摘要
鉴于实际工作中 ,经常需要将多幅图象拼成一幅大图象的问题 ,提出了一种针对显微照片的新拼接方法 .该方法是应用模板匹配技术来实现图象的自动拼接 ,由于是通过利用图象信息来选择模板 ,从而为模板匹配的定位创造了条件 .该方法分为模板选择、模板匹配和图象拼接 3步 .实际运用结果表明 ,该方法简单易行 ,在电路照片的拼接中 ,定位较准确 ,且拼接效果好 .
In this paper a method of image merge on micrograph is given, which introduces the template matching technique into image merge. Other problems occurred in the new application is also discussed. such as relative position nice adjustment of image. Template matching is more simple and effective than other methods of image merge fot that image which has no or small transform. Filter matching is one method of template matching. Since we don't know the noise function of the filter matching model in most cases, we hardly to use it directly. We do some pre process to make it work. Our method of image merge consists of three steps:template selection, template matching, and image align. To reduce the influence of noise we select the template on the basis of image segmentation. After template matching, both images are in alignment by rotating one image with an appropriate angle obtained from a multi resolution searching. The experimental result shows that our method is effective, simple and easy to use for micrograph merging.
出处
《中国图象图形学报(A辑)》
CSCD
北大核心
2001年第3期301-306,共6页
Journal of Image and Graphics