计算机科学 ›› 2020, Vol. 47 ›› Issue (5): 154-160.doi: 10.11896/jsjkx.190200295

• 计算机图形学&多媒体 • 上一篇    下一篇

基于WFSOA的2D-Otsu钢轨缺陷图像分割方法

曹义亲, 段也钰, 武丹   

  1. 华东交通大学软件学院 南昌330013
  • 收稿日期:2019-02-15 出版日期:2020-05-15 发布日期:2020-05-19
  • 通讯作者: 段也钰(1958194676@qq.com)
  • 作者简介:yqcao@ecjtu.jx.cn
  • 基金资助:
    国家自然科学基金(61663009);江西省科技支撑计划重点项目(20161BBE50081)

2D-Otsu Rail Defect Image Segmentation Method Based on WFSOA

CAO Yi-qin, DUAN Ye-yu, WU Dan   

  1. School of Software,East China Jiaotong University,Nanchang 330013,China
  • Received:2019-02-15 Online:2020-05-15 Published:2020-05-19
  • About author:CAO Yi-qing,born in 1964,professor,is a member of China Computer Federation.His main research interests include image processing,pattern recognition.
    DUAN Ye-yu,born in 1994,master's degree.Her main research interests include image processing and so on.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China(61663009),Key Project of Jiangxi Science and Technology Support Plan(20161BBE50081).

摘要: 针对二维最大类间方差阈值法(2D-Otsu)抗噪性较弱、计算时间较长的问题,文中提出了一种基于随机权重及异步价值因子取值的人群搜索算法,并将其应用于2D-Otsu中对钢轨缺陷图像进行分割。该算法采用随机权重加快收敛速度,采用异步价值因子提高搜索能力,有利于全局收敛到最优值。根据测试函数分析,WFSOA算法能够快速收敛,寻优值结果精度高,收敛时间短,算法稳定性好。在钢轨缺陷图像分割中,将2D-Otsu的迹函数作为WFSOA的目标函数,实验结果表明图像检测实时性高,对表面灰度不匀或生锈的钢轨缺陷分割结果清晰,有效降低了钢轨缺陷误检率和漏检率,在计算时间上仅占2D-Otsu算法的2%,可满足实际工程对实时性的需求。

关键词: 2D-Otsu, 改进人群搜索算法, 钢轨缺陷, 图像分割, 阈值

Abstract: Aiming at the problem that the two-dimensional maximum inter-class variance threshold method (2D-Otsu) had weak anti-noise and long calculation time,a seeker optimization algorithm based on random weight and asynchronous value factor is proposed.The algorithm is applied to the image segmentation of rail defects in 2D-Otsu.The random weight is used to speed up the convergence speed of the algorithm,and the asynchronous value factor is used to improve the algorithm's search ability,which is conducive to global convergence to the optimal value.Through the test function analysis,the WFSOA algorithm can converge quickly,the precision value of the optimization value is high,the convergence time is small,and the algorithm has good stability.In the image segmentation of rail defects,the 2D-Otsu trace function is used as the objective function of WFSOA.The experimental results show that the image detection has high real-time performance,the segmentation result of the rail defects is clear,and the false detection rate and missed detection rate of the rail defects are effectively reduced.Time is only 2% of the 2D-Otsu algorithm,which meets the needs of actual engineering.

Key words: 2D-Otsu, Image segmentation, Improved seeker optimization algorithm, Rail defect, Threshold

中图分类号: 

