Image-based soft drink type classification and dietary assessment system using deep convolutional neural network with transfer learning
Rubaiya Hafiz, Mohammad Reduanul Haque, Aniruddha Rakshit, Mohammad Shorif Uddin
Abstract
Nowadays, people are taking soft drinks (carbonated nonalcoholic beverages) at an increasing rate. Health experts around the world have cautioned from time to time that these drinks lead to weight gain, raise the risk of non-communicable diseases, and so on. To develop consciousness among people, the present work describes an image-based tool to self-monitor the nutritional information of soft drinks by using a deep convolutional neural network (CNN) along with transfer learning. At first, a pre-processing function is done through noise reduction and contrast enhancement. Then the location of the drinks region is extracted through visual saliency and mean-shift segmentation technique. After removing backgrounds and segment out only the region of interest from the image a deep CNN-based transfer learning model is employed for the drink classification. Finally, the size of each drink bottle is estimated using the bag-of-feature (BoF) and distance ratio calculation to find the nutrition value from the nutrition fact table. To perform experimentation a dataset is built containing ten most consumed soft drinks in Bangladesh using images from the ImageNet dataset, internet sources and also self-capturing. The experiment confirms that our system can detect and recognize different types of drinks with an accuracy of 98.51%.