Fine-Grained Food Classification Methods on the UEC FOOD-100 Database

OUR PROPOSED TITLE:

Fine-Grained Food Classification using Deep Learning

IEEE BASE PAPER ABSTRACT:

The development of an automatic food recognition system has several interesting applications ranging from waste food management, to advertisement, to calorie estimation, and daily diet monitoring. Despite the importance of this subject, the number of related studies is still limited. Moreover, the comparison in the literature was currently done over the best-shot performance without considering the most common method of averaging over several trials. This article surveys the most common deep learning methods used for food classification, it presents the publicly available databases of food, it releases benchmark results for the food classification experiment averaged over five-trials, and it beats the current best-shot performance experiment reaching the state-of-the- art accuracy of 90.02% on the UEC Food-100 database. The best results have been achieved by the ensemble method averaging the predictions of ResNeXt and DenseNet models. All the experiments are run on the UEC Food-100 database because it is one of the most used databases, and it is challenging due to the presence of multifood images, which need to be cropped before processing. This article aims to contribute to automatic food recognition by presenting the most common algorithms used for food classification, introducing the main databases of food items currently available, and reaching the state-of-the-art performance in the best-shot classification experiment of the UEC Food-100 database. That is, this article improves the current best-shot performance by 0.44 percentage points, and fixes it to 90.02%. Furthermore, with the best of our knowledge, this is the first article to introduce to the research community comparison of performances of the classification experiment on the UEC Food-100 database averaged over five-trails. As expected, performance averaged is slightly lower than the best-shot one.

Impact Statement—This article aims to contribute to automatic food recognition by presenting the most common algorithms used for food classification, introducing the main databases of food items currently available, and reaching the state-of-the-art performance in the best-shot classification experiment of the UEC Food-100 database. That is, this article improves the current best-shot performance by 0.44 percentage points, and fixes it to 90.02%. Furthermore, with the best of our knowledge, this is the first article to introduce to the research community comparison of performances of the classification experiment on the UEC Food-100 database averaged over five-trails. As expected, performance averaged is slightly lower than the best-shot one.

PROJECT OUTPUT VIDEO:

OUR PROPOSED ABSTRACT:

Food classification and recognition is a developing area of study that goes beyond the social network realm. Indeed, because to its growing advantages from a medical standpoint, researchers are concentrating on this field. Tools for automatically identifying foods will make it easier to estimate calories, identify food quality, create diet monitoring systems to fight obesity, and more.

Image categorization is emerging as a significant and promising area in the study of object detection using computer vision. Studies, however, have only begun to scrape the surface. The classification of their traditional cuisine has a big impact on how nutritionally fit people of different ethnicities are currently, according to the superficial classification of food images. Different types of foods are categorised by existing models. These models are only able to classify a few food categories at a time. The greatest possible number of foods must be recognised in a single model, nevertheless.

The main goal of this research is to develop a recognition model that classifies different food products using the MobileNet Architecture. The built model accurately categorised 101 different food types using MobileNet Architecture with a 98% accuracy rate. Our model outperformed other cutting-edge models in terms of accuracy.

ALGORITHM / MODEL USED:

MobileNet Architecture.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 4 GB.

SOFTWARE REQUIREMENTS:

Operating System : Windows 10 / 11.
Coding Language : Python 3.8.
Web Framework : Flask.
Frontend : HTML, CSS, JavaScript.

REFERENCE:

Berker Arslan, Sefer Memis, Elena Battini Sönmez , and Okan Zafer Batur , Member, IEEE, “Fine-Grained Food Classification Methods on the UEC FOOD-100 Database”, IEEE TRANSACTIONS ON ARTIFICIAL INTELLIGENCE, VOL. 3, NO. 2, APRIL 2022.

Python IEEE Projects

Fine-Grained Food Classification Methods on the UEC FOOD-100 Database