A Comparative Study of Deep Learning Methods on Food Classification Problem

Memis, S.Arslan, B.Batur, O.Z.Sonmez, E.B.2024-07-182024-07-1820209781728191362https://doi.org/10.1109/ASYU50717.2020.9259904https://hdl.handle.net/11411/63862020 Innovations in Intelligent Systems and Applications Conference, ASYU 2020 -- 15 October 2020 through 17 October 2020 -- -- 165305This paper gives a comparative study on the performances of several deep learning methods for the food images recognition challenge. The experiments were conducted on the UEC Food-100 dataset using ResNet-18, Inception-V3, Resnet-50, Densenet-121, Wide Resnet-50 and ResNext-50 with images of size 320x320 and 299x299. The limited size of the database required the transfer learning approach; that is, all models were trained with pretrained ImageNet weights. The best classification result was obtained using ResNext-50 with 87.7 % accuracy. © 2020 IEEE.eninfo:eu-repo/semantics/closedAccessClassificationDeep LearningDensenetInceptionMachine LearningResnetResnextUec Food 100Intelligent SystemsLearning SystemsTransfer LearningClassification ResultsComparative StudiesFood İmageLearning MethodsDeep LearningA Comparative Study of Deep Learning Methods on Food Classification ProblemConference Object2-s2.0-8509796210010.1109/ASYU50717.2020.9259904N/A