cdbjnjxu

计算“高位平面图像”的伪Zernike矩（低 6阶），并作为特征。(Computing " high dimensional images," the pseudo-Zernike moments (low order 6), and as a feature.)

Magnetic resonance (MR) images can be used to detect lesions in the brains of multiple sclerosis (MS) patients and is essential for diagnosing the disease and monitoring its progression. An automatic method is presented for segmentation of MS lesions in multispectral MR images. Firstly a PD-w image is subtracted its corresponding T1-w image to get an image in which the cerebral spinal fluid (CSF) is enhanced. Then based on kernel fuzzy c-means (KFCM) algorithm, the enhanced image and the corresponding T2-w image are segmented respectively to extract the CSF region and the CSF combining MS lesions region. A raw MS lesions image is obtained by subtracting the CSF region CSF combining MS region. By applying median filter and thresholding to the raw image, the MS lesions are detected finally. Results are quantitatively uated on BrainWeb images using Dice similarity coefficient (DSC). Finally, the potential of the method as well as its limitations are discussed.

说明：  利用matlab仿真软件仿真SVPWM的波形，例子中有这个实例的解决过程(Matlab simulation using SVPWM waveform simulation software, examples in the process of resolving this instance)

基于模糊控制的变速恒频风力发电最大风能跟踪研究(The maximum follow-up study of wind speed constant frequency wind power generation based on fuzzy control)

An ad-hoc network with a sender, a destination and a third station act- ing as a relay is analysed. The channels are modelled containing thermal noise, Rayleigh fading and path loss. Di® erent combining methods and di- versity protocols are compared. The amplify and forward protocol shows a better performance than the decode and forward protocol, unless an error correcting code is simulated. To combine the incoming signals the chan- nel quality should be estimated as well as possible. Information about the average quality shows nice bene¯ ts, and a rough approximation about the variation of the channel quality increases the performance even more.

信号发生器和电子琴。其中电子琴有36个按键，跨3个八度，分别为小字组、小字一组和小字二组，可以播放含基音、泛音和包络的声音(Signal generator and keyboard. Keyboard comes with 36 keys which spans three octaves, respectively, for the small print group, the small print of a group and the small print of two groups, containing the pitch, overtones, and the sound envelope can play)

对图像分割，初始轮廓为椭圆。变化的过程中始终以椭圆为约束(For image segmentation, the initial contour is an ellipse.)

code for face align using ica (independent component analysis) .a good code for reaserch .

novel based approach for object segmentation

采用db4小波对是与信号进行降噪处理，实际效果良好(Using DB4 wavelet denoising is processing and signal, the actual effect is good)