PCNN-Algorithm

阴影检测,基于OpenCV用于对图像中阴影的检测(Shadow detection, OpenCV for image shadow detection)

将2D图像转换为红蓝3D效果。程序由本人编写，算法来自论文《A novel 2D-to-3D conversion technique based on relative height depth cue》by Yong Ju Jung等。(2D-to-3D Conversion. The codes are written by myself and according to the article "A novel 2D-to-3D conversion technique based on relative height depth cue" by Yong Ju Jung.)

一个阈值去噪程序，包括经典的去噪方法，如折中阈值，自适应阈值等等。(A threshold denoising procedures, including the classical denoising methods, such as compromise threshold, adaptive threshold and so on.)

数字信号处理或图像处理常用工具箱matlab(Common toolbox for digital signal processing)

VC++,DirectX,运动图像检测,运动轨迹跟踪(VC++, DirectX movement trajectory tracking image detection)

这是个criminisi算法的源码，可以对图像进行相应的修补。效果很好。(This is a criminisi algorithm source code, images can be appropriate patch. With good results.)

采用MATLAB语言编程实现了基于遗传算法的最大熵单阈值、最大熵双阈值、二维最大熵单阈值图像分割和基于最大类间方差遗传算法的图像分割(Through the study of threshold segmentation method and genetic algorithm theory, matlab programming language used to achieve the genetic algorithm based on maximum entropy single threshold, dual-threshold maximum entropy, maximum entropy of two-dimensional single-threshold image segmentation and otsu genetic algorithm for image segmentation.)

本程序实现了对影像特征点自动提取，利用Morevac、Forstner、Harris3个经典算子。在此基础上利用相关系数法实现影像自动匹配，并且引入最小二乘平差，使匹配点精度有所提高。 在搜索点过程中，利用了核线影像特性，对二维影像搜索使用了爬山法启发式搜索。对大数据量影像采用影像金字塔结构处理。 1、使用GDAL库读取影片，支持TIFF、PNG、JPEG、JPG、BMP、GIF、IMG格式读取。使用GDI绘图。 2、防止大数据量绘图视图闪烁，图片显示采用双缓存技术。 3、保存视图数据为图片文件，支持TIFF、PNG、JPEG、JPG、BMP、GIF格式保存。 4、TreeCtrl控件、ListCtrl控件的基本操作。 5、MFC单文档程序视图通讯、更换视图、视图分割。(This program of image features automatic extraction point, use Morevac, Forstner, Harris3 a classic operator. Based on the correlation coefficient method using the image matching, realization and introducing least squares adjustment, the matching point to improve precision. In the search process, the use of the image characteristics of nuclear line, 2d image search using the heuristic method of climbing. For large quantity of data using image processing image pyramid structure. 1, using film, read GDAL repository support JPEG, TIFF, PNG, GIF, BMP, JPG, read IMG format. Use GDI drawing. 2 and prevent large amount of data, drawing view pictures showed adopt double caching techniques. 3, save for the image file, views data support JPEG, TIFF, JPG, PNG, GIF, BMP format. 4 and TreeCtrl controls, the basic operation ListCtrl controls. 5 and MFC single document procedure view communication, replace view, view.)

一种点云数据的配准算法，可用于进一步的三维建模处理，配准效果良好。(One kind of point cloud data registration algorithm, three-dimensional modeling can be used for further processing, registration to good effect.)

本算法主要采用变分贝叶斯求解图像忙恢复问题。(This package contains implementations of the MAP_k blind deconvolution algorithms described in the paper "Efficient Marginal Likelihood Optimization in Blind Deconvolution" Levin, Weiss, Durand and Freeman, )