Threshold-segmentation

基于稀疏字典和稀疏编码的图像去噪算法，基于低秩约束的高光谱条纹噪声去除，包含论文及代码(Based on sparse dictionary and sparse coding image denoising algorithm, based on low rank constraints of hyperspectral fringe noise removal, including papers and code)

说明：  选择一张灰度图片，添加高斯噪声并进行双边滤波(Select a gray image, add Gaussian noise and perform bilateral filtering)

说明：  立体图像质量评价方向优秀论文的实现代码，仅供参考。(Stereo image quality evaluation direction of the excellent paper implementation code, for reference only.)

集成ITK、VTK、MFC读取DICOM的代码，建成win32程序即可。运行完美(Integrated ITK, VTK, MFC to read DICOM code, built win32 program can. Works perfect)

混合高斯背景建模，可以把连续帧图片前景与背景区分开来(Mixed gaussian background modeling, can continuous frame picture foreground and background to distinguish )

说明：  自组织神经网络SOM的算法，经过调试可以用(Self-organizing neural network SOM algorithm can be used after debugging)

利用多尺度高斯函数去除场景的光照分量；然后构造了一种二维伽马函数，利用光照分量的分布特性调整二维伽马函数的参数，降低光照过强区域的亮度值，提高光照过暗区域的亮度值，最终实现对光照不均匀图像的自适应校正处理。(The multi scale Gauss function is used to remove the illumination component of the scene, and then a two-dimensional gamma function is constructed. The parameters of the two-dimensional gamma function are adjusted by the distribution characteristics of the illumination component, the brightness value of the light illuminated region is reduced and the brightness value of the light dark area is improved. Finally, the adaptive correction of the uneven illumination image is realized. Positive treatment.)

Ransac拟合直线和最小二乘法拟合的比较，对初次接触ransac的读者帮助很大(Ransac fitting straight line and the least-squares fitting of the comparison, the initial contact with the readers of great help to ransac)

python写的图像相似度算法。比较图像相似度，选出最相思的图片(python write the image similarity algorithm. Compare image similarity, image to select the most Acacia)

用matlab进行图像检索，基于边缘直方图（EHD）描述子，它是MPEG-7标准中提出的一种边缘描述子，它具有描述图像亮度变化的方向和频率的能力。资料为主程序代码。(Matlab for image retrieval, based on the description of the edge histogram (EHD) sub, it is proposed in the MPEG-7 standard descriptor an edge, it has the direction of the change and the frequency of the described image brightness capability. Data the main program code.)