Fine Tuning of Quasi Linear Feature Descriptors

Prohászka, Zoltán [Prohászka, Zoltán Ferenc (Gépi látás, robotika), szerző] Irányítástechnika és Informatika Tanszék (BME / VIK)

Angol nyelvű Tudományos Konferenciaközlemény (Egyéb konferenciaközlemény)
    This paper focuses on the optimal weighting of the compo- nents of a rotation invariant feature vector. This feature descriptor is not expected to be outstanding in performance, it is published here to illustrate the mathematics of the tuning problem. Theoretical tools are used to find proper distance functions. It is assumed, that the result- ing error is properly expressed as the sum of squared pixel differences of the corresponding images. This leads to closed formulae for the ele- ments of the weighting matrix. The deductions are intended to be general enough, enabling the application to any linear feature vector. Test results are presented to show differences between uniform and weighted distance measures. Application of the results to the Self Affine Feature Transform (SAFT) is shown briefly.
    Hivatkozás stílusok: IEEEACMAPAChicagoHarvardCSLMásolásNyomtatás
    2021-03-05 05:21