An image processing method for recognition of four aquatic macroinvertebrates genera in freshwater environments in the A
- PDF / 2,063,036 Bytes
- 11 Pages / 547.087 x 737.008 pts Page_size
- 39 Downloads / 183 Views
An image processing method for recognition of four aquatic macroinvertebrates genera in freshwater environments in the Andean region of Colombia Juan Pablo Serna López & David Stephen Fernández Mc Cann & Fabio de Jesús Vélez Macías & Néstor Jaime Aguirre Ramírez
Received: 27 May 2020 / Accepted: 9 August 2020 # Springer Nature Switzerland AG 2020
Abstract The aquatic macroinvertebrate community reflects the ecological status of a river. Typically, some extraction methods have been implemented, but the capture and preservation of organisms are necessary. The techniques of digital image processing applied to ecology have become innovative tools for the characterization of aquatic macroinvertebrates. This research implements a methodology for the processing and classification of four aquatic macroinvertebrates genera Thraulodes, Traverella (Ephemeroptera), Anacroneuria (Plecoptera), and Smicridea (Trichoptera) present in three rivers in Antioquia (Colombia), which includes two phases. The first of these was the collection and capture of organisms to obtain a database of the most abundant genera, at laboratory scale. The second was the use of simulations that allow the classification of data through a process of selection and extraction of (*) : F. Vélez Macías :
J. P. Serna López N. J. Aguirre Ramírez GeoLimna Research group, Faculty of Engineering, University of Antioquia, Medellín, Colombia e-mail: [email protected]
F. Vélez Macías e-mail: [email protected] N. J. Aguirre Ramírez e-mail: [email protected] D. S. Fernández Mc Cann Gepar Research group, Faculty of Engineering, University of Antioquia, Medellín, Colombia e-mail: [email protected]
characteristics using the bag of visual words technique. Of all the classifiers tested, Gaussian vector support machines obtained a percentage of success in the recognition up method of four organisms to the genus level of 97.1 %. The training and computational processing for classification enabled the standardization of an appropriate methodology that will serve as a starting point for aquatic biomonitoring and inventory in Colombia and internationally. Keywords Machine learning . Vector support machines . Digital image processing . Aquatic macroinvertebrates . Water quality monitoring
Introduction The monitoring of water quality in watercourse environments seeks to identify the anthropic impacts on aquatic systems and how these impacts are reflected in changes and modifications in the abundance of organisms (Burden et al. 2002). One of the most sensitive groups of organisms to these types of modifications are aquatic macroinvertebrates, which undergo significant changes in terms of the abundance and richness of their populations. Therefore, these are widely studied and are considered excellent bioindicators when determining the quality of an aquatic ecosystem. Aquatic macroinvertebrates are important as revealers of environmental conditions. This is because these organisms are sedentary and have longer life cycles than other inferior aquat
Data Loading...
