上海交通大学学报(自然版) ›› 2012, Vol. 46 ›› Issue (06): 892-899.

• 无线电电子学、电信技术 • 上一篇    下一篇

二维直方图θ-划分最小误差图像阈值分割

吴一全1,2,张晓杰1,吴诗婳1,张国华2,张生伟2,于素芬2   

  1. (1. 南京航空航天大学 电子信息工程学院, 南京 210016;2. 光电控制技术重点实验室, 河南 洛阳 471009)
  • 收稿日期:2011-05-06 出版日期:2012-06-28 发布日期:2012-06-28
  • 基金资助:

    国家自然科学基金资助项目(60872065),光电控制技术重点实验室和航空科学基金联合资助项目(20105152026),南京大学计算机软件新技术国家重点实验室开放基金资助项目(KFKT2010B17)

Image Thresholding Based on 2-D Histogram θ-Division and Minimum Error

 WU  Yi-Quan-1, 2 , ZHANG  Xiao-Jie-1, WU  Shi-Hua-1, ZHANG  Guo-Hua-2, ZHANG  Sheng-Wei-2, YU  Su-Fen-2   

  1. (1. College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China; 2. Science and Technology on Electro-optic Control Laboratory, Luoyang 471009,Henan,China)
  • Received:2011-05-06 Online:2012-06-28 Published:2012-06-28

摘要:  针对常用二维直方图区域直分法存在错分的问题,并为适应实际中不同图像及分割目的的需要,提出了更具普适性的二维直方图θ划分最小误差阈值分割方法(θ为分割直线的法线与灰度级轴的夹角).导出了相应的阈值选取公式及其快速递推算法,根据实验结果分析了θ取值对分割结果和算法运行时间的影响.与二维直方图直分最小误差法相比,所提方法的分割结果更为准确,抵抗噪声更为稳健,且所需运行时间也大为减少;而直线形最小误差法只是文中方法中θ=45°的特例.

关键词: 图像处理, 阈值分割, 二维直方图区域&theta, -划分, 最小误差, 递推算法

Abstract: Aiming at the problem of wrong segmentation in common 2-D histogram region division, in order to meet the requirement of different images and segmentation objectives, the 2-D linear-type minimum error threshold segmentation method was generalized, and a much more widely suitable thresholding method was proposed based on 2-D histogram θ-division and minimum error. The threshold selection formulae and its fast recursive algorithm  were deduced. The influence of different θ values on segmented results and running time was analyzed according to the experimental results. Compared with the conventional 2-D minimum error method, the proposed method not only achieves more accurate segmented result and more robust anti-noise, but also significantly reduces the running time. The linear-type minimum error threshold segmentation method is only a special case with θ=45° of the proposed method.

Key words: image processing, thresholding, 2-D histogram region θdivision, minimum error, recursive algorithm

中图分类号: