Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/70211
Title: SMACC: a system for microplastics automatic counting and classification
Authors: Lorenzo Navarro, José Javier 
Castrillón Santana, Modesto Fernando 
Santesarti, Enrico
De Marsico, Maria
Martínez Sánchez, Ico 
Raymond, Eugenio
Gómez Cabrera, María Milagrosa 
Herrera Ulibarri, Alicia 
UNESCO Clasification: 120304 Inteligencia artificial
330811 Control de la contaminación del agua
Keywords: Computer vision
Deep learning
Microplastics classification
Issue Date: 2020
Project: Evaluación del impacto de microplásticos y contaminantes emergentes en las costas de la Macaronesia 
Estudio de la incorporación de microplásticos marinos a las redes tróficas en Canarias 
Journal: IEEE Access 
Abstract: The management of plastic debris is a serious issue due to its durability. Unfortunately, million tons of plastic end up in the sea becoming one of the biggest current environmental problems. One way to monitor the amount of plastic in beaches is to collect samples and visually count and sort the plastic particles present in them. This is a very time-consuming task. In this work, we present a Computer Vision-based system which is able to automatically count and classify microplastic particles (1-5 mm) into ve different visual classes. After cleaning a collected sample in the lab, the proposed system makes use of a pair of its images with different characteristics. The procedure includes a segmentation step, which is based on the Sauvola thresholding method, followed by a feature extraction and classi cation step. Different features and classi ers are evaluated as well as a deep learning approach. The system is tested on 12 different beach samples with a total of 2507 microplastic particles. The particles of each sample were manually counted and sorted by an expert. This data represents the ground truth, which is compared later with the results of the automatic processing proposals to evaluate their accuracy. The difference in the number of particles is 34 (1.4%) and the error in their classi cation is less than 4% for all types except for the line shapes particles. These results are obtained in less than half of the time needed by the human expert doing the same task manually. This implies that it is possible to process more than twice as many samples using the same time, allowing the biologists to monitor wider areas and more frequently than doing the process manually.
URI: http://hdl.handle.net/10553/70211
ISSN: 2169-3536
DOI: 10.1109/ACCESS.2020.2970498
Source: IEEE Access [ISSN 2169-3536], v. 8, p. 25249 - 25261
Appears in Collections:Artículos
Thumbnail
pdf
Adobe PDF (1,79 MB)
Show full item record

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.