Technology developed by researchers at Australia's La Trobe University (LTU) that measures the presence of alcohol in digital images could help recovering alcoholics evaluate their exposure to alcohol marketing on social media.
The researchers upgraded their Alcoholic Beverage Identification Deep Learning Algorithm (ABIDLA) and trained it on 191,286 images downloaded from Google and Bing image search results.
The upgrade, ABIDLA2, automatically identified images featuring one of eight beverage categories with 77% accuracy, then classified images containing an "alcoholic beverage" or "other" with 87.7% accuracy.
LTU's Abraham Albert Bonela said, "There is the possibility to integrate ABIDLA2 into a web browser [as a plugin] or a mobile application to quantify or limit exposure to alcohol exposure depending on individuals' preferences."
From La Trobe University (Australia)
View Full Article
Abstracts Copyright © 2023 SmithBucklin, Washington, DC, USA