A Hierarchical deep model for food classification from photographs

• Heekyung Yang,
• Sungyong Kang,
• Chanung Park,
• JeongWook Lee,
• Kyungmin Yu,
• Kyungha Min,

Vol. 14, No. 4, April 30, 2020
10.3837/tiis.2020.04.016, Download Paper (Free):

• CNN
• DenseNet
• Classification
• Food
• dietetics

Abstract

Recognizing food from photographs presents many applications for machine learning, computer vision and dietetics, etc. Recent progress of deep learning techniques accelerates the recognition of food in a great scale. We build a hierarchical structure composed of deep CNN to recognize and classify food from photographs. We build a dataset for Korean food of 18 classes, which are further categorized in 4 major classes. Our hierarchical recognizer classifies foods into four major classes in the first step. Each food in the major classes is further classified into the exact class in the second step. We employ DenseNet structure for the baseline of our recognizer. The hierarchical structure provides higher accuracy and F1 score than those from the single-structured recognizer.

Statistics

Cite this article