BP

求图像峰值信噪比，可以用于图像质量的评估。(Peak signal to noise ratio for images that can be used for image quality assessment.)

处理计算机视觉中图像分析的图像轮廓检测和分层图像分割问题(Image processing computer vision analysis of image contour detection and hierarchical image segmentation)

模糊C聚类的应用!!利用MATLAB本身自带的FCM函数做的一个例子(Application of fuzzy clustering C!! Using MATLAB itself FCM)

matlab图像分割实例，基于Lab空间的色彩分，割调用库函数实现，带注释，简单易懂；(matlab example of image segmentation, based on Lab color space points, call the library functions achieve cutting, with comments, easy to understand )

灰色预测模型matlab,灰色模型GM(1,1)程序二次拟合和等维新陈代谢改进预测程(Matlab of gray prediction model, gray model GM (1,1) procedures for the second fitting and the same dimension metabolism to improve the forecasting process )

基于Curvelet变换的样本块图像修复算法提高现有样本块修复算法性能。首先利用Curvelet 变换估计待修复图像的4方向特征．然后利用颜色信息与方向信息共同衡量样本块间的相似度，在此基础上构造颜色-方向结构稀疏度函数．(Based on the sample block transform image restoration algorithm Curvelet enhance existing sample block repair algorithm performance. Firstly Curvelet transform estimated to be repaired 4 directional characteristics of the image. Then use the color information and direction information together measure the similarity between the sample block, constructed on the basis of color- direction sparsity structure function.)

说明：  基于稀疏表达的多源图像数据融合，遥感图像融合(Multi-source image data fusion based on sparse expression, remote sensing image fusion)

基于CFA（颜色滤波阵列）插值检测的图像篡改检测程序(Image tamper detection based on CFA (color filter array) interpolation detecting.)

读取avi视频，并进行帧间差分法运算，检测运动目标(Read the avi video, and make inter-frame difference method for computing, moving target detection)

该算法首先通过字典学习得到含噪图像的冗余字典，然后对相似的图像块进行聚类构成块群，并通过迭代收缩和L1正则化约束，对同类的图像块在字典上进行稀疏表示，以达到降噪的目的。实验结果表明，在常规的图像处理上，本文提出的算法能较好的保留图像的结构信息，与K-SVD和BM3D等现有的流行算法相比，具有更高的峰值信噪比（PSNR）(It firstly get the redundant dictionary of a noised image by dictionary learning.Then,the image patches are gathered according to their similarities.Meanwhile,the similar patches get sparse representation showed in dictionaries by iterative shrinkage and L1 regularization constraints and eventually the image is restored and noise is removed.The experimental results indicate that the proposed algorithm can well preserve the structure information of the common image with a higher Peak Signal to Noise Ratio(PNSR),compared with state-of-the-art algorithms,such as K-SVD and BM3D)