On Rotation Invariant Texture Classification Using Two-Grid Coupled CNNs
Paul Ungureanu, Emilian David, Liviu Goraş · 2006
This paper presents several results of rotation-invariant texture classification using a bank of 2D band-pass CNN filters with approximately circular frequency response. The filters are autonomous two grid coupled CNNs, capable of producing Turing patterns used in the central linear part of their characteristic. The classification performances of the CNN filters are compared with the performances of the ideal circular filters