  • TN391.41
[1]WANG K,ZHANG Y.Infrared Image Segmentation Based on Improved Dimensional OTSU and Genetic Algorithm[J].Journal of System Simulation,2017,29(6):1229-1236.
[2]LIU Z,WANG W,ZHANG X,et al.Inspection of Rail Surface Defects Based on Image Processing[C]//International Asia Conference on Informatics in Control.IEEE,2010:472-475.
[3]DUBEY A K,JAFFERY Z A.Maximally Stable Extremal Region Marking-Based Railway Track Surface Defect Sensing[J].IEEE Sensors Journal,2016,16(24):9047-9052.
[4]HOU Y,LI B L,LIU J J,et al.Railway Fasteners Positioning Feature Extraction Based on Gray-scale Invariance[J].ComputerApplications and Software,2015,32(11):193-196.
[5]MA K,VICENTE T F Y,SAMARAS D,et al.Texture classification for rail surface condition evaluation[C]//Applications of Computer Vision.IEEE,2016:1-9.
[6]YU X.Adaptive Canny Operator Based Digital Image Processing Scheme for Photoshop Filter Plugin Unit[C]//International Conference on Intelligent Transportation.2018.
[7]MIN Y Z,YUE B,MA H F,et al.Rail Surface Defects Detection Based on Gray Scale Gradient Characteristics of Image[J].Chinese Journal of Scientific Instrument,2018,39(4):220-229.
[8]YUAN X C,WU L S,CHEN W H.Rail Image Segmentation Based on Otsu Threshold Method[J].Optics and Precision Engineering,2016,24(7):1772-1781.
[9]LIU J Z,LI W Q.Two-Dimensional Otsu Automatic Threshold Segmentation Method for Grayscale Images[J].Acta Ayutoma-tica Sinica,1993,19(1):101-105.
[10]GONG J,LI L,CHEN W.A Fast-Recursive Algorithm for Two-Dimensional Thresholding[C]//International Conference on Signal Processing.IEEE,1998:1155-1158.
[11]FAN J L,ZHAO F.Two-Dimensional Otsu's Cure Thresholding Segmentation Method for Gray-Level Images[J].Acta Ayutomatica Sinica,2007,35(4):751-755.
[12]ZHANG X M,SUN Y J,ZHENG Y B.Precise Two-DimensionalOtsu's Image Segmentation and Its Fast Recursive Realization[J].Acta Ayutomatica Sinica,2011,39(8):1778-1784.
[13]WU Y Q,FAN J.Fast iterative algorithm for image segmentation based on an improved two-dimensional Otsu thresholding[J].Journal of Electronic Measurement and Instrument,2011,25(3):218-225.
[14]CHEN Q,ZHAO L,LU J,et al.Modified two-dimensional Otsu image segmentation algorithm and fast realization [J].let Image Processing,2012,6(4):426-433.
[15]YUAN J,CHENG G T.Rapid Otsu Method Based on Two-Dimensional Histogram of Double Slope[J].Application Research of Computers,2017,34(6):1905-1908.
[16]CHENG W S,ZANG X J,ZHAO J,et al.Modified strategy to inertia weight in PSO for searching threshold of Otsu rule [J].Optics and Precision Engineering,2008,16(10):1907-1912.
[17]ZHOU C H,TIAN L W,ZHAO H W,et al.Two-Dimensional Otsu Image Segmentation Based on Improved Firefly Algorithm[J].Journal of Shenyang University (Natural Science),2016,28(1):45-50.
[18]CAO S,AN J C.A Fast Two-Dimensional Otsu Image Segmentation Algorithm Based on Wolf Pack Algorithm Optimization[J].Computer Engineering & Science,2018,40(7):1221-1226.
[19]PARVANEH H,DIZGAH S M,SEDIGHIZADEH M,et al.Load Frequency Control of A Multi-Area Power System by Optimum Designing of Frequency-based PID Controller Using Seeker Optimization Algorithm[C]//Thermal Power Plants.2016.
[20]SAHA S K,KAR R,MANDAL D,et al.Digital Stable IIR Band Pass Filter Design Using Seeker Optimization Technique[J].Advanced Materials Research,2014,905:406-410.
