Texture classification: are filter banks necessary?
We question the role that large scale filter banks have traditionally played in texture classification. It is demonstrated that textures can be classified using the joint distribution of intensity values over extremely compact neighborhoods (starting from as small as 3 /spl times/ 3 pixels square),...
Autores principales: | Varma, M, Zisserman, A |
---|---|
Formato: | Conference item |
Lenguaje: | English |
Publicado: |
IEEE
2003
|
Ejemplares similares
-
Unifying statistical texture classification frameworks
por: Varma, M, et al.
Publicado: (2004) -
A statistical approach to texture classification from single images
por: Varma, M, et al.
Publicado: (2005) -
Estimating illumination direction from textured images
por: Varma, M, et al.
Publicado: (2004) -
Texture classification with minimal training images
por: Targhi, AT, et al.
Publicado: (2009) -
Deep filter banks for texture recognition, description, and segmentation
por: Cimpoi, M, et al.
Publicado: (2016)