ImgCropper

说明：  运用低通滤波器，中心削波和自相关技术估计一段男性和女性语音信号的基音周期，画出基音轨迹曲线，给出估计准确率。(The use of low-pass filter, the center clipping and related technologies is estimated from a male and female speech signal pitch period, pitch trajectory drawn curves of estimated accuracy.)

说明：  图像融合，实现两幅图像合成一张宽视野的广角图(Image fusion, the two images are combined into a wide field of view)

Algorithm is used to seperate the blind signal using matlab based on image processing

说明：  BCS代码稀疏重构Lena.bmp图像，包中含有代码和图片本身，题主给了一定注释，便于CS初学者学习(BCS code sparsely reconstructs Lena. BMP image. The package contains code and image itself. The theme is given a certain comment, which is convenient for CS beginners to learn.)

广度优先搜索和深度优先搜索在网络拓扑图上的实现。广度优先搜索是从某一节点开始，搜索与其线连接的所有节点，按照广度方向像外扩展，直到不重复遍历所有节点；深度优先搜索是从某一节点开始，沿着其搜索到的第一个节点不断深入下去，当无法再深入的时候，回溯节点，然后再在回溯中的某一节点开始沿另一个方向深度搜索，直到不重复的遍历所有节点。 (Breadth-first search and depth-first search in the network topology is realized. Breadth-first search is started from a node, searching all the nodes connected to its line, in accordance with the breadth direction as extracapsular extension, until no repeat traverse all nodes depth-first search is started from a node along its search to the first nodes deepening it, when it can not go any further, backtracking node, and then back again in the beginning of a node depth search in the other direction until the non-repetition of the traverse all nodes.)

说明：  区域生长算法。不用手动选择种子点，可自动选择。(Image segmentation by growing region method. No manual selection of seed points, automatic selection)

说明：  python实现双目立体匹配SGBM算法(SGBM algorithm for binocular stereo matching based on Python)

本案例采用基于块匹配的图像拼接流程来执行拼接操作，载入图片文件夹来作为待拼接对象，通过进行图片序列的匹配、融合来得到拼接效果，并分别对灰度图像、彩色图像进行处理。(This case is based on block matching process to perform image stitching splicing operation, load images folder as an object to be spliced, by matching the fusion image sequence to get the mosaic effect, respectively, on the gray image, color image processing .)

时移相位差校正法，通过时移，进行前后两次FFT分析，利用离散频谱对应峰值谱线的相位差以求出频率和相位校正量。(Phase difference correcting method by time-shifting. Make two FFT analysis before and after the time-shifting,and make use of the phase difference of the peak spectral lines to get frequency and phase correction amount.)

说明：  DOG高斯差分实现物体识别中的特征提取,对不同尺度空间的图像进行差分，从而获得描述物体的特征值(difference of gaussian to achieve the feature point exaction of object recognition)