神经网络实现人脸识别任务

contourlet对LENA512灰度图的LP,DEF分解与系数重构代码,经过调试.(Contourlet LENA512 grayscale of the LP, DEF coefficient decomposition and reconstruction of the code after debugging.)

Finding MSER regions and Canny edges in natural images

斑点噪声的去除方法，主要适用sar图像，比较适合开题使用(Speckle noise removal methods, mainly for sar image, more suitable for the use of open questions)

地图代数距离变换，八边形距离变换，马哈顿距离变换(Map algebra distance transform, eight sided distance transform, distance transformation)

实现了三维超声PNN算法的GPU加速；实现GPU加速的CT圆轨道平板探测器FDK重建算法；提供对canny边缘检测算法的支持；提供交互式graph cut分割方法；实现OSTU分割算法；(Three dimensional ultrasound PNN algorithm GPU acceleration to achieve GPU accelerated CT reconstruction algorithm for circular orbits FDK flat panel detector provide support for canny edge detection algorithm provide interactive graph cut segmentation achieve OSTU segmentation )

对话框以及树控件的描述及应用,很值得初学者学习，代码可以直接运行(Dialog boxes, and a description of the tree control and application, it is worth learning for beginners, the code can be run directly)

这是我本科的毕业设计做的关于医学图像的基于形状的图像检索。预处理用小波去噪 ，特征选用不变矩。(This is my undergraduate graduation design done on the medical images based on the shape of the image retrieval. Pretreatment with wavelet denoising, feature selection invariant moment.)

MSE，最小均方误差,用于图像匹配，可用，亲测(MSE, minimum mean square error for image matching, available, pro-test)

说明：  利用IDL语言编写程序 计算差值植被指数，包括波段的读取，波段数据的分块和指数计算(Using IDL language program to calculate the difference vegetation index, including the band read the sub-band data block and index calculation)

SVM实现数据分类，可自行选取核函数，用于图像分割操作。程序可自动训练分类平面。(SVM for data classification, are free to select the kernel function，For image segmentation operation. The program can automatically train classifiers plane.)