CODE

能够将图像坐标转化为世界坐标，根据图像像素修改参数(Can transform image coordinates into world coordinates, and modify parameters according to image pixels.)

首先读入图像，转化成hsi彩色空间，然后只对亮度I分量作直方图均衡化，最后合成三个分量返回到RGB图，但是这种方法容易使颜色失真，失去了部分图像细节。(First read in the image, into the hsi color space, and then only on the brightness I component for histogram equalization, the final synthesis of the three components of return to RGB chart, but this method is easy to make color distortion, loss of part of image detail. )

包含五个文件夹。 （1）MATLAB程序：其中包含10余个MATLAB程序或（函数）的源代码。程序中所作的注释，与书中关于对应算法的描述是一致的 （2）二值图像：其中的图像可供形态学图像处理实验用，也可通过提取对象的边界，供曲线演化实验使用。 （3）灰度图象和彩色图像：其中的图像，可以作为图像分割，平滑滤波，反差增强，彩色增强以及图像放大等实验的素材。 （4) 视频剪辑：，"two_cells"是采用改进的变分水平集方法，实现GAC模型图像分割的演化过程；"denoissing"是利用P_M方程，对图像平滑去噪的演化过程 "curve_linear_heat_flow"是利用FT实现的闭合曲线的线性热流演化过程。 (These codes are focused on PDE image processing)

demons三维非刚性图像配准，速度很快，基于ITK(demons of 3D non-rigid image registration, very fast, based on ITK)

对矩形件的排样过程进行编码实现，通过visual c++(layout problem)

opencvsharp检测圆

摄象机标定的两步法修改程序代码，标定摄象机内外参数(Two-step camera calibration procedure to amend the code, both within and outside the parameters of camera calibration)

说明：  level set方法中的经典模型cv模型的matlab的源程序 (level set method of classical model cv model of the source Matlab)

说明：  深度学习，读取二进制文件，识别手写数字。(Deep learning, reading binary files, recognizing handwritten numbers.)

SSD: Single Shot MultiBox Object Detector, in PyTorch A PyTorch implementation of Single Shot MultiBox Detector from the 2016 paper by Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang, and Alexander C. Berg. The official and original Caffe code can be found here. Table of Contents Installation Datasets Train Evaluate Performance Demos Future Work Reference