摘要
目标部分遮挡或缺失是计算机视觉应用到制造业中经常遇到的问题。对现实生产中工件间遮挡的图像匹配问题进行研究,提出了小波变换和Shi-Tomasi角点检测相结合的算法。对小波分解后的低频图像进行特征点提取,舍弃图像的高频成分,有效降低噪声对图像的影响。选用常见的法兰盘作为实验对象,在多种环境下验证文中算法的可行性,最后用RANSAC算法消除误匹配。匹配结果表明,该算法不仅可以减少遮挡工件匹配的计算量,去除伪角点,加快识别速度,而且在噪声干扰、旋转、尺度变化等条件下也有较好的匹配效果。
Partial occlusion or defect has been a common problem in the field of computer vision when it comes to manufacturing industry. A workpiece image matching algorithm based on wavelet transform combined with Shi-Tomasi corner detection was proposed to deal with this problem in practice.With the help of using low-frequeney images to participate in matching and filtering high-fiequency images in wavelet decomposition,the effect of noise on image is reduced effectively.The common flange plate is chosen as the experimental object to verify the feasibility of the proposed algorithm in a variety of environments. At last, the RANSAC algorithm is used to eliminate the false matching Experimental results demonstrate that the presented algorithm can not only reduce computation cost for occluded workpiece image matching,exclude pseudo-corner points and improve speed of recognition,but also achieve better matching performance in the respects of noise interference,ratation,zoom scaling
出处
《机械设计与制造》
北大核心
2017年第11期118-121,共4页
Machinery Design & Manufacture
基金
国家自然科学基金项目(50875159)
关键词
部分遮挡
计算机视觉
图像匹配
小波变换
角点检测
低频图像
Partial Occlusion
Computer Vision
Image Matching
Wavelet Transform
Corner Detection
Low-Fre-quency Images