Title :
A Kind of Shape-Color Moment Invariants
Author :
Gong, Ming ; Hu, Ping ; Cao, Weiguo ; Li, Hua
Author_Institution :
Nat. Res. Center for Intell. Comput. Syst., Beijing, China
Abstract :
Shape or color based moment invariants are conventional pattern sensitive features in the object recognition and image description. However, the existing moment invariants are not robust because they handle simplified cases, such as single impact of shape transformation, single color transformation, and a simple combination of them. In this paper, we propose a kind of shape-color moment invariants (SCMIs), taking complicated shape and color transformation into account. It is applicable to more complicated cases, such as changing viewpoints, different illuminations, different camera white balance modes, and different color spaces. The integral-based SCMI construction framework is extensible and general. We evaluate the technique through comprehensive experiments.
Keywords :
feature extraction; image colour analysis; integral equations; object recognition; color transformation; image description; integral-based SCMI construction framework; object recognition; pattern sensitive features; shape transformation; shape-color moment invariants; Additives; Cameras; Color; Image color analysis; Lighting; Mathematical model; Shape; Color transformations; Moment invariants; Recognition; Shape deformations; Shape-Color primitives;
Conference_Titel :
Computer-Aided Design and Computer Graphics (CAD/Graphics), 2011 12th International Conference on
Conference_Location :
Jinan
Print_ISBN :
978-1-4577-1079-7
DOI :
10.1109/CAD/Graphics.2011.49
