Saliency-Detection

基于深度图像的图像修复算法，首先得到待修复图像的深度图像，然后利用图像的深度图对破损区域进行修复。(Based on the image restoration algorithm of depth image, the depth image of the image to be repaired is obtained, and then the damaged region is repaired by using the depth map of the image.)

本代码主要给出了激光粒度仪颗粒散射光强分布以及4种粒度反演算法，以及4种算法之间的比较。四种反演算法为：TSVD、Chaine、Tikhonov和l1正则化。(The code gives the Zetasizer particle scattering intensity distribution, and four kinds of particle inversion algorithm, as well as a comparison between the four algorithms. Four kinds of inversion algorithm is: TSVD, Chaine, Tikhonov and l1 regularization.)

zhou wang提出的结构相似性图像质量评价算法，是一种全参考的质量评价模式(zhou we analyze the dynamic process of the structural similarity of image quality evaluation algorithm, is a reference to the quality of the whole evaluation model)

利用Matlab编写的基于hough变换的椭圆检测程序，已经运行过的，附图(Written in Matlab, hough transform based ellipse detection procedure has been run off, with photos)

针对齿轮滚动轴承等的早期损伤类故障, 提出将小波包分解作为包络分析的前置处理手段以提取振动信号的故障信息特征 。 在简述小波包基本原理的基础上, 通过仿真信号, 对振动信号的具体处理过程进行分析, 并对可能遇到的问题, 提出处理办法, 然后应用于诊断实例 。 (Early damage fault for rolling bearings and other gear, the proposed wavelet packet decomposition as pre-processing means envelopment analysis to extract characteristic vibration signal fault information. On the basis of the basic principles outlined wavelet packet, through simulation signal processing for specific vibration signals are analyzed, and the problems that may be ncountered, proposed approach, and then applied to the diagnosis example.)

利用粒子群算法做的关于基于指数熵对数熵TSALLIS熵的多阈值的图像分割，内附无优化算法，可以做时间比较(Using particle swarm optimization to do on the entropy-based index of the number of entropy TSALLIS entropy of multi-threshold image segmentation, containing no optimization, can do more time)

采用的是基于弦中点的hough变换椭圆检测算法，大家可以在百度上搜这篇论文，由于不是用的标准hough变换的算法，所以运行速度还不错(Used is based on the midpoint of the chord hough transform ellipse detection algorithm, we can search on Baidu paper, because the algorithm is not used in standard hough transform, so the speed is also good)

通过maketform和cp2form指令将倾斜图形通过放射变换和投影变换纠正过来(By maketform and cp2tform instructions diagonal pattern by affine transformation and projection transformation corrected)

基于FPGA开发的均值滤波程序，效率很高，非常有用(Based on FPGA development of the mean filter program)

复杂场景中的红色交通标志牌检测与识别，结合颜色与圆形的标志牌定位，然后提取特征，最后用模板匹配的方法实现识别，内附图片和程序说明，对初学者有帮助(Red detection and recognition of traffic signs in complex scenes, the combination of colors and circular signs positioning, and feature extraction, the last with template matching methods to achieve recognition, included pictures and a description of the procedures for beginners)