global Contrast Based Salient Region Detection. Proceedings of IEEE Conference onComputer Vision and Pattern Recognition (CVPR), 2011
[3] Chen H. Preattentive Co-Saliency Detection. Proceedings of 17th International Conference on Image Processing,Hong Kong,2010, 1117-1120
[4] Li H,Ngan N. A Co-Saliency Model of Image Pairs. IEEE Trans on Image Processing, 2011, 20(12): 3365-3375
[5] David E,Dan B,Eli S. Cosaliency: Where People Look When Comparing Images. Proceedings of 23rd Annual ACM Symposi-um on User Interface Software and Technology, 2010, 219-227
[6] Wang M,Konrad J,Ishwar P,Jing K,Rowley H. Image Saliency: from Intrinsic to Extrinsic Context. Proceedings of Confer-ence on Computer Vision and Pattern Recognition, 2011, 417-424
[7] Olshausen A. Emergence of Simple-Cell Receptive Field Properties by Learning a Sparse Code for Natural Images. Nature, 1996
[8] Bell A,Sejnoiwski T. The Independent Components of Natural Scenes Are Edge Filters. Vision Research,37(23): 3327-3338, 1997
[9] Hou X,Zhang L. Dynamic Visual Attention: Searching for Coding Length Increments. Proceedings of the Neural InformationProcessing Systems, 2008, 681-688
相关文献:
1.郝帅, 程咏梅, 马旭, 赵建涛.无人直升机视觉着舰中合作目标角点检测算法[J]. 西北工业大学, 2013,31(4): 653-659