基于GPN径向基神经网络的边缘检测方法
作者:
基金项目:

国家自然科学基金(11571293)


Edge Detection Method Based on GPN Radial Basis Neural Network
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [23]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    在基于神经网络的边缘检测模型中,大部分模型的检测效率不高,检测效果也有待提升.本文受人眼视觉系统特性的启发,提出了一种新的基于GPN (Gaussian Positive-Negative)径向基神经网络的边缘检测方法.首先,本文构造了一种新型的基于GPN径向基神经网络,将图像中经高斯滤波预处理后的每个像素点作为GPN径向基神经网络的中心点,并将其输入神经网络;然后,在每层之间使用卷积神经网络的部分特性进行处理,经过扩展层和隐层计算后输出结果;最后根据输出结果利用轮廓跟踪的方法将边缘提取出来.本文在检测效果以及效率这2个方面进行了相应的数值实验.针对合成图像以及部分灰度不均匀图像,相较于脉冲耦合神经网络模型、遗传神经网络模型以及卷积神经网络模型,本文模型在效率上得到了提升,且边缘的连通性更好.实验结果表明,本文提出的基于GPN径向基神经网络的边缘检测方法是一种新的、有效的边缘检测方法,比传统的神经网络边缘检测方法效率更高,且在检测效果上也有所提升.

    Abstract:

    In the edge detection model based on neural network, most of models have lower detection efficiency, and the detection effect needs to be improved. Inspired by the characteristics of biological vision systems, a new edge detection method based on Gaussian Positive-Negative (GPN) radial basis neural network is proposed in this study. Firstly, we construct a new GPN radial-based neural network, which takes each pixel point preprocessed by Gaussian filtering in the image as the center point of the GPN radial-based neural network and inputs it into the neural network. Then, the partial characteristics of the convolutional neural network are used between each layer for processing, and the results are output after the expansion layer and the hidden layer are calculated. Finally, the edges are extracted by the contour tracking method according to the output result. In this study, the corresponding numerical experiments are carried out in two aspects:detection effect and efficiency. For the composite images and some intensity inhomogeneous images, compared with the pulse-coupled neural network model, the genetic neural network model and the convolutional neural network model, the proposed model is improved in efficiency and the edge connectivity is better. The experimental results show that the proposed edge detection method based on GPN radial basis neural network is a new and effective edge detection method, which is more efficient than the traditional neural network edge detection method, and the detection effect is also improved.

