Matching-neighborhood-difference-

LMMSE图像超分辨率重建，基于先验知识的图像超分辨率重建(LMMSE image super-resolution reconstruction, image super-resolution reconstruction based on prior knowledge)

说明：  matlab图像配准算法，确定归一化互相关最大值及其位置，利用相关找到的偏移量，判断两幅图是否相同。(MATLAB image registration algorithm determines the maximum normalized cross-correlation and its location, and uses the offset found by correlation to determine whether the two images are the same.)

SAR图像的非相干cloude分解，最后得到熵值、散射角、反熵。合成三色彩色图，最终将结果显示出来。(SAR image non coherent cloude decomposition , finally entropy,scatter degree were obtaind.)

Images of diffraction

高动态图像(HDR)合成算法，多曝光图像的配准算法(High dynamic image (HDR) synthesis algorithm, multi-exposure image registration algorithm)

在产生混沌伪随机序列的混沌映射中，Logistic映射(Logistic Map)是一种简单而经典的映射。其中u称为分形参数，随着u逐渐增大，出现倍周期分岔现象。可用于密文域图像加密。(Logistic Map is a simple and classical mapping for generating chaotic pseudo-random sequences. U is called fractal parameter, and with the increase of u, period doubling bifurcation occurs. It can be used for image encryption in ciphertext domain.)

本文用用Harris算子提取特征点，基于特征点的匹配，加权融合图像拼接(In this paper, feature extraction using Harris operator point, based on feature matching, weighted fusion image mosaic)

一个局部直方图均衡化算法，输入为图像和窗口的长宽，并且长宽只能为奇数(A local histogram equalization algorithm, input images and the length and width of the window, and the length and width of only odd-numbered)

CNN中的手写识别LeNet5实现，用python，进行了中文注释(CNN handwritten recognition LeNet5 implementation, using python, carried out in Chinese Notes)

背景差分法运动目标检测，建立背景模型，然后使用当前模型与背景模型相减，再和阈值相比较，比阈值大的即判断为有运动目标，比阈值小的即判断为没有运动目标，阈值大小可以自己适当调试，根据经验值设置最佳阈值。(Background difference method is used for moving target detection and setting up background model, then using current model and background model subtracting, and comparing with threshold, it is judged to have moving target compared with the threshold value, which is smaller than threshold. The size of threshold can be adjusted properly, and the best threshold is set according to experience value.)