Affine invariants for object recognition using the wavelet transform

摘要

Dyadic wavelet transform has been to derive affine invariant functions. The invariant functions are based on the dyadic wavelet transform of the object boundary. Three invariant functions have been calculated using different numbers of dyadic levels. Experimental results show that these invariant functions outperform some traditional in- variant functions. The stability of these invariant functions have been tested for a large perspective transforma- tion.