A new stitching algorithm based on area feature and cross correlation for the sequence image with transformation of translation, rotation and isometric scaling is proposed.
针对具有平移、旋转、缩放变换的序列图像连续拼接，提出一种将基于区域特征的配准算法和基于灰度交叉相关的配准算法相结合的拼接算法。
The result which has the maximum reliability was obtained through the matching between the regions which contain the feature points based on cross correlation theory.
通过局部特征点所在区域的相关匹配，获得具有最大可信度的匹配结果。
Then, normalized cross-correlation matching and probability support matching method are used to match the images feature points.
然后利用归一化互相关匹配法和概率支撑法对特征点进行匹配。
Then, normalized cross-correlation matching and probability support matching method are used to match the images feature points.
然后利用归一化互相关匹配法和概率支撑法对特征点进行匹配。
应用推荐