Food image recognition using deep convolutional network with pre-training and fine-tuning

Yanai, Keiji; Kawano, Yoshiyuki

doi:10.1109/icmew.2015.7169816

Cited by 267 publications

(128 citation statements)

References 9 publications

Supporting

Mentioning

121

Contrasting

Order By: Relevance

“…They used the pre-trained AlexNet model as a feature extractor and integrated both CNN features and Fisher Vector encoded conventional SIFT and color features. Yanai et al [21] fine-tuned the AlexNet model and achieved the best results on public food datasets so far, with top-1 accuracy of 78.8% for UEC-FOOD-100 dataset and 67.6% for UEC-FOOD-256 [22] (another Japanese food image dataset with 256 classes). Their works showed that the recognition performance on small image datasets like UEC-FOOD-256 and UEC-FOOD-100 (both of which contained 100 images for each class) can be boosted by fine-tuning the CNN network which was pre-trained on a large dataset of similar objects.…”

Section: Food Image Recognitionmentioning

confidence: 99%

Food/Non-food Image Classification and Food Categorization using Pre-Trained GoogLeNet Model

Singla

Lin

Ebrahimi

2016

Proceedings of the 2nd International Workshop on Multimedia Assisted Dietary Management

159

View full text Add to dashboard Cite

Recent past has seen a lot of developments in the field of image-based dietary assessment. Food image classification and recognition are crucial steps for dietary assessment. In the last couple of years, advancements in the deep learning and convolutional neural networks proved to be a boon for the image classification and recognition tasks, specifically for food recognition because of the wide variety of food items. In this paper, we report experiments on food/non-food classification and food recognition using a GoogLeNet model based on deep convolutional neural network. The experiments were conducted on two image datasets created by our own, where the images were collected from existing image datasets, social media, and imaging devices such as smart phone and wearable cameras. Experimental results show a high accuracy of 99.2% on the food/non-food classification and 83.6% on the food category recognition.

show abstract

Section: Food Image Recognitionmentioning

confidence: 99%

Food/Non-food Image Classification and Food Categorization using Pre-Trained GoogLeNet Model

Singla

Lin

Ebrahimi

2016

Proceedings of the 2nd International Workshop on Multimedia Assisted Dietary Management

159

View full text Add to dashboard Cite

show abstract

“…Another of the topics studied is the evaluation of whether, for these tasks, it is better to train a network from scratch (full training) or to use fine tuning of a pre-trained network. There is a reference that analyzes this specific aspect in medical images [21] and something similar in images of food [34,35], but no bibliography in the field of architectural heritage is known.…”

Section: Image Classificationmentioning

confidence: 99%

Classification of Architectural Heritage Images Using Deep Learning Techniques

et al. 2017

View full text Add to dashboard Cite

Abstract:The classification of the images taken during the measurement of an architectural asset is an essential task within the digital documentation of cultural heritage. A large number of images are usually handled, so their classification is a tedious task (and therefore prone to errors) and habitually consumes a lot of time. The availability of automatic techniques to facilitate these sorting tasks would improve an important part of the digital documentation process. In addition, a correct classification of the available images allows better management and more efficient searches through specific terms, thus helping in the tasks of studying and interpreting the heritage asset in question. The main objective of this article is the application of techniques based on deep learning for the classification of images of architectural heritage, specifically through the use of convolutional neural networks. For this, the utility of training these networks from scratch or only fine tuning pre-trained networks is evaluated. All this has been applied to classifying elements of interest in images of buildings with architectural heritage value. As no datasets of this type, suitable for network training, have been located, a new dataset has been created and made available to the public. Promising results have been obtained in terms of accuracy and it is considered that the application of these techniques can contribute significantly to the digital documentation of architectural heritage.

show abstract

“…In [17,18], the user is requested to draw a bounding box around the food items, while in [19], the user must mark the initial seeds before starting to grow segments. In this work, a semi-automatic method is designed which can be run on smartphones in a user-friendly manner.…”

Section: Segmentationmentioning

confidence: 99%

A New Approach to Image-Based Estimation of Food Volume

et al. 2017

View full text Add to dashboard Cite

Abstract:A balanced diet is the key to a healthy lifestyle and is crucial for preventing or dealing with many chronic diseases such as diabetes and obesity. Therefore, monitoring diet can be an effective way of improving people's health. However, manual reporting of food intake has been shown to be inaccurate and often impractical. This paper presents a new approach to food intake quantity estimation using image-based modeling. The modeling method consists of three steps: firstly, a short video of the food is taken by the user's smartphone. From such a video, six frames are selected based on the pictures' viewpoints as determined by the smartphone's orientation sensors. Secondly, the user marks one of the frames to seed an interactive segmentation algorithm. Segmentation is based on a Gaussian Mixture Model alongside the graph-cut algorithm. Finally, a customized image-based modeling algorithm generates a point-cloud to model the food. At the same time, a stochastic object-detection method locates a checkerboard used as size/ground reference. The modeling algorithm is optimized such that the use of six input images still results in an acceptable computation cost. In our evaluation procedure, we achieved an average accuracy of 92% on a test set that includes images of different kinds of pasta and bread, with an average processing time of about 23 s.

show abstract

Food image recognition using deep convolutional network with pre-training and fine-tuning

Cited by 267 publications

References 9 publications

Food/Non-food Image Classification and Food Categorization using Pre-Trained GoogLeNet Model

Food/Non-food Image Classification and Food Categorization using Pre-Trained GoogLeNet Model

Classification of Architectural Heritage Images Using Deep Learning Techniques

A New Approach to Image-Based Estimation of Food Volume

Contact Info

Product

Resources

About