nlm_code_for_mri

说明：  根据：基于不变矩特征和神经网络的图像模式模糊分类 论文 在matlab上做的实验，有7个不变矩生成和神经网络分类的代码，还要论文原文(According to: Based on the characteristics of moment invariants and neural network image mode fuzzy classification papers in matlab to do the experiment, there are seven moment invariants and neural network classifier to generate the code, but also the original papers)

视频图像处理，采用三帧差分法进行视频前景和背景的分离(Video image processing, inter-frame difference method of separating the foreground and background video)

本程序实现医学图像的增强，实验显示，处理后的医学图像轮廓清晰，可识性较好。(This procedure to achieve medical image enhancement, experiments showed that the treated medical image outline a clear, identifiable better.)

建立了混合高斯模型，可以对静止背景下运动目标进行检测。(Gaussian mixture model is established, you can still detect moving target in the background.)

meanshift用于目标跟踪，用于视频序列检测目标，手动选择目标(meanshift target tracking)

抠图算法 使用matlab实现 抠图算法 使用matlab实现 (Matting Matting algorithm implementation using matlab using matlab algorithm to achieve)

混合高斯(Mixture of Gaussian, MOG) 背景建模算法和Codebook 背景建模算法被广泛应用于监控视频的运动目标检测问题, 但混合高斯的球体模型通常假设RGB 三个分量是独立的, Codebook 的圆柱体模型假设背景像素值在圆柱体内均匀分布且背景亮度值变化方向指向坐标原点, 这些假设使得模型对背景的描述能力下降. 本文提出了一种椭球体背景模型, 该模型克服了混合高斯球体模型和Codebook 圆柱体模型假设的局限性, 同时利用主成分分析(Principal components analysis, PCA) 方法来刻画椭球体背景模型, 提出了一种基于主成分分析的Codebook 背景建模算法. 实验表明, 本文算法不仅能够更准确地描述背景像素值在RGB 空间中的分布特征, 而且具有良好的鲁棒性.(The background modeling algorithm of mixture of Gaussian (MOG) and codebook is widely used in moving object detection of surveillance video. However, the ball model of MOG usually assumes that the three components of RGB are independent, while the cylinder model of codebook assumes that the value of background pixel is distributed uniformly within the cylinder and the changing direction of brightness points to the origin of the coordinate system. These assumptions reduce the descriptive capability for background modeling. Therefore, the paper proposes an ellipsoid- based background model, which overcomes the MOG and codebook0s limitations. By using principal component analysis to depict the ellipsoid background model, a novel PCA-based codebook background modeling algorithm is proposed. Experiments show that this algorithm can not only give more accurate description of the distribution of background pixels but also have a better robustness.)

opencv图像库函数集，有关最新的opencv新增函数的应用(opencv functions)

说明：  利用相位一致性提取图像边缘，K-means聚类后区域生长进行图像分割，附参考论文。(Using phase coherence image edge extraction, K-means clustering image after region growing segmentation, attached reference paper.)

自适应正则化的超分辨率重建程序，采用L1L2范数。(Adaptive Regularized super-resolution reconstruction of the program, using L1L2 norm.)