A new algorithm for task dependent selection of wavelet packet trees for signal classification is suggested. The algorithm is based on a class separability measure rather than energy or entropy. At each level the class separabilities obtained from a parent node and its children are computed and compared. The decomposition of the node (or subband) is performed if it provides larger separability. The suggested algorithm is tested for texture classification. The method can also be used with other tree structured local basis e.g. local trigonometric basis functions. Also it can be applied to detection, classification or segmentation of different l-D and 2-D signals.<>
Separability based tree structured local basis selection for texture classification
Proceedings of 1st International Conference on Image Processing ; 3 ; 441-445 vol.3
01.01.1994
505035 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Separability Based Tree Structured Local Basis Selection for Texture Classification
British Library Conference Proceedings | 1994
|CLASSIFICATION OF TREE SPECIES ON THE BASIS OF TREE BARK TEXTURE
Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2019
|Signal denoising in tree-structured Haar basis
IEEE | 2003
|Signal De-Noising in Tree-Structured Haar Basis
British Library Conference Proceedings | 2003
|