摘要
基于机器视觉的质量检测在印刷行业的应用日益重要,而图像匹配算法是其中的关键步骤。针对此问题提出一种应用于印刷行业的快速高精度匹配算法。首先利用尺度不变特征转换(SIFT)算法精确稳定地提取关键点,然后通过基于灰度相关系数的模板匹配算法在定位图像与模板图像的关键点之间找到匹配关系,并结合随机抽样一致(RANSAC)方法剔除错误匹配,从而使得整个快速匹配算法高效、稳定、准确。与SIFT算法比较,该算法不仅在时间上快很多,能够满足实时应用的要求,并且极少出现错误匹配。
With rapid development of printing industry recently, the quality detection based on computer vision in the printing industry is becoming increasingly important. Since the image matching algorithm is one of the key steps, this paper proposed a fast high-precision matching algorithm for application of printing industry. Firstly used the Scale-Invariant Feature Transform （SIFT） algorithm to extract the key points accurately and stability, then adopted the template matching algorithm, which was based on gray correlation coefficient, to match the relationship between the key points of matching image and template image respectively, furthermore, the RANdom SAmple Consensus （RANSAC） method eliminated false matches. The experimental results show that the improved SIFT algorithm is not only faster than before and can meet the requirements of real- time applications, but also ensure minimal error matching in terms of accuracy.
出处
《计算机应用》
CSCD
北大核心
2013年第A01期186-189,共4页
journal of Computer Applications
关键词
图像匹配
模板匹配
尺度不变特征转换算法
印刷质量检测
亚像素
image matching
template matching
Scale-Invariant Feature Transform（SIFT） algorithm
printing quality detection
sub-pixel
