mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments
Sensors · 2023
DOI: 10.3390/s24010209 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Thierry Roland Baban A Erep und 1 weiteren Autor:innen. Beteiligte Einrichtung: Toulouse INP, University of Toulouse, Institut de Recherche en Informatique de Toulouse, 31400 Toulouse, France. Hauptthemen laut MEDLINE: Nutrition Assessment, Semantics. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Recent decades have witnessed the development of vision-based dietary assessment (VBDA) systems. These systems generally consist of three main stages: food image analysis, portion estimation, and nutrient derivation. The effectiveness of the initial step is highly dependent on the use of accurate segmentation and image recognition models and the availability of high-quality training datasets. Food image segmentation still faces various challenges, and most existing research focuses mainly on Asian and Western food images. For this reason, this study is based on food images from sub-Saharan Africa, which pose their own problems, such as inter-class similarity and dishes with mixed-class food. This work focuses on the first stage of VBDAs, where we introduce two notable contributions. Firstly, we propose mid-DeepLabv3+, an enhanced food image segmentation model based on DeepLabv3+ with a ResNet50 backbone. Our approach involves adding a middle layer in the decoder path and SimAM after each extracted backbone feature layer. Secondly, we present CamerFood10, the first food image dataset specifically designed for sub-Saharan African food segmentation. It includes 10 classes of the most consumed food items in Cameroon. On our dataset, mid-DeepLabv3+ outperforms benchmark convolutional neural network models for semantic image segmentation, with an mIoU (mean Intersection over Union) of 65.20%, representing a +10.74% improvement over DeepLabv3+ with the same backbone.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Toulouse INP, University of Toulouse, Institut de Recherche en Informatique de Toulouse, 31400 Toulouse, France.
ORCID-Profile: Thierry Roland Baban A Erep, Lotfi Chaari
Zitieren
APA
Baban A Erep, T. R., & Chaari, L. (2023). mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments. Sensors. https://doi.org/10.3390/s24010209
Vancouver
Baban A Erep TR, Chaari L. mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments. Sensors. 2023. doi:10.3390/s24010209
BibTeX
@article{BabanAErep2023,
author = {Baban A Erep, Thierry Roland and Chaari, Lotfi},
title = {mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments},
journal = {Sensors},
year = {2023},
doi = {10.3390/s24010209}
}
EUVIMED