4

说明：  计算两个离散变量x和y的联合熵z = H（x，y）。 输入：x，y：两个相同长度的整数向量输出：z：联合熵 可以使用，有利于学习目的(Compute joint entropy z=H(x,y) of two discrete variables x and y. Input: of x, y: two integer vector of the same length Output: z: joint entropy good for learning purposes)

burg距离方位分别外推超分辨算法，实现对稀疏数据的超分辨成像。(burg extrapolation distance and orientation were super-resolution algorithm to achieve the super-resolution imaging sparse data.)

说明：  运用OMP、BP、StOMP及MP算法对lena图像进行重构。(Use OMP, BP, StOMP and MP algorithms to reconstruct the lena image.)

基于JPG2000图像的超分辨率重建的matlab程序(JPG2000-based super-resolution reconstruction of image matlab program)

alpha稳定分布噪声的matlab实现(alpha stable distribution noise matlab implementation)

harrisconer角点检测，提取焊缝的角点位置信息，进行焊缝的特征识别(harrisconer extractionfeature extraction.The position information of the corner point of the weld is extracted and the characteristics of the weld are identified)

匹配追踪的主程序,用原子与信号内积的方式，对波包进行分解，再进行时频分析(match persuit)

利用相位相关法对图像进行配准，配准精度可达到0.01(The registration accuracy can reach 0.01 by using phase correlation method.)

Image retrieval lecture

于轻小型光学成像系统，小孔径限制了 图像的极限分辨率，衍射退化造成了截止频率外信息的丢失成像系统所期望的 大视场不可避免的带来边缘视场的像差恶化，各视场退化情况不同，影响信息的 判读 (Small light optical imaging system, the small aperture limit the ultimate resolution of the image, diffraction degradation aberration deterioration of the desired cutoff frequency outside the loss of information imaging system field of view inevitably bring the edge of the visual field, each referred to as field degradation, affecting the interpretation of the information)