基于快速递推模糊2-划分熵图割的红外图像分割

考虑现有图割算法没有充分考虑红外图像的模糊特性, 分割精度和运行效率低的缺点, 提出了基于快速递推模糊2-划分熵图割的红外图像分割算法以实现复杂背景下红外图像的自动高效分割。该方法利用图像感兴趣区域的最大模糊熵信息设计图割能量函数的似然能, 基于局部最大模糊2-划分熵值迭代检测出包含图像最大信息的感兴趣区域来确保提取目标信息的完整性。为了提高最大模糊熵寻优的效率, 引入时间复杂度为O(n2)的递推算法, 将模糊熵计算转化为递推过程, 并保存所有递推的熵函数值用于后续的穷举寻优。针对确定的感兴趣区域, 利用该区域最大模糊2-划分时隶属度函数分布设置图割能量函数的似然能, 从而充分考虑图像的模糊特性。对分割结果与几种常用的算法进行了视觉比较及运行时间, 错分率, F指标的量化分析。结果表明：该算法分割精度F值高达95%, 运行时间较其他常用算法至少缩短了72%, 基本满足自动红外图像分割对精度、效率和鲁棒性的要求。

Abstract

Most of existing Graph Cut (GC) algorithms have not considered the fuzzy feature, poorer segmentation precision and lower operating efficiency of infrared images sufficiently. So this paper proposes an infrared image segmentation method based on the GC of fast recursive fuzzy 2-partition entropy to implement the automatic segmentation of an infrared image in complex backgrounds. The information of the maximum fuzzy entropy from a Region of Interest (ROI) was used to set the likelihood energy of the GC. The ROI containing the maximum image information was detected by the iterative condition scheme based on the local fuzzy entropy values to ensure the completeness of the extracted target information . To improve the searching efficiency of the maximum fuzzy entropy, a recursive algorithm with time complexity O(n2) was presented to convert the computation of fuzzy entropy into a recursive process, and all the values of recursive entropy function were cached for the succeeding exhaustive optimization. For certain ROI, the likelihood energy of the GC energy function was set by the maximum fuzzy 2-partition membership functions of the ROI. By this way, the fuzzy feature of the infrared image can be considered sufficiently. The experimental analysis of the proposed algorithm on visual results, running time, misclassification error as well as F values were compared to those of several common algorithms. A plenty of experimental results indicate that the segmentation precision of proposed algorithm is up to 95% and the running time is 72% shorter than those of compared algorithms. It satisfies the requirements of automatic infrared image segmentation for higher precision, rapid speed, as well as stronger robustness.

参考文献

[1] MASTORAKIS G, MAKRIS D. Fall detection system using Kinect’s infrared sensor[J]. Journal of Real-Time Image Processing, 2014, 9(4): 635-646.

[2] LIU Y Y. Research on library lighting intelligent control based on infrared image processing techniques [J]. Optik-International Journal for Light and Electron Optics, 2015, 126(18): 1559-1561.

[3] 武治国,李桂菊. 动态目标识别中的实时复杂巡航场景运动检测[J].液晶与显示, 2014, 29(5): 844-849.

WU ZH G, LI G J. Real-time complex cruise scene detection technology in target recognition [J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(5):844-949. (in Chinese)

[4] 云廷进, 郭永彩, 高潮. K-均值聚类中心分析法实现红外人体目标分割[J].光电工程, 2008, 35(3): 140-144.

YUN T J, GUO Y C, GAO C. Human segmentation algorithm in infrared images based on K-means clustering centers analysis [J]. Opto-Electronic Engineering, 2008, 35(3):140-144. (in Chinese)

[5] 付冬梅, 于晓, 童何俊. 基于免疫模板聚类的模糊中波红外图像目标提取[J].光谱学与光谱分析, 2014, 34(3): 673-676.

FU D M, YU X, TONG H J. Extracting target from blurred midwave infrared image based on immune template clustering[J]. Spectroscopy and Spectral Analysis, 2014, 34(3): 673-676.

[6] CIESIELSKI K C, HERMAN G T, KONG T Y. General theory of fuzzy connectedness segmentations [J]. Neurocomputing, 2015, 24(6): 170-186.

[7] BO H, MA F L, HAN B J, et al. SAR image segmentation based on immune algorithm [C]. Proceedings of the Fifth International Conference on Control and Automation, Shanghai, P.R. China: ICCA , 2005: 1279-1282.

[8] XIA D X, LI C G,YANG S H. Fast threshold selection algorithm of infrared human images based on two-dimensional fuzzy tsallis entropy[J]. Mathematical Problems in Engineering, 2014, 2014(3): 57-69.

