IBP

直接线性变换DLT，直接由像平面坐标到地面空间坐标的直接变换，可用于量测相机，非量测相机（本人用的是 高速相机）。配合前方交会验证l系数的准确与否。以DLT得到的结果为初值，用光束法平差可以期望得到更高精度。是数字摄影测量课程作业的例子。(Direct linear transformation DLT, and the direct conversion of coordinates directly from the image plane to the ground space coordinates, the camera can be used for measuring the non-measurement camera (I use a high-speed camera). Tie the forward intersection verify l coefficient accurate or not. To the the DLT results obtained for the initial value, bundle adjustment can expect greater accuracy. Examples of digital photogrammetry course work.)

利用svm算法分类图像。示例中：将篮球场和网球场利用算法自动分类，包含了基于颜色矩的彩色图像特征提取算法(image classification using SVM algorithm)

说明：  实现多个阈值的图像分割及K-mean聚类的图像分割(Multiple threshold image segmentation or K-mean clustering image segmentation)

通过用户给定的标签信息，来提取图像中的标记像素点位置，保存为种子点(Through the label information given by the user, the position of the label pixels in the image is extracted and saved as seed points.)

基于KSVD算法的图像去噪算法，稀疏表示，字典学习，OMP算法，基于DCT字典的图像去噪，demo可以直接运行。(Image denoising by KSVD algorithm，spare representation，dictionary learning，OMP algorithm，DCT dictionary)

使用ssd深度学习方法来实现生活中想要识别的目标(Using SSD in-depth learning method to achieve the goals you want to identify in your life)

matlab模拟产生马鞍形光学条纹图，通过求取其条纹方向，二值化得到其巨齿包裹图，中心线图。这些对于激光散斑（ESPI），雷达干涉（INSAR）图像的去包裹有重要的指导意义。()

说明：  进行三维去高后，根据sar参数信息，将斜距转变为地距。(After performing three-dimensional height removal, the slope distance is converted to ground distance according to the sar parameter information.)

说明：  EM算法概述，用来进行图像重采样检测的代码(EM algorithm overview)

基于DCT域音频水印完整源代码，包括水印图像的预处理（二维二值图像Arnold变换、混沌加密、降维），水印的嵌入提取以及检测，信噪比和相似性系数。(Based on the the DCT domain audio watermarking complete source code, including the watermark image preprocessing (two-dimensional binary images Arnold transform chaotic encryption, dimensionality reduction), the embedded watermark extraction and detection, signal-to-noise ratio and similarity coefficient.)