首页 > 论文 > 激光与光电子学进展 > 56卷 > 15期(pp:151005--1)

基于改进型UL-PCNN的绝缘子图像分割

Insulator Image Segmentation Based on Improved Unit-Linking Pulse-Coupled Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

绝缘子图像分割是通过图像处理技术实现绝缘子识别和提取的基础性操作。为了能够准确地分割出绝缘子图像,提出一种基于改进型单位连接脉冲耦合神经网络(UL-PCNN)的绝缘子图像分割算法。根据相邻神经元之间的关系,改进原始UL-PCNN模型中的连接输入和耦合系数;利用改进的UL-PCNN模型对绝缘子图像进行分割,得到多幅输出图像;利用梯度算法计算原始图像和输出图像的边缘,并分别计算输出图像和原始图像边缘的均方误差(MSE),均方误差值最小的输出图像即为分割效果最好的绝缘子图像。实验结果表明,本文算法能够准确地分割出不同环境下的绝缘子图像,并具有较好的抗噪性能。

Abstract

Insulator image segmentation is the basic operation used to conduct insulator recognition and extraction using image processing. To segment insulator images accurately, an improved unit-linking pulse-coupled neural network (UL-PCNN)-based insulator image segmentation method is proposed in the present study. First, the link input and coupled parameters of the original UL-PCNN model are improved based on the relationship between a neuron and its neighbors. Next, the improved model is used to segment an insulator image to obtain multiple output images. Finally, the gradient algorithm is used to calculate the edges of the original image and output images, and the mean square error (MSE) of the edge of the original image and MSE of each output image are calculated. The output image with the smallest MSE is considered as the optimal result of insulator image segmentation. The experimental results demonstrate that this improved method can accurately segment insulator images in different environments and has good anti-noise performance.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.151005

所属栏目:图像处理

基金项目:四川省科技支撑计划(2016GZ0145);

收稿日期:2019-01-21

修改稿日期:2019-03-06

网络出版日期:2019-08-01

作者单位    点击查看

杜小燕:四川大学电气工程学院, 四川 成都 610065
钟俊:四川大学电气工程学院, 四川 成都 610065

联系人作者:钟俊(zhongjun55@163.com)

备注:四川省科技支撑计划(2016GZ0145);

【1】Tong W G. Research on methods for recognition and status detection of power line based on aerial images. Beijing: North China Electric Power University. 65-73(2011).
仝卫国. 基于航拍图像的输电线路识别与状态检测方法研究. 北京: 华北电力大学. 65-73(2011).

【2】Xu X T, Li B S, Cui K B et al. The application of improved PCNN in infrared insulator image segmentation. Insulators and Surge Arresters. 24-29(2013).
徐雪涛, 李宝树, 崔克彬 等. 改进型PCNN在绝缘子图像分割中的应用. 电瓷避雷器. 24-29(2013).

【3】Huang X B, Liu X H, Zhang Y et al. Classification recognition method of insulator in aerial image based on the red-blue difference and developed K-means algorithm. High Voltage Engineering. 44(5), 1528-1534(2018).
黄新波, 刘新慧, 张烨 等. 基于红蓝色差和改进K-means算法的航拍绝缘子分类识别方法. 高电压技术. 44(5), 1528-1534(2018).

【4】Cui K B. Research on the key technologies in insulator defect detection based on image. Beijing: North China Electric Power University. 34-49(2016).
崔克彬. 基于图像的绝缘子缺陷检测中若干关键技术研究. 北京: 华北电力大学. 34-49(2016).

【5】Zhang J J, Han J, Zhao Y B et al. Insulator recognition and defects detection based on shape perceptual. Journal of Image and Graphics. 19(8), 1194-1201(2014).
张晶晶, 韩军, 赵亚博 等. 形状感知的绝缘子识别与缺陷诊断. 中国图象图形学报. 19(8), 1194-1201(2014).

【6】Zhang J Y and Huang J D. An image segmentation algorithm research based on optimized PCNN. [C]//2018 11th International Conference on Intelligent Computation Technology and Automation (ICICTA), September 22-23, 2018, Changsha, China. New York: IEEE. 86-90(2018).

【7】He F L, Guo Y C and Gao C. Improved PCNN method for human target infrared image segmentation under complex environments. Acta Optica Sinica. 37(2), (2017).
贺付亮, 郭永彩, 高潮. 复杂环境下用于人体目标红外图像分割的改进PCNN方法. 光学学报. 37(2), (2017).

【8】Gu X D. Feature extraction using unit-linking pulse coupled neural network and its applications. Neural Processing Letters. 27(1), 25-41(2008).

【9】Ma Y D, Li L, Zhan K et al. Pulse coupled neural network and digital image processing. 8-22(2008).
马义德, 李廉, 绽琨 等. 脉冲耦合神经网络与数字图像处理. 8-22(2008).

【10】Su J, Li B and Wang Y Z. Infrared image enhancement based on PCNN segmentation and fuzzy set theory. Acta Optica Sinica. 36(9), (2016).
苏娟, 李冰, 王延钊. 结合PCNN分割和模糊集理论的红外图像增强. 光学学报. 36(9), (2016).

【11】Lin L B, Li J X, Luo K et al. A modified pulse coupled neural network model for nut image segmentation. Journal of Fujian Normal University(Natural Science Edition). 34(6), 19-23(2018).
林龙彬, 李建兴, 罗堪 等. 基于改进脉冲耦合神经网络的螺母工件图像分割. 福建师范大学学报(自然科学版). 34(6), 19-23(2018).

【12】Xu C and Ping X L. Line detection algorithm based on improved random hough transformation. Laser & Optoelectronics Progress. 56(5), (2019).
徐超, 平雪良. 基于改进随机Hough变换的直线检测算法. 激光与光电子学进展. 56(5), (2019).

【13】Sahoo P K and Soltani S. Wong A K C. A survey of thresholding techniques. Computer Vision, Graphics, and Image Processing. 41(2), 233-260(1988).

引用该论文

Xiaoyan Du, Jun Zhong. Insulator Image Segmentation Based on Improved Unit-Linking Pulse-Coupled Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(15): 151005

杜小燕, 钟俊. 基于改进型UL-PCNN的绝缘子图像分割[J]. 激光与光电子学进展, 2019, 56(15): 151005

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF