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),...
Główni autorzy: | Varma, M, Zisserman, A |
---|---|
Format: | Conference item |
Język: | English |
Wydane: |
IEEE
2003
|
Podobne zapisy
-
Unifying statistical texture classification frameworks
od: Varma, M, i wsp.
Wydane: (2004) -
A statistical approach to texture classification from single images
od: Varma, M, i wsp.
Wydane: (2005) -
Estimating illumination direction from textured images
od: Varma, M, i wsp.
Wydane: (2004) -
Texture classification with minimal training images
od: Targhi, AT, i wsp.
Wydane: (2009) -
Deep filter banks for texture recognition, description, and segmentation
od: Cimpoi, M, i wsp.
Wydane: (2016)