English

应用科学学报 ›› 2010, Vol. 28 ›› Issue (1): 24-31.

• 信号与信息处理 • 上一篇    下一篇

结合对比特性与局部清晰特性的图像显著区域检测

郁志鸣， 王朔中， 张新鹏， 刘婷婷   

  1. 上海大学通信与信息工程学院，上海200072
  • 收稿日期:2009-10-26 修回日期:2009-11-18 出版日期:2010-01-20 发布日期:2010-01-20
  • 通信作者: 王朔中，教授，博导，研究方向：信号处理、数字图像处理、信息隐藏、水声学，E-mail: shuowang@online.sh.cn
  • 基金资助:

    国家自然科学基金(No.60872116, No.60832010, No.60773079)；国家“863”高技术研究发展计划基金(No.2007AA01Z477)资助

Image Saliency Detection Based on Contrast Features and Local Sharpness

YU Zhi-ming, WANG Shuo-zhong, ZHANG Xin-peng, LIU Ting-ting   

  1. School of Communication and Information Engineering, Shanghai University, Shanghai 200072, China
  • Received:2009-10-26 Revised:2009-11-18 Online:2010-01-20 Published:2010-01-20

PDF

2142

被引次数

9

摘要：

为了有效地确定图像中的重要区域，文中根据人眼视觉关注中自上而下和自下而上的两种特点，提出了一种结合图像对比特性与清晰区域的显著检测方法. 图像中颜色的全局和局部对比引起低级视觉关注，而图像的清晰部分通常对应于拍摄时所关注的对象，反映高级视觉特性. 采用颜色分类和检测图像细节区域的方法分别提取了两类显著图，并将它们组合起来. 实验结果表明，通过综合考虑两种视觉特性得到的显著图，对多类图像都能较好地检测出与人眼视觉关注相吻合的区域.

关键词: 视觉显著性, 颜色对比, 清晰区检测

Abstract:

To extract important areas in an image that attract visual attention, a saliency detection scheme using both contrast features and local sharpness in the image is proposed. The local sharpness is related to the focusing status, which reflects the human judgment of the scene being imaged. Therefore, the presented method integrates two different visual characteristics, which we call low- and high-level human visual attention (HVA). The globe and local color contrast in the image arouse the low-level HVA, whereas the local sharpness affects the high-level HVA. Two saliency maps are thus generated with color classification and detailed area detection, respectively, and combined. Experiments show that integration of the saliency maps can provide good correspondence to HVA areas for different images.

Key words: visual saliency, color contrast, sharpness region detection

中图分类号: