Novel approach to fish classification: Fractalysis and machine learning-based approach.

Fractalysis has emerged as a potential analytical tool in almost all branches of science and technology. The non-integer dimension, called the fractal dimension, quantifies the complexity of the system. The current work attempts to introduce a novel approach based on fractalysis for the classification of different fishes from simple photographs. Many natural processes are complicated, necessitating the use of a spectrum of generalised dimensions/multifractals to describe the system entirely. The multifractal analysis of the fish scale images are carried out to obtain the three dimensions information, box-counting, and correlation dimension. These features are given as input parameters for supervised machine learning-based classification. The machine learning-based analysis employing the fractal features reveals its potential in the classification of fishes from the fractalysis of fish scale images. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)