imagecompress

用帧差法找出运动物体，并用形态学滤波恢复物体(Identify moving objects in frame difference method and morphological filtering restore objects)

考虑雨衰 阴影 和多径影响，可直接计算得到多重分形谱,非归零型差分相位调制信号建模与仿真分析 。( Consider shadow rain attenuation and multipath effects It can be directly calculated multi-fractal spectrum, NRZ type differential phase modulation signal modeling and simulation analysis.)

压缩感知正则化正交匹配算法（ROMP）以及用此算法实现一维信号和二维图像的恢复，亲自编写调试可用(The ROMP algorithm for compressive sensing and using this method to reconstruct the 1D signal and 2D image.)

总变分正则化超分辨率重建 包括两种范数形式的正则化(Total Variation Regularized super-resolution reconstruction, including two-norm in the form of regularization)

本程序能够去除一幅照片中由于光线发散而产生的红眼效应，即去除红眼(the function is to remove red part of eyes in a picture or photo)

1.设计一个程序，对一幅灰度图像的实现如下几何变换,1)放大为原图1.5倍 2)绕中心旋转30度(CW) 3)采用偏移量插值实现一个透视变换. 灰度差值用最近邻插值和双线性插值 2. 绘制一幅灰度图像的梯度幅度图像（三点法求梯度），针对梯度幅度图像合理的选择一个阈值（通过试验即可）将其二值化，以获得图像边缘检测图像。 ((1) design a program, a grayscale image as geometric transformation, zoom 1) for 1.5 times the original 2) around the center of rotation of 30 degrees (CW) 3) interpolation of the offset to achieve a perspective transformation.gray level difference between the nearest neighbor interpolation and bilinear interpolation (2) draw a grayscale image of the gradient magnitude image (three-point method seeking gradient), the gradient magnitude image is reasonable to select a threshold value (the test can be) the second value to the image edge detection image.)

混合高斯(Mixture of Gaussian, MOG) 背景建模算法和Codebook 背景建模算法被广泛应用于监控视频的运动目标检测问题, 但混合高斯的球体模型通常假设RGB 三个分量是独立的, Codebook 的圆柱体模型假设背景像素值在圆柱体内均匀分布且背景亮度值变化方向指向坐标原点, 这些假设使得模型对背景的描述能力下降. 本文提出了一种椭球体背景模型, 该模型克服了混合高斯球体模型和Codebook 圆柱体模型假设的局限性, 同时利用主成分分析(Principal components analysis, PCA) 方法来刻画椭球体背景模型, 提出了一种基于主成分分析的Codebook 背景建模算法. 实验表明, 本文算法不仅能够更准确地描述背景像素值在RGB 空间中的分布特征, 而且具有良好的鲁棒性.(The background modeling algorithm of mixture of Gaussian (MOG) and codebook is widely used in moving object detection of surveillance video. However, the ball model of MOG usually assumes that the three components of RGB are independent, while the cylinder model of codebook assumes that the value of background pixel is distributed uniformly within the cylinder and the changing direction of brightness points to the origin of the coordinate system. These assumptions reduce the descriptive capability for background modeling. Therefore, the paper proposes an ellipsoid- based background model, which overcomes the MOG and codebook0s limitations. By using principal component analysis to depict the ellipsoid background model, a novel PCA-based codebook background modeling algorithm is proposed. Experiments show that this algorithm can not only give more accurate description of the distribution of background pixels but also have a better robustness.)

快速双边滤波器，对双边滤波器进行的改进，可以使用，对写论文的同学会有些帮助，可以参考看一下。(Rapid bilateral filter, to the improvement of bilateral filter, can be used, to write a paper of homecoming some help, you can refer to see.)

三维血管重建的matlab代码，毕业设计常用，非常实用的。(Three dimensional vascular reconstruction)

直方图均衡（HE），自适应直方图均衡（AHE），限制对比度的直方图均衡（CLAHE）的图像处理算法，运行无错误，效果还不错。包含循行结果对比。(Histogram equalization (HE), adaptive histogram equalization (AHE), and contrast-limited histogram equalization (CLAHE) image processing algorithm run without error, and the effect is good. Include line-by-line results comparison.)