FCM

计算一幅灰度图像的直方图；进行简单的线性变换，并与源图像的直方图做变换；利用直方图均衡化进行图像增强(Calculating a gray-scale image histogram simple linear transformation, and to do with the source image histogram transformation the use of histogram equalization for image enhancement)

基于遗传模拟退火和Otsu法的图像分割。采用一种基于模拟退火算法(SA)的混合遗传算法(GASA),来进行Otsu方法选择阈值，其中进行求解时是非线性的遗传算法（GA）的应用优化了求阈值过程，并尽可能地减少其运算量,而加入SA则避免了遗传算法(GA)常见的早熟收敛现象,从而实现有效简单的图像分割。 (adopt hybrid genetic algorithm(GASA) based on simulated annealing algorithm,choose threshold by Ostu method,which applicated the non-linear genetic algorithm(GA) allows us to optimize the process of threshold. And, where possible, to reduce the computation. in order to achieve effectivly and simply image segmentation. Combination SA is to avoid the common phenomenon about premature convergence in genetic algorithm (GA) to achieve a simple and effective image segmentation.)

用于提取图像的Zernike矩特征，从而实现目标识别，可运行(Used to extract the image of the Zernike moment characteristics, so as to realize target identification, can run)

对图像进行模糊处理，用逆滤波和维纳滤波恢复图像，也是实验时自己编写的代码，请多指教。(Fuzzy image processing, inverse filtering and Wiener filter to restore the image, but also experiments have written code, like him Zhijiao.)

em算法求解混合高斯模型，适合图像处理中，对象分割(em algorithm Gaussian mixture model suitable for image processing, object segmentation)

说明：  图像评估指标FSIM，传统全参考图像质量衡量标准FSIM（feature similarity），仿效SSIM的计算构成，同样由两部分耦合的幂指数，FSIM由PC项和GM项耦合(FSIM, the traditional full reference image quality measurement standard (FSIM), is composed of two parts of power index, FSIM is composed of PC term and GM term)

本人收集的BM3D资料，包括文献，代码，实验效果图，希望对大家有用(I collected BM3D information, including documentation, code, experimental results map, want to be useful)

互信息和梯度相结合的图像配准算法，在配准中引入了图像的空间信息(Mutual information and gradient combination of image registration algorithm, the introduction of registration in the image of the spatial information)

关于分水岭图像分割的源码，需要的可以下来用(watershed image segmentation on the source need to be down with the)

近期成果，与大家分享：奇异值分解、小波降噪、zoom细化 谱峭度 和滤波器设计，共勉(Recent achievements to share with you: singular value decomposition, wavelet noise reduction, zoom refined spectral kurtosis and filter design, encouragement)