Undecimated-DWT

采用ESIHE算法增强图像对比度，适用于夜间道路拍摄的图像(ESIHE algorithm is used to enhance image contrast, which is suitable for night road images.)

基于GA和MP的信号稀疏分解,算法速度比元来的有很多改进。(Based on GA and MP sparse signal decomposition, the algorithm faster than the yuan to have many improvements.)

单帧图像超分辨率重建。对于学习超分辨率重建很有帮助。(Super-resolution reconstruction of single frame image.It is helpful for learning super-resolution reconstruction.)

VisualC++数字图像处理技术详解第2版光盘，第十二章(VisualC++ digital image processing technology Detailed Version 2 discs, Chapter XII)

Retinex理论的基础理论是物体的颜色是由物体对长波（红色）、中波（绿色）、短波（蓝色）光线的反射能力来决定的，而不是由反射光强度的绝对值来决定的，物体的色彩不受光照非均匀性的影响，具有一致性，即retinex是以色感一致性（颜色恒常性）为基础的。不同于传统的线性、非线性的只能增强图像某一类特征的方法，Retinex可以在动态范围压缩、边缘增强和颜色恒常三个方面打到平衡，因此可以对各种不同类型的图像进行自适应的增强。(The basic theory of Retinex theory is the color of the object by object for the long wavelength (red), medium (green), short wave (blue) light reflection ability to decide, rather than by the intensity of reflected light of the absolute value to decide, the color of the object under illumination nonuniformity effects, consistent with the Retinex, that is based on color constancy (color constancy based). Different from the traditional linear, nonlinear image enhancement method of only one kind of features, Retinex can be in dynamic range compression, edge enhancement and three aspects of color constancy hit the balance, thus enhancing adaptive to a variety of different types of images can be.)

基于深度图像的图像修复算法，首先得到待修复图像的深度图像，然后利用图像的深度图对破损区域进行修复。(Based on the image restoration algorithm of depth image, the depth image of the image to be repaired is obtained, and then the damaged region is repaired by using the depth map of the image.)

PIVlab - 时间分辨粒子图像测速（PIV）工具： 一种基于GUI的工具，用于预处理，分析，验证，后处理，可视化和模拟PIV数据。 使用MATLAB网络研讨会进行人脸识别代码： 使用MATLAB在线讲座的人脸识别中的主要演示文件。 Gabor特征提取： 该程序生成一个自定义Gabor滤波器组; 并使用它们提取图像特征。 主成分分析： 用于特征提取； 链码： 基于MATLAB的freeman的曲面轮廓描述(PIVlab - time resolved particle image velocimetry (PIV) tool: A GUI based tool for preprocessing, analysis, validation, post processing, visualization, and Simulation of PIV data. Using MATLAB webinar for face recognition code: The main demo file is used in MATLAB online lectures for face recognition. Gabor feature extraction: The program generates a custom Gabor filter bank and uses them to extract image features. Principal component analysis: For feature extraction; Chain code: Surface contour description of Freeman based on MATLAB)

人脸68点标注，用于人类面部关键点检测，结合dlib(face landmark master)

一个ICA 源代码,非常完整，希望对大家有帮助(fast ICA)

图像融合程序，用以提取图像的高分辨率部分，实现图像的清晰化(image fusion procedure to extract high-resolution images, the images clearer)