刊名:Optik - International Journal for Light and Electron Optics
出版年:2017
出版时间:February 2017
年:2017
卷:130
期:Complete
页码:1426-1437
全文大小:1142 K
卷排序:130
文摘
A new computer vision algorithm is proposed specifically for the analysis of mechanical workpieces’ image. KDD is selected to realize the adaptive selection and reduction of shape features which improves its speed and accuracy. The generated semantic knowledge assists to distinguish between discoidal-shaped parts and rod-shaped parts automatically. The selected parts can be classified accurately at 100% efficiency. The algorithm proposed in this paper is much more effective than template matching algorithm.