摘要
为了解决背景和噪声干扰、部分遮挡等复杂环境下的图像匹配问题,给出了一种有效的基于边缘匹配的工件识别算法。该算法采用了Canny算子提取的边缘信息作为匹配特征,将改进的Hausdorff距离作为图像匹配的相似性度量,在搜索过程中采用了自适应代沟替代策略的遗传算法,在不损失解的质量的情况下,使遗传算法求解效率得到明显的改善。实验结果证明,该算法不仅加快了匹配过程,提高了抗噪性能,而且能有效解决具有平移、旋转和部分遮挡等情况下的图像匹配识别问题。
To solve the problem of image matching under complex conditions including background and noise corruption, partial occlusion etc. , an effective workpiece recognition algorithm based on edge matching approach is introduced. The algorithm adopts the edge information captured by Canny operator as matching feature, and applies improved Hausdorff distance to measure the degree of similarity between two objects; and by applying a replacement strategy with adaptive generation gap, the efficiency of genetic algorithms is improved. Experimental results show that the proposed method not only speeds up matching process greatly and improves denoising performance but also correctly detects the objects in images regardless of their changes due to translation, rotation and partial occlusion.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2008年第5期986-991,共6页
Chinese Journal of Scientific Instrument
基金
陕西省机械制造装备重点实验室项目(05JS29)资助