    参考文献
    [1] Liu JY, Tang QJ, Yang W, et al. Defects'geometric feature recognition based on infrared image edge detection. Infrared Physics&Technology, 2014, 67:387-390
    [2] Zheng HB, Zhu XC. Sampling adaptive block compressed sensing reconstruction algorithm for images based on edge detection. The Journal of China Universities of Posts and Telecommunications, 2013, 20(3):97-103.[doi:10.1016/S1005-8885(13)60056-4
    [3] Guo YY, He DJ, Song HB. Region detection of lesion area of knee based on colour edge detection and bilateral projection. Biosystems Engineering, 2018, 173:19-31.[doi:10.1016/j.biosystemseng.2017.12.006
    [4] Kumar V, Asati A, Gupta A. Hardware implementation of a novel edge-map generation technique for pupil detection in NIR images. Engineering Science and Technology, An International Journal, 2017, 20(2):694-704.[doi:10.1016/j.jestch.2016.11.001
    [5] Price A, Pyke J, Ashiri D, et al. Real time object detection for an unmanned aerial vehicle using an FPGA based vision system. Proceedings of 2006 IEEE International Conference on Robotics and Automation. Orlando, FL, USA. 2006. 2854-2859.
    [6] Shahabi HH, Ratnam MM. In-cycle detection of Built-Up Edge (BUE) from 2-D images of cutting tools using machine vision. The International Journal of Advanced Manufacturing Technology, 2010, 46(9-12):1179-1189.[doi:10.1007/s00170-009-2180-y
    [7] Patel A, Patel A. Performance enhancement in image edge detection technique. Proceedings of 2016 International Conference on Signal and Information Processing. Vishnupuri, India. 2016. 1-5.
    [8] 郑子华,陈家祯,叶锋.基于曲率估计的Canny边缘检测算法.计算机系统应用, 2017, 26(12):148-154.[doi:10.15888/j.cnki.csa.006139
    [9] Huang LX, Li CG, Zheng LX, et al. Edge detection algorithm of Daliushu river based on adaptive weighted morphology. Proceedings of the 20172nd International Conference on Materials Science, Machinery and Energy Engineering. Dalian, China. 2017. 6.
    [10] Zhou XL, Xu LM, Wang J. Road crack edge detection based on wavelet transform. IOP Conference Series:Earth and Environmental Science, 2019, 237:032132.[doi:10.1088/1755-1315/237/3/032132
    [11] Wen CB, Liu PL, Ma WB, et al. Edge detection with feature re-extraction deep convolutional neural network. Journal of Visual Communication and Image Representation, 2018, 57:84-90.[doi:10.1016/j.jvcir.2018.10.017
    [12] Paik JK, Katsaggelos AK. Edge detection using a neural network. Proceedings of 1990 International Conference on Acoustics, Speech, and Signal. Albuquerque, NM, USA. 1990. 2145-2148.
    [13] Barrios V, Torres J, Montilla G, et al. Cellular edge detection using a trained neural network explorer. Proceedings of the 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Baltimore, MD, USA. 1994. 1075-1076.
    [14] Aizenberg IN, Aizenberg NN, Vandewalle J. Precise edge detection:Representation by Boolean functions, implementation on the CNN. Proceedings of the 19985th IEEE International Workshop on Cellular Neural Networks and Their Applications. London, UK. 1998. 301-306.
    [15] Ling H, Xia C, Wei Q. Image edge detection based on pulse coupled neural network and modulus maxima in non-subsampled contourlet domain. Journal of China Universities of Posts and Telecommunications, 2018, 25(3):55-64
    [16] 张红霞,王灿,刘鑫,等.图像边缘检测算法研究新进展.计算机工程与应用, 2018, 54(14):11-18.[doi:10.3778/j.issn.1002-8331.1804-0205
    [17] Wang W, Yang LJ, Xie YT, et al. Edge detection of infrared image with CNN_DGA algorithm. Optik, 2014, 125(1):464-467.[doi:10.1016/j.ijleo.2013.07.049
    [18] 赵显达,黄欢.基于细胞神经网络边缘检测的自适应研究.云南大学学报(自然科学版), 2019, 41(2):268-277
    [19] Chou Y, Lee DJ, Zhang D. Edge detection using convolutional neural networks for nematode development and adaptation analysis. Proceedings of the 11th International Conference on Computer Vision Systems. Shenzhen, China. 2017. 228-238.
    [20] 张涛,杨剑,宋文爱,等.改进卷积神经网络模型设计方法.计算机工程与设计, 2019, 40(7):1885-1890
    [21] Long L. Research on four axis manipulator trajectory tracking Based on RBF Neural Network Algorithm. Journal of Physics:Conference Series, 2019, 1187(3):032016.[doi:10.1088/1742-6596/1187/3/032016
    [22] 沈莉萍.浅析"马赫带"效应在绘画中的应用.大众文艺, 2019,(1):113-115.[doi:10.3969/j.issn.1007-5828.2019.01.083
    [23] 陈彦燕,王元庆.常用边缘检测算法的定量比较.计算机工程, 2008, 34(17):202-204.[doi:10.3969/j.issn.1000-3428.2008.17.072
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

刘洋,杨晟院,钟雅瑾.基于GPN径向基神经网络的边缘检测方法.计算机系统应用,2020,29(3):140-147

复制
分享
文章指标
  • 点击次数:1688
  • 下载次数: 2200
  • HTML阅读次数: 2035
  • 引用次数: 0
历史
  • 收稿日期:2019-07-26
  • 最后修改日期:2019-09-09
  • 在线发布日期: 2020-03-02
  • 出版日期: 2020-03-15
文章二维码
您是第11418814位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号