计算机科学 ›› 2019, Vol. 46 ›› Issue (3): 267-276.doi: 10.11896/j.issn.1002-137X.2019.03.040
毛莺池1,王静1,陈小丽1,徐淑芳1,陈豪2
MAO Ying-chi1,WANG Jing1,CHEN Xiao-li1,XU Shu-fang1,CHEN Hao2
摘要： 大坝缺陷识别分类技术是人类智能的基本表现,它是最典型、最困难的模式识别问题之一。由于大坝缺陷图像具有信噪比低、光照分布极度不均匀等特征,分类识别算法的识别率较低。针对这些问题,文中提出一种基于图像LBP特征和Gabor特征组合与CNN相结合(LBP and Gabor feature combination and CNN,LGk-CNN)的缺陷图像识别方法,对采集到的大坝图像进行分析,实现对缺陷图像的识别和分类。该方法首先分别提取图像的LBP特征与Gabor特征;然后将得到的LBP特征和Gabor特征组合作为CNN的输入;最后通过逐层训练网络,实现大坝缺陷类型的分类识别。实验结果表明,LGk-CNN的平均识别准确率为88.39%,缺陷召回率为92.75%,与相同参数设置下的CNN分类识别算法相比,识别准确率和缺陷召回率分别约提高了3.1%和2.5%,具有最优的结果。
中图分类号:
| [1]苏南.我国200米级高坝密集,安全风险不容忽视.http://www.thepaper.cn/newsDetail_forward_1858088.2017. [2]ZHANG S B,LIU N,HUO H,et al.Image classification based on hierarchical shape feature extraction model .High-tech communication,2016,26 (1):81-88.(in Chinese) 张盛博,刘娜,霍宏,等.基于层次形状特征提取模型的图像分类.高技术通讯,2016,26(1):81-88. [3]DENG H B,JIN L W.Facial Expression Recognition Based on Local Gabor Filter Bank and PCA+LDA.Journal of Image &Graphics,2007,12(2):322-329.(in Chinese) 邓洪波,金连文.一种基于局部Gabor滤波器组及PCA+LDA的人脸表情识别方法.中国图象图形学报,2007,12(2):322-329. [4]BELARBI M A,MAHMOUDI S,BELALEM G.PCA as Di- mensionality Reduction for Large-Scale Image Retrieval Systems.International Journal of Ambient Computing and Intelligence (IJACI),2017,8(4):45-58. [5]ZHANG R,WANG Q,ZHANG P.Image Texture Feature Extraction Based on Gabor Transform.Revista Tecnica de la Facultad de Ingenieria Universidad del Zulia,2016,39(1):237-244. [6]RAHMAN S,RAHMAN M M,HUSSAIN K,et al.Image enhancement in spatial domain:A comprehensive study∥2014 17th International Conference on Computer and Information Technology (ICCIT).IEEE,2014:368-373. [7]XIE F,CHEN L T,QIU H.Research on image classification method based on texture feature extraction and system implementation.Computer Application Research,2009,26(7):2767-2770.(in Chinese) 谢菲,陈雷霆,邱航.基于纹理特征提取的图像分类方法研究及系统实现.计算机应用研究,2009,26(7):2767-2770. [8]ZARNDY ,REKECZKY C,SZOLGAY P,et al.Overview of CNN research:25 years history and the current trends∥2015 IEEE International Symposium on Circuits and Systems (ISCAS).IEEE,2015:401-404. [9]ZHAO J,TONG W Q.Near infrared face recognition based on LBP and Gabor hybrid features.Journal of East China Normal University (Natural Science Edition),2016(4):77-85.(in Chinese) 赵骥,童卫青.基于 LBP 和 Gabor 混合特征的近红外人脸识别.华东师范大学学报 (自然科学版),2016(4):77-85. [10]JIANG Z,WU Q,TAN Y,et al.Analysis Range of Coefficients in Learning Rate Methods of Convolution Neural Network∥International Symposium on Distributed Computing & Applications for Business Engineering & Science.2016. [11]GAO Y ,MA J ,ZHAO M ,et al.NDDR-CNN:Layer-wise Feature Fusing in Multi-Task CNN by Neural Discriminative Dimensionality Reduction.https://arxiv.org/pdf/1801.08297.pdf. [12]TAN W X,ZHAO C,WU H,et al.Intelligent alerting for fruit-melon lesion image based on momentum deep learning.Multimedia Tools & Applications,2016,75(24):1-21. [13]PENG C,XIAO T,LI Z,et al.MegDet:A Large Mini-Batch Object Detector∥IEEE Conference on Computer Vision and Pattern Recognition.2018:6181-6189. [14]ELLEUCH M,MAALEJ R,KHERALLAH M.A New Design Based-SVM of the CNN Classifier Architecture with Dropout for Offline Arabic Handwritten Recognition.Procedia Computer Science,2016,80:1712-1723. [15]LIU W,WEN Y,YU Z,et al.Large-margin softmax loss for convolutional neural networks∥International Conference on International Conference on Machine Learning.2016. [16]NIE X,CHENG A,SHEN D,et al.New Algorithm SGD of Surface Modification and Its Application in Springback Compensation.China Mechanical Engineering,2008,24(19):2972-2976. [17]CHERKASSKY V,MA Y.Practical selection of SVM parameters and noise estimation for SVM regression.Neural Networks,2004,17(1):113-126. [18]ZHANG Y,ZHOU X,WITT R M,et al.Dendritic spine detection using curvilinear structure detector and LDA classifier.Neuroimage,2007,36(2):346-360. [19]RTSCH G,ONODA T,MLLER K R.Soft Margins for AdaBoost.Machine Learning,2001,42(3):287-320. [20]CHEN S,COWAN