[21]DAI C H,CHEN W R,ZHU Y F,et al.II R Digital Filter Design Via Seeker Optimization Algorithm[J].Journal of Southwest Jiaotong University,2009,44(6):871-876.
[22]HE L W,YUAN Y,WANG Y S,et al.Placement Strategy Of Cloud Virtual Machine Based On WFSOA Algorithm[J].Application Research of Computers,2017,34(2):591-594.
[23]GAN J,LI Q,WANG J,et al.A Hierarchical Extractor-Based Visual Rail Surface Inspection System[J].IEEE Sensors Journal,2017,PP(99):1-1.
[1] 张翕然, 刘万平, 龙华.
物联网僵尸网络病毒的传播动力学模型与分析
Dynamic Model and Analysis of Spreading of Botnet Viruses over Internet of Things
计算机科学, 2022, 49(6A): 738-743. https://doi.org/10.11896/jsjkx.210300212
[2] 徐汝利, 黄樟灿, 谢秦秦, 李华峰, 湛航.
基于金字塔演化策略的彩色图像多阈值分割
Multi-threshold Segmentation for Color Image Based on Pyramid Evolution Strategy
计算机科学, 2022, 49(6): 231-237. https://doi.org/10.11896/jsjkx.210300096
[3] 祝一帆, 王海涛, 李可, 吴贺俊.
一种高精度路面裂缝检测网络结构:Crack U-Net
Crack U-Net:Towards High Quality Pavement Crack Detection
计算机科学, 2022, 49(1): 204-211. https://doi.org/10.11896/jsjkx.210100128
[4] 叶中玉, 吴梦麟.
融合时序监督和注意力机制的脉络膜新生血管分割
Choroidal Neovascularization Segmentation Combining Temporal Supervision and Attention Mechanism
计算机科学, 2021, 48(8): 118-124. https://doi.org/10.11896/jsjkx.200600150
[5] 金海燕, 彭晶, 周挺, 肖照林.
基于Graph Cuts多特征选择的双目图像分割方法
Binocular Image Segmentation Based on Graph Cuts Multi-feature Selection
计算机科学, 2021, 48(8): 150-156. https://doi.org/10.11896/jsjkx.200800221
[6] 许华杰, 张晨强, 苏国韶.
基于深层卷积残差网络的航拍图建筑物精确分割方法
Accurate Segmentation Method of Aerial Photography Buildings Based on Deep Convolutional Residual Network
计算机科学, 2021, 48(8): 169-174. https://doi.org/10.11896/jsjkx.200500096
[7] 周俊, 王帅, 刘凡漪.
基于小波包分析的虹膜识别研究
Research on Iris Recognition Algorithm Based on Wavelet Packet Decomposition
计算机科学, 2021, 48(6A): 57-62. https://doi.org/10.11896/jsjkx.200900218
[8] 杨秀璋, 武帅, 夏换, 于小民.
基于自适应图像增强技术的水族文字提取与识别研究
Research on Shui Characters Extraction and Recognition Based on Adaptive Image Enhancement Technology
计算机科学, 2021, 48(6A): 74-79. https://doi.org/10.11896/jsjkx.200900070
[9] 曹林, 于威威.
基于图像分割的自适应窗口双目立体匹配算法研究
Adaptive Window Binocular Stereo Matching Algorithm Based on Image Segmentation
计算机科学, 2021, 48(11A): 314-318. https://doi.org/10.11896/jsjkx.201200264
[10] 顾兴健, 朱剑峰, 任守纲, 熊迎军, 徐焕良.
多尺度U网络实现番茄叶部病斑分割与识别
Multi-scale U Network Realizes Segmentation and Recognition of Tomato Leaf Disease
计算机科学, 2021, 48(11A): 360-366. https://doi.org/10.11896/jsjkx.201000166
[11] 刘峰, 王一帆, 杨杰, 周爱民, 齐佳音.
一种基于区块链的融合DKG与BLS的高阈值签名协议
Blockchain-based High-threshold Signature Protocol Integrating DKG and BLS
计算机科学, 2021, 48(11): 46-53. https://doi.org/10.11896/jsjkx.210200129
[12] 王静宇, 刘思睿.
大数据风险访问控制研究进展
Research Progress on Risk Access Control
计算机科学, 2020, 47(7): 56-65. https://doi.org/10.11896/jsjkx.190700157
[13] 彭浩, 和丽芳.
基于改进树种算法的彩色图像多阈值分割
Multi-threshold Segmentation for Color Image Based on Improved Tree-seed Algorithm
计算机科学, 2020, 47(6A): 220-225. https://doi.org/10.11896/JsJkx.191000180
[14] 杨志伟, 戴铭, 周智恒.
基于直方图差异的工业产品表面缺陷检测方法
Surface Defect Detection Method of Industrial Products Based on Histogram Difference
计算机科学, 2020, 47(6A): 247-249. https://doi.org/10.11896/JsJkx.191000049
[15] 程煜, 刘伟, 孙童心, 魏志刚, 杜薇.
近阈值电压下可容错的一级缓存结构设计
Design of Fault-tolerant L1 Cache Architecture at Near-threshold Voltage
计算机科学, 2020, 47(4): 42-49. https://doi.org/10.11896/jsjkx.190300088
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!