A Kind of Affine Weighted Moment Invariants
This work addresses image retrieval challenges by enhancing geometric invariants, though it appears incremental as it builds on existing moment invariant methods.
The paper tackled the problem of feature extraction for image retrieval by proposing affine weighted moment invariants (AWMIs), which combine local affine differential invariants with a global integral framework to improve efficiency and increase low-order invariants, achieving better results than traditional moment invariants in experiments.
A new kind of geometric invariants is proposed in this paper, which is called affine weighted moment invariant (AWMI). By combination of local affine differential invariants and a framework of global integral, they can more effectively extract features of images and help to increase the number of low-order invariants and to decrease the calculating cost. The experimental results show that AWMIs have good stability and distinguishability and achieve better results in image retrieval than traditional moment invariants. An extension to 3D is straightforward.