GRAPPA

对已有图像进行锐化，这里有不同的方法对比，效果非常好，非常显著(The existing image sharpening, there are different methods to contrast, effect is very good, is very significant )

Speedy GA Graphical analysis

基于DCT的数字视频水印源程序，Matlab编写，可以直接运行(DCT-based digital video watermarking source code, Matlab can be run directly)

多个图像增强的源代码 包括小波增强 边缘增强 直方图滤波等等。。。(Multiple image enhancement of source code includes wavelet edge histogram filtering, enhance enhancement.)

图像的嵌入与提取：VC++中在一个图像A中嵌入一图像B，并能把图像B提取出来。(Image embedding and extraction: VC++ in an image embedded in an image A, B, and B images can be extracted.)

本程序实现灰度图像各向异性扩散(Anisotropic Diffusion)滤波算法，可以用于平滑信号，保留边缘，增强边缘对比度。与普通高斯Gaussian算法相比，它不会平滑边缘的图像。(The program implements grayscale image using anisotropic diffusion filtering algorithm.It can be used to smooth the signal, keep the edge, enhance the edge of the contrast. Compared with ordinary Gaussian algorithm, it does not smooth the image edges.)

中值滤波：采用5*5窗口对噪声污染的图像进行去噪处理。(Median filter: 5* 5 window on the noise pollution to deal with the image de-noising.)

图像检测的算法，Faster R-CNN算法，先对整张图像进行卷积计算，然后通过感兴趣区域池化层(RoI Pooling Layer)将选择性搜索算法推荐出来的候选区域和卷积网络计算出的特征映射图进行融合，得到候选区域对应的特征矢量，这种共享卷积计算的操作极大地减少了卷积计算的次数。而且这些特征矢量的维度统一，方便后续的分类工作。通过感兴趣区域池化层处理卷积特征，并将得到的特征送往两个并行计算任务进行训练，分类和定位回归。通过这些方法和改进的框架，Fast R-CNN 用更短的训练和测试时长，取得了比 R-CNN 更好的效果(Faster R-CNN algorithm first convolutes the whole image, then fuses the candidate regions recommended by the selective search algorithm and the feature mapping maps calculated by the convolution network through the RoI Pooling Layer to get the corresponding feature vectors of the candidate regions, which greatly reduces the number of convolution calculations. Moreover, the dimension of these feature vectors is unified, which facilitates the subsequent classification work. The convolution feature is processed by the pooling layer of the region of interest, and the obtained feature is sent to two parallel computing tasks for training, classification and positioning regression. Through these methods and improved framework, Fast R-CNN uses shorter training and testing time and achieves better results than R-CNN.)

sobel segmentation, this algorithme has a great effect for segmenting

说明：  血管骨架提取文件。冠脉血管树重建冠状动脉造影图像的三维重建是一个复杂的过程 主要包括血管骨架提取与表达、血管段匹配、骨架点匹配、三维骨架重建、表面重建等步骤。(Extraction file of vascular skeleton. Three dimensional reconstruction of coronary angiography image is a complex process, which mainly includes the extraction and expression of vascular skeleton, vascular segment matching, skeleton point matching, 3D skeleton reconstruction, surface reconstruction and so on.)