Automatic Expansion of a Food Image Dataset Leveraging Existing Categories with Domain Adaptation

Kawano, Yoshiyuki; Yanai, Keiji

doi:10.1007/978-3-319-16199-0_1

Cited by 180 publications

(122 citation statements)

References 18 publications

Supporting

Mentioning

122

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%

“…The food images were selected from already existing and publicly available food image datasets, including Food-101 [17], UEC-FOOD-100 [20] and UEC-FOOD-256 [22]. The food images were selected in such a way that they could cover a wide variety of food items.…”

Section: Dataset 1: Food-5kmentioning

confidence: 99%

“…The 11 categories are: Bread, Dairy products, Dessert, Egg, Fried food, Meat, Noodles/Pasta, Rice, Seafood, Soup and Vegetable/Fruit. The dataset was mainly collected from existing food image datasets including Food-101 [17], UEC-FOOD-100 [20] and UEC-FOOD-256 [22]. For certain categories (Diary products and Vegetable/Fruit), we downloaded images from social media sites, Flickr and Instagram.…”

Section: Dataset 2: Food-11mentioning

confidence: 99%

See 2 more Smart Citations

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

169

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%

Section: Dataset 1: Food-5kmentioning

confidence: 99%

Section: Dataset 2: Food-11mentioning

confidence: 99%

See 1 more Smart Citation

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

169

View full text Add to dashboard Cite

show abstract

“…On the other hand, Branson et al 12) proposed complementary use of AMT with object classifiers by giving AMT workers simple easy questions to tackle difficult fine-grained object classification. Kawano et al 61) proposed to use AMT after applying automatic image re-ranking based on domain-adaptation which utilizes the knowledge of existing image categories for automatic extension of food image database. Note that not all the AMT workers are trusty, and some of them try to cheat requesters to save their time.…”

Section: )mentioning

confidence: 99%

[Invited Paper] A Review of Web Image Mining

Yanai

2015

MTA

Self Cite

View full text Add to dashboard Cite

In this paper, we review works related to big visual data on the Web in the literature of computer vision and multimedia research regarding the following points: (1) Web image acquisition for construction of visual concept database for image/video recognition, (2) Web image application for visual concept analysis and data-driven computer graphics, and (3) real-world sensing through Web images to detect location-dependent and event-related visual information.

show abstract

“…The dataset contains 9, 060 images of 100 Japanese food categories. It has grown into UEC FOOD 256, which contains 31, 397 images of 256 categories [12]. One notable characteristic of these datasets is that bounding boxes indicating the location of foods in each image are also available.…”

Section: Related Workmentioning

confidence: 99%

Cookpad Image Dataset

Harashima¹,

Someya²,

Kikuta³

2017

Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

In food-related services, image information is as important as text information for users. For example, in recipe search services, users find recipes based not only on text but also images. To promote studies on food images, many datasets have recently been published. However, they have the following three limitations: most of the datasets include only thousands of images, they only take account of images after cooking not during the cooking process, and the images are not linked to any recipes. In this study, we construct the Cookpad Image Dataset, a novel collection of food images taken from Cookpad, the largest recipe search service in the world. The dataset includes more than 1.64 million images after cooking, and it is the largest among existing datasets. Additionally, it includes more than 3.10 million images taken during the cooking process. To the best of our knowledge, there are no datasets that include such images. Furthermore, the dataset is designed to link to an existing recipe corpus and thus, a variety of recipe texts, such as the title, description, ingredients, and process, is available for each image. In this paper, we described our dataset's features in detail and compared it with existing datasets.

show abstract

Automatic Expansion of a Food Image Dataset Leveraging Existing Categories with Domain Adaptation

Cited by 180 publications

References 18 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

[Invited Paper] A Review of Web Image Mining

Cookpad Image Dataset

Contact Info

Product

Resources

About