MutualInfo

改进SIFT算法，用于光学图像和SAR图像配准(Improved SIFT methods for Registration of Optical and SAR image.)

采用改进的CV图像分割算法用于提取图像边缘轮廓，代码注释很详细。(CV improved image segmentation algorithm for extracting image edge profile, the code is very detailed notes.)

基于互信息的图像配准算法，优化算法采用Powell和粒子群向结合的算法(Based on mutual information image registration algorithm, using Powell optimization algorithm and particle swarm algorithm to combine)

PCA_进行indian_pines数据集合分类。((use PCA to classify the indian_pines data with train and test data in the rar))

有关图像的目标识别："给出一种基于特征分类辨识的合成孔径雷达图像目标检测方法#用恒虚警和扩展分形方法对3&E图像进行目 标检测后用面积和峰值能量比算子辨识目标和背景杂波!去除一部分虚警!用小波域主成分分析对每个检测窗口内的图 像提取特征向量!用支持向量机对提取得到的特征向量进行分类!辨识目标和背景杂波!完成目标检测#使用&K?3数 据对该方法进行验证和分析!实验结果表明!经过特征分类辨识后!在检测率不变的情况下!虚警数目显著降低# (Related to the image target recognition)

C# 给图片添加水印 图片类型转换 例子

读入光流估计的结果，将运动矢量转化成颜色，生成颜色的光流估计图像。(Read optical flow estimation result, the color motion vector conversion, optical flow estimation to generate a color image.)

对两幅遥感图像进行变化监测，先求得差值图像，然后用FCM聚类方法分成变化类和不变类(On two remote sensing image change detection, the first difference image is obtained, then FCM clustering into the same category and class changes)

说明：  图像去噪的评价指标ENL, SSIM, PSNR,SNR,EPI(The evaluation indexes of image denoising are ENL, SSIM, PSNR,SNR and EPI)

《VC++数字图像识别技术典型案例》第九章光学字符识别技术，包括预处理、边缘跟踪和特征提取算法("VC Digital Image Recognition Technology typical case," the ninth chapter of optical character recognition technologies, including pretreatment, Edge tracking and feature extraction algorithm)