Document Type


Publication Date


Publication Title

LUROP Poster Session

Publisher Name

Loyola University Chicago

Publisher Location

Chicago, IL


The US is a culturally and ethnically diverse country, and with this diversity comes a myriad of cuisines and eating habits that expand well beyond that of western culture. Each of these meals have their own good and bad effects when it comes to the nutritional value and its potential impact on human health. Thus, there is a greater need for people to be able to access the nutritional profile of their diverse daily meals and better manage their health. A revolutionary solution to democratize food image classification and nutritional logging is using deep learning to extract that information from analyzing images a user inputs. However, current computer vision (a subspeciality of deep learning) applications that are used to classify foods are limited by the western-biased datasets they are trained on [2]. Additionally, a diverse image dataset for training computational models for classification is not plausible as there are just too many cuisines for any model to. Clearly there is a need for a pipeline that can learn to predict new categories of foods continuously. In this project, we propose to design an adaptable prototype pipeline using hierarchical neural networks which can classify international food images the model has rarely or never seen.


Author Posting © The Authors, 2024. This poster was presented at the LUROP Poster Session in April 2024.

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.