计算机科学 ›› 2019, Vol. 46 ›› Issue (6A): 196-199.
彭金喜1,3, 苏远歧1, 薛笑荣2
PENG Jin-xi1,3, SU Yuan-qi1, XUE Xiao-rong2
摘要: 由于合成孔径雷达图像(SAR)存在相干斑噪声,采用传统的SAR图像解译工作相当复杂,且传统SAR图像检索方法获得的图像纹理精度和视觉效果不佳。由于SAR图像包含的信号和噪声分布以及纹理信息非常丰富,为了提高SAR图像的检索效率,根据图像的视觉特征提出一种图像检索方法,以改善图像的视觉效果,方便人工直觉观察纹理特征信息;由此,采用深度学习方法,结合模糊理论和神经网络的优点来改善图像处理的性能。首先,根据图像像素单元的统计特征和模糊神经网络语义,提出了一种高效的基于图像纹理特征和深度语义分析的方法,对图像纹理风格优势进行数据语义匹配归类;然后,根据语义特征的特性提出一种检索方法。首先,利用深度数据语义聚类提取SAR图像的纹理特征,然后根据同生矩阵方法对SAR图像进行特征分析;最后,利用深度方法对SAR图像的纹理特征和滤波后的灰度组成的矢量进行检索,进而对图像单元归类。实验结果表明,该方法在SAR图像检索方面能取得较好的效果,且视觉效果和分析效率得到较好的提高,便于分析和应用;而且该方法能抑制相干斑噪声,同时提高SAR图像纹理特征的视觉效果。
中图分类号:
[1]ARSENAULT H H,APRIL L .Properties of Speckle Integra-ted with a Finite Aperture and Logarithmically Transformed[J].Journal of the Optical Society of America,1976,66(11):1160-1163. [2]BARALDI A,PARMIGGIAN F.An Investigation of the Tex-ture Characteristics Associated with Gray Level Co-occurrence Matrix Statistical Parameters[J].IEEE Transaction on Geo-science and Remote Sensing,1995,33(2):293-303. [3]LIU F,JIAO L C,HOU B,et al.POL-SAR Image Classification Based on Wishart DBN and Local Spatial Information[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(6):3250-3308. [4]HARALICK R M.Statistical and Structural Approaches to Texture[J].Proceeding of IEEE,1975,67(5):780-804. [5]XIE H,PIERCE L E,ULABY F T.SAR Speckle Reduction Using Wavelet Denoising and Markov Random Field Modeling[J].IEEE Transaction on Geoscience and Remote Sensing,2002,40(10):2196-2212. [6]LEE J S,POTTIER E.Polarimetric Radar Imaging.Unsuper-vised Amplitude and Texture Classification of SAR Images With Multinomial Latent Model[J].IEEE Transactions on Ima-ge Processing,2008,22(2):561-572. [7]GAN L,WU Y,WANG F,et al.Unsupervised SAR Image Segmentation Based on Triplet Markov Fields with Graph Cuts[J].IEEE Transactions on Geoscience and Remote Sensing Letters,2014,11(4):853-857. [8]YU P,QIN A K,CLAUSI D A.Unsupervised Polarimetric SAR Image Segmentation and Classification Using Region Growing With Edge Penalty.IEEE Transactions on Geoscience and Remote Sensing,2012,50(4):1302-1317. [9]GHOSH S,BISWAS D,BISWAS S,et al.Soil Classification From Large Imagery Databases Using a Neuro-Fuzzy Classifier[J].Canadian Journal of Electrical and Computer Engineering,2016,39(4):333-343. [10]WONG W C,CHO S Y,QUEK C.R-POPTVR:A Novel Reinforcement-Based POPTVR Fuzzy Neural Network for Pattern Classification[J].IEEE Transactions on Neural Networks,2009,20(11):1740-1755. [11]吴恩达.Machine Leaning Yearning[M]∥斯坦福大学讲义.2017:130-190. [12]焦李成.深度学习、优化与识别[M].北京:清华大学出版社,2017:241-300. [13]METCHELL T M.Deep learning机器学习[M].曹华军,等译.:125-139. |
[1] | 郭拯危, 付泽文, 李宁, 白澜. 高分辨率斜视聚束SAR回波仿真加速算法研究 Study on Acceleration Algorithm for Raw Data Simulation of High Resolution Squint Spotlight SAR 计算机科学, 2022, 49(8): 178-183. https://doi.org/10.11896/jsjkx.210600066 |
