<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[WillVictory的专栏]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/WillVictory</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; WillVictory]]></copyright><item><title><![CDATA[图像配准之 互信息篇（续）]]></title><link>https://blog.youkuaiyun.com/WillVictory/article/details/5543159</link><guid>https://blog.youkuaiyun.com/WillVictory/article/details/5543159</guid><author>WillVictory</author><pubDate>Thu, 29 Apr 2010 16:36:00 +0800</pubDate><description><![CDATA[可能互信息做配准属于比较传统的做法了，适合学习 互信息配准 相当于采用了一种模板匹配的方法，计算量很大，应该有优化的算法，不过数学学的不好，优化就很难办了。 简单分析了K.Artyushkova的 image_registr_MI.m文件的程序 程序中确实是用直方图来做的，用根据灰度直方图来计算概率值，进而求得熵 Hx，Hy，h_xy三项为 两幅图像的熵及其联合熵]]></description><category></category></item><item><title><![CDATA[图像配准之 互信息篇（简介）]]></title><link>https://blog.youkuaiyun.com/WillVictory/article/details/5470401</link><guid>https://blog.youkuaiyun.com/WillVictory/article/details/5470401</guid><author>WillVictory</author><pubDate>Sat, 10 Apr 2010 14:38:00 +0800</pubDate><description><![CDATA[最近琢磨了一下图像配准，上来就看理论似乎很挑战忍耐力，于是先找找开源代码还好codesoso里可以找到matlab源码，效果还不错，算是增加点信心吧原始链接如下：http://www.mathworks.com/matlabcentral/fileexchange/6978里边涉及到一个名词“Mutual Information”，中]]></description><category></category></item></channel></rss>