搜索资源列表
co-training
- 半监督学习co-training 回归算法的java代码实现。-COREG is a co-training style semi-supervised regression algorithm, which employs two kNN regressors using different distance metrics to select the most confidently labeled unlabeled examples for each other.
SLLE
- 引入数据类别信息的有监督局部线性嵌入算法，可用于数据分类-Supervised Locally Linear Embedding
ClassifierforUSPSdata
- 用于对USPS数据进行分类的各种分类器，用于对多维采样点进行无监督分类。可根据类别数修改分类器，模式识别作业的部分代码。 -USPS data for the various classification categories, for sampling points on the multi-dimensional non-supervised classification. Can be modified in accordance with several types of class
NPE
- 本代码实现基于成对约束的半监督图嵌入算法-Following the intuition that the image variation of faces can be effectively modeled by low dimensional linear spaces, we propose a novel linear subspace learning method for face analysis in the framework of graph embeddi
harmonic_function
- 大牛所利用的半监督学习算法进行分类使用的调和函数的matlab实现-Daniel, the use of semi-supervised learning algorithm to classify the use of harmonic functions matlab implementation
Image
- 遥感图像的打开处理程序，能够打开单波段，多波段图像，几何图像变换，线性拉伸变换，平滑 处理包括并行和串行，锐化处理包括梯度锐化、Roberts锐化、laplace锐化、sobel锐化等，还 有用绝对距离和马氏距离算法进行的监督分类算法等，包括了RAW格式数据资源-The opening of remote sensing image processing, to open the single-band, multi-band images, geometric image
KLFDA
- 这是一个关于Fisher线性判别分析的Matlab的m文件，给出了在高斯核下的程序源码。-This is a Fisher linear discriminant analysis on the Matlab m-file, given the procedures in the lower-Gaussian source.Kernel Local Fisher Discriminant Analysis for Supervised Dimensionality Reduction.
Two_layer_neural_network
- 监督分类算法，很好很强大 为IDL和ENVI二次算法中的东西，可方便的交互使用-Supervised classification algorithms, IDL and ENVI very very much what the second algorithm can be used to facilitate interaction
meanS3VM
- means3vm算法，matlab 是实现半监督学习的较好的方法，能够对多种数据集进行测试，代码中包含例子，下载即可以使用-means3vm algorithm, matlab is better to achieve semi-supervised learning methods can be tested on a variety of data sets, the code contains examples that can be used to download
ssSVMToolbox-Bin.win32.win32.x86
- SSSvm， 半监督学习算法，文档在sourceforge上下载-SSSvm, semi-supervised learning algorithm, the document in the sourceforge download
hdda_toolbox_1.1
- The High Dimensional Discriminant Analysis (HDDA) toolbox contains an efficient supervised classifier for high-dimensional data. This classifier is based on Gaussian models adapted for high-dimensional data. Reference: C. Bouveyron, S. Girard
ClusteringanalysisbasedonSOFMnetwork
- 基于自组织特征映射网络的聚类分析，是在神经网络基础上发展起来的一种新的非监督聚类方法，分析了基于自 组织特征映射网络聚类的学习过程，分析了权系数自组织过程中邻域函数和学习步长的一般取值问题，给出了基于自组织 特征映射网络聚类实现的具体算法，并通过实际示例测试，证实了算法的正确性。 -Based on self-organizing feature map network cluster analysis, neural network is developed on the basi
S-Isomap
- S-ISOMAP is a manifold learning algorithm, which is a supervised variant of ISOMAP.
unsupervisepart
- 提供遥感图像的非监督分类，专业性比较强，可以提供给GIS RS GPS等地理专业的同志参看-Provide remote sensing image supervised classification of non-professional are relatively strong, could be made available to the GIS RS GPS and other geo-professional comrades see
AerialImageClassificationMethodBasedonFractalTheor
- 提出一种基于分形理论和BP 神经网络的航空遥感图像有监督分类方法。该方法尝试将航空图像 的光谱信息和纹理特征相结合。它首先将彩色航空图像由RGB 格式转化为HSI 格式,然后,根据亮度计算分 数维、多重分形广义维数谱q-D( q) 和“空隙”等基于分形的纹理特征,同时加入归一化的色度和饱和度作为光 谱特征,采用BP 神经网络作为分类器。通过对彩色航空图像的分类实验,结果证实该方法行之有效。-Based on fractal theory and BP neural network
Semi_Supervised_Learning_With_SVMs
- sssvm相关的文档，也可以在sourceforge上下载-sssvm related documents, can also be downloaded at sourceforge
Neural-Network-pattern-recognition
- 根据神经网络的算法对三幅训练图像和测试图像进行识别。-According to neural network training algorithm for three test images and image recognition.
MeanShift
- Meanshift的非监督聚类方法,主要用于图像处理和模式识别。-Meanshift non-supervised clustering method, mainly used in image processing and pattern recognition.
isodata
- 非监督分类程序，采用isodata算法，分类自组织迭代分类算法。-Non-supervised classification procedures, using ISODATA algorithm, iterative classification of self-organization classification algorithm.
unsupervisedClassification
- 非监督分类程序，MATLAB环境，采用K均值算法，通过初始聚类中心逐次迭代而得到所要分类，并输出分类后的图像。-Non-supervised classification procedures, MATLAB environment, using K-means algorithm, the initial cluster center through successive iterations to be classified, and the output classification im