EdgePreservingSmoothingFilter

能够将图像坐标转化为世界坐标，根据图像像素修改参数(Can transform image coordinates into world coordinates, and modify parameters according to image pixels.)

光流法、帧间差分法、高斯背景模型差分法，在opencv环境下实现运动目标检测(moving objective detection matlab)

卷积神经网络（Convolutional Neural Network）是一个专门针对图像识别问题设计的神经网络。它模仿人类识别图像的多层过程：瞳孔摄入像素；大脑皮层某些细胞初步处理，发现形状边缘、方向；抽象判定形状（如圆形、方形）；进一步抽象判定（如判断物体是气球）。(Convolutional neural network is a neural network specially designed for image recognition. It imitates the multi-layer process of human recognition image: pupil ingestion of pixels; some cells in the cerebral cortex preliminary processing to find shape edges and directions; Abstract judgment of shape (such as circles and squares); and further Abstract judgment (such as judging objects are balloons).)

图像SURF特征提取，用于图像拼接和篡改检测，注释比较详细，程序很好理解(SURF feature extraction, image is used for image matching and tamper detection, comments are detailed, the program is easy to understand)

有效地MR图像重建算法，主要用于在MR图像的成像过程中对图像进行压缩(Efficient MR Image Reconstruction for Compressed MR Imaging)

主成分分析方法（PCA），PCA算法的理论依据是K-L变换，通过一定的性能目标来寻找线性变换W，实现对高维数据的降维。(Principal component analysis (PCA), PCA algorithm is based on the theory of KL transform, through a certain performance targets to find the linear transformation W, the realization of high-dimensional data, dimensionality reduction.)

使用camshift方法进行运动目标跟踪，（修改了网上原有的camshift算法里的一些bug）(moving object tracking by camshift method,(modification edition of the original code on the web))

用matlab实现自适应图像阈值分割最大类方差法代码(Using MATLAB to achieve adaptive threshold image segmentation Otsu method code )

说明：  次文件夹包含两个程序，可以对振动信号进行包络分析，适合信号处理入门的朋友(do envelope analysis on vibration signal)

局部拉普拉斯滤波代码，效果很好，可以直接运行(Edge-aware Image Processing with a Laplacian Pyramid)