[9] 张健,李宏升. 基于图论阈值算法的图像分割研究[J].液晶与显示, 2014, 29(4):592-597.

ZHANG J, LI H SH. Image mosaic research based on wavelet and rough set algortihtm [J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(4):592-597. (in Chinese)

[10] BOYKOV Y, KOLMOGOROV V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1124-1137.

[11] WANG T, JI Z X, SUN Q S, et al. Image segmentation based on weighting boundary information via graph cut [J]. Journal of Visual Communication and Image Representation, 2015, 33(1): 10-19.

[12] ROTHER C, KOLMOGOROV V, BLAKE A. Grabcut: interactive foreground extraction using iterated graph cuts [J]. ACM Transactions on Graphics (TOG), 2004, 23(3): 309-314.

[13] CHITTAJALLU D R, BRUNNER G, KURKURE U, et al. Fuzzy-cuts: A knowledge-driven graph-based method for medical image segmentation [C]. 2009 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Alaska, US：IEEE, 2009: 715-722.

[14] SALAH M B, MITICHE A, AYED I B. Multiregion image segmentation by parametric kernel graph cuts[J]. IEEE Transactions on Image Processing, 2011, 20(2):545-557.

[15] 刘松涛, 王慧丽, 殷福亮. 基于图割和模糊连接度的交互式舰船红外图像分割方法[J].自动化学报, 2012, 38(11): 1735-1750.

LIU S T, WANG H L, YIN F L. Interactive ship infrared image segmentation method based on graph cut and fuzzy connectedness[J]. Acta Automatica Sinica, 2012, 38(11):1735-1750. (in Chinese)

[16] LI Y, MAO X, FENG D, et al. Fast and accuracy extraction of infrared target based on Markov random field [J]. Signal Processing, 2011, 91(5): 1216-1223.

[17] YUAN J, BAE E, TAI X C. A study on continuous max-flow and min-cut approaches[C]. Processding of the Twenty-Seventh International on Computer Vision and Pattern Recognition, San Francisco, US：CVPR, 2010: 2217-2224.

[18] MALCOLM J, RATHI Y,TANNENBAUM A. Graph cut segmentation with nonlinear shape priors [C].IEEE International Conference on Image Processing, Texas, US: ICIP, 2007: IV-365-IV-368.

[19] YIN S B, ZHAO X M, WANG W X, et al. Efficient multilevel image segmentation through fuzzy entropy maximization and graph cut optimization [J]. Pattern Recognition, 2014, 47(9): 2894-2907.

[20] 张怀柱, 向长波, 宋建中, 等. 改进的遗传算法在实时图像分割中的应用[J].光学精密工程, 2008, 16(2): 333-337.

ZHANG H ZH, XIANG CH B, SONG J Z, et al. Application of improved adaptive genetic algorithm to image segmentation in real time[J]. Opt. Percision Eng., 2008, 16(2): 333-337. (in Chinese)

[21] NESHAT M, SEPIDNAM G, SARGOLZAEI M, et al. Artificial fish swarm algorithm: a survey of the state-of-the-art, hybridization, combinatorial and indicative applications[J]. Artificial Intelligence Review, 2014, 42(4): 965-997.

[22] 尹诗白, 赵祥模, 王卫星, 等. 递推人工蜂群的模糊划分熵多阈值分割算法[J].西安交通大学学报, 2012, 46(10): 72-77.

YIN SH B, ZHAO X M, WANG W X, et al. A fuzzy partition entropy approach for multi thresholding segmentation based on the rcursive artificial bee colony algorithm [J]. Journal of Xi'an Jiaotong University, 2012, 46(10): 72-77. (in Chinese)

[23] GRINBERG H. Variance squeezing and information entropy squeezing via Bloch coherent states in two-level nonlinear spin models[J]. Optik-International Journal for Light and Electron Optics, 2014, 125(19): 5566-5572.

[24] YU H Y, ZHI X B, FAN J L. Image segmentation based on weak fuzzy partition entropy[J]. Neurocomputing, 2015, 168(15): 994-1010.

尹诗白, 王一斌, 邓箴. 基于快速递推模糊2-划分熵图割的红外图像分割[J]. 光学精密工程, 2016, 24(3): 668. YIN Shi-bai, WANG Yi-bin, DENG Zhen. Infrared image segmentation based on graph cut of fast recursive fuzzy 2-partition entropy[J]. Optics and Precision Engineering, 2016, 24(3): 668.

基于快速递推模糊2-划分熵图割的红外图像分割

关于本站 Cookie 的使用提示

全站搜索

基于快速递推模糊2-划分熵图割的红外图像分割

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索