A method to implement multi-scale symmetry transform in the wavelet coefficients domain decomposed by using anti-symmetrical biorthogonal wavelets (ASBW) is presented with application to location of feature points on human face image.Compared to the original symmetry transform

which is performed on a single resolution level

our method can yield results with higher location accuracy without increment of computational burden.In addition

if an image is compressed based on ASBW decomposition

then our method provides a way to extract image features in compressed data domain without need of completely reconstructing the image.This is one of the most important technical consideration in the content-based indexing (CBI) problem.