canny

图像 自动 标注 通过分析 训练集 ，学习 图像 和标注词 之间的关系，得出 之间的关系，得出 一些规则， 然后使用这些规则 自动 推导出 图像 最适合的标注词 ，这些标注词代表了图像的 ，这些标注词代表了图像的 高层 语义信息 。(Automatic image annotation by analyzing the training set, learning image and mark the relationship between words, the relationship between the draw, draw some rules, and then use these rules to automatically derive the most suitable image annotation words, these words represent the image annotation , these words represent the image annotation level semantic information.)

graphcut 图像分割经典论文 英文版(graphcut image segmentation classic paper in English)

利用迭代残差插值的去马赛克算法，进一步减小估计误差，得到更准确的全彩色图像，性能很不错。(Iterative interpolation residuals demosaicing algorithm to further reduce the estimation error, more accurate full-color images, the performance is very good.)

说明：  使用gpu、cpu并行进行sift算子计算匹配，能够在原来的基础上加速处理，但对显卡要求较高，具体环境配置使用方法可以参照mannual(SiftGPU is an implementation of SIFT [1] for GPU. SiftGPU processes pixels parallely to build Gaussian pyramids and detect DoG Keypoints. Based on GPU list generation[3], SiftGPU then uses a GPU/CPU mixed method to efficiently build compact keypoint lists. Finally keypoints are processed parallely to get their orientations and descriptors. SiftGPU is inspired by Andrea Vedaldi s sift++[2] and Sudipta N Sinha et al s GPU-SIFT[4] . Many parameters of sift++ ( for example, number of octaves, number of DOG levels, edge threshold, etc) are also available in SiftGPU. The shader programs are dynamically generated according to the parameters that user specified. SiftGPU also includes a GPU exhaustive/guided sift matcher SiftMatchGPU. It basically multiplies the descriptor matrix on GPU and find closest feature matches on GPU. Both GLSL and CUDA implementations are provided. )

新一代的arnold图像之乱变换算法，文件中详细说明了代码的含义，达到一定迭代次数后图像可以复原，是学习图像加密同学的必备代码(The chaos of a new generation of arnold image transformation algorithm, the paper detailed the meaning of the code, after a certain number of iterations the image can be restored, is essential for students to learn the code image encryption)

说明：  图像处理-人脸识别技术：识别出图像中人物的五官形态，从而达到识别人脸的目的。(Image Processing-Face Recognition Technology)

遥感信息工程学院遥感原理与应用课程实习植被指数(Vegetation Index of Remote Sensing Principle and Application Course Practice)

应用灰度共生矩阵求解纹理特征并用熵，相关性，惯性矩，能量，局部平衡等参数带有实例照片可以直接编译(Applying the grayscale symbiotic matrix to solve the texture features and using entropy, correlation, inertia moment, energy, local equilibrium and other parameters with example photos can be compiled directly.)

KRUSAL算法实现最小生成数的 最小生成数的 最小生成数的(The KRUSAL algorithm realizes the minimum generating number of the minimum generating numbe)

光学车间加工，很好很强大的一本书。里面有不少值得学习的东西。(Optical shop testing)