Multi-Task Learning for Food Identification and Analysis with Deep Convolutional Neural Networks

Zhang, Xijin; Lu, Yifan; Zhang, Song-Hai

doi:10.1007/s11390-016-1642-6

Cited by 54 publications

(21 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To our best knowledge, there has never been a DCNN-based food recognition algorithm developed for Korean food. One of the challenges we faced was the unique characteristics of Korean foods [13]. Input images were different in terms of shape, texture, size and color as the Korean foods lack a typical or generalized layout.…”

Section: Discussionmentioning

confidence: 99%

“…A Convolutional Neural Network (CNN) usually consists of convolutional layers and pooling layers [13]. Notations w and h represent width and height, ch is the RGB color channels of the input image I (w, h, ch) .…”

Section: Methodsmentioning

confidence: 99%

“…In addition, two training schemas (20 and 40 epochs) were implemented to determine the different behaviors of the model. Dropout is used to prevent overfitting in neural networks [13]. The dropout layer was used twice within the model to reduce overfitting and both dropout layers had a 0.4 equal rate during training.…”

Section: Methodsmentioning

confidence: 99%

“…Currently, in Korea, PAPI or CAPI-based nutrition surveys have been performed, but there is a growing demand for mobile device-based dietary assessment tools. However, Asian foods including Korean foods, include a greater variety of cooking methods and a higher number of ingredients than those in Western foods [13]. Furthermore, some similar Korean foods may look different while some entirely different Korean foods look very similar, which makes the identification of food items from images difficult [14].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The development of food image detection and recognition model of Korean food for mobile dietary management

et al. 2019

View full text Add to dashboard Cite

BACKGROUND/OBJECTIVESThe aim of this study was to develop Korean food image detection and recognition model for use in mobile devices for accurate estimation of dietary intake.SUBJECTS/METHODSWe collected food images by taking pictures or by searching web images and built an image dataset for use in training a complex recognition model for Korean food. Augmentation techniques were performed in order to increase the dataset size. The dataset for training contained more than 92,000 images categorized into 23 groups of Korean food. All images were down-sampled to a fixed resolution of 150 × 150 and then randomly divided into training and testing groups at a ratio of 3:1, resulting in 69,000 training images and 23,000 test images. We used a Deep Convolutional Neural Network (DCNN) for the complex recognition model and compared the results with those of other networks: AlexNet, GoogLeNet, Very Deep Convolutional Neural Network, VGG and ResNet, for large-scale image recognition.RESULTSOur complex food recognition model, K-foodNet, had higher test accuracy (91.3%) and faster recognition time (0.4 ms) than those of the other networks.CONCLUSIONThe results showed that K-foodNet achieved better performance in detecting and recognizing Korean food compared to other state-of-the-art models.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The development of food image detection and recognition model of Korean food for mobile dietary management

et al. 2019

View full text Add to dashboard Cite

show abstract

“…However, it remains challenging for artificial intelligent agents to do so. During the past two decades, many researchers have considered various related fields, such as image aesthetic assessment [2][3][4] and food image analysis [5][6][7]. Some have already explored aesthetic assessment of food images [8], but they resorted to hand-crafted visual features and did not perform quantitative studies on a large-scale dataset.…”

Section: Introductionmentioning

confidence: 99%

Learning to assess visual aesthetics of food images

et al. 2020

View full text Add to dashboard Cite

Distinguishing aesthetically pleasing food photos from others is an important visual analysis task for social media and ranking systems related to food. Nevertheless, aesthetic assessment of food images remains a challenging and relatively unexplored task, largely due to the lack of related food image datasets and practical knowledge. Thus, we present the Gourmet Photography Dataset (GPD), the first large-scale dataset for aesthetic assessment of food photos. It contains 24,000 images with corresponding binary aesthetic labels, covering a large variety of foods and scenes. We also provide a non-stationary regularization method to combat over-fitting and enhance the ability of tuned models to generalize. Quantitative results from extensive experiments, including a generalization ability test, verify that neural networks trained on the GPD achieve comparable performance to human experts on the task of aesthetic assessment. We reveal several valuable findings to support further research and applications related to visual aesthetic analysis of food images. To encourage further research, we have made the GPD publicly available at https://github.com/Openning07/GPA.

show abstract

Literature Survey—Food Recognition and Calorie Measurement Using Image Processing and Machine Learning Techniques

Reddy¹,

Kumari²,

Muralidharan³

et al. 2019

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Multi-Task Learning for Food Identification and Analysis with Deep Convolutional Neural Networks

Cited by 54 publications

References 18 publications

The development of food image detection and recognition model of Korean food for mobile dietary management

The development of food image detection and recognition model of Korean food for mobile dietary management

Learning to assess visual aesthetics of food images

Literature Survey—Food Recognition and Calorie Measurement Using Image Processing and Machine Learning Techniques

Contact Info

Product

Resources

About