kuaipipei

图像处理，手写数字识别，GUI界面内自写数字，可以用来学习。(Image processing, digital handwriting recognition, digital write within the GUI interface, can be used to learn.)

可以成功实现双目视觉标定,在做试验的时候成功实现(Binocular vision can be successfully realize calibration tests in the time to do the successful implementation of)

我自己做的一个bmp文件进行24位真彩转256灰度和二进制的程序，并能用sobel算法，识别物体的边界。 (I myself make a bmp file for 24-bit true color to 256 gray-scale and binary procedures and sobel algorithm can be used to identify object boundaries.)

改进的聚类光流法，聚类方法有kmeans和DBSCAN，光流法金字塔LK可以用，HS光流法占用内存太多。(Improved clustering optical flow method, clustering method kmeans and DBSCAN, pyramid LK optical flow method can be used, HS optical flow occupy too much memory.)

提出了一种针对复杂环境下的过人脸检测方法，首先在CbCgCr空间利用直接最小二乘法构建了对光照和复杂背景鲁棒性更好肤色聚类模型，实现了准确的肤色检测；然后针对人脸中姿态和表情变化，提出了基于Adaboost的多姿态人脸检测，精确的实现了人脸检测定位。(Extraordinary face detection method for complex environments, the first space CbCgCr ​ ​ direct least squares method to build a better robustness to light and complex background color clustering model to achieve accurate color detection forface, posture and facial expression changes, proposed the multi-pose face detection based on Adaboost, accurate face detection and location. )

说明：  压缩感知的经典代码，包括观测，稀疏表示，重建，其中观测用的高斯观测矩阵，稀疏用的DCT，重建用的OMP算法(Compressed sensing of the classic code, including observations, sparse representation, reconstruction, observed with a Gaussian observation matrix, sparse use of the DCT, re-use of the OMP algorithm)

多传感器多目标跟踪技术研究，，主要研究多传感器多目标跟踪技术 (Multi-sensor multi-target tracking technology research, mainly multi-sensor multi-target tracking technology)

利用pcnn和nsct实现图像融合，非下采样Contourlet变换，脉冲耦合神经网络，连接强度(Using NSCT and PCNN image fusion, the sampling Contourlet transform, the pulse coupled neural network, the connection strength)

进行图像的特征提取，为图像拼接做准备，matlab(Feature extraction of image)

说明：  MATLAB实现数字图像处理和函数绘图的学习，不仅可以掌握基本MATLAB的使用，而且是数字图像处理的入门级学习。(The learning of digital image processing and functional drawing by MATLAB can not only grasp the use of basic MATLAB, but also be an entry-level learning of digital image processing.)