19,473
社区成员
发帖
与我相关
我的任务
分享图像配准算法
对同一份word文档产生的两幅图像进行图像配准，图像中还有汉字、数组、表格等，其中一幅图像为标准图像类似于原word文档，另一份图像为打印机打印后扫描生成的图像，可能还有噪声、旋转、缩放、亮度等变化也可能是非刚性变化，现对此2幅图像进行配准，有经验的高手们，有什么好的配准方法吗？
...全文
请发表友善的回复…
发表回复
nicole_cute 2012-12-24
- 打赏
- 举报
貌似有点复杂！
聪明亮 2011-12-07
- 打赏
- 举报
很好的帖子，顶一下啊
ymd378362996 2011-12-07
- 打赏
- 举报
大家一直在说sift，请问有没有人知道harris的公式推导理论。并且在知道理论的基础上如何将其用代码实现呢
聪明亮 2011-12-04
- 打赏
- 举报
顶
很好的算法
很好的算法
iflyforever 2011-10-25
- 打赏
- 举报
请问楼主的问题解决了吗？
sweetshen 2011-10-06
- 打赏
- 举报
3分到手 学习中
leileigaui 2011-09-26
- 打赏
- 举报
真好～～～ 受用了
zhangjunkaihb 2011-07-28
- 打赏
- 举报
我的QQ 396745857,我想我们可以讨论一下
gsj292866 2011-07-12
- 打赏
- 举报
很好的帖子
oscar201314 2011-06-29
- 打赏
- 举报
哎 我就是有代码 也不知道怎么实现啊 悲剧啊。。。。。
jack2011zyj 2011-06-06
- 打赏
- 举报
我在用SIFT做insar图像配准，感觉好慢，insar图像太大了
zuiqf99 2011-05-24
- 打赏
- 举报
话说还不是很懂，再仔细研究研究
zuiqf99 2011-05-24
- 打赏
- 举报
还不是很懂滴说，还是再研究研究吧
s303792451 2011-03-19
- 打赏
- 举报
谁会基于小波的配准呢
gaokinglong 2011-01-08
- 打赏
- 举报
大家有用向量的相关系数法做图像匹配的吗？
shenlongenjoyjava 2010-10-07
- 打赏
- 举报
路过，学习了，原来配准还有这么多算法，长见识了
bios8086 2010-08-31
- 打赏
- 举报
收藏此帖！
a624844254 2010-08-27
- 打赏
- 举报
这很复杂，看不懂。初学者飘过！
swimmingfish2004 2010-08-26
- 打赏
- 举报
怎么没有人提Shi-Tomasi角点特征+Lucas-kanade（光流）。
swimmingfish2004 2010-08-26
- 打赏
- 举报
非高手，差不多。
learning Opencv，P318。
Harris's original definition involved taking the determinant of H(p), subtracting the trace of H(p) (with some weighting coefficient), and then comparing this difference to a predetermined threshold. It was later found by Shi and Tomasi [Shi94] that good corners resulted as long as the smaller of the two eigenvalues was greater than a minimum threshold. Shi and Tomasi's method was not only sufficient but in many cases gave more satisfactory results than Harris's method.
learning Opencv，P318。
Harris's original definition involved taking the determinant of H(p), subtracting the trace of H(p) (with some weighting coefficient), and then comparing this difference to a predetermined threshold. It was later found by Shi and Tomasi [Shi94] that good corners resulted as long as the smaller of the two eigenvalues was greater than a minimum threshold. Shi and Tomasi's method was not only sufficient but in many cases gave more satisfactory results than Harris's method.
加载更多回复（100）
