inverse-with-Calibration-parameters

基于efficient subwindow search算法的windows实现(efficient subwindow search for windows )

视觉注意力模型，寻找感兴趣区域，模仿人眼找出最感兴趣的区域，再找出第二感兴趣的区域，以此类推(Visual attention model to find the region of interest, to imitate the human eye to identify the most interesting region, and then find the second region of interest, and so on)

压缩感知CS——采用小波变换进行稀疏表示，高斯随机矩阵为观测矩阵，重构算法为OMP算法，对256*256的lena图处理，比较原图和OMP算法在不同采样比例(0.74、0.5、0.3)下的重构效果，并各运行50次，比较算法性能PSNR和每次的运行时间 (Compressed sensing CS- using wavelet transform as sparse representation, Gaussian random matrix as the observation matrix and OMP algorithm as the reconstruction algorithm. Compare lena figure and the reconstruction results using OMP algorithm at different sampling ratio (0.74,0.50.3),then each runs 50 times, compare the performance of PSNR and each running time)

说明：  思想：把原始图的直方图变换为均匀分布的形式，这样就增加了灰度值的动态 范围从而达到增强图像整体对比度的效果。其优点是能自动地增强整个 图像的对比度。 1、对灰度图像进行直方图的均衡化处理，达到图像增强的目的。 2、利用平均滤波和中值滤波对图像进行平滑滤波。 3、利用拉普拉斯运算对图像进行锐化滤波。(Idea: transform the histogram of the original image into the form of uniform distribution, so as to increase the dynamic gray value Range to enhance the overall contrast of the image. Its advantage is that it can automatically enhance the contrast of the whole image. 1. The gray image is processed by histogram equalization to achieve the purpose of image enhancement. 2. Average filter and median filter are used to smooth the image. 3. Using Laplace operation to sharpen the image.)

说明：  实现matlab对感兴趣区域（ROI）提取(Implement MATLAB to extract ROI)

数字图像处理代码,包括二值化,平滑,边缘检测等(Digital image processing code, including the binarization, smoothing, edge detection and so on)

人脸识别考勤系统

snake算法的c源代码,一般snake算法可以用于图像的边缘检测,是一种比较新的方法(snake algorithm c source code, the general snake algorithm can be used to image edge detection, is a relatively new approach)

关于深度玻尔兹曼机的工具箱，可以进行图像的分类和识别。(About Deep Boltzmann Machine Toolbox,which you can use for image classification and identification.)

利用摄像头工具箱标定得到的内部参数还原透视图像为“鸟瞰图”。本例中使用的图像时棋盘格。(Using the internal parameters obtained from the camera calibration toolbox. reducting perspective images as the "bird s eye view". In this case, use the image of the checkerboard.)