江汉大学学报(自然科学版) ›› 2017, Vol. 45 ›› Issue (1): 62-67.doi: 10.16389/j.cnki.cn42-1737/n.2017.01.010

• 图像识别技术 • 上一篇    下一篇

基于MATLAB的直方图和区域对比度相结合的图像显著性检测

马朋   

  1. 华中科技大学 生命科学与技术学院,湖北 武汉 430074
  • 出版日期:2017-02-28 发布日期:2017-02-28
  • 作者简介:马朋(1991—),男,硕士生,研究方向:生物医学图像处理。

Saliency Detection in Image with Method of Combination of Histogram and Region Contrast Based on MATLAB

MA Peng   

  1. College of Life Science and Technology,Huazhong University of Science and Technology,Wuhan 430074,Hubei,China
  • Online:2017-02-28 Published:2017-02-28

摘要: 在分析现有显著性检测模型的基础上,采用直方图和区域对比度相结合的方法对彩色图像进行显著性值计算。基于颜色直方图得到原彩色图像的显著图,使用聚类方法将图像分割成不同的区域,计算区域之间的相似性,把区域中心间的欧氏距离作为区域之间的空间权值,计算得到原彩色图像的另一显著图。为两幅显著图分配和为1的权值,相加得到最终的显著图。结果表明,此方法获得的显著区域比较符合人眼视觉效果。

关键词: 显著性, 全局对比度, 显著图, MATLAB

Abstract: On the basis of analyzing the existing model of saliency detection,the author considers calculating significant values of color image with the method of combination of histogram and region contrast in this paper. Firstly,we get the saliency image of the original color image based on color histogram. Then we use the clustering method to segment the input image into different regions,calculate the similarities between the regions and weight the similarities with the Euclidean distance of regional center. In this way,we obtain the another saliency image of the original color image. Finally,two weights with sum of one are reassigned to the two saliency images,and add them,we obtain the final saliency image. The results show the significant regions with the proposed method are relatively consistent with the effects of human visual system.

Key words: saliency, global contrast, saliency map, MATLAB

中图分类号: