PNLM

基于傅里叶描述子对旋转、平移等运动的不敏感性，识别目标(recognize the objects with rotation, translation, etc based on fourier descriptor.)

提取SIFT特征点，配准拼接的代码，能运行(detect sift features)

包含canny edge detector 和 shape context 的优化计算。(Contains the canny edge detector and the shape context of the optimization calculation.)

DOG检测算子，能够构造高斯尺度空间，并检测其中的极值，从而得到有价值的特征点位置(DOG detection operator, the Gaussian scale space can be constructed, and tested one of the extremes, resulting in valuable feature position)

该程序包中有基于Hough变换的车道线检测，还有卡尔曼跟踪和别的小程序，都是可运行的，读者可自行学习(The package, the lane detection based on Hough transform, Kalman tracking and other small programs are running, readers can learn on their own)

任务：用BFS或是DFS对图进行搜索，实现任何拓扑不连通的块的计算，算法要求写在CBFSSearch类中 工程名：Project_BFS 要求：对于生成的任意拓扑，求出其分枝个数，并输出每个分枝的节点 (Task: Using BFS or DFS for searching the graph to achieve any topology unconnected blocks calculation algorithm requires written in CBFSSearch class project name: Project_BFS Requirements: for generating arbitrary topology, find the number of its branches, and output node of each branch)

一种新的改进的LBP特征提取方法，采用多块比较的方法(a new LBP feature extraction method)

图像二值化算法，试用效果还不错，欢迎大家试用(Improved Image and Text Binarization Algorithm)

说明：  图像融合中的平均梯度、相关系数、信息熵、交叉熵、联合熵、均方误差、互信息、信噪比、峰值信噪比、均方根误差、空间频率、标准差、均值、扭曲程度、偏差指数等等(Average gradient, correlation coefficient, information entropy, cross-entropy, joint entropy, mean square error, mutual information, signal-to-noise ratio, peak signal-to-noise ratio, root mean square error, spatial frequency, standard deviation, mean, distortion degree, deviation index, etc. in image fusion)

说明：  给图像加扰动，扰动方式以zernike多项式的形式加入，Image为源图像，Co为要加的zernike系数，为行向量， 输出分别为扰动后的图像，扰动PV值，扰动RMS值(failed to translate)