computer_vision_calibr

毕业设计，基于内容的图像检索，支持的检索特征包括 sift,颜色直方图，灰度矩阵，HU不变矩，边缘方向直方图，检索方法使用K-means和K-D树两种，需要OPENCV支持，运行时请先选定一个文件夹来生成特征库，特征库用access数据库保存，只支持JPG文件(Graduate design, content-based image retrieval, search features, including support sift, color histogram, gray matrix, HU moment invariants, edge direction histogram, retrieval method using the K-means and KD trees are two kinds of needs OPENCV support Please select a runtime folder to generate the feature library, feature library with access database save, only supports JPG files)

这是一个常用的基于Fcm的图像分割源程序，希望对大家有用(This is a commonly used image segmentation based on FCm source, in the hope that useful to everybody)

说明：  1. 对图像进行傅里叶变换。 2. 根据傅里叶变换的结果去除图像的竖条纹噪声。 3. 对图像进行傅里叶逆变换，得到分割图像。 (1. For the image Fourier transform. 2. According to the results of Fourier transform to remove the image of the vertical stripe noise. 3. Inverse Fourier Transform of the images obtained segmented image.)

这是新提出来的用于图像去噪的非局部均值滤波方法, matlab程序.非常好,你试试.(this is a new proposed image denoising method--non local means filtering, matlab file. you can try!)

用来计算水印算法中的psnr值，非常好用一直在用这个(Watermarking algorithm used to calculate the value of psnr, very easy to use )

说明：  基于区域生长,(区域增长)的目标分割方法,简单实用,易上手,m语言编写,易懂易用,没有调用内部函数,方便以后改写为c语言代码,请尽情享用(Based on regional growth, (regional growth) of the object segmentation method is simple and practical易上手, m language easy to understand and use, there is no call to internal function, convenient to rewrite the future for the c language code, please enjoy)

说明：  结合Retinex和CLAHE图像去雾，Retinex有ssr，msr，msrcr。(Combine Retinex and clean image to remove fog)

说明：  本部分源码是处理静态图像时候，需要的一部分代码，希望对于那些正在研究图像处理技术的朋友有用。(This section is the source when dealing with a static image, the need for part of the code, I hope for those who are studying image processing technology useful friends.)

首先利用形态学开运算将图像中小于结构元素的亮点去掉，利用源图像与处理后的图像作差，对差图像进行阈值分割，得到二值图像，将二值图像中的一些干扰区域去掉，提取二值图像中的圆形区域，并在源图像上对小目标进行标记，实现对圆形亮目标的检测(Remove the area in the image smaller than structural element by morphologic open operation，receive image A，original image subtract image A，threshold segmentation for difference image，receive binary image，remove the interference region in the binary image，then extract circular area，and sign the target in the original image. Realize the circular bright target detection)

C#连接摄像头，可以干好多事情了，自己扩展，这个只是个demo