Recognizing and counting Dendrocephalus brasiliensis

• Published in: PloS one Vol. 16; no. 3; p. e0248574
• Main Authors: Astolfi, Angelica Christina Melo Nunes, Astolfi, Gilberto, Ferreira, Maria Gabriela Alves, Centurião, Thaynara D'avalo, Clemente, Leyzinara Zenteno, de Oliveira, Bruno Leonardo Marques Castro, Porto, João Vitor de Andrade, Roche, Kennedy Francis, Matsubara, Edson Takashi, Pistori, Hemerson, Soares, Mayara Pereira, da Silva, William Marcos
• Format: Journal Article
• Language: English
• Published: Public Library of Science 18-03-2021
• Subjects: Cysts; Fairy shrimp; Genetic aspects; Identification and classification; Machine learning; Physiological aspects; Protection and preservation; Brazil
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0248574

The Dendrocephalus brasiliensis, a native species from South America, is a freshwater crustacean well explored in conservational and productive activities. Its main characteristics are its rusticity and resistance cysts production, in which the hatching requires a period of dehydration. Independent of the species utilization nature, it is essential to manipulate its cysts, such as the counting using microscopes. Manually counting is a difficult task, prone to errors, and that also very time-consuming. In this paper, we propose an automatized approach for the detection and counting of Dendrocephalus brasiliensis cysts from images captured by a digital microscope. For this purpose, we built the DBrasiliensis dataset, a repository with 246 images containing 5141 cysts of Dendrocephalus brasiliensis. Then, we trained two state-of-the-art object detection methods, YOLOv3 (You Only Look Once) and Faster R-CNN (Region-based Convolutional Neural Networks), on DBrasiliensis dataset in order to compare them under both cyst detection and counting tasks. Experiments showed evidence that YOLOv3 is superior to Faster R-CNN, achieving an accuracy rate of 83,74%, R.sup.2 of 0.88, RMSE (Root Mean Square Error) of 3.49, and MAE (Mean Absolute Error) of 2.24 on cyst detection and counting. Moreover, we showed that is possible to infer the number of cysts of a substrate, with known weight, by performing the automated counting of some of its samples. In conclusion, the proposed approach using YOLOv3 is adequate to detect and count Dendrocephalus brasiliensis cysts. The DBrasiliensis dataset can be accessed at: