The state of the art of classification based on the fractal analysis with applications in biology will be presented. Fractal features describe closely the properties of natural forms. For this reason, the interest in this new mathematical field, fractal geometry, grows quickly. New techniques of fractal analysis are developed and these techniques prove their utility in real systems in various fields such as informatics, economics, engineering, medical screening and biology. This chapter discusses problems of classification based on the fractal theory with applications in biology. Here are introduced the necessary notions for the defining of the fractals and their quantitative evaluation and an algorithm for fractal dimension computation based on biofractal contours processing is also presented. Concretely, there were extracted window-images from the interested area; the contours of the window-images were processed with the "box-counting" algorithm in order to establish the fractal dimensions for the analysed sections. The algorithm based on the "box-counting" method offers two major advantages: it is easy to implement in case of using a computer and can be applied for images no matter how complex. The first application is dedicated to the analysis of the particularities of some species from Gentianaceae family, with the purpose of establishing their affiliation to the Gentiana genus, knowing the fact that, up to the present, there have been used only evaluations based on the distinctive morphological characteristics. Concretely, there were extracted window-images from the rind and the central cylinder of the root and stem and also from the mesophyll and leaf nervure/rib and those areas where analysed by using fractal techniques. We consider that the acquiring of samples from more sections of a species (the studied one) for the statistical processing of the data will lead for the first time in botany to very precise characterizations of that species. The second applications use the same procedure in order to classify mammary tumours: benign or malign. The fractal dimension of the FAR (Focused Attention Region) is computed, by using the same box-counting algorithm. Depending on the size of the fractal dimension, a classification can be made: over 30 lesions cases with known diagnostic were Source: Image Processing, Book edited by: Yung-Sheng Chen, ISBN 978-953-307-026-1, pp. 572, December 2009, INTECH, Croatia, downloaded from SCIYO.COM www.intechopen.com
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.