基于改进神经网络的图像边缘分割技术

详细信息    查看全文 | 推荐本文 |

英文篇名：Image edge segmentation technology based on improved neural network 作者：卫洪春 英文作者：WEI Hongchun;School of Intelligent Manufacturing,Sichuan University of Arts and Science; 关键词：改进神经网络 ; 图像边缘 ; 图像分割 ; 梯度特征 ; 中值特征 ; 改进BP算法 英文关键词：improved neural network;;image edge;;image segmentation;;gradient feature;;median feature;;improved BP al gorithm 中文刊名：XDDJ 英文刊名：Modern Electronics Technique 机构：四川文理学院智能制造学院; 出版日期：2018-08-14 16:05 出版单位：现代电子技术 年：2018 期：v.41;No.519 基金：四川省教育厅项目(15ZB0326);; 四川文理学院项目(2015TP003Y)~~ 语种：中文; 页：XDDJ201816028 页数：4 CN：16 ISSN：61-1224/TN 分类号：120-123

摘要

采用梯度下降法进行图像边缘分割时受到噪声的干扰,训练过程中存在局部最佳解,从而导致图像边缘分割效果和泛化性能差。为此,提出基于改进神经网络的图像边缘分割方法,采集样本图像的中值特征量、基于梯度的特征量、Krisch算子方向特征量,融合三个特征向量塑造具备较强抗噪性能的样本图像特征向量,通过基于特征向量和BP神经网络的边缘检测算法,将样本图像特征向量输入四层BP神经网络,采用改进BP算法训练四层BP神经网络,采用训练后的改进神经网络完成图像边缘分割。实验结果表明,所提图像边缘分割方法细节保有性能强,分割精度和泛化能力强。
        There exist noise interference when the gradient descent method is used for image edge segmentation and local optimal solution in its training process,resulting in poor image edge segmentation effect and generalization performance. Therefore,an image edge segmentation method based on improved neural network is proposed. The median feature quantity,gradientbased feature quantity,and Krisch operator direction feature quantity of sample images are collected. The three feature vectors are fused to shape the feature vector with strong anti-noise performance for the sample image. The feature vectors of sample images are input into the four-layer BP neural network by means of the edge detection algorithm based on the feature vector and BP neural network. The improved BP algorithm is used to train the four-layer BP neural network. The improved neural network is used to complete image edge segmentation. The experimental results show that the proposed image edge segmentation method has strong detail preservation performance,segmentation precision,and generalization capability.

引文

[1]易盟,隋立春.基于改进全卷积神经网络的航拍图像语义分类方法[J].计算机工程,2017,43(10):216-221.YI Meng,SUI Lichun.Aerial image semantic classification method based on improved full convolution neural network[J].Computer engineering,2017,43(10):216-221.
    [2]靳淑祎.基于改进型脉冲耦合神经网络图像噪声滤波算法研究[J].激光杂志,2016,37(1):142-144.JIN Shuyi.Research on image noise filtering algorithm based on improved pulse coupled neural network[J].Laser journal,2016,37(1):142-144.
    [3]廖晓磊,赵涓涓.基于改进自生成神经网络的肺部CT序列图像分割[J].计算机科学,2017,44(8):296-300.LIAO Xiaolei,ZHAO Juanjuan.Segmentation of lung CT image sequences based on improved self-generating neural networks[J].Computer science,2017,44(8):296-300.
    [4]邹瑜,帅仁俊.基于改进的SOM神经网络的医学图像分割算法[J].计算机工程与设计,2016,37(9):2533-2537.ZOU Yu,SHUAI Renjun.Improved segmentation algorithm of medical images based on SOM neural network[J].Computer engineering and design,2016,37(9):2533-2537.
    [5]黄卫,文坤梅.基于改进神经网络的4K超高清图像清晰化技术研究[J].现代电子技术,2017,40(14):120-123.HUANG Wei,WEN Kunmei.Research on 4K ultrahigh-definition image clearness technology based on improved neural network[J].Modern electronics technique,2017,40(14):120-123.
    [6]彭晏飞,周娟,訾玲玲.于卫星地域遥感图像分割方法研究仿真[J].计算机仿真,2017,34(1):332-335.PENG Yanfei,ZHOU Juan,ZI Lingling.The simulation research on regional satellite remote sensing image segmentation method[J].Computer simulation,2017,34(1):332-335.
    [7]吴曦,姚楠,许建刚.基于改进神经网络算法的变电站变压器裂纹图像识别[J].现代电子技术,2017,40(13):66-69.WU Xi,YAO Nan,XU Jiangang.Substation transformer crack image recognition based on improved neural network algorithm[J].Modern electronics technique,2017,40(13):66-69.
    [8]周鹏飞,张月琴.基于模糊BP神经网络的图像分割方法研究[J].计算机工程与设计,2014(7):2423-2426.ZHOU Pengfei,ZHANG Yueqin.Study on image segmentation based on fuzzy BP neural network[J].Computer engineering and design,2014(7):2423-2426.
    [9]BALAKUMAR B,RAVIRAJ P.Automatic morphology-based MRI brain segmentation in edge detection with neural-network optimization[J].International journal of applied engineering research,2015,10(7):18221-18229.
    [10]LI W,PENG D,WU J.Extraction of seedlings information based on improved edge segmentation algorithm[J].Transactions of the Chinese Society for Agricultural Machinery,2014,45(4):259-263.