FVC2004

将源图像做高斯卷积，以光滑化源图像，用于图像的预处理(source image makes convolution with gauss so as to smooth the image as a preprocess.)

需安装Halcon

基于NCC与SSDA的快速特征点匹配融合算法（图像匹配）(NCC and the SSDA-based feature points matching the rapid integration algorithm (matching))

本程序集合了互信息配准，PV差值，powell算法，基于小波变换的图像融合的一整套算法。只需要在GUI界面输入两幅图像，即可自动完成图像的配准融合。程序包含Matlab源代码。用Matlab打开imagefusion.m，即会弹出gui界面。融合前要输入参考和浮动图像。图像要求像素的 长＊宽 一样。否则会报错。程序只能处理灰度图像，彩色图像也会转化成灰度图像处理。程序代码已经有详细的注释，方便读者理解。(The procedures set of mutual information, PV difference, powell algorithm, based on wavelet transform image fusion set of algorithms. Only need to enter the two images in the GUI interface, you can automatically complete the image registration fusion. Program contains Matlab source code. Using Matlab open imagefusion.m, gui interface will pop up. Fusion before the input reference and floating images. Image requires the same pixel length* width. Otherwise incorrect. Can only handle grayscale images, color images into gray image processing also. Program code has detailed notes, to facilitate understanding.)

采用Graph Cut算法进行multiple-label的图像分割，算法很完整，非常适合初学者以及开发人员参考(multiple-label image segmentation using Graph Cut based algorithm, suitable for beginners and developers)

说明：  基于内容的图像检索，包括纹理、形状、颜色(Content-based image retrieval, including texture, shape, color)

对Lena图先进行jpeg压缩，再对压缩后的图像分别进行小波软阈值去噪和非抽样硬阈值去噪，比较两种去噪方案，非抽样硬阈值有更好的效果。这是根据一篇外文文献来进行编程的，最后有图像对比结果。(According to the paper of OPTIMAL WAVELET THRESHOLDING FOR VARIOUS CODING SCHEMES ,I firstly compresse the Lena picture using the jpeg method ,then respectivly denoise it using the wavelet soft-thresholding method and the undecimated DWT hard-thresholding method.Comparing the two method ,we can find the undecimated DWT hard-thresholding have a better result.)

SIFT 算法的实质上是提取局部特征的算法, 该算法在尺度空间寻找极值点, 然后根据极值点来获得尺度、旋转不变量和位置等特征。(In essence, the SIFT algorithm is an algorithm to extract local features. The algorithm finds the extreme points in the scale space and then obtains the characteristics of scale, rotation invariant and position according to the extreme point.)

本代码实现了基于卡方分布(nakagami 分布)的恒虚警检测(CFAR)，通过在查找表的形式，实现参数估计和阈值估计，完成对目标的检测。(The code based on the chi-square distribution (nakagami distribution) of the CFAR (CFAR), through the form of a lookup table to achieve the threshold parameter estimates and estimates to complete the target detection.)

迭代法阈值分割，迭代法自动计算最优阈值。已经写成函数形式，输入灰度图，输出分割好后的阈值图。(Threshold segmentation iterative method, iterative method for automatically calculating the optimal threshold. Function has been written in the form of input grayscale output partition threshold after a good map.)