Abstract. Quadrature filters are a well known method of low-level computer vision for estimating certain properties of the signal, as there are local amplitude and local phase. How...
In many vision problems, rotation-invariant analysis is necessary or preferred. Popular solutions are mainly based on pose normalization or brute-force learning, neglecting the in...
Kun Liu, Qing Wang, Wolfgang Driever, Olaf Ronnebe...
Abstract. We introduce a new type of local feature basedon the phaseand amplitude responsesof complex-valuedsteerable filters. The designof this local feature is motivated by a des...
In this paper, a new method of feature extraction with rotation invariant property is presented. One of the main contributions of this study is that a rotation invariant signature...
We present a framework for object detection that is invariant to object translation, scale, rotation, and to some degree, occlusion, achieving high detection rates, at 14 fps in c...
Michael Villamizar, Alberto Sanfeliu, Juan Andrade...