sift-mosaic

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)

混合高斯(Mixture of Gaussian, MOG) 背景建模算法和Codebook 背景建模算法被广泛应用于监控视频的运动目标检测问题, 但混合高斯的球体模型通常假设RGB 三个分量是独立的, Codebook 的圆柱体模型假设背景像素值在圆柱体内均匀分布且背景亮度值变化方向指向坐标原点, 这些假设使得模型对背景的描述能力下降. 本文提出了一种椭球体背景模型, 该模型克服了混合高斯球体模型和Codebook 圆柱体模型假设的局限性, 同时利用主成分分析(Principal components analysis, PCA) 方法来刻画椭球体背景模型, 提出了一种基于主成分分析的Codebook 背景建模算法. 实验表明, 本文算法不仅能够更准确地描述背景像素值在RGB 空间中的分布特征, 而且具有良好的鲁棒性.(The background modeling algorithm of mixture of Gaussian (MOG) and codebook is widely used in moving object detection of surveillance video. However, the ball model of MOG usually assumes that the three components of RGB are independent, while the cylinder model of codebook assumes that the value of background pixel is distributed uniformly within the cylinder and the changing direction of brightness points to the origin of the coordinate system. These assumptions reduce the descriptive capability for background modeling. Therefore, the paper proposes an ellipsoid- based background model, which overcomes the MOG and codebook0s limitations. By using principal component analysis to depict the ellipsoid background model, a novel PCA-based codebook background modeling algorithm is proposed. Experiments show that this algorithm can not only give more accurate description of the distribution of background pixels but also have a better robustness.)

在静态背景下的运动目标检测程序，在windows 7 系统下运行的MATLAB版程序代码(moving object detection)

图像处理标准测试图片库，用于数字图像处理各种仿真实验。(Standard test image gallery image processing to digital image processing all kinds of simulation experiments. )

连接边缘算法提取的孤立点，实现图像边缘连接(link the point to get edges in the image )

对图像矩阵进行zigzag扫描,从而达到对图像纹理（灰度值）置乱的效果。( scanning of the image matrix by Zigzag，To achieve the scrambling effect of the image texture (gray value).)

利用脉冲耦合神经网络（pcnn）实现图像滤波的源程序，已经过测试。(Using pulse coupled neural networks (pcnn) the realization of the source image filtering, has been tested.)

在激光三维测量中，提取每一张图片的激光条纹中心坐标得到激光中心线。(In the laser 3D measurement, the central coordinates of the laser stripe are extracted from each image to obtain the central line of the laser.)

实现凸多边形排样，使用临界多边形NFP判断两个凸多边形是否相交,使用启发式算法提高效率(It s a good implement of convex polygon stock.)

读取一24位彩色图像，计算其以下图像特征： 1）灰度直方图 2）颜色直方图（RGB3个通道） 3）方向梯度直方图（HOG，将图像分成4*4 16个块，8个梯度方向） (Read a 24-bit color images, calculate the following image features: 1) Histogram 2) color histogram (RGB3 channels) 3) histogram of oriented gradients (HOG, the image is divided into 4* 4 16 blocks, 8 gradient directions))