FRACTAL DIMENSION AND LACUNARITY COMBINATION FOR PLANT LEAF CLASSIFICATION
Abstract: Plants play
important roles for the existence of all beings in the world. High diversity of
plant’s species make a manual observation of plants classifying becomes very
difficult. Fractal dimension is widely known feature descriptor for shape or
texture. It is utilized to determine the complexity of an object in a form of
fractional dimension. On the other hand, lacunarity is a feature descriptor
that able to determine the heterogeneity of a texture image. Lacunarity was not
really exploited in many fields. Moreover, there are no significant research on
fractal dimension and lacunarity combination in the study of automatic plant’s
leaf classification. In this paper, we focused on combination of fractal
dimension and lacunarity features extraction to yield better classification
result. A box counting method is implemented to get the fractal dimension
feature of leaf boundary and vein. Meanwhile, a gliding box algorithm is
implemented to get the lacunarity feature of leaf texture. Using 626 leaves
from flavia, experiment was conducted by analyzing the performance of both
feature vectors, while considering the optimal box size r. Using support vector
machine classifier, result shows that combined features able to reach 93.92 %
of classification accuracy.
Author: Mutmainnah Muchtar,
Nanik Suciati, Chastine Fatichah
Journal Code: jptkomputergg160014
