Foveated Object Recognition Using Corners
Thomas L. Arnow, Alan Conrad Bovik · 2008
We present a gray scale object recognition system that is based on foveated corner finding and that uses elements of Lowe's SIFT algorithm. The principles behind the algorithm are the use of high-information gray-scale corners as features, and an efficient corner- finding strategy to find them. The system is tested on a set of tool and airplane images and shown to perform well.