FSITM

使用特征差别提取，通过特征差别相减，以去除高斯背景(Using the characteristics of different extraction, the characteristics of different background subtraction, to remove Gauss)

说明：  1.学习使用fft2,ifft2,fftshift,ifftshift函数。用fft2函数对”lena.bmp”做二维傅立叶变换，并显示其频谱，用fftshift函数将频谱坐标原点移动到图像中心。用ifft2函数做傅立叶反变换。（提示：显示频谱时，可以先对频谱取对数，这样可以压缩动态范围很大的频谱，获得更好的显示效果）(1. Learn to use fft2, ifft2, fftshift, ifftshift functions. With the FFT 2 function, the lena.bmp'The two-dimensional Fourier transform is performed and the spectrum is displayed. The origin of the spectrum coordinate is moved to the center of the image by using the FFT shift function. The inverse Fourier transform is done with ifft2 function. (Note: when displaying the spectrum, the logarithm of the spectrum can be taken first, so that the spectrum with a large dynamic range can be compressed to obtain better display effect.))

基于纹理特征的图像检索源码，用双树复小波（DT－CWT）三级分解提取图像的纹理特征(Texture-based image retrieval source code, using dual tree complex wavelet (DT-CWT) to extract texture features three levels of decomposition)

m_map使用方法详细介绍，采用matlab下载世界地图，可以获取海岸线等数据库(M_map uses the method to introduce in detail, uses the MATLAB to download the world map.)

实现BM3d denoising的源代码。 (BM3d denoising implementation source code)

鼠标写毛笔字源码例程，程序结合易语言扩展界面支持库和图像格式转换支持库，实现用鼠标写出毛笔字的效果。可以展现多种毛笔字形态，启动时有使用帮助说明。(Mouse calligraphy source routines, programs combined with easy language support library expansion interface and image format conversion support library , use the mouse to write calligraphy achieve results. )

说明：  对图像进行配准，方便快捷，分为对比差异，粗配准与精细配准三步(Image registration is convenient and fast. It can be divided into three steps: contrast difference, rough registration and fine registration.)

卷积神经网络（Convolutional Neural Network）是一个专门针对图像识别问题设计的神经网络。它模仿人类识别图像的多层过程：瞳孔摄入像素；大脑皮层某些细胞初步处理，发现形状边缘、方向；抽象判定形状（如圆形、方形）；进一步抽象判定（如判断物体是气球）。(Convolutional neural network is a neural network specially designed for image recognition. It imitates the multi-layer process of human recognition image: pupil ingestion of pixels; some cells in the cerebral cortex preliminary processing to find shape edges and directions; Abstract judgment of shape (such as circles and squares); and further Abstract judgment (such as judging objects are balloons).)

数字图像处理，分水岭算法matlab源码,可以实现图像分割。(Digital image processing, watershed algorithm matlab source code, can achieve image segmentation.)

sift算法在cv领域的重要性不言而喻，该作者的文章引用率在cv界是number1.本篇博客只是本人把sift算法知识点整理了下，以免忘记。本文比较早的一篇博文opencv源码解析之(3)：特征点检查前言1 中有使用opencv自带的sift做了个简单的实验，而这次主要是利用Rob Hess的sift源码来做实验，其实现在的opencv版本中带的sift算法也是Rob Hess的，只是稍微包装了下。 下面来做下试验,试验sift代码采用Rob Hess的代码，opencv目前版本中的sift源码也是采用Rob Hess的。代码可以在他的主页上下载：http://blogs.oregonstate.edu/hess/code/sift/ 这里我下载的是windows版本的，并采用Qt做了个简单的界面。(sift algorithm is self-evident the importance of the cv field, the author of the article referenced in the cv sector is number1 this blog I just sift algorithm knowledge compiled under, so as not to forget. This article compares the earlier blog post opencv source code analysis (3): check the preface of the feature points 1 the opencv bring their own sift to do a simple experiment, but this time Rob Hess' s sift source to experiment. In fact, with the opencv version sift algorithm is Rob Hess, only slightly packing the next. Below to do the next test, test sift code using the code of Rob Hess, sift source opencv version of Rob Hess. The code can be downloaded on his home page: http://blogs.oregonstate.edu/hess/code/sift/ here I downloaded the windows version, and using Qt to do a simple interface.)