pipeijiao

利用K-高斯混合模型提取视频的前景信息。(The use of K-Gaussian mixture model for the future of video information extraction)

飞机的设计和制造一直是与性能优异的材料 联系在一起。20世纪60年代中期以碳纤维为增强体 的复合材料问世，70年代初开始应用于军用飞机 结构，80年代开始应用于民用飞机结构。复合材料 具有比强度高和比刚度高的独特优点，飞机结构 采用复合材料，其重量可相应减少20%~30%[1]。此 外，复合材料还具有可设计性强、疲劳性能好、耐 腐蚀、易于大面积整体成型、维护性好等优点。目 前，复合材料已经成为重要的飞机结构材料。(he design and manufacture of aircraft has been a material with excellent performance Relate. In the mid 1960s, carbon fibers were used as reinforcements The composite material came out and was used in military aircraft in the early 70s The structure began to be applied to civil aircraft structures in 80s. Compound material The aircraft structure has the unique advantages of high specific strength and high specific stiffness The weight of the composites can be reduced by 20%~30%[1] accordingly. this Besides, the composite material has the advantages of good design, good fatigue performance and good resistance to fatigue Corrosion, easy to form a large area, good maintainability and so on. order Before, composite materials have become important aircraft structural materials.)

进行图像区域合并操作,能够较为有效，较好的进行图像合并(combine the image，very effcient)

使用MFC以及Gabor小波处理进行图像的特征纹理提取(Using MFC and Gabor wavelet to extract texture features for image)

说明：  基于图像变换的火炮身管膛线参数检测技术研究(Based on image transform the Gun Barrel rifling parameter detection technology)

本软件包包括四个程序，主要用于图像处理（图像去噪，图像分割）和模拟退火算法。(This package includes four procedures, mainly used for image processing (image denoising, image segmentation) and simulated annealing algorithm.)

本程序实现医学图像的增强，实验显示，处理后的医学图像轮廓清晰，可识性较好。(This procedure to achieve medical image enhancement, experiments showed that the treated medical image outline a clear, identifiable better.)

产生螺旋波面的m文件，拓扑核数是3,相位改变量和高度可以自己调节。内附平面波和球面波的示意图以及产生的图片(generating helical wavefront whose topological number is three)

三个很好的程序，有染色体的识别，车牌跟踪，还有神经网络设计，肯定是非常好的，希望大家从中学习(Three very good procedures, there are chromosome recognition, license plate tracking, as well as neural network design, is certainly very good, I hope you learn from)

compute the root-mean-square error