Abstract
Algorithms have been developed for computing the fractal dimensions of textural images by overlaying them with standards and by overlaying them with two-dimensional surfaces, which showed the best results. The main fractal characteristics (the fractal dimension and lacunarity) of landscape images, which are natural fractal formations, have been calculated. These were supplemented with statistical indices such as the mean brightness, variance, third moment, homogeneity, entropy, and certain other characteristics. A software complex has been developed for estimating the fractal dimension of textures when recognizing landscape images. Two databases of natural textures were used for the studies: Textures Library--Forest (400 images) and Brodatz (110 images).
© 2010 Optical Society of America
PDF Article
More Like This
Cited By
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription