Image features are obtained by using some kind of interest point detector, which often is based on a symmetricmatrix such as the structure tensor or the Hessian matrix. These features need to be invariant to rotation and tosome degree also to scaling in order to be useful for feature matching in applications such as image registration.Recently, the spinor tensor has been proposed for edge detection. It was investigated herein how it also can beused for feature matching and it will be proven that some simplifications, leading to variations of the responsefunction based on the tensor, will improve its characteristics. The result is a set of different approaches thatwill be compared to the well known methods using the Hessian and the structure tensor. Most importantly theinvariance when it comes to rotation and scaling will be compared.
Invariant Interest Point Detection Based on Variations of the Spinor Tensor
Anders Hast;Andrea Marchetti
2014
Abstract
Image features are obtained by using some kind of interest point detector, which often is based on a symmetricmatrix such as the structure tensor or the Hessian matrix. These features need to be invariant to rotation and tosome degree also to scaling in order to be useful for feature matching in applications such as image registration.Recently, the spinor tensor has been proposed for edge detection. It was investigated herein how it also can beused for feature matching and it will be proven that some simplifications, leading to variations of the responsefunction based on the tensor, will improve its characteristics. The result is a set of different approaches thatwill be compared to the well known methods using the Hessian and the structure tensor. Most importantly theinvariance when it comes to rotation and scaling will be compared.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.