Moment-based image normalization with high noise-tolerance

Martin Grůber, Ken-Yuh Hsu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 1997 · 46 citations · 6 references

Concepts

Abstract

In this paper the effects of noise with nonzero mean on existing moment-based image normalization methods are studied. Several modifications to reduce noise sensitivity are presented and tested. They involve nonlinear mapping and fractional- and negative-order moments.

References

6