imageretrieval_matlab

这是一个可以计算图片分形维数的软件，可用于图片分形维数计算(Fractal dimension of a picture can be calculated a small software)

完成水果的尺寸形状表面缺陷的判别，BP神经网络的训练判别表面缺陷(Fruit size, shape and surface defects are identified. BP neural network is used to identify surface defects.)

说明：  计算机视觉 dlt 相机标定 简单易懂 注释清晰(Calibration of computer vision DLT camera is simple, easy to understand and clear to note cv)

冈萨雷斯数字图像处理MATLAB版，是我们学习图像处理必备的书籍(Gonzales digital image processing MATLAB version, we study the image processing necessary books)

说明：  基于改进遗传算法的单阈值图像分割方法，该方法在基础遗传算法的基础上进行了改进(Application of Basic Genetic Algorithms in Image Segmentation)

说明：  包括如何将几百个*.txt的文件读入程序，并通过快速傅立叶变换进行数据处理画出图像。(including how to hundreds*. txt file into the process, and through the fast Fourier transform data processing paint images.)

说明：  基于IDL语言，使用珠海一号内蒙古地区样例数据、珠海一号贵阳省高光谱数据、Landsat5济南上下幅TM数据（用于拼接验证），实现文件基本操作、遥感图像预处理、高光谱数据处理、生态评价、最大似然法分类、K-Means分类等遥感图像初步处理功能。(Based on IDL language, using Zhuhai No.1 Inner Mongolia area sample data, Zhuhai No.1 Guiyang province hyperspectral data, landsat5 Jinan upper and lower TM data (for splicing verification), the preliminary processing functions of remote sensing image, such as file basic operation, remote sensing image preprocessing, hyperspectral data processing, ecological evaluation, maximum likelihood classification, K-means classification, etc.)

说明：  这个是在运行的时候为了调试而写的，主要应用的场合是循环多，跟踪不方便的时候，记录到日志，引用了一个单元Unit_HBase,Unit_LogSp，已上传(this is the time to run the debugger and writing, the main application is a revolving occasions, tracking inconvenient time to record log, quoted a unit Unit_HBase, Unit_LogSp, uploaded)

极易分词源码包,好用最新版本,双向匹配分词(vulnerable segmentation source package, the latest version easier to use, two-way matching word)

首先将非平稳的故障振动信号进行双树复小波包分解，得 到不同频带的分量；然后对每个分量求其峭度值和相关系数并进行比较；最后选取峭度值和相关系数较大的分量 进行软阈值降噪和双树复小波包重构，即可有效地消除振动信号中噪声的干扰，同时保留信号中的有效信息即实 现了故障特征信息的提取。(In view of the above situation, a new fault diagnosis method is proposed based on dual-tree complex wavelet packet transform and threshold de-noising. Firstly, the non-stationary fault signal is decomposed into several different frequency band components through dual-tree complex wavelet packet decomposition. Secondly, Kurtosis and the cross-correlation coefficient of each component are obtained and compared. Due to the kurtosis reflecting the signal variations, if the kurtosis value is bigger, the degree of the change of signal is bigger too. The correlation coefficient can reflect the proximity between the component and the original signal at the same time, the correlation coefficient is bigger, the more similar with the original signal. Finally, the components that have a bigger value are chosen to be de-noised by a soft threshold and reconstructed by dual-tree complex wavelet packet transform. The noise interference was eliminated effectively, and the effective si)