计算机应用 ›› 2012, Vol. 32 ›› Issue (07): 1875-1878.DOI: 10.3724/SP.J.1087.2012.01875

• 图形图像技术 • 上一篇    下一篇

离焦模糊图像模糊半径检测的新方法

范海菊1,冯云芝1,王涛2,冯乃勤1   

  1. 1. 河南师范大学 计算机与信息技术学院,河南 新乡453007
    2. 河南新飞电器有限公司 冰箱制造一部,河南 新乡453007
  • 收稿日期:2011-12-15 修回日期:2012-02-01 发布日期:2012-07-05 出版日期:2012-07-01
  • 通讯作者: 范海菊
  • 作者简介:范海菊(1979-),女,河南新乡人,讲师,硕士,主要研究方向:数字图像处理、建模与仿真;冯云芝(1970-),女,河南新乡人,讲师,主要研究方向:神经网络、人工智能;王涛(1979-),男,河南新乡人,助理工程师,主要研究方向:冰箱制冷;冯乃勤(1953-),男,河南新乡人,教授,博士,主要研究方向:神经网络、人工智能。
  • 基金资助:

    河南省重点科技攻关项目(102102210176);河南省教育厅基础与前沿项目(2010A520027; 2011A520026)

New method of blurred radius detection in defocused image

FAN Hai-ju1, FENG Yun-zhi1, WANG Tao2, FENG Nai-qin1   

  1. 1. College of Computer and Information Science, Henan Normal University, Xinxiang Henan 453007, China;
    2. The First Refrigerator Manufacturing Department, Henan Xinfei Electric Limited Company, Xinxiang Henan 453007, China
  • Received:2011-12-15 Revised:2012-02-01 Online:2012-07-05 Published:2012-07-01
  • Contact: FAN Hai-ju

摘要: 针对离焦模糊图像盲复原中模糊半径难以快速精确检测的问题,提出了局部熵和直方图统计相结合的算法。首先对模糊图像进行局部熵滤波提取图像的灰度变化信息量,利用Canny边缘算子和Hough变换检测出离焦图像的直线边缘;然后利用相互平行直线边缘区域内的直方图统计特性和Grubbs检验法,定位出阶跃直线边缘求出线扩散函数;最后利用线扩散函数得到模糊半径。实验结果表明所提算法在模糊半径较小时能够精确快速地定位阶跃边缘,从而提高模糊半径的识别精度和识别效率。

关键词: 离焦图像, 模糊半径, 局部熵, 直方图统计, 阶跃边缘

Abstract: An algorithm combining local entropy and histogram statistics was proposed in order to solve the problem that it is difficult to detect the blurred radius quickly and correctly in defocused image blind restoration. Firstly, the gray level information of blurred image was extracted by local entropy filter and straight lines were detected by Canny edge detector and Hough transform. Secondly, the straight step edges were located to compute the line spread function adopting Grubbs method and histogram feature of the parallel line area. Finally, the blurred radius could be obtained by line spread function. The experimental results show that the step edges can be located quickly and accurately when blurred radius is small, thus increasing recognition accuracy and recognition efficiency.

Key words: defocused image, blurred radius, local entropy, histogram statistics, step edge

中图分类号: