科研之友
微信
新浪微博
Facebook
分享链接
摘要
We propose an algorithm for object recognition based on clustering of vectors in the space of coefficients of affine transformations obtained as a result of the formation of hypotheses about the correspondence of segments of contours of a reference image and an input image approximated by linear segments. The results of numerical studies using a collection of images from New York University show that the proposed algorithm has a higher efficiency than an algorithm based on invariant moments or an algorithm for the invariant-to-scale comparison of singular points.
- 出版日期2017-5-1
