Food image recognition with deep convolutional features

Kawano, Yoshiyuki; Yanai, Keiji

doi:10.1145/2638728.2641339

Cited by 176 publications

(112 citation statements)

References 5 publications

Supporting

Mentioning

112

Contrasting

Order By: Relevance

“…To combine different image representations, there are two existing approaches: (1) concatenate different image representations with pre-normalization or post-normalization and feed into one classifier; (2) feed different image representations into different classifiers with following late fusion. Regarding the food image recognition problem, [30] adopted the first approach with pre-normalization; [33][34][35][36] adopted the second approach with late fusion. In this work, we concatenate two local feature image representations (R SIFT , R Color ) as R Low and two distance feature image representations (R SIFT−LDC , R Color−LDC ) as R LDC separately with pre-normalization, then feed R Low and R LDC into two linear SVMs classifiers [37].…”

Section: Final Image Representationmentioning

confidence: 99%

“…The protocol ensures that no image of any given food item ever appears in both the training and testing sets and guarantees that food images are selected from different restaurants on different days. In our experiment, to have a fair comparison, we employed common settings in feature extraction and coding as in the literature [28,30,36]. For SLIC Superpixels Segmentation, we set n s to 300 for all images.…”

Section: Experiments On Pfid Databasementioning

confidence: 99%

“…The total number of food images in UEC Food 100 is 12,905. We followed the experiment protocol as stated in [36]. For each category we selected 20 images as testing data, and the rest are training data.…”

Section: Experiments On Uec Food 100 Databasementioning

confidence: 99%

“…For fair comparison, we employed the same settings for feature extraction and coding as in [36]. We extracted SIFT at the scale of every 6 pixels and the same color descriptors as in [36].…”

Section: Experiments On Uec Food 100 Databasementioning

confidence: 99%

See 3 more Smart Citations

Food Image Recognition via Superpixel Based Low-Level and Mid-Level Distance Coding for Smart Home Applications

2017

View full text Add to dashboard Cite

Abstract:Food image recognition is a key enabler for many smart home applications such as smart kitchen and smart personal nutrition log. In order to improve living experience and life quality, smart home systems collect valuable insights of users' preferences, nutrition intake and health conditions via accurate and robust food image recognition. In addition, efficiency is also a major concern since many smart home applications are deployed on mobile devices where high-end GPUs are not available. In this paper, we investigate compact and efficient food image recognition methods, namely low-level and mid-level approaches. Considering the real application scenario where only limited and noisy data are available, we first proposed a superpixel based Linear Distance Coding (LDC) framework where distinctive low-level food image features are extracted to improve performance. On a challenging small food image dataset where only 12 training images are available per category, our framework has shown superior performance in both accuracy and robustness. In addition, to better model deformable food part distribution, we extend LDC's feature-to-class distance idea and propose a mid-level superpixel food parts-to-class distance mining framework. The proposed framework show superior performance on a benchmark food image datasets compared to other low-level and mid-level approaches in the literature.

show abstract

Section: Final Image Representationmentioning

confidence: 99%

Section: Experiments On Pfid Databasementioning

confidence: 99%

Section: Experiments On Uec Food 100 Databasementioning

confidence: 99%

Section: Experiments On Uec Food 100 Databasementioning

confidence: 99%

See 2 more Smart Citations

Food Image Recognition via Superpixel Based Low-Level and Mid-Level Distance Coding for Smart Home Applications

2017

View full text Add to dashboard Cite

show abstract

“…In comparison, IFV [6], which is a kind of hand-crafted image representation, has achieved competitive performance to the CNN in fine-grained image recognition tasks involving food image recognition [10], [11]. IFV represents an image by the distribution of low-level image features using higherorder statistics of local image descriptors including SIFT and SURF.…”

Section: Related Workmentioning

confidence: 99%

Food Image Recognition Using Covariance of Convolutional Layer Feature Maps

Tatsuma

Aono

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Atsushi TATSUMA†a) and Masaki AONO †b) , Members SUMMARY Recent studies have obtained superior performance in image recognition tasks by using, as an image representation, the fully connected layer activations of Convolutional Neural Networks (CNN) trained with various kinds of images. However, the CNN representation is not very suitable for fine-grained image recognition tasks involving food image recognition. For improving performance of the CNN representation in food image recognition, we propose a novel image representation that is comprised of the covariances of convolutional layer feature maps. In the experiment on the ETHZ Food-101 dataset, our method achieved 58.65% averaged accuracy, which outperforms the previous methods such as the Bag-of-Visual-Words Histogram, the Improved Fisher Vector, and CNN-SVM.

show abstract

Proposal of New Activation Function in Deep Image Prior

Segawa

Hayashi

Fujii

2020

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

We propose a new activation function and verify its performance in a deep image prior network. The new activation function is RSwish, which is Swish with a random slope for x < 0 assuming that the input value of the activation function is x. In addition, we manipulate the probability of the random number and observe the effect. As a result, we found that RSwish can perform better than Swish by manipulating probabilities according to the degree of color change in the image. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

show abstract

Food image recognition with deep convolutional features

Cited by 176 publications

References 5 publications

Food Image Recognition via Superpixel Based Low-Level and Mid-Level Distance Coding for Smart Home Applications

Food Image Recognition via Superpixel Based Low-Level and Mid-Level Distance Coding for Smart Home Applications

Food Image Recognition Using Covariance of Convolutional Layer Feature Maps

Proposal of New Activation Function in Deep Image Prior

Contact Info

Product

Resources

About