Usefulness of synthetic datasets for diatom automatic detection using a deep-learning approach - Université de Lorraine Accéder directement au contenu
Article Dans Une Revue Engineering Applications of Artificial Intelligence Année : 2023

Usefulness of synthetic datasets for diatom automatic detection using a deep-learning approach

Résumé

Benthic diatoms are unicellular microalgae that are routinely used as bioindicators for monitoring the ecological status of freshwater. Their identification using light microscopy is a time-consuming and laborintensive task that could be automated using deep-learning. However, training such networks relies on the availability of labeled datasets, which are difficult to obtain for these organisms. Herein, we propose a method to generate synthetic microscopy images for training. We gathered individual objects, i.e. 9230 diatoms from publicly available taxonomic guides and 600 items of debris from available real images. We collated a comprehensive dataset of synthetic microscopy images including both diatoms and debris using seamless blending and a combination of parameters such as image scaling, rotation, overlap and diatom-debris ratio. We then performed sensitivity analysis of the impact of the synthetic data parameters for training state-of-the art networks for horizontal and rotated bounding box detection (YOLOv5). We first trained the networks using the synthetic dataset and fine-tuned it to several real image datasets. Using this approach, the performance of the detection network was improved by up to 25% for precision and 23% for recall at an Intersectionover-Union(IoU) threshold of 0.5. This method will be extended in the future for training segmentation and classification networks.
Fichier principal
Vignette du fichier
venkataramanan_2023_eaai_accepted_version.pdf (4.44 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03852321 , version 1 (27-11-2022)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

Citer

Aishwarya Venkataramanan, Pierre Faure-Giovagnoli, Cyril Regan, David Heudre, Cécile Figus, et al.. Usefulness of synthetic datasets for diatom automatic detection using a deep-learning approach. Engineering Applications of Artificial Intelligence, 2023, 117, pp.105594. ⟨10.1016/j.engappai.2022.105594⟩. ⟨hal-03852321⟩
169 Consultations
47 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More