eyeball-detection-in-video

基于efficient subwindow search算法的windows实现(efficient subwindow search for windows )

根据RBM深度网络（Hinton，2006）进行MINST手写文字的分类器的训练，利用训练得到的权值制作了这个小程序，通过这个程序可以看出训练结果对数据集内的测试样本和训练样本都能进行很好的识别，但是对其他的手写字体识别就没有那么好了。(According to RBM depth network (Hinton, 2006) conducted MINST handwritten text classifier training, using the training to get the right value to produce this small program, this program can be seen through the results of the training data set and the training sample test samples are can be well identified, but on the other handwriting recognition is not so good.)

基于ART算法的CT图像重建 刚找到的，不知能不能用(CT image reconstruction based on ART algorithm)

数学形态学及相关算法的C语言实现实例 源代码调用OpenCV的cxcore和highgui两个库，应用C语言编写，实现对染色体图像中染色体数目的统计。代码中的核心算法为数学形态学的重要算法——开运算、闭运算（腐蚀和膨胀）。包含腐蚀处理、膨胀处理、自适应中值滤波、微分直方图法确定二值化阈值、种子填充算法等图像处理算法的C语言实现，值得参考。(Mathematical Morphology and related algorithms realize the C language source code examples of cxcore call OpenCV and highgui two libraries, the application of C language to realize pairs of chromosomes in the chromosome number of image statistics. The core algorithm code for an important mathematical morphology algorithms- open operation, closing operation (corrosion and expansion). Contains corrosion treatment, expansion of treatment, adaptive median filter, histogram method to determine differential binarization threshold, the seed fill algorithm, such as image processing algorithms realize the C language, it is also useful.)

图像匹配程序，原理清晰，算法明确，功能全面(Image matching procedures, the principle of clarity, the algorithm clear, full-featured)

实现对图像的经验模态分解，得到经验模态分解后的第一层IMF分量，反映了图像的主要信息，去除冗余信息，为识别提供了基础。(Empirical mode decomposition of image, obtain the empirical mode decomposition of the first layer of IMF component, reflected the main information of the image, to remove redundant information, provide the basis for identification. )

用VC编写的一个图像处理的程序：它可以实现图像的增强，包括：图像的平滑、中值滤波、梯度锐化、拉普拉斯锐化和伪彩色编码(VC prepared by an image processing procedures : it can enhance the images, including : image smoothing, Median filtering, sharpening gradient, Laplacian sharpening and pseudo-color coding)

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

用CUDA并行处理方法改写的图像降噪算法，包括KNN,NLM,以及改进的NLM方法。配置环境适合VS2010+CUDA5.0,对使用CUDA的同学来说是很好的教材。(Image denoising algorithms including KNN,NLM and refined NLM run on CUDA, useful demo for who learns CUDA based parallel programming.)

图像处理中图像几何畸变校正程序，用于图像的广角畸变的校正。(Image processing procedures for image geometric distortion correction for images of wide-angle distortion correction.)