jbigkit-2.1

说明：  lsb数字水印算法，SB算法利用了数字图像处理中位平面的原理,即改变图像的最低位的信息,对图像信息产生的影响非常小,人眼的视觉感知系统往往不能察觉。以一幅256灰度的图像为例, 256 灰度共需要8 个位来表示,但其中每一个位的作用是不一样的,越高位对图像的影响越大,反之越低的位影响越小,甚至不能感知。(Digital watermarking algorithm based on lsb)

DensePose用深度学习把2D图像坐标映射到3D人体表面上，再加上以每秒多帧的速度处理密集坐标，最后实现动态人物的精确定位和姿态估计。该技术集目标检测、姿态估计、目标部分/实例分割等多种计算机视觉任务于一身的一个综合问题。(DensePost maps 2D image coordinates to 3D human body surface by in-depth learning, and processes dense coordinates at the speed of multiple frames per second. Finally, it realizes precise positioning and attitude estimation of dynamic characters. This technology integrates many kinds of computer vision tasks, such as target detection, attitude estimation, target part/instance segmentation, etc.)

说明：  60轨CAD断面图，严格按照国家标准作图，60轨CAD断面图(Cross-sectional drawing of 60-rail CAD)

vtk、itk、tcl/tk联合开发教程。(vtk, itk, tcl/tk Joint Development Guide.)

本程序是基2的时间抽取FFT变换，可以将信号从时域转换到频域。(This procedure is the base 2 time extraction FFT transform, can transform the signal from time domain to frequency domain.)

鱼眼图像校正并将校正后的图像转换成鸟瞰图，即俯视图，纯C代码，没有调用其它库(fish eye image correction,then change it to bird s eye view)

结构光重建MATLAB模拟代码，采用PMP原理(MATLAB simulation code for structural light reconstruction)

实现对图像的任意形状的裁剪。注意：图像裁剪后带有背景色(Realization of arbitrary shape image cropping. Note: the image is cropped with a background color)

车牌识别程序源码，很有用的！我也是从网上下载下来的，不过我自已做了些修改！(plates source identification procedures, very useful! I also downloaded from the Internet, but I do own some changes!)

说明：  掌握OpenGL中的矩阵变换、模型视图变换及投影变换。(The perspective projection, main view, overhead view and side view of the space tetrahedron shown in Figure 7-41 of the textbook P228 are displayed in four viewing areas using the multi-view area in OpenGL.)