计算机应用 ›› 2010, Vol. 30 ›› Issue (06): 1619-1621.

• 图形图像处理与模式识别 • 上一篇    下一篇

一种图像显著区域的提取方法

王国营1,梁春迎2   

  1. 1. 信息工程大学电子技术学院
    2.
  • 收稿日期:2009-11-19 修回日期:2010-01-26 发布日期:2010-06-01 出版日期:2010-06-01
  • 通讯作者: 王国营

Extraction of salient regions in image

  • Received:2009-11-19 Revised:2010-01-26 Online:2010-06-01 Published:2010-06-01

摘要: 图像的显著区域能代表图像的主要内容,提取图像的显著区域在图像检索、敏感图像识别等方面有重要的作用。结合多尺度分析先提取图像的显著图,而后在显著图的基础上根据经验阈值对事先的分割区域进行判断取舍,最后根据取舍结果来确定图像的显著区域,取得了良好的效果。与具有代表性的Itti方法相比易于实现,速度快。

关键词: 显著度, 显著图, 显著区域, 多尺度分析, 图像分割

Abstract: Image salient regions may express the main content of image. Extraction of the salient regions in image plays an important role in searching image and identifying sensitive image. First, extract the salient maps of image in combination with multi-scale analysis. Then, accept or reject the previously segmented regions according to experience threshold value based on saliency maps. Finally, fix on salient maps of image according to front judgment. Good effect is achieved. The algorithm is fast and easy to implement compared to Itti method.

Key words: Saliency value, Saliency maps, Salient regions, Multi-scale analysis, image segmentation