首页--工业技术论文--自动化技术、计算机技术论文--计算技术、计算机技术论文--计算机的应用论文--信息处理(信息加工)论文--模式识别与装置论文

基于半监督学习的高光谱图像分类方法研究

摘要第5-6页
ABSTRACT第6-7页
符号对照表第11-13页
缩略语对照表第13-18页
Chapter 1 Introduction第18-32页
    1.1 Background and applications第18-21页
        1.1.1 Hyperspectral imagery第18-20页
        1.1.2 Applications第20-21页
    1.2 Techniques and challenges第21-23页
        1.2.1 Techniques第21-23页
        1.2.2 The challenges第23页
    1.3 Semi-supervised learning第23-26页
        1.3.1 Assumptions in semi-supervised learning第24页
        1.3.2 Algorithms for semi-supervised learning第24-26页
        1.3.3 Open issues and future directions第26页
    1.4 Related work第26-28页
        1.4.1 Semi-supervised classification for HSIs第26-27页
        1.4.2 Sparse feature learning for HSIs第27-28页
        1.4.3 Semi-supervised band selection for HSIs第28页
    1.5 Thesis goals and contributions第28-29页
    1.6 Outline第29-32页
Chapter 2 Modified co-training process with spectral and spatial views for HSIclassification第32-56页
    2.1 Introduction第32-33页
    2.2 Motivation第33-35页
    2.3 Modified co-training with spectral and spatial views for HSI classification第35-41页
        2.3.1 View construction for hyperspectral imagery第35-37页
        2.3.2 A new sample selection scheme for co-training第37-41页
    2.4 Experimental results and analysis第41-54页
        2.4.1 Data description第41-42页
        2.4.2 Experimental design第42-43页
        2.4.3 Results and discussions第43-51页
        2.4.4 Performance analysis第51-54页
    2.5 Conclusion第54-56页
Chapter 3 Semi-supervised dictionary learning for HSI classification第56-70页
    3.1 Introduction第56-57页
    3.2 Sparse representation and dictionary learning第57-58页
        3.2.1 Sparse representation第57-58页
        3.2.2 Dictionary learning第58页
    3.3 SSDL第58-61页
        3.3.1 Dictionary learning with both labeled and unlabeled samples第58页
        3.3.2 Dictionary learning with semi-supervised classification第58-60页
        3.3.3 Solution of SSDL第60-61页
    3.4 Experimental results and analysis第61-69页
        3.4.1 Data description第61-63页
        3.4.2 Experimental settings第63-64页
        3.4.3 Experiments with the AVIRIS Indian Pines dataset第64-67页
        3.4.4 Experiments with the ROSIS University of Pavia dataset第67-69页
    3.5 Conclusion第69-70页
Chapter 4 Joint sparsity based semi-supervised band selection for HSIs第70-86页
    4.1 Introduction第70-71页
    4.2 Problem formulation第71页
    4.3 Joint sparse norm regularization第71-73页
    4.4 Manifold smoothness regularization第73-75页
    4.5 Experimental results and analysis第75-84页
        4.5.1 Data description第75-76页
        4.5.2 Experimental settings第76-77页
        4.5.3 Experiments with the AVIRIS Indian Pines dataset第77-82页
        4.5.4 Experiments with the ROSIS University of Pavia dataset第82-84页
    4.6 Conclusion第84-86页
Chapter 5 Conclusion and future work第86-88页
    5.1 Conclusion第86-87页
    5.2 Future work第87-88页
Reference第88-98页
Acknowledgement第98-99页
Biography第99-100页
    1. Basic information第99页
    2. Educational background第99页
    3. Research achievements第99-100页

论文共100页,点击 下载论文
上一篇:基于稀疏重构的SAR成像技术研究
下一篇:海杂波背景下的过采样MTD方法研究