MosaicKit

数字图像处理中的滤波和傅里叶压缩，包括理想低通滤波器，巴特沃茨高通滤波器，高斯带通滤波器，高斯带阻滤波器，FFT图像压缩。附原图像和处理后的图像截图。(Digital image processing in filtering and Fourier compression, including the design of an ideal low-pass filter, design Batewoci high-pass filter, bandpass filter design Gaussian, Gaussian band stop filter, FFT image compression. Attached to the original image and processed image capture.)

基于小波的去噪算法，采用BAYES原理选取阈值，源代码，参考文献：Adaptive Wavelet Thresholding for Image Denoising and Compression(Wavelet-based denoising algorithm using the principle to select threshold BAYES, source code references: Adaptive Wavelet Thresholding for Image Denoisingand Compression)

我自己做的一个bmp文件进行24位真彩转256灰度和二进制的程序，并能用sobel算法，识别物体的边界。 (I myself make a bmp file for 24-bit true color to 256 gray-scale and binary procedures and sobel algorithm can be used to identify object boundaries.)

实现两幅图像匹配。应用SSD+SAD+NCC算法的匹配，很好用的程序(Realizing Two Image Matching.Application of SSD+SAD+NCC algorithm matching, very useful program)

这个算法包实现了从多幅拥有共同结构的图像里提取出共同形状的骨架。( This package implements the algorithm for Sketching the Common as described in: Shai Bagon, Or Brostovsky, Meirav Galun and Michal Irani "Detecting and Sketching the Common", CVPR 2010)

说明：  calibration摄像机镜头的校正程序(calibration Calibration camera lens calibration procedure)

说明：  这是基于Camshift的目标跟踪code，编程语言为matlab。下载解压后可以直接运行。(This is the target tracking code based on CAMSHIFT, and the programming language is matlab. After downloading and decompressing, you can run it directly.)

Image processing functions: Gamma correction Contrast stretching histogram equalization

用于实现基于压缩感知在傅里叶系数域上的图像融合(For image fusion based on compressed sensing in the domain of Fourier coefficients)

编程实现二维8*8图像块的DFT，DCT变换 输入一副RGB图像，将其转化为YCbCr颜色空间，然后对Y分量做分块DFT变换，保存为灰度图像，统计计算时间 编程实现8*8块DCT变换,然后分别显示，当使用64个DCT系数里面的一些系数进行重构，比较其质量；同时熟悉采用FFT来实现DCT变换的思想，并显示2维8*8DCT变换的基函数图像(Programming the DFT, DCT transform of two dimensional 8*8 image block Input a pair of RGB images, transform it into YCbCr color space, then divide the Y component into block DFT transform, save as gray image, and calculate the calculation time The 8*8 block DCT transform is implemented by programming, and then it is shown that when using some coefficients in 64 DCT coefficients, the quality is reconstructed. Meanwhile, the idea of DCT transformation is familiar with FFT, and the base function image of the 2 dimensional 8*8DCT transform is displayed.)