examplw5_10

此程序为计算雷达目标特性角闪烁特性的函数代码(computing the anglar glint)

自动图像拼接，利用SIFT特征匹配算法，RANSAC(random sample consensus)算法，加权平滑算法等技术克服了传统图像拼接技术中的局限性(如光照、尺度变化的影响等)，实现了光照和尺度变化条件下的多视角无缝图像拼接(Automatic Image Stitching  Local features detection  Features Matching  Homography Estimation RANSAC Image blending )

求质心到图像轮廓边缘的距离，并将其用figure表示出来(The distance from the center of mass to the edge of the image contour)

基于Harris角点检测的图像拼接matlab实现， 主要内容包括Harris角点检测，NCC,RANSAC以及2幅图像的拼接(A image mosaicing algorithem which based on Harris corner feature detection achieved in matlab. The main contents include the Harris corner detector, the NCC, the RANSAC and two image mosaicing)

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.)

初步的代码，只保存边界的声波逆时偏移 RTM

实现图像识别，基于小波变换实现图像特征提取，然后神经网络进行训练(The image recognition is realized, the image feature extraction is realized based on wavelet transform, and then the neural network is trained.)

图像识别，包括人脸识别和虹膜识别，在数字图像中虹膜位置的有效定位是虹膜识别的关键问题。用一种基于主动轮廓线模型的方法定位虹膜的位置，先用灰度投影法检测出瞳孔内的一点作为瞳孔的伪圆心，该圆心只要能落在瞳孔内部即可。(Image recognition, including face recognition and iris recognition, iris position in the digital image of the iris recognition and effective positioning is the key issue. Using a model based on active contour method of positioning the iris position, the first gray projection method used to detect a point within the pupil as a pupil of the pseudo-center of a circle, the center of a circle can be as long as it falls within the pupil.)

说明：  此算法可以实现任意两个图像的配准（整体平移） (This algorithm can achieve any two image registration (the overall translation))

图像从背景图中提取 可以用来提取边缘，将背景图与图像分离(Images extracted from the background image can be used to extract the edge of the background map and image separation)