sound_sep1

实现盲源信号的分离，在一个信号源中提取出有用的信号。(Blind source signal separation, in a signal source to extract useful signals.)

基于提升格式的整数小波变换及其编解码( And its arranges based on the promotion form integer wavelet transformation decodes )

图像的5/3小波变换的matlab代码。程序简短，易懂。(Image 5/3 wavelet transform matlab code. Program brief and easy to understand.)

说明：  Curvelet变换是由一种特殊的滤波过程和多尺度脊波变换组合而成：本程序对彩色图像进行了curvelet变换从而实现图像去噪的效果。首先对图像进行子带分解；然后对不同尺度的子带图像采用不同大小的分块；最后对每个分块进行Ridgelet分析。(Curvelet transform is a combination of a special filtering process and multi-scale ridgelet transform. In this program, curvelet transform is applied to color image to achieve the effect of image denoising. First, the image is decomposed into sub-band; then the sub-band images of different scales are divided into different sizes; finally, each sub-band image is analyzed by ridgelet.)

数字全息和计算程式 计算全息图的制作和再现过程主要分为以下几个步骤： 1抽样。得到物体或波面在离散样点上的值。 2.计算。计算物光波在全息平面上的光场分布。 3.编码。把全息平面上光波的复振幅分布编码成全息图的透过率变化。 4.成图。在计算机控制下，将全息图的透过率变化在成图设备上成图。如果成图设备分辨率不够，再经光学缩版得到实用的全息图。 5.再现。这—步骤在本质上与光学全息图的再现没有区别。 (Digital Holography and CGH for calculating the production and reproduction process is divided into the following steps: 1 sampling. Be objects, or wavefront-like point in the discrete value. 2. Calculated. Calculation of complex light plane in the holographic optical field distribution. 3. Coding. The hologram plane the complex amplitude distribution of light into a hologram coding changes in the transmittance. 4. As Fig. Under the control of the computer, the hologram transmittance change in the mapping device mapping. Mapping equipment, if not resolution, then reduced by the optical version of a hologram to be practical. 5. Reproduction. This is- these in essence a hologram and the optical reproduction is no different.)

说明：  用Java实现97提升小波变换，动态演示和可视化(Realizes 97 promotion wavelet transformation with Java, dynamic demonstration and visualization )

基于小波变换的嵌入式零树小波编码算法,可以多等级压缩图像(The embedded zerotree wavelet coding algorithm based on wavelet transform can compress images at multiple levels.)

利用小波提升算法实现了第二代小波变换,将之应用在信号去噪中,实现了数据的边界对称延拓,去噪效果较好.(Wavelet Lifting algorithm using the second generation wavelet transform, to be used in signal de-noising, the realization of the data symmetric boundary extension, denoising better.)

基于小波变换的包络分析用于轴承故障诊断的源代码(Bearing envelope analysis)

小波神经网络,实现曲线拟和，数据分类，故障诊断，学习速度快于传统BP。(Wavelet neural network, and realize curve fitting, data classification, fault diagnosis, learning faster than the traditional BP.)