Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Idea to Innovation

University of Western Ontario

$69,000.00

Improving glucoguide with meter and food recognition using cameras on smartphones

EF 2014-15

Résumé
Diabetes is a chronic disease that leads to serious complications. It is estimated that 9 million Canadians are diabetic or pre-diabetic - that is about 1 in every 4 Canadians. We have been developing a personalized recommendation system, called GlucoGuide for Type-2 diabetes. Our system collects a variety of lifestyle data via patients' smartphones, mines the data with novel data-mining algorithms, and sends personalized recommendations to patients that can improve their diabetic conditions. We have conducted a three-month clinical trial with patients, and obtained very promising results. Roughly speaking, GlucoGuide can potentially turn an early diabetic patient into a pre-diabetic, and a pre-diabetic one into a non-diabetic. However, one cumbersome step of using GlucoGuide is to enter meter readings (from glucometers and so on) and food items. In this R&D project, we propose to use the camera function available on almost all smartphones, and develop specialized recognition systems for digit/character from meters, food labels, restaurant menus, and even for food items from pictures of food directly. Digit and character recognition has been studied by many researchers for many years, and some have been used in real life (such as postal code recognition for automatic mail sorting). We will improve these existing methods for a variety of specific devices that diabetes patients use (such as glucometers and blood pressure monitors). This can significantly improve the recognition accuracy of the general digit/character recognition methods. Food recognition from photos, on the other hand, is highly challenging. Currently few such systems or apps can do this. We plan to explore the very recent work of deep learning to learn to predict how healthy the food is specifically for diabetes patients. GlucoGuide for iOS devices (iPhone?, iPad?) will also be developed. We believe that this work would significantly improve the usability of GlucoGuide, and pave the way to commercialize GlucoGuide. This will bring huge benefits to the health of millions of Canadians who have type-2 diabetes.
Programme
Idea to Innovation
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
463245-2014
Name nom
Ling, Charles
Department département
Computer Science
Organization id
36
Institution établissement
University of Western Ontario
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2014
Award amount
69000
Program id
I2IPJ
Program name en
Idea to Innovation
Program name fr
De l'idée à l'innovation
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1101
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Human health (including medically-related psychological research)
Area of application fr
Santé publique (y compris recherche psychologique liée à la médecine)
Research subject code
2800
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Artificial intelligence (computer vision, use2603)
Research subject fr
Intelligence artificielle (vision artificielle, utiliser 2603)
Partie
1
Nb partie
1
Application title
Improving glucoguide with meter and food recognition using cameras on smartphones
Keyword
NSERC
Application summary
Diabetes is a chronic disease that leads to serious complications. It is estimated that 9 million Canadians are diabetic or pre-diabetic - that is about 1 in every 4 Canadians. We have been developing a personalized recommendation system, called GlucoGuide for Type-2 diabetes. Our system collects a variety of lifestyle data via patients' smartphones, mines the data with novel data-mining algorithms, and sends personalized recommendations to patients that can improve their diabetic conditions. We have conducted a three-month clinical trial with patients, and obtained very promising results. Roughly speaking, GlucoGuide can potentially turn an early diabetic patient into a pre-diabetic, and a pre-diabetic one into a non-diabetic. However, one cumbersome step of using GlucoGuide is to enter meter readings (from glucometers and so on) and food items. In this R&D project, we propose to use the camera function available on almost all smartphones, and develop specialized recognition systems for digit/character from meters, food labels, restaurant menus, and even for food items from pictures of food directly. Digit and character recognition has been studied by many researchers for many years, and some have been used in real life (such as postal code recognition for automatic mail sorting). We will improve these existing methods for a variety of specific devices that diabetes patients use (such as glucometers and blood pressure monitors). This can significantly improve the recognition accuracy of the general digit/character recognition methods. Food recognition from photos, on the other hand, is highly challenging. Currently few such systems or apps can do this. We plan to explore the very recent work of deep learning to learn to predict how healthy the food is specifically for diabetes patients. GlucoGuide for iOS devices (iPhone?, iPad?) will also be developed. We believe that this work would significantly improve the usability of GlucoGuide, and pave the way to commercialize GlucoGuide. This will bring huge benefits to the health of millions of Canadians who have type-2 diabetes.