【摘要】 提出了基于目标区域几何形状分布统计特征的拼接方法,有效地解决了特征稀少图像的拼接问题.论述了区域几何形状分布特征增强的差分动态二值化方法,阐述了特征稀少图像的拼接原理和计算步骤.实践应用表明,该拼接方法可成功用于特征稀少的混泥土表面图像的拼接,其精度与速度都是令人满意的,正确拼接的成功率可达98%,拼接精度可达0~2个像素.更多还原

【Abstract】 An images merging algorithm base on statistic principle of region geometric shape was proposed.The algorithm solves images merging problems efficiently when there are little point′s features on those images.For enhancing the region geometric shape features we described a Difference Dynamic Binary Method.And then the merging principle of images on which there is little point′s feature was discussed.Last the process and steps of merging image are been described in all details.It is shown that the algorithm is satisfying in its precision and speed for merging images of concrete surface on which there is little point′s feature,the percentage of correct merging can arrive at 98%,the precision of the images merging algorithm can be 0～2 pixels.更多还原