Advertisement

Towards Personalised Training of Machine Learning Algorithms for Food Image Classification Using a Smartphone Camera

  • Patrick McAllister
  • Huiru ZhengEmail author
  • Raymond Bond
  • Anne Moorhead
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10069)

Abstract

This work is related to the development of a personalised machine learning algorithm that is able to classify food images for food logging. The algorithm would be personalised as it would allow users to decided what food items the model will be able to classify. This novel concept introduces the idea of promoting dietary monitoring through classifying food images for food logging by personalising a machine learning algorithm. The food image classification algorithm will be trained based on specific types of foods decided by the user (most popular foods, food types e.g. vegetarian). This would mean that the classification algorithm would not have to be trained using a wide variety of foods which may lead to low accuracy rate but only a small number of foods chosen by the user. To test the concept, a range of experiments were completed using 30 different food types. Each food category contained 100 images. To train a classification algorithm, features were extracted from each food type, features such as SURF, LAB colour features, SFTA, and Local Binary Patterns were used. A number of classification algorithms were used in these experiments; Nave Bayes, SMO, Neural Networks, and Random Forest. The highest accuracy achieved in this work was 69.43 % accuracy using Bag-of-Features (BoF) Colour, BoF-SURF, SFTA, and LBP using a Neural Network.

Keywords

Obesity Machine learning Classification Food logging Photographs 

References

  1. 1.
    DHSSPSNI, Health Survey Northern Ireland, First Results 2013/2014 (2013–2014)Google Scholar
  2. 2.
    Nhs.uk, “Obesity, NHS Choices”, Nhs.uk (2016). www.nhs.uk/Conditions/Obesity/Pages/Introduction.aspx. Accessed 15 Jun 2016
  3. 3.
    Noo.org.uk “About Obesity: Public Health England” (2016). www.noo.org.uk/NOO_about_obesity/adult_obesity/UK_prevalence_and_trends
  4. 4.
    Scarborough, P., Bhatnagar, P., Wickramasinghe, K., Allender, S., Foster, C., Rayner, M.: The economic burden of ill health due to diet, physical inactivity, smoking, alcohol and obesity in the UK: an update to 2006–07 NHS costs. J. Public Health 33(4), 527–535 (2011)CrossRefGoogle Scholar
  5. 5.
    Noo.org.uk, “Economics of obesity: Public Health England Obesity Knowledge and Intelligence team", Noo.org.uk (2016). www.noo.org.uk/NOO_about_obesity/economics. Accessed 15 Jun 2016
  6. 6.
    MyFitnessPal, C.: M. LLc, “Calorie Counter & Diet Tracker by MyFitnessPal on the App. Store”, App. Store (2016). itunes.apple.com/gb/app/calorie-counter-diet-tracker/id341232718?mt=8. Accessed 15 Jun 2016
  7. 7.
    McAllister, P., et al.: Semi-automated system for predicting calories in photographs of meals. In: IEEE International Conference on Engineering, Technology and Innovation/International Technology Management Conference (ICE/ITMC). IEEE (2015)Google Scholar
  8. 8.
    Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 – mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VI. LNCS, vol. 8694, pp. 446–461. Springer, Heidelberg (2014)Google Scholar
  9. 9.
    Bosch, M., et. al.: Food texture descriptors based on fractal and local gradient information. In: 19th European Signal Processing Conference, pp. 764–768. IEEE (2011)Google Scholar
  10. 10.
    Farinella, G.M., Allegra, D., Stanco, F.: A benchmark dataset to study the representation of food images. In: ECCV European Conference in Computer Vision. Zurich, Workshop Assistive Computer Vision and Robotics (2014)Google Scholar
  11. 11.
    Joutou, T., Yanai, K.: A food image recognition system with multiple kernel learning. In: 16th IEEE International Conference on Image Processing (ICIP), pp. 285–288. IEEE (2009)Google Scholar
  12. 12.
    Kawano, Y., Yanai, K.: Foodcam-256: a large-scalereal-time mobile food recognition system employing high-dimensional features and compression of classifier weights. In: Proceedings of the ACM International Conference on Multimedia, ser. MM 14, pp. 761–762 (2014)Google Scholar
  13. 13.
    Hartigan, J.A., Manchek, A.W.: Algorithm AS 136: a k-means clustering algorithm. J. Roy. Stat. Soc.: Ser. C (Appl. Stat.) 28(1), 100–108 (1979)Google Scholar
  14. 14.
    Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  15. 15.
    Costa, A.F., Humpire-Mamani, G., Traina, A.J.M.: An efficient algorithm for fractal analysis of textures. In: 25th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). IEEE (2012)Google Scholar
  16. 16.
    “Lab Color - MATLAB", Uk.mathworks.com (2016). http://uk.mathworks.com/discovery/lab-color.html. Accessed 15 Jun 2016
  17. 17.
    Ojala, T., Pietikinen, M., Harwood, D.: Performance evaluation of texture measures with classification based on Kullback discrimination of distributions. In: Proceedings of the 12th IAPR International Conference on Pattern Recognition (ICPPR 1994), vol. 1, pp. 582–585 (1994)Google Scholar
  18. 18.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  19. 19.
    Platt, J.C.: Sequential Minimal Optimization: a fast algorithm for training support vector machines. In: Advances Kernel Methods, pp. 185–208 (1998)Google Scholar
  20. 20.
    Bosch, M., Zhu, F., Khanna, N., Boushey, C.J., Delp, E.J.: Combining global and local features for food identification in dietary assessment. In: Proceedings - International Conference on Image Processing, ICIP, pp. 1789–1792 (2011)Google Scholar
  21. 21.
    Kawano, Y., Yanai, K.: FoodCam: a real-time mobile food recognition system employing fisher vector. In: Gurrin, C., Hopfgartner, F., Hurst, W., Johansen, H., Lee, H., O’Connor, N. (eds.) MMM 2014, Part II. LNCS, vol. 8326, pp. 369–373. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  22. 22.
    MATLAB - MathWorks: Matlab.co.uk (2016). http://matlab.co.uk. Accessed 15 Jun 2016
  23. 23.
    Weka 3 - Data Mining with Open Source Machine Learning Software in Java. Cs.waikato.ac.nz (2016). http://www.cs.waikato.ac.nz/ml/weka/. Accessed 15 Jun 2016
  24. 24.
    (Convolutional) Neural Network, “amten/NeuralNetwork", GitHub (2016). https://github.com/amten/NeuralNetwork. Accessed 15 Sep 2016

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Patrick McAllister
    • 1
  • Huiru Zheng
    • 1
    Email author
  • Raymond Bond
    • 1
  • Anne Moorhead
    • 2
  1. 1.School of Computing and MathematicsUlster UniversityNewtownabbeyNorthern Ireland
  2. 2.School of CommunicationUlster UniversityNewtownabbeyNorthern Ireland

Personalised recommendations