Hybrid Learning-based Demographic Estimation and Nutrition Recommendation using Dental Panoramic X-Ray Images

View at publisher Summarise with VIRAT
Authors: J. Ponnudurai, M. Kaliappan
Cited by: 0
References: 12

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Dental radiography is essential to the diagnosis and treatment planning process in the modern oral healthcare setting. Using dental panoramic X-ray images, this study suggests a hybrid computational architecture that might not only estimate age and gender but also offer personalized food recommendations. Although the Convolutional Neural Networks are used to extract precise radiographic information from the dento-maxillofacial region that classical machinelearning classifiers are used to improve prediction accuracy and generalization across a range of populations. A rule-based nutrition recommendation system recommends appropriate dietary practices to improve oral health and lower the risk of dental conditions including caries and enamel erosion based on the anticipated demographic profile. By lowering the amount of manual interpretation work and facilitating effective decision assistance in both clinic-based and remote dental care settings, the technology is intended to help dental professionals. During the expert review, the experimental assessment shows high acceptability of dietary recommendations and great performance in the demographic prediction. For better clinical applicability, future improvements will involve extending the dataset, adding multimodal imaging and implementing the model in real-time scenarios.

Fields of Study & Subjects

Dental Radiography and Imaging Forensic Anthropology and Bioarchaeology Studies Face recognition and analysis

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1381–1386
Publication date
21 January 2026
Language
EN