基于统计曲线差分法的多目标图像阈值分割

doi:10.16182/j.issn1004731x.joss.201711044

系统仿真学报 ›› 2017, Vol. 29 ›› Issue (11): 2927-2933.doi: 10.16182/j.issn1004731x.joss.201711044

• 短文 • 上一篇

基于统计曲线差分法的多目标图像阈值分割

朱远飞, 张思祥, 周围, 王晓辰, 李志东

河北工业大学机械工程学院,天津 300130

收稿日期:2016-05-30 发布日期:2020-06-05
作者简介:朱远飞(1993-),男,安徽,硕士生,研究方向为工业控制和传感器技术,图像处理与检测。
基金资助:
河北工业大学优秀青年科技创新基金(2012008),河北省青年基金(B2014202260)

Multi-Objective Image Threshold Segmentation Based on Statistical Curve Difference Method

Zhu Yuanfei, Zhang Sixiang, Zhou Wei, Wang Xiaochen, Li Zhidong

School of mechanical engineering, Hebei University of Technology, Tianjin 300130, China

Received:2016-05-30 Published:2020-06-05

摘要/Abstract

摘要： 为准确地分割目标面积过小,目标和背景灰度值相近的多目标图像,提出一种基于统计曲线差分法的阈值分割算法。建立多目标灰度图像的山地模型,对图像灰度归一化处理。用等间隔的阈值逐一分割,计算连通区域个数。绘制统计曲线,曲线横坐标为等间隔的灰度级,纵坐标为计数结果。对统计曲线进行差分,差分值趋近于零的点,就是所要求得的阈值点。实验结果表明：与目前性能较优越的Otsu、最大熵阈值分割方法相比,所提出的方法在多目标图像分割效果准确性更高。

关键词: 多目标图像, 统计曲线, 阈值分割, 灰度归一化

Abstract: In order to accurately segment the multi-objective image whose objective area is too small, and the background gray value is similar to the objective, a threshold segmentation algorithm based on statistical curve difference method is proposed. The mountain model of multi-objective gray image is established and the gray image is normalized. The number of connected area is counted by threshold division. The statistical curve is plotted with the horizontal coordinate being the gray level with equal interval, and the vertical coordinate being the counting result. The threshold point is the point where the difference value of the statistical curve is close to zero. Experiment results show that the proposed method is more accurate than the Otsu and the maximum entropy threshold segmentation method.

Key words: objective image, statistical curve, threshold segmentation, gray normalization

中图分类号:

TP311

朱远飞, 张思祥, 周围, 王晓辰, 李志东. 基于统计曲线差分法的多目标图像阈值分割[J]. 系统仿真学报, 2017, 29(11): 2927-2933.

Zhu Yuanfei, Zhang Sixiang, Zhou Wei, Wang Xiaochen, Li Zhidong. Multi-Objective Image Threshold Segmentation Based on Statistical Curve Difference Method[J]. Journal of System Simulation, 2017, 29(11): 2927-2933.

参考文献

[1] Albuquerque M P, Esquef I A, Mello A R G. Image thresholding using Tsallis entropy. Pattern Recognition Let-ters (S0167-8655), 2004, 25(10): 1059-1065.
[2] OTSU N.A threshold selection method from gray-level histogram[J]. IEEE Trans.on Systems, Man and Cybernetic (S2168-2216), 1979, 9: 62-66.
[3] Jostein Dahle, Manish Kakar, etc. Automated counting of mammalian cell colonies by means of a flat bed scanner and image processing[J]. Journal of the Internation Society for Ad vancement of Cytometry (S1552-4930), 2004, 6: 182-188.
[4] Chen, W B, Zhang C. An automated bacterial co-lony counting and classification system[J]. Information Sys-tems Frontiers (S1572-9419), 2009, 11(4): 349-368.
[5] Qian R J,and Huang T S.Optimal edge detection in two-dimendional images[J]. IEEE Trans.Image Processing (S1057-7149), 1996, 5(7): 1215-1220.
[6] Rajapakse J C, Giedd J N, Rapoport J L.Statistical approach to segmentation of single-channel cerebral MR images[J]. IEEE Trans-actions on Medical Imaging (S0278-0062), 1997, 16(2): 176-186.
[7] 景晓军, 蔡安妮, 孙景鳌. 一种基于二维最大类间方差的图像分割算法[J]. 通信学报, 2001, 22(4): 71-76.
Jing Yi, Cai Anni, Sun Jingao.An image segmentation algorithm based on two dimensional maximum inter class variance[J]. Journal of Communications, 2001, 22(4): 71-76.
[8] 吴成茂. 一种新信息熵定义及其在图像分割中的应用[J]. 西安邮电学院学报, 2009, 14(1): 72-79.
Wu Chengmao.A new definition of information entropy and its application in image segmentation[J]. Journal of Xi'an University of Posts and Telecommunications, 2009, 14(1): 72-79.
[9] 房华, 程国建, 吴文海. 一种基于最大熵的改进型 PCNN图像分割新方法[J]. 软件导刊, 2010, 9(5): 189-191.
Fang Hua, Cheng Guojian, Wu Wenhai.A new segmentation method of improved PCNN image based on maximum entropy[J]. Software Guide, 2010, 9(5): 189-191.
[10] Doyle W.Operation. Useful for Similarity-Invariant Pattern Recognition[J]. Assoc. Computer. Mach (S0004-5411), 1962, 9: 259-267.
[11] LAN J H, ZENG Y L Multi-threshold image segmentation using maximum fuzzy entropy based on a new 2D histogram[J]. Optik-Int. J. Light Electron Opt.(S0030-4026), 2013, 124(18): 3756-3760.
[12] C Yi, Y L Tian.Text string detection from natural scene by structure-based partion and grouping[J]. IEEE transation on image processing (S1057-7149), 2011, 20(9): 2594-2605.
[13] 宋斌. 一种新的图像连通区域快速标号算法[J]. 电子测量技术, 2009, 32(9): 67-68.
Song Bin.A new fast labeling algorithm for image connected regions[J]. electronic measurement technology, 2009, 32(9): 67-68.
[14] Zhang B G, Zhou Y.Oscillation of Difference Equations with Several Delays[J]. Computers and Mathematics with Applications (S0898-1221), 2002, 44(5): 817-821.
[15] Wang X P.Oscillation of Delay Difference Equations with Several Delays[J]. J. Math. Anal. Appl (S0022-247X), 2003, 286(2): 664-674.
[16] Gong X H, Zhong X Z, Jia J Q, et al.Oscillation of First-order Neutral Difference Equation[J]. Modem Applied Science (S1913-1844), 2009, 3(8): 90-94.

基于统计曲线差分法的多目标图像阈值分割

Multi-Objective Image Threshold Segmentation Based on Statistical Curve Difference Method

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价