Comparing Shape and Texture Features for Pattern Recognition in Simulation Data.

Newsam, S. ; Kamath, C.

Technical Information Center Oak Ridge Tennessee

关键词: Pattern recognition;    Shapes;    Textures;    Simulation;    Meetings;   

RP-ID  :  DE200515011533

学科分类：工程和技术（综合）

美国|英语

来源: National Technical Reports Library

【 摘 要 】

In this paper, we investigate shape and texture features for pattern recognition in simulation data. In particular, we explore which features are suitable for characterizing regions of interest in images resulting from fluid mixing simulations. Three texture featurs-gray level co-occurrence matrices, wavelets, and Gabor filters-and two shape features-geometric moments and the angular radial transform-are compared. The features are evaluated using a similarity retrieval framework.