Compressive-Image-Super-resolution

基于BP神经网络的人脸识别(java源码)

编程实现LoG或Sobel算子，并利用该算子提取给定图像中的边缘；全局最优阀值和自适应阀值分割的工作原理，编程实现阀值分割算法。 (Programming LoG or Sobel operator, and using the edge of the operator to extract a given image global optimal threshold and adaptive threshold segmentation of the working principle of programming to achieve a threshold segmentation algorithm.)

基于贝叶斯(BAYES)阈值的小波(WAVELET)图像去噪算法源代码IMAGE DENOISING USING BAYES THRESHOLDING OF WAVELET COEFFICIENTS (Based on Bayesian (BAYES) Wavelet thresholding (WAVELET) image denoising algorithm source code IMAGE DENOISING USING BAYES THRESHOLDING OF WAVELET COEFFICIENTS)

图像融合，加权平均值，PCA方法，拉普拉斯方法，源程序(Image fusion, weighted average, PCA method, Laplace method, source)

利用高斯混合模型进行视频前景运动目标的提取！请使用自己的AVI文件。(extract the foreground moving object using the Gaussian mixture model)

采用了小波去噪的思想，已经调试成功.内含m文件，可直接运行，用于建立主成分分析模型。( Using wavelet denoising thought, Has been successful debugging. M contains files can be directly run, Principal component analysis model for establishing.)

图像的阈值分割，基于matlab的一维非广延熵Tsallis熵算法的灰度图像分割(Image segmentation, matlab-based one-dimensional non-extended entropy Tsallis entropy algorithm gray-scale image segmentation)

可以随意选取图像中多个感兴趣的区域进行操作(Can select multiple images in areas of interest to operate)

此文件一共包含3个m文件。第一个文件的功能是绘制一个二值图像，并显示其傅立叶幅度谱。文件2功能是设计频域理想低通滤波器，并加以验证：读入一个二值图像(cameraman.tif)加噪声后在频域进行低通滤波观察滤波后的图像效果。文件3的功能是对图像eight.tif加入椒盐噪声后，实现Butterworth低通滤波.(This file contains 3 m documents. Functions of first file is to draw a binary image, and displays its Fourier amplitude spectrum. Document 2 is designed to function a frequency domain ideal low-pass filter , and verified it: reading a binary image (cameraman.tif) plus noise on it and smoothing it in the frequency domain using low-pass filtering.The filtered effect will be observed by displaying image.Document 3 is designed to read a binary image(eight.tif) and add salt and pepper noise on it, realized frequence domain Butterworth low-pass filter.)

斯坦福大学概率图模型课程作业，利用马尔科夫随机场进行图像分割，能运行，附有英文说明文档(Stanford University Probability Chart Model Assignment, using Markov random field for image segmentation, operation, with English documentation)