gauss

基于MRI的脑组织分割。首先从给定的MRI图像中得到脑区域，而后计算脑容积；再得到脑白质灰质区域，并计算百分比。(Given an MRI scan, first segment the brain mass from the rest of the head, then determine the brain volume. Also compare portions of gray and white matter present. )

实现基于样本块的图像修复，是Criminisi经典图像修复算法。(Criminisi algorithm about exemplar-based inpainting)

非常好的椭圆拟合算法，拟合进度很高，算法很好理解，代码质量高(Ellipse fitting algorithm is very good, very fit schedule, a good understanding of algorithms, high code quality)

说明：  实现机器视觉双目标定，三维重建等算法，具有很好地擦考价值( Robot with two cameras to switch recognition system. (Note that not binocular vision) and the reference used opencv1.0 cmv. )

基于SURF算法实现图像特征提取与描述，使用RANSAC进行图像细配准(SURF algorithm was used to extract and describe image features, and RANSAC was used for image registration)

图像特征隐写分析，用于分析图像是否含有秘密信息(Image feature steganalysis for the analysis of the image if it contains confidential information)

说明：  数学地角度来看，信号与图像处理可以统一看作是信号处理（图像可以看作是二维信号），在小波分析地许多分析的许多应用中，都可以归结为信号处理问题。对于其性质随时间是稳定不变的信号，处理的理想工具仍然是傅立叶分析。但是在实际应用中的绝大多数信号是非稳定的，而特别适用于非稳定信号的工具就是小波分析。(Mathematically, signal and image processing can be regarded as signal processing (image can be regarded as two-dimensional signal). In many applications of wavelet analysis, they can be reduced to signal processing. For signals whose properties are stable over time, the ideal tool for processing is still Fourier analysis. However, most of the signals in practical applications are unstable, and the tool especially suitable for unstable signals is wavelet analysis.)

使用全变分模型对受噪声污染的图像进行修复(Using the total variation model of the image affected by noise pollution, to repair)

随着红外成像技术的发展，红外小目标检测在军事领域有越来越重要的应用。以此为背景，研究了天空、海面、大地等各种背景下红外视频中弱小目标的检测问题。 (With the development of infrared technology,dim small targets detection play a more and more important part in the military. The problem of dim small targets detecting in a infrared video with the background of the sky,the sea and the groundhas been studied. )

基于序贯蒙特卡罗方法的人体跟踪程序，对于学习蒙特卡罗粒子滤波器的人有重要参考价值。(Sequential Monte Carlo method based on human tracking procedures, Monte Carlo particle filter for learning a person has an important reference value.)