We examine the use of high frequency features in high resolution images and demonstrate how they can increase texture classification accuracy when used in combination with lower frequency features. We used eight features, four low frequency and four high frequency, derived from patches of 4032x2688 images. Furthermore, we experiment with both single and multiple classifiers to illustrate the effectiveness of such a combination. Outcomes of classification tests on outdoor scene patches are presented and discussed.
|Translated title of the contribution
|Classification in High Resolution Images with Multiple Classifiers
|Title of host publication
|J. J. Villanueva
|417 - 421
|Number of pages
|Published - Sept 2002