GUI

在这个程序中，我们读取两张图像，进行特征匹配。然后根据匹配得到的特征，计算相机运动以及特征点的位置。这是一个典型的Bundle Adjustment，我们用g2o进行优化。

图像融合中常用的评价指标（非常全面）如：平均梯度、相关系数、信息熵、交叉熵、联合熵、均方误差、互信息、信噪比、峰值信噪比、均方根误差、空间频率、标准差、均值、扭曲程度、偏差指数等等。(Image fusion evaluation (very comprehensive): average gradient, correlation coefficient, entropy, cross entropy, joint entropy, mean square error and mutual information, signal to noise ratio, peak signal to noise ratio, root mean square error, spacefrequency, standard deviation, mean, distorting the degree of deviation index.)

对图像的融合结果进行评价，有均值，标准偏差，熵，梯度，相关系数，光谱扭曲度(Image fusion results of the evaluation, there is the mean, standard deviation, entropy, gradient, correlation coefficient, spectral degree twist)

OCT 成像GPU加速,非常有价值,请参考(S0141 GPU Accelerated Optical Coherence Tomography Imaging)

影像仿射变换特征提取，结合 sift 等局部特征可以处理较大视角变化下的图像匹配。(This is an implementation of Hessian-Affine detector. )

极化SAR图像处理中，将协方差矩阵转换为STOKES矩阵或Mueller矩阵的程序(Polarization SAR image processing, the covariance matrix will be converted to matrix or Mueller matrix STOKES procedures)

Object Detection Combining Recognition and Segmentation, Eighth Asian Conference on Computer Vision (ACCV), 2007 源代码(Object Detection Combining Recognition and Segmentation, Eighth Asian Conference on Computer Vision (ACCV), 2007 source code)

用matlab写的sift算法的全过程，用于提取特征点，是图像识别的一种好算法(The algrithm of sift)

说明：  DNA编码方法，可以更有效的保护图像信息，提高加密系统的安全性。(DNA coding method can protect image information more effectively and improve the security of encryption system.)

一个基于帧间差分的目标跟踪matlab源代码，解压后可直接运行，对学习跟踪有重大帮助(Frame difference of a target tracking based on matlab source code, extract can be directly run a major help in learning track)