Description: 一种新的计算马氏距离的算法，算法采用二次协方差矩阵操作，进而使距离考加入相对性因素。-a new Mahalanobis distance calculation algorithm, the algorithm using quadratic covariance matrix operations, thereby enabling the relative distance to take factors. Platform: |
Size: 1380 |
Author:bodiz2002 |
Hits:
Description: 基于内容的图像检索中的一些关键环节：特征提取：颜色直方图；纹理特征等
相似度：马氏距离，欧氏距离等
相关反馈：机器学习方法，如SVM，神经网络等
检索与分类：两个很相似的样本距离很小，虽然两个不相似的样本距离未必很大-content-based image retrieval of some of the key issues : Feature Extraction : color histogram; Texture characteristics of similarity : Mahalanobis distance, the Euclidean distance relevance feedback : machine learning methods, such as SVM. Neural network search and classification : two very similar samples from the small, although the two are similar to the samples may not be much distance Platform: |
Size: 159744 |
Author:耿上 |
Hits:
Description: 一种新的计算马氏距离的算法，算法采用二次协方差矩阵操作，进而使距离考加入相对性因素。-a new Mahalanobis distance calculation algorithm, the algorithm using quadratic covariance matrix operations, thereby enabling the relative distance to take factors. Platform: |
Size: 1024 |
Author:bodiz2002 |
Hits:
Description: 用于计算马氏距离，并可以用于优选近红外光谱的校正集和预测集-used in the calculation of the Mahalanobis distance, and can be used for optimization of near-infrared spectroscopy calibration set and the prediction Platform: |
Size: 1024 |
Author:xunny |
Hits:
Description: 马氏距离判别(MahalanobisDistanceDiscrimination)的演示过程,求均值向量,协方差矩阵及线形判别函数-Mahalanobis distance criterion (MahalanobisDistanceDiscrimina tion) demonstration process for the mean and covariance matrix and linear discriminant function Platform: |
Size: 3072 |
Author:陈伟 |
Hits:
Description: 產生k個d維的常態分布樣本，產生某個事前機率為P(wi)的常態分布的discriminant
function，計算任兩點間的Euclidean distance及Mahalanobis distance
-Generated k-d-dimensional normal distribution of samples to generate a prior probability P (wi) of the normal distribution of the discriminant function, calculated between any two points in Euclidean distance and Mahalanobis distance Platform: |
Size: 38912 |
Author:amy |
Hits:
Description: 本文针对SLAM算法中数据关联过程，提出了一种简单易行的改进方法，将欧氏距离与马氏距离结合用于数据关联。算法不必计算地图所有特征与所有量测之间的马氏距离，而是首先利用相对简单的欧氏距离计算缩小了待关联特征的搜寻范围。利用人工合成数据的仿真结果表明，改进后的数据关联方法可以大幅减少系统计算量，提高关联效率，且不会造成错误关联的增加。-This article SLAM algorithm for data association process, a simple method to Euclidean distance combined with the Mahalanobis distance for data association. Algorithms do not have to calculate all the characteristics of the map with all measurements between the Mahalanobis distance, but the first to use a relatively simple calculation of Euclidean distance to be associated characteristics of narrowing the search. The use of synthetic data simulation results show that the improved methods of data association can significantly reduce the system to calculate the volume and improve the efficiency of association, and will not lead to errors associated with an increase. Platform: |
Size: 13312 |
Author:liancb |
Hits:
Description: 用matlab实现的几种模式识别的方法，有切比雪夫距离法，马氏距离法，欧氏距离法。而且每种方法都给出了多种编程-Matlab achieved using several methods of pattern recognition, there are Chebyshev distance, Mahalanobis distance method, Euclidean distance method. But each method are given a variety of programming Platform: |
Size: 82944 |
Author:mr yao |
Hits:
Description: Activity recognition program using Motion History Image s 7 Hu moments. The program compare the Mahalanobis distance of the Hu moments of the video input with the reference and find out the activities. Platform: |
Size: 246784 |
Author:Illidanstorm |
Hits:
Description: 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 transformations, linear stretching transformation, smoothing, including parallel and serial processing, including gradient sharpening sharpening, Roberts sharpening, laplace sharpening, sobel sharpening, as well as with the absolute distance and Mahalanobis distance algorithm of the supervised classification algorithms, including the RAW format of data resources Platform: |
Size: 10661888 |
Author:幻影 |
Hits:
Description: This package contains Matlab m-files for learning finite Gaussian mixtures from sample data and performing data classification with Mahalanobis distance or Bayesian classifiers. Each class in training set is learned individually with one of the three variations of the Expectation Maximization algorithm: the basic EM algorithm with covariance fixing, the Figueiredo-Jain clustering algorithm and the greedy EM algorithm.
The basic EM and FJ algorithms can handle complex valued data directly, the greedy EM algorithm cannot.
Platform: |
Size: 20480 |
Author:李 |
Hits:
Search - Mahalanobis distance