video_avg33_filter

网页版物流跟踪，直接登录web服务器进行物流单号查询(Web version logistics tracking, logistics single query)

ENVI中HDF5科学数据支持补丁,更新为一个SAV文件 ,放在安装目录的save_add文件 夹下，启动ENVI即可使用。(HDF5 scientific data in support of ENVI patches, updates to a SAV file on the installation directory save_add folder, start ENVI can be used.)

采用canny算子加上lee滤波器对SAR图像进行去噪(canny algorithm and lee filter to aiti-noise SAR image)

基于matlab实现干涉显微镜图像重构中的二维解包裹函数。( QualityGuidedUnwrap2D implements 2D quality guided path following phase unwrapping algorithm. Inputs: 1. Complex image in .mat double format 2. Binary mask (optional) Outputs: 1. Unwrapped phase image 2. Phase quality map This code can easily be extended for 3D phase unwrapping. Technique adapted from: D. C. Ghiglia and M. D. Pritt, Two-Dimensional Phase Unwrapping: Theory, Algorithms and Software. New York: Wiley-Interscience, 1998. Posted by Bruce Spottiswoode on 22 December 2008 2010/07/23 Modified by Carey Smith)

基于模板匹配的另一种人脸识别的算法，很实用，利用肤色建模来建立人脸皮肤模型(Another based on template matching algorithm for face recognition, very practical, using skin color modeling to create a human face skin model)

说明：  

用基于稀疏表示和KSVD字典学习去噪方法在对数域对SAR图像抑斑，本方法相对于一些经典的SAR图像抑斑方法，抑斑效果大大提高。(Based on the sparse representation and KSVD dictionary learning denoising method in the logarithmic domain，we despeckle SAR image, compared with some of the classic SAR image speckle suppression method, this method is much more effective.)

说明：  带精英决策的多目标优化关键程序之遗传算法主程序(Main program of genetic algorithm for key program of multi-objective optimization with elite decision)

非线性超声成像仿真工具，考虑组织畸变、衰减、谐波等因素。(toolbox for nonlinear ultrasound imaging simulation)

压缩感知CS——采用小波变换进行稀疏表示，高斯随机矩阵为观测矩阵，重构算法为ILRS算法，对256*256的lena图处理，比较原图和IRLS算法在不同采样比例(0.74、0.5、0.3)下的重构效果，并各运行50次，比较算法性能PSNR和每次的运行时间(Compressed sensing CS- using wavelet transform as sparse representation, Gaussian random matrix as the observation matrix and IRLS algorithm as the reconstruction algorithm. Compare lena figure and the reconstruction results using IRLS algorithm at different sampling ratio (0.74,0.50.3),then each runs 50 times, compare the performance of PSNR and each running time)