Texture Classification Using Averages of Local Pattern Matches
Abstract
Laws has introduced a class of texture features based on average degrees of match of the pixel neighborhoods with a set of standard masks. These features yield better texture classification than standard features based on pairs of pixels. This paper investigates simpifications of these features, and shows that their performance is not greatly affected by their exact form, and also appears to remain the same if only local match maxima are used. It also presents an alternative definition of such features based on sums and differences of Gaussian convolutions.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 1981
- Accession Number
- ADA124807
Entities
People
- Azriel Rosenfeld
- Larry S. Davis
- Matti Pietikaeinen
Organizations
- University of Maryland