huxiangguangtuixangpipei

凸多边形检测和显示--先把图像中的显著区域提取出来，然后用最小凸多边形囊括显著区域，并把凸多边形显示出来(Convex polygon detection and show- first images extracted significant area, and then use the smallest convex polygon covering a significant area, and the convex polygon displayed)

基于图像签名的显著性区域检测，算法很巧妙，好用(computation of a saliency map based on the Image Signature, as described in the following paper: "Image Signature: Highlighting sparse salient regions", Xiaodi Hou, Jonathan Harel, and Christof Koch, IEEE Trans. Pattern Anal. Mach. Intell. 34(1): 194-201 (2012))

船舶数据处理程序，可以实现船舶任意运动姿态的数据，描绘运动轨迹，从而分析船舶运动姿态(ship data extraction)

harris角点检测，并且实现两幅图像特征点的匹配，最终完成图像的拼接(harris corner detection, and realize two image feature point matching, the final completion of image stitching)

GUI的指纹特征提取,其中用到的处理函数可以自己编写，也可以直接使用Matlab的库函数(Fingerprint character extract in GUI form, within which the functions can be either designed by users or apply the available functions in Matlab)

图像处理技术边缘检测源码Source image processing edge detection(Image processing edge detection source Source image processing edge detection)

从回波中估计多普勒参数是合成孔径雷达运动补偿的关键。文中研究了多目标回波对参数估计的影响，从理论上推导了估计多普勒中心和调频率对回波的不同要求，并用两个指标举例分析了一段实测机载SAR数据，给出了实际应用中参数估计时选择回波的原则。(Doppler parameters estimation from radar echoes is a key step in SAR(Synthetic Aperture Radar}motion cornpensation． This paper researched the efect of multiple targets echoes to estimate parameters and deducted theoretically the different requirement for echoes in estimating doppler centroid and doppler frequency modulation rate．Th en giving a real airborne SAR echo as example，we analyzed it with two measurements and concluded the principle about choosing echoes in practice．)

该程序是一种最小均方误差滤波算法的matlab实现，主要应用于干扰对消方面(The program is a minimum mean square error filtering algorithm matlab realize, mainly used in interference cancellation)

说明：  LCD彩色图片转换工具BMP_to_H,可以进行24位色的BMP图片转换(LCD color image conversion tools BMP_to_H)

包括最后计算压缩图像的峰值信噪比和压缩效果的源码,包含特征值与特征向量的提取、训练样本以及最后的识别，毕设内容，高光谱图像基本处理。( Including the final calculation of the compressed image peak signal to noise ratio and compression of the source, Contains the eigenvalue and eigenvector extraction, the training sample, and the final recognition, Complete set content, basic hyperspectral image processing.)