Abstract
This paper presents a feasibility study into a deep learning image recognition system that is embedded into a prototype mobile test-bed application designed to help users maintain healthy eating habits. A natural multimodal interaction is favored allowing a user to take photos of the food ingredients she has at her disposal for preparing a meal. The application utilizes the image recognition system to recognize a variety of fruits, vegetables and other food products as a basis for suggesting well-balanced dietary alternatives. The paper presents our initial explorations with several convolutional neural networks (CNNs) architectures of varying depth and structure. We compare the recognition accuracies and performance of different combinations of the model hyper-parameters complemented with few data augmentation techniques.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: 26th Annual Conference on Neural Information Processing Systems, Lake Tahoe, Nevada (2012)
Kwolek, B.: Face detection using convolutional neural networks and Gabor filters. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) Artificial Neural Networks: Biological Inspirations – ICANN 2005. LNCS, vol. 3696. Springer, Heidelberg (2005)
Browne, M., Ghidary, S.S.: Convolutional neural networks for image processing: an application in robot vision. In: Gedeon, T.D., Fung, L.C.C. (eds.) Advances in Artificial Intelligence, AI 2003. LNCS, vol. 2903. Springer, Heidelberg (2003)
Fawzi, A., Samulowitz, H., Turaga, D., Frossard, P.: Adaptive data augmentation for image classification. In: 23rd IEEE International Conference on Image Processing, pp. 3688–3692. IEEE (2016)
Wang, J., Perez, L.: The effectiveness of data augmentation in image classification using deep learning, Technical report no. 300, Stanford University (2017)
Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural Information Processing Systems 27. NIPS Proceedings, pp. 2672–2680 (2014)
Salimans, T., Goodfellow, I.J., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems 29. NIPS Proceedings, pp. 2234–2242 (2016)
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size, Technical report, Stanford University (2016)
Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: ImageNet classification using binary convolutional neural networks. In: European Conference on Computer Vision (2016)
Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: MobileNets: efficient convolutional neural networks for mobile vision applications. Technical report, Google (2017)
Chen, C., Lee, C., Lu, W.C.: A mobile cloud framework for deep learning and its application to smart car camera. In: Third International Conference on Internet of Vehicles – Technologies and Services, pp. 14–25 (2016)
Acknowledgments
This research was partially funded by the Faculty of Computer Science and Engineering, University of “Ss. Cyril and Methodius”, Macedonia.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Krstova, A., Petreski, A., Gievska, S. (2018). Explorations into Deep Learning Mobile Applications. In: Karwowski, W., Ahram, T. (eds) Intelligent Human Systems Integration. IHSI 2018. Advances in Intelligent Systems and Computing, vol 722. Springer, Cham. https://doi.org/10.1007/978-3-319-73888-8_66
Download citation
DOI: https://doi.org/10.1007/978-3-319-73888-8_66
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-73887-1
Online ISBN: 978-3-319-73888-8
eBook Packages: EngineeringEngineering (R0)