hkdes_1.0

利用传统的SVM-HOG算法，进行行人检测(HOG-SVM algorithm for pedestrian detection)

这是一个口形特征点粗定位程序，首先对唇部图象进行边缘检测，然后利用几何特征进行定位。(This is a lip feature points coarse positioning procedures, first of all on the lip image edge detection, and then positioning the use of geometrical features.)

叠加平均去噪过程的实现，信号产生，加噪，去噪效果的显示(Average denoising, signal generation, noise addition, display the denoising effects)

本程序主要实现暗背景下含高斯噪声的光斑滤除噪声，实现光斑中心提取。采用了sobel算子和梯度倒数加权滤噪、最大类间方差法（Otsu）确定阈值、质心法提取光斑中心坐标。(The program is mainly realized under a dark background Gaussian noise spot containing noise filtering, to achieve spot center extraction. Using sobel operator and gradient inverse weighting filter noise, Otsu method (Otsu) to determine the threshold, the center coordinates of the spot centroid extraction.)

计算机图形学基础算法z-buffer， 实现隐藏面消除(Computer graphics based algorithm z-buffer, to achieve hidden surface removal)

processing编写的圆形速度运动代码(processing written in the circular speed of movement code)

基于opencv的图像灰度化，将24位彩色图像重新量化为8位灰度图像(gray image)

针对遥感图像可控参数误差造成的图像模糊，进行模糊核估计(Remote sensing images for image blur caused by controllable parameter error, blur kernel estimation)

目标检测，利用上下文关系 (object detection using context)

对SAR图像分割 用马尔科夫随机长进行的。可以任意输入类别数目(For SAR image segmentation using Markov old airport)