C N,GRANT P M.Orthogonal least squares learning algorithm for radial basis function networks.IEEE Transactions on Neural Netw,1991,64(5):829-837. [21]STOEAN C.In Search of the Optimal Set of Indicators when Classifying Histopathological Images∥International Symposium on Symbolic & Numeric Algorithms for Scientific Computing.2017. [22]BAG S,HARIT G.A medial axis based thinning strategy and structural feature extraction of character images∥IEEE International Conference on Image Processing.2010. [23]FAN X,WU J,SHI P,et al.A novel automatic dam crack detection algorithm based on local-global clustering.Multimedia Tools & Applications,2018,77(20):26581-26599. [24]KAWASAKI Y,MATSUSHIMA K,ZHONG Z.Image-based pavement crack detection by percolation theory∥2017 9th International Conference onInformation Technology and Electrical Engineering (ICITEE).IEEE,2017:1-6. [25]YU N,QIU T,FENG B,et al.Image Features Extraction and Fusion Based on Joint Sparse Representation.IEEE Journal of Selected Topics in Signal Processing,2011,5(5):1074-1082. [26]WANG Z,CUI P,LI F,et al.A data-driven study of image feature extraction and fusion.Information Sciences,2014,281(4):536-558. [27]TYCHSEN-SMITH L,PETERSSON L.DeNet:Scalable Real-time Object Detection with Directed Sparse Sampling∥2017 IEEE International Conference on Computer Vision(ICCV).IEEE Computer Society,2017. |
| [1] | 陈志强, 韩萌, 李慕航, 武红鑫, 张喜龙. 数据流概念漂移处理方法研究综述 Survey of Concept Drift Handling Methods in Data Streams 计算机科学, 2022, 49(9): 14-32. https://doi.org/10.11896/jsjkx.210700112 |
| [2] | 周旭, 钱胜胜, 李章明, 方全, 徐常胜. 基于对偶变分多模态注意力网络的不完备社会事件分类方法 Dual Variational Multi-modal Attention Network for Incomplete Social Event Classification 计算机科学, 2022, 49(9): 132-138. https://doi.org/10.11896/jsjkx.220600022 |
| [3] | 武红鑫, 韩萌, 陈志强, 张喜龙, 李慕航. 监督和半监督学习下的多标签分类综述 Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning 计算机科学, 2022, 49(8): 12-25. https://doi.org/10.11896/jsjkx.210700111 |
| [4] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
| [5] | 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064 |
| [6] | 闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042 |
| [7] | 高振卓, 王志海, 刘海洋. 嵌入典型时间序列特征的随机Shapelet森林算法 Random Shapelet Forest Algorithm Embedded with Canonical Time Series Features 计算机科学, 2022, 49(7): 40-49. https://doi.org/10.11896/jsjkx.210700226 |
| [8] | 杨炳新, 郭艳蓉, 郝世杰, 洪日昌. 基于数据增广和模型集成策略的图神经网络在抑郁症识别上的应用 Application of Graph Neural Network Based on Data Augmentation and Model Ensemble in Depression Recognition 计算机科学, 2022, 49(7): 57-63. https://doi.org/10.11896/jsjkx.210800070 |
| [9] | 张洪博, 董力嘉, 潘玉彪, 萧宗志, 张惠臻, 杜吉祥. 视频理解中的动作质量评估方法综述 Survey on Action Quality Assessment Methods in Video Understanding 计算机科学, 2022, 49(7): 79-88. https://doi.org/10.11896/jsjkx.210600028 |
| [10] | 邵欣欣. TI-FastText自动商品分类算法 TI-FastText Automatic Goods Classification Algorithm 计算机科学, 2022, 49(6A): 206-210. https://doi.org/10.11896/jsjkx.210500089 |
| [11] | 陈景年. 一种适于多分类问题的支持向量机加速方法 Acceleration of SVM for Multi-class Classification 计算机科学, 2022, 49(6A): 297-300. https://doi.org/10.11896/jsjkx.210400149 |
| [12] | 杨健楠, 张帆. 一种结合双注意力机制和层次网络结构的细碎农作物分类方法 Classification Method for Small Crops Combining Dual Attention Mechanisms and Hierarchical Network Structure 计算机科学, 2022, 49(6A): 353-357. https://doi.org/10.11896/jsjkx.210200169 |
| [13] | 杨涵, 万游, 蔡洁萱, 方铭宇, 吴卓超, 金扬, 钱伟行. 基于步态分类辅助的虚拟IMU的行人导航方法 Pedestrian Navigation Method Based on Virtual Inertial Measurement Unit Assisted by GaitClassification 计算机科学, 2022, 49(6A): 759-763. https://doi.org/10.11896/jsjkx.211200148 |
| [14] | 岳晴, 尹健宇, 王生生. 基于改进CNN的低剂量CT图像肺结节自动检测 Automatic Detection of Pulmonary Nodules in Low-dose CT Images Based on Improved CNN 计算机科学, 2022, 49(6A): 54-59. https://doi.org/10.11896/jsjkx.210400211 |
| [15] | 杜丽君, 唐玺璐, 周娇, 陈玉兰, 程建. 基于注意力机制和多任务学习的阿尔茨海默症分类 Alzheimer's Disease Classification Method Based on Attention Mechanism and Multi-task Learning 计算机科学, 2022, 49(6A): 60-65. https://doi.org/10.11896/jsjkx.201200072 |
|
||
首页