Food Image Recognition Based on Densely Connected Convolutional Neural Networks

Convolutional neural networks have been widely used for image recognition as they are capable of extracting features with high accuracy. In this paper, we propose a DenseFood model based on densely connected convolutional neural network architecture, which consists of multiple layers. A combination of softmax loss and center loss is used during the training process to minimize the variation within the same category and maximize the variation across different ones. For performance comparison, three models, namely, DenseFood, DenseNet121, and ResNet50 are trained using VIREO-172 dataset. In addition, we fine tune pre-trained DenseNet121 and ResNet50 models to extract features from the dataset. Experimental results show that the proposed DenseFood model achieves an accuracy of 81.23% and outperforms the other models in comparison.

[1]  Keiji Yanai,et al.  Automatic Expansion of a Food Image Dataset Leveraging Existing Categories with Domain Adaptation , 2014, ECCV Workshops.

[2]  Jindong Tan,et al.  DietCam: Multiview Food Recognition Using a Multikernel SVM , 2016, IEEE Journal of Biomedical and Health Informatics.

[3]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Bo Li,et al.  Face Recognition Based on Densely Connected Convolutional Networks , 2018, 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM).

[5]  A. Kannan,et al.  Automatic food recognition system for diabetic patients , 2014, 2014 Sixth International Conference on Advanced Computing (ICoAC).

[6]  Frank Hutter,et al.  SGDR: Stochastic Gradient Descent with Warm Restarts , 2016, ICLR.

[7]  Shashidhar G. Koolagudi,et al.  Food classification from images using convolutional neural networks , 2017, TENCON 2017 - 2017 IEEE Region 10 Conference.

[8]  Taskeed Jabid,et al.  Food Image Classification with Convolutional Neural Network , 2018, 2018 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS).

[9]  Gian Luca Foresti,et al.  Wide-Slice Residual Networks for Food Recognition , 2016, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[10]  Yuzhen Lu,et al.  Food Image Recognition by Using Convolutional Neural Networks (CNNs) , 2016, ArXiv.

[11]  Matthieu Guillaumin,et al.  Food-101 - Mining Discriminative Components with Random Forests , 2014, ECCV.

[12]  Chong-Wah Ngo,et al.  Deep-based Ingredient Recognition for Cooking Recipe Retrieval , 2016, ACM Multimedia.

[13]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[15]  Monica Mordonini,et al.  Food Image Recognition Using Very Deep Convolutional Networks , 2016, MADiMa @ ACM Multimedia.

[16]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[17]  B. Koroušić Seljak,et al.  NutriNet: A Deep Learning Food and Drink Image Recognition System for Dietary Assessment , 2017, Nutrients.

[18]  Bappaditya Mandal,et al.  FoodNet: Recognizing Foods Using Ensemble of Deep Networks , 2017, IEEE Signal Processing Letters.

[19]  Keiji Yanai,et al.  Food image recognition with deep convolutional features , 2014, UbiComp Adjunct.

[20]  Beatriz Remeseiro,et al.  Grab, Pay, and Eat: Semantic Food Detection for Smart Restaurants , 2018, IEEE Transactions on Multimedia.

[21]  Jian Cheng,et al.  NormFace: L2 Hypersphere Embedding for Face Verification , 2017, ACM Multimedia.

[22]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Keiji Yanai,et al.  Food image recognition using deep convolutional network with pre-training and fine-tuning , 2015, 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).

[24]  Hammad Afzal,et al.  A Framework to Estimate the Nutritional Value of Food in Real Time Using Deep Learning Techniques , 2019, IEEE Access.

[25]  Rama Chellappa,et al.  On the size of Convolutional Neural Networks and generalization performance , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[26]  Touradj Ebrahimi,et al.  Food/Non-food Image Classification and Food Categorization using Pre-Trained GoogLeNet Model , 2016, MADiMa @ ACM Multimedia.

[27]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[28]  Petia Radeva,et al.  Food Recognition Using Fusion of Classifiers Based on CNNs , 2017, ICIAP.

[29]  Kiyoharu Aizawa,et al.  Personalized Classifier for Food Image Recognition , 2018, IEEE Transactions on Multimedia.

[30]  Jingfan Wang,et al.  Deep Learning Based Food Recognition , 2016 .