hungarian-rvm

SIFT，即尺度不变特征变换（Scale-invariant feature transform，SIFT），是用于图像处理领域的一种描述。这种描述具有尺度不变性，可在图像中检测出关键点，是一种局部特征描述子。[1] 该方法于1999年由David Lowe[2] 首先发表于计算机视觉国际会议（International Conference on Computer Vision，ICCV），2004年再次经David Lowe整理完善后发表于International journal of computer vision（IJCV）。截止2014年8月，该论文单篇被引次数达25000余次。(SIFT, namely Scale Invariant Feature Transform (Scale-invariant feature transform, SIFT), it is a description for image processing. This description has scale invariance, can detect critical point in the image, it is a local feature descriptor. [1] The method in 1999 by David Lowe [2] First published in the International Conference on Computer Vision (International Conference on Computer Vision, ICCV), 2004 was again perfect finishing after David Lowe published in the International journal of computer vision (IJCV) . As of August 2014, the paper cited the number of times a single article of more than 25,000 times.)

本代码是用Matlab实现图像的超分辨率重建，方法为凸集投影法，能从多幅低分辨率图像重建一幅高分辨率图像。(We use Matlab to reconstruct image. The method is convex projection on suoer-resolution(POCS).)

用于对图像特征的分类，随机森林算法是一类很好的算法(For the classification of image features, random forest algorithm is a kind of a good algorithm)

RGB颜色空间转换到HSV颜色空间的C++Builer 程序(RGB color space conversion to HSV color space C Builer procedures)

四个IMAGE窗口，分别对图像进行读取，最大值滤波，最小值滤波及中值滤波。(Four IMAGE window, read the image, respectively, maximum filter, the minimum filter and median filter.)

双峰法是一种简单的阈值分割方法，即如果灰度级直方图呈现明显的双峰状，则选双峰之间的谷底所对应的灰度级作为阈值分割。(Two peaks is a simple threshold segmentation method, that is, if the gray level histogram showed a clear bimodal shape, then choose between the two peaks corresponding to the bottom of the gray level as threshold segmentation.)

通过求差分曲线，利用阈值分割算法对图像进行自动多阈值分割(image segment method)

说明：  matlab开发的粒子滤波目标跟踪程序，跟踪目标良好。(Matlab development of particle filtering procedures。)

图像处理之Matlab特征提取和表达-一些规则图形的特征提取(Matlab feature extraction and expression in image processing - feature extraction of some regular patterns)

程序设计步骤： 1、去均值 2、计算协方差矩阵及其特征值和特征向量 3、计算协方差矩阵的特征值大于阈值的个数 4、降序排列特征值 5、去掉较小的特征值 6、去掉较大的特征值(一般没有这一步） 7、合并选择的特征值 8、选择相应的特征值和特征向量 9、计算白化矩阵 10、提取主分量(Programming steps: 1 to mean 2, calculation of covariance matrix and its eigenvalues and eigenvectors 3, the calculation of covariance matrix eigenvalues greater than the threshold number of 4, in descending order of eigenvalue 5, remove the smaller eigenvalue 6, remove the larger eigenvalue (usually not this step) 7, the combined choice of eigenvalues 8, select the appropriate eigenvalues and eigenvectors 9, computing whitening matrix 10, principal component extraction)