[2] | 沈超, 何希平. 基于纹理特征增强和轻量级网络的人脸防伪算法 Face Anti-spoofing Algorithm Based on Texture Feature Enhancement and Light Neural Network 计算机科学, 2022, 49(6A): 390-396. https://doi.org/10.11896/jsjkx.210600217 |
[3] | 高捷, 刘沙, 黄则强, 郑天宇, 刘鑫, 漆锋滨. 基于国产众核处理器的深度神经网络算子加速库优化 Deep Neural Network Operator Acceleration Library Optimization Based on Domestic Many-core Processor 计算机科学, 2022, 49(5): 355-362. https://doi.org/10.11896/jsjkx.210500226 |
[4] | 焦翔, 魏祥麟, 薛羽, 王超, 段强. 基于深度学习的自动调制识别研究 Automatic Modulation Recognition Based on Deep Learning 计算机科学, 2022, 49(5): 266-278. https://doi.org/10.11896/jsjkx.211000085 |
[5] | 范红杰, 李雪冬, 叶松涛. 面向电子病历语义解析的疾病辅助诊断方法 Aided Disease Diagnosis Method for EMR Semantic Analysis 计算机科学, 2022, 49(1): 153-158. https://doi.org/10.11896/jsjkx.201100125 |
[6] | 毋琳, 白澜, 孙梦伟, 郭拯危. 基于特征优化的SAR图像水华识别方法 Algal Bloom Discrimination Method Using SAR Image Based on Feature Optimization Algorithm 计算机科学, 2021, 48(9): 194-199. https://doi.org/10.11896/jsjkx.200800142 |
[7] | 王春静, 刘丽, 谭艳艳, 张化祥. 基于模糊颜色特征和模糊相似度的图像检索方法 Image Retrieval Method Based on Fuzzy Color Features and Fuzzy Smiliarity 计算机科学, 2021, 48(8): 191-199. https://doi.org/10.11896/jsjkx.200800202 |
[8] | 辛元雪, 史朋飞, 薛瑞阳. 基于区域提取与改进 LBP 特征的运动目标检测 Moving Object Detection Based on Region Extraction and Improved LBP Features 计算机科学, 2021, 48(7): 233-237. https://doi.org/10.11896/jsjkx.200600131 |
[9] | 周欣, 刘硕迪, 潘薇, 陈媛媛. 自然交通场景中的车辆颜色识别 Vehicle Color Recognition in Natural Traffic Scene 计算机科学, 2021, 48(6A): 15-20. https://doi.org/10.11896/jsjkx.200800078 |
[10] | 刘东, 王叶斐, 林建平, 马海川, 杨闰宇. 端到端优化的图像压缩技术进展 Advances in End-to-End Optimized Image Compression Technologies 计算机科学, 2021, 48(3): 1-8. https://doi.org/10.11896/jsjkx.201100134 |
[11] | 王晓飞, 周超, 刘利刚. 基于特征聚类的轻量级图像搜索系统 Lightweight Image Retrieval System Based on Feature Clustering 计算机科学, 2021, 48(2): 148-152. https://doi.org/10.11896/jsjkx.191200104 |
[12] | 潘雨, 邹军华, 王帅辉, 胡谷雨, 潘志松. 基于网络表示学习的深度社团发现方法 Deep Community Detection Algorithm Based on Network Representation Learning 计算机科学, 2021, 48(11A): 198-203. https://doi.org/10.11896/jsjkx.210200113 |
[13] | 马琳, 王云霄, 赵丽娜, 韩兴旺, 倪金超, 张婕. 基于多模型判别的网络入侵检测系统 Network Intrusion Detection System Based on Multi-model Ensemble 计算机科学, 2021, 48(11A): 592-596. https://doi.org/10.11896/jsjkx.201100170 |
[14] | 徐行, 孙嘉良, 汪政, 杨阳. 基于特征变换的图像检索对抗防御 Feature Transformation for Defending Adversarial Attack on Image Retrieval 计算机科学, 2021, 48(10): 258-265. https://doi.org/10.11896/jsjkx.200800222 |
[15] | 刘天星, 李伟, 许铮, 张立华, 戚骁亚, 甘中学. 面向高维连续行动空间的蒙特卡罗树搜索算法 Monte Carlo Tree Search for High-dimensional Continuous Control Space 计算机科学, 2021, 48(10): 30-36. https://doi.org/10.11896/jsjkx.201000129 |
|