chwpai

利用灰度积分投影直接对人脸图像进行检测和眼睛定位是一种常用的算法,但是直接采用该算法会受到背 景、特征等因素的影响,识别准确率较低。提出了一种基于最大类间方差阈值和区域膨胀相结合的检测与定位算法。该算 法首先计算最大类间方差设置阈值,把灰度图像转换为二值图像并检测出人脸区域,然后通过对该人脸区域中的连通区域 进行膨胀及连通性处理,精确定位眼睛坐标。实验表明,此算法可靠,具有较好的识别效果。(face recognized)

在桌面上显示图像，C++Builder精选编程学习源码，很好的学习资料。(Image display on the desktop, C++Builder select learning programming source code, very good learning materials.)

说明：  SAR图像变化检测代码，基于差异图和比值图融合的(SAR image change detection code, based on the ratio of different maps and map integration)

超分辨率POCS（投影到凸集集合理论复原方法）算法代码(The POCS super-resolution algorithm code)

说明：  本程序是基于小波和盒维数的车型识别程序，可以选择不同车型，有GUI界面，有图片，有程序，能运行，相信初学者一定能够获益。(This program is based on the wavelet and box dimension of the vehicle type recognition program, you can choose different models, GUI interface, pictures, programs, can run, I believe beginners will benefit.)

光流运动中经典的LUCAS-CANADE-TOMASI算法。内中有附说明和图片。(optical flow movement classical Lucas-CANADE- TOMASI algorithm. With a description and photo attached.)

gabor_lpb纹理结合了gabor小波和LBP的特征，提取的纹理具有很好的鲁棒性(gabor_lpb texture combines gabor wavelets and LBP features extracted texture with a very robust)

用C++编写的实现GVF的活动轮廓模型的提取，值得你参考(Extracted with implementations written in C++ GVF active contour models, it is worth your reference)

用于姿态初始化（position initialize）(for position initializing)

主分量分析的源代码，附有简单的解释说明，主要对图像矩阵做降维处理，适用多幅图像的变化检测(Principal component analysis of the source code, a simple explanation, the main image matrix reducing dimension, suitable for image change detection)