FOOD RECOGNITION AND NUTRITION FACTS DETERMINATION WITH DEEP CONVOLUTION NEURAL NETWORK MODELS

Basit Öğe Kaydı
dc.authoridyücel, özgün/0000-0001-8916-2628
dc.authorwosidyücel, özgün/JAN-6493-2023
dc.contributor.authorTarlak, Fatih
dc.contributor.authorYucel, Ozgun
dc.contributor.authorYilmaz, Onur
dc.date.accessioned2024-06-13T20:18:33Z
dc.date.available2024-06-13T20:18:33Z
dc.date.issued2023
dc.departmentİstanbul Gedik Üniversitesi
dc.description.abstractFood recognition plays a crucial role in various domains including healthcare, nutrition, and the food industry. In healthcare, food recognition is valuable for individuals to monitor their daily food intake and manage their diet effectively. It also aids dietitians and nutritionists in creating personalized meal plans for patients based on their nutritional requirements and preferences. The objective of this research was to develop software capable of recognizing and predicting the nutritional information of commonly consumed fruits and vegetables in Turkey. Basic nutrition data for each food item was collected and organized. A dataset comprising 9,000 food images was gathered, encompassing 200 images for each food item. To train the images, deep learning (DL) algorithms such as GoogleNet, ResNet-50, and Inception-v3 were utilized on platforms like Matlab and.NET Core. Additionally, 900 food images were reserved for external validation purposes. The DL algorithms achieved excellent accuracy, with all models surpassing 98.3% accuracy in predicting food categories. Notably, the Inception-v3 algorithm outperformed the others, achieving an accuracy of 99.1% during the testing phase. Consequently, the Inception-v3 algorithm was chosen to develop software for food recognition and nutrition analysis, intended for both computers and smartphones. The software can be relied upon for food recognition and nutrition analysis, making it highly valuable in healthcare, particularly in tracking the dietary intake of patients with chronic conditions like diabetes, heart disease, or obesity. The system can effectively track the types and quantities of foods consumed, providing personalized feedback to both patients and healthcare providers.
dc.identifier.doi10.34302/SI/236
dc.identifier.issn2066-6845
dc.identifier.issn2344-5459
dc.identifier.scopus2-s2.0-85188148903
dc.identifier.scopusqualityQ4
dc.identifier.urihttps://doi.org/10.34302/SI/236
dc.identifier.urihttps://hdl.handle.net/11501/1440
dc.identifier.wosWOS:001167439700006
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherNorth Univ Center Baia Mare
dc.relation.ispartofCarpathian Journal of Food Science and Technology
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectVision System Approach
dc.subjectColor Measurements
dc.titleFOOD RECOGNITION AND NUTRITION FACTS DETERMINATION WITH DEEP CONVOLUTION NEURAL NETWORK MODELS
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu