Neural-Network-pattern-recognition

说明：  阴影3D重建,对于人脸有效，基于yale2BDB(SFS, effective for face, based on yale 2 B database)

这个是用于合成孔径雷达图像自聚焦的算法，易于实验，具有良好的效果。适合入门者。(this is a algorithm used for SAR image autofocus. this method is very simple and easy to realize and is suitable for beginner. )

说明：  关于全变分的图像修复算法。。 。。 。。 。。 (On the whole variational image restoration algorithm. . . . . . . .)

可对lytro相机所得到的光场图像进行各种处理(The light field image obtained by lytro camera can be processed in various ways.)

说明：  双目匹配计算视差，生成深度图。（前提是用自己标定好的摄像头拍的图片，导入内外参数然后进行立体匹配）(Binocular matching calculates parallax and generates depth map.(The premise is to take a picture with your own calibrated camera, import internal and external parameters, and then stereo matching))

2007年ICIP国际会议论文的源码，用于实现对图像的反卷积恢复。(2007 International Conference on ICIP paper source for the realization of the restoration of image deconvolution.)

利用Zernike方法对圆形标志点中心进行提取(The circular mark center is extracted by Zernike method.)

双目匹配计算视差，生成深度图。（前提是用自己标定好的摄像头拍的图片，导入内外参数然后进行立体匹配）(Binocular matching calculates parallax and generates depth map.(The premise is to take a picture with your own calibrated camera, import internal and external parameters, and then stereo matching))

高斯金字塔-对图像进行高斯金字塔表示，先进行高斯滤波，然后逐层抽样(Gaussian Pyramid- Gaussian pyramid of images, said first Gaussian filter, and then layer-by-layer sample)

将RGB格式图像转换到YUV空间，输入RGB图像返回YUV格式数据(Converting RGB format images to YUV space)