Recently a huge amount of work has been done in order to develop Convolutional Neural Networks (CNNs) for supervised food recognition. These CNNs are trained to classify a predefined set of food classes within a specific food dataset. CNN-based features have been largely experimented for many image retrieval domains and to a lesser extent to the food domain. In this paper, we investigate the use of CNN-based features for food retrieval by taking advantage of existing food datasets. To this end, we have built the Food524DB, the largest publicly available food dataset with 524 food classes and 247,636 images by merging food classes from existing datasets in the state of the art. We have then used this dataset to fine tune a Residual Network, ResNet-50, which has demonstrated to be very effective for image recognition. The last fully connected layer is finally used as feature vector for food image indexing and retrieval. Experimental results are reported on the UNICT-FD1200 dataset that has been specifically design for food retrieval.

Ciocca, G., Napoletano, P., Schettini, R. (2017). Learning CNN-based Features for Retrieval of Food Images. In New Trends in Image Analysis and Processing – ICIAP 2017 (pp.426-434). Springer Verlag [10.1007/978-3-319-70742-6_41].

Learning CNN-based Features for Retrieval of Food Images

Ciocca, G;Napoletano, P
;
Schettini, R
2017

Abstract

Recently a huge amount of work has been done in order to develop Convolutional Neural Networks (CNNs) for supervised food recognition. These CNNs are trained to classify a predefined set of food classes within a specific food dataset. CNN-based features have been largely experimented for many image retrieval domains and to a lesser extent to the food domain. In this paper, we investigate the use of CNN-based features for food retrieval by taking advantage of existing food datasets. To this end, we have built the Food524DB, the largest publicly available food dataset with 524 food classes and 247,636 images by merging food classes from existing datasets in the state of the art. We have then used this dataset to fine tune a Residual Network, ResNet-50, which has demonstrated to be very effective for image recognition. The last fully connected layer is finally used as feature vector for food image indexing and retrieval. Experimental results are reported on the UNICT-FD1200 dataset that has been specifically design for food retrieval.
paper
CNN-based features; Food dataset; Food recognition; Food retrieval; Theoretical Computer Science; Computer Science (all)
English
International Conference on Image Analysis and Processing, ICIAP 2017 SEP 11-15
2017
New Trends in Image Analysis and Processing – ICIAP 2017
978-3-319-70741-9
2017
10590
426
434
none
Ciocca, G., Napoletano, P., Schettini, R. (2017). Learning CNN-based Features for Retrieval of Food Images. In New Trends in Image Analysis and Processing – ICIAP 2017 (pp.426-434). Springer Verlag [10.1007/978-3-319-70742-6_41].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/184577
Citazioni
  • Scopus 52
  • ???jsp.display-item.citation.isi??? 42
Social impact