Convolutional Neural Networks in the Inspection of Serrasalmids (Characiformes) Fingerlings

• Published in: Animals (Basel) Vol. 14; no. 4; p. 606
• Main Authors: Fernandes, Marília Parreira, Costa, Adriano Carvalho, França, Heyde Francielle do Carmo, Souza, Alene Santos, Viadanna, Pedro Henrique de Oliveira, Lima, Lessandro do Carmo, Horn, Liege Dauny, Pierozan, Matheus Barp, Rezende, Isabel Rodrigues de, Medeiros, Rafaella Machado Dos S de, Braganholo, Bruno Moraes, Silva, Lucas Oliveira Pereira da, Nacife, Jean Marc, Pinho Costa, Kátia Aparecida de, Silva, Marco Antônio Pereira da, Oliveira, Rodrigo Fortunato de
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01-02-2024
• Subjects: Accuracy; Animal behavior; Aquaculture; Aquaculture industry; Artificial intelligence; Automation; Collaboration; Datasets; Health aspects; Inspection; International economic relations; Internet of Things; Labeling; Machine learning; Mariculture; neural network; Neural networks; Performance evaluation; Process controls; Brazil; United States > US; Internet of Things; aquaculture; neural network
• ISSN: 2076-2615; 2076-2615
• DOI: 10.3390/ani14040606

Aquaculture produces more than 122 million tons of fish globally. Among the several economically important species are the Serrasalmidae, which are valued for their nutritional and sensory characteristics. To meet the growing demand, there is a need for automation and accuracy of processes, at a lower cost. Convolutional neural networks (CNNs) are a viable alternative for automation, reducing human intervention, work time, errors, and production costs. Therefore, the objective of this work is to evaluate the efficacy of convolutional neural networks (CNNs) in counting round fish fingerlings (Serrasalmidae) at different densities using 390 color photographs in an illuminated environment. The photographs were submitted to two convolutional neural networks for object detection: one model was adapted from a pre-trained CNN and the other was an online platform based on AutoML. The metrics used for performance evaluation were precision (P), recall (R), accuracy (A), and F1-Score. In conclusion, convolutional neural networks (CNNs) are effective tools for detecting and counting fish. The pre-trained CNN demonstrated outstanding performance in identifying fish fingerlings, achieving accuracy, precision, and recall rates of 99% or higher, regardless of fish density. On the other hand, the AutoML exhibited reduced accuracy and recall rates as the number of fish increased.