计算机科学 ›› 2018, Vol. 45 ›› Issue (7): 259-263.doi: 10.11896/j.issn.1002-137X.2018.07.045

• 图形图像与模式识别 • 上一篇    下一篇

基于显著性与脉冲耦合神经网络的图像分割

王燕,许宪法   

  1. 兰州理工大学计算机与通信学院 兰州730050
  • 收稿日期:2017-05-16 出版日期:2018-07-30 发布日期:2018-07-30
  • 作者简介:王 燕(1971-),女,硕士,教授,主要研究方向为模式识别和图像处理,E-mail:wangyan@lut.cn(通信作者);许宪法(1992-),男,硕士,主要研究方向为图像处理。

Image Segmentation Based on Saliency and Pulse Coupled Neural Network

WANG Yan ,XU Xian-fa   

  1. College of Computer and Communication,Lanzhou University of Technology,Lanzhou 730050,China
  • Received:2017-05-16 Online:2018-07-30 Published:2018-07-30

摘要: 针对复杂图像易受背景干扰的问题,提出一种基于显著性与脉冲耦合神经网络(Saliency and Pulse Coupled Neural Network,SPCNN)的图像分割方法。首先,利用显著性检测算法和最大类间方差法获得显著性图以及目标图像,排除了背景对初始种子点选取的干扰;然后,计算出显著性图的质心,并将其作为初始种子点;最后,采用改进的基于区域生长的脉冲耦合神经网络对目标图像进行分割。在Berkeley图像库和Ground truth Database图像库上对SPCNN模型进行了验证。实验结果表明,在一致性系数CC、相似性系数SC、综合指标IC 3个方面,SPCNN模型均优于所对比的PCNN模型、区域生长模型和RG-PCNN模型。

关键词: 脉冲耦合神经网络, 图像分割, 显著性, 种子点

Abstract: Aiming at the problem that complicated images are interfered by background,an image segmentation method based on saliency and pulse coupled neural network (SPCNN) was proposed.Firstly,with the saliency filtering algorithm and the method of maximum between-class variance,the saliency map and the object image are obtained.Based on this,the interference which comes from the background for the initial seed point selection is eliminated.Secondly,according to saliency values in saliency map,the most saliency region is captured and the initial seed points are produced.Finally,the operations of object image segmentation are achieved via the improved RG-PCNN model.The experimental segmentation results of the gray natural images are obtained from the Berkeley segmentation dataset and ground truth database.There are three evaluating indicators:consistency coefficient(CC),similarity coefficient(SC) and integrate coefficient(IC).The experiment results show that the proposed model has better performance in terms of CC,SC and IC comparing with pulse coupled neural network (PCNN),region growing model (RG) and SPCNN.

Key words: Image segmentation, Pulse coupled neural network, Saliency, Seed points

中图分类号: 

  • TP183
[1]ZHAN K,SHI J H,LI Q Q,et al.Image Segmentation using Fast Linking SCM[C]∥International Joint Conference on Neural Networks.Ireland:IEEE Press,2015:1-8.
[2]CHEN Y L,PARK S K,MA Y D,et al.A New Automatic Parameter Setting Method of a Simplified PCNN for Image Segmentation[J].IEEE Transactions on Neural Networks,2011,22(6):880-892.
[3]ZHOU D,ZHOU H,GAO C,et al.Simplified parameters model of PCNN and its application to image segmentation[J].Pattern Analsysi and Applications,2016,19(4):939-951.
[4]ZHENG X,PENG Z M.Image segmentation based on activity degree with pulse coupled neural networks[J].Optics and Precision Engineering,2013,21(3):821-827.(in Chinese)
郑欣,彭真明.基于活跃度的脉冲耦合神经网络图像分割[J].光学精密工程,2013,21(3):821-827.
[5]AN Q,LI M,HE Y J,et al.Novel PCNN model and its application on imagesegmentation [J].Computer Science,2014,41(6A):215-217.(in Chinese)
安琦,李敏,何玉杰,等.一种优化脉冲耦合神经网络模型及在图像分割中的应用[J].计算机科学,2014,41(6A):215-217.
[6]WANG A W,SONG Y J.Image segmentation based on pulse coupled neural network[J].Computer Science,2017,44(4):317-322.(in Chinese)
王爱文,宋玉阶.基于脉冲耦合神经网络的图像分割[J].计算机科学,2017,44(4):317-322.
[7]XU G Z,ZHANG L,ZOU Y B,et al.Retinal blood segmentation with adaptive PCNN matched filter[J].Optics and Precision Engineering,2017,25(3):756-764.(in Chinese)
徐光柱,张柳,邹耀斌,等.自适应脉冲耦合神经网络与匹配滤波器相结合的视网膜血管分割[J].光学精密工程,2017,25(3):756-764.
[8]JIANG W,ZHOU H Y,SHEN Y,et al.Image segmentation with pulse-coupled neural network and Canny operators[J].Computers and Electrical Engineering,2015,46(C):528-538.
[9]HELMY A K,EL-TAWEEL G S.Image segmentation scheme based on SOM-PCNN in frequency domain[J].Applied Soft Computing,2016,40:405-415.
[10]STEWART R D,FERMIN I,OPPER M.Region Growing With Pulse-Coupled Neural Networks:An Alternative to Seeded Region Growing[J].IEEE Transactions on Neural Networks,2002,13(6):1557-1562.
[11]LU Y,MIAO J,DUAN L J,et al.A new approach to image segmentation based on simplified region growing PCNN[J].Applied Mathematics and Computation,2008,205(2):807-814.
[12]TONG N,LU H C,ZHANG L H.Saliency Detection withMulti-Scale Superpixels[J].IEEE Signal Processing Letters,2014,21(9):1035-1039.
[13]JOHNSON J L,PADGETT M L.PCNN Model and Applications[J].IEEE Transactions on Neural Networks,1999,10(3):480-497.
[14]WANG Z B,MA Y D,CHENG F Y.Review of pulse-coupled neural networks[J].Image and Vision Computing,2010,28(5):5-13.
[15]ADAMS R,BISCHOF L.Seeded region growing[J].IEEETransactions on Pattern Analysis & Machine Intelligence,1994,16(6):641-647.
[16]CHANG H H,ZHUANG A H,VALENTINO D J,et al.Performance measure characterization for evaluating neuroimage segmentation algorithms [J].Neuroimage,2009,47(1):122-135.
[1] 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
[2] 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
[3] 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
[4] 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
[5] 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
[6] 温荷, 罗频捷.
基于改进脉冲耦合神经网络的动态人脸识别
Dynamic Face Recognition Based on Improved Pulse Coupled Neural Network
计算机科学, 2021, 48(6A): 85-88. https://doi.org/10.11896/jsjkx.200600172
[7] 刘翔宇, 蹇木伟, 鲁祥伟, 何为凯, 李晓峰, 尹义龙.
基于眼动点视觉先验与边缘优化的显著性检测
Saliency Detection Based on Eye Fixation Prediction and Boundary Optimization
计算机科学, 2021, 48(6A): 107-112. https://doi.org/10.11896/jsjkx.201100116
[8] 潘明远, 宋慧慧, 张开华, 刘青山.
学习全局引导渐进特征聚合轻量级网络的显著性目标检测
Learning Global Guided Progressive Feature Aggregation Lightweight Network for Salient Object Detection
计算机科学, 2021, 48(6): 103-109. https://doi.org/10.11896/jsjkx.200600068
[9] 袁星星, 吴秦.
基于显著性特征和角度信息的遥感图像目标检测
Object Detection in Remote Sensing Images Based on Saliency Feature and Angle Information
计算机科学, 2021, 48(4): 174-179. https://doi.org/10.11896/jsjkx.191200027
[10] 张倩, 肖丽.
基于流线的流场可视化绘制方法综述
Review of Visualization Drawing Methods of Flow Field Based on Streamlines
计算机科学, 2021, 48(12): 1-7. https://doi.org/10.11896/jsjkx.201200108
[11] 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
[12] 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
[13] 王教金, 蹇木伟, 刘翔宇, 林培光, 耿蕾蕾, 崔超然, 尹义龙.
基于3D全时序卷积神经网络的视频显著性检测
Video Saliency Detection Based on 3D Full ConvLSTM Neural Network
计算机科学, 2020, 47(8): 195-201. https://doi.org/10.11896/jsjkx.190600148
[14] 袁野, 和晓歌, 朱定坤, 王富利, 谢浩然, 汪俊, 魏明强, 郭延文.
视觉图像显著性检测综述
Survey of Visual Image Saliency Detection
计算机科学, 2020, 47(7): 84-91. https://doi.org/10.11896/jsjkx.190900006
[15] 刘俊琦, 李智, 张学阳.
基于视觉显著性的海面船只候选区域检测方法
Candidate Region Detection Method for Maritime Ship Based on Visual Saliency
计算机科学, 2020, 47(6A): 237-241. https://doi.org/10.11896/JsJkx.191000196
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!