Institute of Information Theory and Automation

You are here

Publication details

Rotation invariants from Gaussian-Hermite moments of color images

Journal Article

Yang B., Suk Tomáš, Flusser Jan, Shi Z., Chen X.

serial: Signal Processing vol.143, 1 (2018), p. 282-291

project(s): GA15-16928S, GA ČR

keywords: Color images, Object recognition, Rotation invariants, Gaussian–Hermite moments, Joint invariants

preview: Download

abstract (eng):

The topic of the paper is recognition of objects and patterns in color images regardless of their position, orientation, and scale. Gaussian–Hermite moment invariants designed especially for color images are in- troduced in this paper. We extend the existing invariants for graylevel images and show that in the case of color images there exist additional independent invariants, which can be constructed as joint invari- ants from cross-channel moments and/or from new non-trivial low-order moments. The experiments on real data confirmed that the new invariants improve the recognition rate.


bocek: 2012-12-21 16:10