Comparison of convolutional neural network models for food image classification

ABSTRACT

According to some estimates of World Health Organization, in 2014, more than 1.9 billion adults were overweight. About 13% of the world’s adult population were obese. 39% of adults were overweight. The worldwide prevalence of obesity more than doubled between 1980 and 2014. Nowadays, mobile applications recording food intake of people become popular. If an improved food classification system is introduced, users take the photo of their meals and system classifies photos into the categories. Hence, we proposed a deep convolutional neural network structure trained from scratch and compared its performance with pre-trained structures Alexnet and Caffenet in INISTA 2017. This study is the extended version of it. Three different deep convolutional neural networks were trained from scratch by using different learning methods: stochastic gradient descent, Nesterov’s accelerated gradient and Adaptive Moment Estimation, and compared with Alexnet and Caffenet fine-tuned with the same learning algorithms. Train, validation and test datasets were generated from Food11 and Food101 datasets. All tests were implemented through NVIDIA Digit interface on GeForce GTX1070. According to the test results, although pre-trained models provided better results than proposed structures, their performances were comparable. Moreover, learning optimization methods accelerated and improved the performances of all the compared models.

KEYWORDS:

• Deep learning
• convolutional neural network
• food classification
• transfer learning

Disclosure statement

No potential conflict of interest was reported by the authors.

ORCID

B. Melis Özyildirim http://orcid.org/0000-0003-1960-3787

Notes on contributors

Gözde Özsert Yiğit completed BSc and MSc in 2012 and 2016, and started her Phd in Computer Engineering Department of Cukurova University. She is working as research assistant in Computer Engineering department at Gaziantep University. Her research areas are artificial neural networks, deep learning.

B. Melis Özyildirim completed BSc, MSc in Computer Engineering Department of Cukurova University and completed Phd in 2015 in Electrical and Electronics Engineering Department of Cukurova University. She is working as assistant professor doctor in Computer Engineering Department of Cukurova University. Her research areas are machine learning, deep learning.