FingerRecognition-CSDN-latent

提出了一种基于非下采样Contourlet 变换的自适应图像去噪方法 首先对噪声图像进行非下采样Contourlet 变换，得到各 个尺度各个方向子带的系数，再根据该系数的能量自适应地调整去噪阈值 实验表明，与Contourlet 多尺度阈值去噪 Contourlet 自 适应阈值去噪相比，该方法在保留图像边缘细节的同时，能提高图像的PSNR 值，减少了Gibbs 现象(A new adaptive method of image de-noising based on NonSubsampled Contourlet Transform （NSCT）is presented.Firstly， the noisy image is decomposed into a set of multiscale and multidirectional frequency subbands by NSCT， and then the threshold is adapted automatically according to the energy of subband coefficients.Compared with the multi-scale threshold using contourlet transform and using adaptive threshold based on contourlet transform， the simulation results show that the performance of this method is superior in PSNR， meanwhile it can maintain the image edge and reduce the Gibbs phenomen)

说明：  小波模极大源代码，可用来进行小波降噪或小波模态参数识别(Wavelet modal maximum source code, can be used for wavelet noise reduction or wavelet modal parameter identification)

说明：  用matlab编写界面，并实现图像的方向滤波和同态滤波，实用方便，效果较好(Matlab prepared to use interface, and the realization of the direction of image filtering and homomorphic filtering, practical convenience, better)

一种基于otsu的二维灰度图像分割算法，包括注释和源代码，适合初学者使用。(A two-dimensional gray image segmentation algorithm based on Otsu, including annotation and source code, which is suitable for beginners.)

数字识别PCA方法，对其它图像同样适用，程序简便。(Digital identification PCA method, on the other images of the same application, the program is simple.)

操作简单，实现双目视觉下的三维重建，输入双目下两张图片，生成渲染后的重建结果。(Simple, to achieve a three-dimensional reconstruction under binocular vision, binocular enter under two pictures, generated reconstructions rendered.)

一个非常实用的las文件处理工具，可以实现很多功能，如读写las文件，分类，分块，抽稀，合并，生成边界线，生成DEM，点云高度归一化，数据格式转换，波形数据压缩等(A very useful the las file processing tools, you can achieve a lot of features, such as read and write las file classification block Rarefy merge to generate the boundary line, generated DEM point cloud height normalized data format conversion, waveform data compression, etc.)

sift匹配与识别演示程序 运行face.m文件，载入图片后可提取sift特征点(sift demonstration.rar. run face.m)

说明：  基于SURF算法实现图像特征提取与描述，使用RANSAC进行图像细配准(SURF algorithm was used to extract and describe image features, and RANSAC was used for image registration)

MNIST数据集中图像数据文件， 60000个训练集(The MNIST dataset image data files, 60000 training set)