mfcc-lpcc

说明：  无下采样的contourlet变换阈值去噪； 无下采样的contourlet变换matlab7.0工具箱(No down-sampling of Contourlet Transform Thresholding Denoising without down-sampling the transform Contourlet matlab7.0 Toolbox)

说明：  slic超像素分割，可以实现图像的超像素分割(SLIC super pixel segmentation)

SVM 用于基于块划分特征提取的图像分类源码(SVM for feature extraction block-based image classification into source)

采用考虑湍流内外尺度影响的退化模型来恢复大气湍流降质图像，运用包含了湍流内外尺度影响的波结构函数、折射率谱以及薄透镜成像的退化函数导出了新的退化模型。(A new degradation model includling the influence of outer-and inner-scale of turbulence is presented to restore atmospheric turbulence degradation images. )

最新的用matlab实现的ＳＰＩＨＴ算法，实现对图像的高性能压缩。(Matlab using the latest achievement of SPIHT, the realization of high-performance image compression.)

实现了geodesic active contour图像分割算法，用到AOS scheme and level set method(Realize the geodesic active contour image segmentation algorithm, using AOS scheme and level set method)

多尺度的光谱图像分割，有对应的论文和matlab及c++代码(Multiscale spectral image segmentation, there are papers and the corresponding matlab and c++ code)

全变分去噪 J=tv(I,iter,dt,ep,lam,I0) 输入: I - 灰度图像, iter - 迭代次数 [1], dt - 时间步长 [0.2], ep - 提升参数epsilon [1], lam - 保真项 lambda [0], I0 - 输入噪声图像 [I0=I] ([]中的是缺省值)( 全变分去噪 J=tv(I,iter,dt,ep,lam,I0) 输入: I - 灰度图像, iter- 迭代次数 [1], dt - 时间步长 [0.2], ep - 提升参数epsilon [1], lam - 保真项 lambda [0], I0 - 输入噪声图像 [I0=I] ([]中的是缺省值))

非精确ALM解决PCA算法的例子，用后效果不错，发上来分享。(This matlab code implements the inexact augmented Lagrange multiplier method for Robust PCA.)

基于粒子滤波和卡尔曼滤波的运动目标视频跟踪程序，非常强大和实用，强烈推荐学习使用。(Kalman filter based on particle filter and target video motion tracking program, very powerful and practical, it is strongly recommended to learn to use.)