Use of smartphones to estimate carbohydrates in foods for diabetes - - PowerPoint PPT Presentation
Use of smartphones to estimate carbohydrates in foods for diabetes management Jurong HUANG, Hang DING, Simon MCBRIDE, David IRELAND, Mohan KARUNANITHI Presenter: Hang Ding | hang.ding@csiro.au | HIC 2015 3 August 2015 HEALTH AND BIOSECURITY
Jurong HUANG, Hang DING, Simon MCBRIDE, David IRELAND, Mohan KARUNANITHI
HEALTH AND BIOSECURITY
Presenter: Hang Ding | hang.ding@csiro.au | HIC 2015 3 August 2015
Use of smartphones to estimate carbohydrates in foods for diabetes management | Hang Ding, 3 August 2015 2 |
Deaths directly caused by diabetes
Adults with diabetes worldwide
Use of smartphones to estimate carbohydrates in foods for diabetes management | Hang Ding, 3 August 2015 3 |
Use of smartphones to estimate carbohydrates in foods for diabetes management | Hang Ding, 3 August 2015 4 |
OpenCV Camera OS Food Classifier Nutrition Database Volume Estimator Carbohydrate Calculation
Use of smartphones to estimate carbohydrates in foods for diabetes management | Hang Ding, 3 August 2015 5 |
Three Features
Colour
(RGB elements)
Shape
(scale Invariant Feature Transform)
Texture
(Local Binary Pattern)
Support Vector Machine
Use of smartphones to estimate carbohydrates in foods for diabetes management | Hang Ding, 3 August 2015 6 |
Food Photo Object with calibrated size Objects extracted Estimated Volume
Use of smartphones to estimate carbohydrates in foods for diabetes management | Hang Ding, 3 August 2015 7 |
10 types of fruits, 60 photos each
(orange, apple, pear, tomato, strawberry, banana, mango, avocado, pineapple, and kiwi fruit)
Training Data 10 types, 50 photos each Test Data 10 types, 10 photos each Randomized ACC = (TP + TN) TP + TN + FP + FN Optimized Classification Parameters Accuracy of Classification
Use of smartphones to estimate carbohydrates in foods for diabetes management | Hang Ding, 3 August 2015 8 |
Types of Tested Fruits Classification Accuracy
Use of smartphones to estimate carbohydrates in foods for diabetes management | Hang Ding, 3 August 2015 9 |
Test Item Model Volume (ml) Actual Volume (ml) Error Rate (%) Estimated Carbs (g) Actual Carbs (g) Error Rate (%) Peach 158 151 4.43 16.3 15.9 2.45 Apple1 165 173 4.85 18.5 21.3 15.1 Apple2 172 190 13.9 19.3 22.4 16.1 Apple3 201 198 1.49 22.5 23.7 3.56 Tomato1 21 22 4.76 0.74 0.78 5.41 Tomato2 17 19 11.7 0.62 0.66 6.45 Average Error 6.86 8.18
Table 1. Summary of the volume and carbohydrate estimations, compared with the actual values measured from the water displacement and weight scale.
Use of smartphones to estimate carbohydrates in foods for diabetes management | Hang Ding, 3 August 2015 10 |
Contact Us Phone: 1300 363 400 or +61 3 9545 2176 Email: enquiries@csiro.au Web: www.csiro.au