Abstract
Healthy eating is an essential element to prevent obesity that will lead to chronic diseases. Despite numerous efforts to promote the awareness of healthy food consumption, the obesity rate has been increased in the past few years. An automated food recognition system is needed to serve as a fundamental source of information for promoting a balanced diet and assisting users to understand their meal consumption. In this paper, we propose a novel Lightweight Neural Architecture Search (LNAS) model to self-generate a thin Convolutional Neural Network (CNN) that can be executed on mobile devices with limited processing power. LNAS has a sophisticated search space and modern search strategy to design a child model with reinforcement learning. Extensive experiments have been conducted to evaluate the model generated by LNAS, namely LNAS-NET. The experimental result shows that the proposed LNAS-NET outperformed the state-of-the-art lightweight models in terms of training speed and accuracy metric. Those experiments indicate the effectiveness of LNAS without sacrificing the model performance. It provides a good direction to move toward the era of AutoML and mobile-friendly neural model design.
Highlights
According to the World Health Organization (WHO), 39% of adults aged 18 years old and above were overweight and 13% were obese in 2016
Extensive experiments are conducted on open-source food datasets to demonstrate the performance gain between Lightweight Neural Architecture Search (LNAS)-NET and existing stateof-the-art thin models, such as MobileNet and ShuffleNet, and the experimental results demonstrate that our proposed method outperforms the state-of-the-art models
This paper proposed a novel Lightweight Neural Architecture Search (LNAS) to automate the process of building new Convolutional Neural Network (CNN) architecture for image-based food classification
Summary
According to the World Health Organization (WHO), 39% of adults aged 18 years old and above were overweight and 13% were obese in 2016. If the provided information is not clear, further interaction with a dietitian is required to capture the detailed information of dietary intake. This has been proven to be helpful, it is not cost-effective and time-consuming for both the end-user and the dietitian to manually provide or review the dietary intake. Based on the digital food images, the dietitian can provide professional feedback to the user [4] This method is designed to minimize the learning barrier for the end-user, but the scalability is constrained by the number of dietitians in a team
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
