Corpus ID: 204852024

Fully-Automatic Semantic Segmentation for Food Intake Tracking in Long-Term Care Homes

  title={Fully-Automatic Semantic Segmentation for Food Intake Tracking in Long-Term Care Homes},
  author={Kaylen J. Pfisterer and Robert Amelard and Audrey G. Chung and Braeden Syrnyk and Alexander MacLean and Alexander Wong},
Malnutrition impacts quality of life and places annually-recurring burden on the health care system. Half of older adults are at risk for malnutrition in long-term care (LTC). Monitoring and measuring nutritional intake is paramount yet involves time-consuming and subjective visual assessment, limiting current methods' reliability. The opportunity for automatic image-based estimation exists. Some progress outside LTC has been made (e.g., calories consumed, food classification), however, these… Expand
Improving the Elementary Leftover Food Estimation Algorithm by Using Clustering Image Segmentation in Nutrition Intake Problem
In the previous research, we created a prototype named Smart Nutrition Box (SNB), which has several features to predict the leftover nutritional content of foods placed at the tray box. However, itExpand
Color space and color channel selection on image segmentation of food images
A comparative study of different color space and color channel selection in image segmentation of food images shows that A in LAB and H in HLS are better to produce segmentation than other color channels, with the Dice score of both is 5 (the highest score). Expand
Deep learning in electron microscopy
This review paper offers a practical perspective aimed at developers with limited familiarity of deep learning in electron microscopy that discusses hardware and software needed to get started with deep learning and interface with electron microscopes. Expand


Semantic Food Segmentation for Automatic Dietary Monitoring
This work addresses semantic segmentation of food images with Deep Learning and explores food and non-food segmentation by getting advantage of supervised learning and demonstrates appealing results on semantic food segmentation. Expand
A New Approach to Image-Based Estimation of Food Volume
A new approach to food intake quantity estimation using image-based modeling that achieves an average accuracy of 92 % on a test set that includes images of different kinds of pasta and bread, with an average processing time of about 23 s. Expand
Grab, Pay, and Eat: Semantic Food Detection for Smart Restaurants
This paper proposes a new approach for food analysis based on convolutional neural networks, which integrates in the same framework food localization, recognition and segmentation, and improves the state-of-art food detection by a considerable margin on the public dataset UNIMIB2016. Expand
DietCam: Multi-view regular shape food recognition with a camera phone
The proposed DietCam system utilizes a multi-view recognition method that separates every food by estimating the best perspective and recognizing them using a probabilistic method, which showed improved performance compared with baseline methods for food recognition. Expand
Food calorie measurement using deep learning neural network
This paper proposes an assistive calorie measurement system, which allows the user to take a picture of the food and measure the amount of calorie intake automatically and shows that the accuracy of the method for food recognition of single food portions is 99%. Expand
Im2Calories: Towards an Automated Mobile Vision Food Diary
A system which can recognize the contents of your meal from a single image, and then predict its nutritional contents, such as calories, is presented, significantly outperforming previous work. Expand
Weakly supervised food image segmentation using class activation maps
A graph based segmentation method is proposed which uses the class activation maps trained on food datasets as a top-down saliency model and achieves competitive classification accuracy compared to the previously reported results. Expand
An Automatic Calorie Estimation System of Food Images on a Smartphone
A novel single-image-based food calorie estimation system which runs on a smartphone as a standalone application without external recognition servers is proposed and the effectiveness of the proposed system was confirmed. Expand
Prototyping the Automated Food Imaging and Nutrient Intake Tracking System: Modified Participatory Iterative Design Sprint
The AFINI-T concept system appears to have good practice relevance as a tool for an intelligent food and fluid intake tracking system in LTC and gives tangible examples of how the sprint method can be adapted and applied to the development of novel needs-based application-driven technology. Expand
Evaluating CNN-Based Semantic Food Segmentation Across Illuminants
Evaluating the performance of an efficient DCNN with respect to variability in illumination conditions that can be found in food images taken in real scenarios and evaluating the food vs. non-food segmentation performance of the network in terms of standard Intersection over Union (IoU) measure. Expand