KMP

asyDraw是一个简单的绘图软件，这个实例会综合运用本章所介绍了Visual C++ 2005的基础知识(this program for paint)

主动轮廓模型结合一个特殊的显著性方法实现目标分割(using active contour with a special salient detction modle to segment an image )

高分辨率遥感图像道路提取算法实现，主要思路是利用道路中心点，得到道路中心线。(Road Extraction from High Resolution Images algorithm, the main idea is to use the center of the road, get the road centerline.)

C++，人脸变形，选择图片，在图片中选择一个四边形窗口（人物脸部），然后再在内部选择一个四边形窗口，逆时针选择，然后点击变形直接呈现变形结果，点击动画可以查看人脸变形过程(C++ program, select a picture, choose a quadrilateral window (human faces) in the picture, and then select a quadrilateral inside the window, counter-clockwise to select, then click on the deformation presented directly deformation results, click animated facial deformation process can be viewed)

将图片转化为BMP位图，然后通过逐行扫描识别图片中的数字。(A picture into a BMP bitmap, and then through the progressive scanned image in the figure.)

用AAM算法进行人脸特征点的标定，即对人脸的眼睛，眉毛，嘴巴，鼻子及脸的轮廓进行标记，此代码标记了68个特征点。(AAM algorithm for facial feature points calibration, calibration of this code is the 68 feature points, see the instance document.)

城轨车辆轮对踏面故障在线监测系统，基于振动检测法的轮对踏面故障监测系统，通过傅里叶变换、小波包分析对釆集到的振动信号进行分析获得信号的特征,研究了基于短时能量判断的踏面故障特征提取算法。(On line monitoring system for wheel tread of urban rail vehicles, based on the vibration detection method of wheel tread fault monitoring system, through the Fu Liye transform, wavelet packet analysis of the collected vibration signals to obtain the characteristics of the signal, the study of the short-term energy judgment based on the feature extraction algorithm.)

傅里叶时域频域变换图形处理S参数在时域的应用(Fourier time domain frequency domain transform graphics processing S-parameters in the application of the time-domain)

SLIC超像素分割matlab版本，主要算法为C++与matlab算法联动(SLIC super pixel segmentation matlab version, the main algorithm is C++ and matlab algorithm linkage)

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.)