The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Exibições de texto completo
73
Nos últimos anos, o aumento da alimentação saudável levou ao surgimento de vários aplicativos de gerenciamento de alimentos que possuem função de reconhecimento de imagem para registrar automaticamente as refeições diárias. No entanto, a maioria das funções de reconhecimento de imagem nos aplicativos existentes não são diretamente úteis para fotos de alimentos com vários pratos e não podem estimar automaticamente as calorias dos alimentos. Enquanto isso, as metodologias de reconhecimento de imagens avançaram muito com o advento da Rede Neural Convolucional (CNN). A CNN melhorou a precisão de vários tipos de tarefas de reconhecimento de imagem, como classificação e detecção de objetos. Portanto, propomos a estimativa de calorias alimentares baseada na CNN para fotos de alimentos com vários pratos. Nosso método estima a localização dos pratos e as calorias dos alimentos simultaneamente, por meio do aprendizado multitarefa de detecção de pratos de alimentos e estimativa de calorias dos alimentos com uma única CNN. Espera-se alcançar alta velocidade e tamanho de rede pequeno por estimativa simultânea em uma única rede. Como atualmente não existe um conjunto de dados de fotos de alimentos de vários pratos anotados com caixas delimitadoras e calorias de alimentos, neste trabalho usamos dois tipos de conjuntos de dados alternadamente para treinar uma única CNN. Para os dois tipos de conjuntos de dados, usamos fotos de alimentos de vários pratos anotadas com caixas delimitadoras e fotos de alimentos de um único prato com calorias alimentares. Nossos resultados mostraram que nosso método multitarefa alcançou maior precisão, maior velocidade e menor tamanho de rede do que um modelo sequencial de detecção de alimentos e estimativa de calorias alimentares.
Takumi EGE
The University of Electro-Communications
Keiji YANAI
The University of Electro-Communications
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Takumi EGE, Keiji YANAI, "Simultaneous Estimation of Dish Locations and Calories with Multi-Task Learning" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 7, pp. 1240-1246, July 2019, doi: 10.1587/transinf.2018CEP0004.
Abstract: In recent years, a rise in healthy eating has led to various food management applications which have image recognition function to record everyday meals automatically. However, most of the image recognition functions in the existing applications are not directly useful for multiple-dish food photos and cannot automatically estimate food calories. Meanwhile, methodologies on image recognition have advanced greatly because of the advent of Convolutional Neural Network (CNN). CNN has improved accuracies of various kinds of image recognition tasks such as classification and object detection. Therefore, we propose CNN-based food calorie estimation for multiple-dish food photos. Our method estimates dish locations and food calories simultaneously by multi-task learning of food dish detection and food calorie estimation with a single CNN. It is expected to achieve high speed and small network size by simultaneous estimation in a single network. Because currently there is no dataset of multiple-dish food photos annotated with both bounding boxes and food calories, in this work we use two types of datasets alternately for training a single CNN. For the two types of datasets, we use multiple-dish food photos annotated with bounding boxes and single-dish food photos with food calories. Our results showed that our multi-task method achieved higher accuracy, higher speed and smaller network size than a sequential model of food detection and food calorie estimation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018CEP0004/_p
Copiar
@ARTICLE{e102-d_7_1240,
author={Takumi EGE, Keiji YANAI, },
journal={IEICE TRANSACTIONS on Information},
title={Simultaneous Estimation of Dish Locations and Calories with Multi-Task Learning},
year={2019},
volume={E102-D},
number={7},
pages={1240-1246},
abstract={In recent years, a rise in healthy eating has led to various food management applications which have image recognition function to record everyday meals automatically. However, most of the image recognition functions in the existing applications are not directly useful for multiple-dish food photos and cannot automatically estimate food calories. Meanwhile, methodologies on image recognition have advanced greatly because of the advent of Convolutional Neural Network (CNN). CNN has improved accuracies of various kinds of image recognition tasks such as classification and object detection. Therefore, we propose CNN-based food calorie estimation for multiple-dish food photos. Our method estimates dish locations and food calories simultaneously by multi-task learning of food dish detection and food calorie estimation with a single CNN. It is expected to achieve high speed and small network size by simultaneous estimation in a single network. Because currently there is no dataset of multiple-dish food photos annotated with both bounding boxes and food calories, in this work we use two types of datasets alternately for training a single CNN. For the two types of datasets, we use multiple-dish food photos annotated with bounding boxes and single-dish food photos with food calories. Our results showed that our multi-task method achieved higher accuracy, higher speed and smaller network size than a sequential model of food detection and food calorie estimation.},
keywords={},
doi={10.1587/transinf.2018CEP0004},
ISSN={1745-1361},
month={July},}
Copiar
TY - JOUR
TI - Simultaneous Estimation of Dish Locations and Calories with Multi-Task Learning
T2 - IEICE TRANSACTIONS on Information
SP - 1240
EP - 1246
AU - Takumi EGE
AU - Keiji YANAI
PY - 2019
DO - 10.1587/transinf.2018CEP0004
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2019
AB - In recent years, a rise in healthy eating has led to various food management applications which have image recognition function to record everyday meals automatically. However, most of the image recognition functions in the existing applications are not directly useful for multiple-dish food photos and cannot automatically estimate food calories. Meanwhile, methodologies on image recognition have advanced greatly because of the advent of Convolutional Neural Network (CNN). CNN has improved accuracies of various kinds of image recognition tasks such as classification and object detection. Therefore, we propose CNN-based food calorie estimation for multiple-dish food photos. Our method estimates dish locations and food calories simultaneously by multi-task learning of food dish detection and food calorie estimation with a single CNN. It is expected to achieve high speed and small network size by simultaneous estimation in a single network. Because currently there is no dataset of multiple-dish food photos annotated with both bounding boxes and food calories, in this work we use two types of datasets alternately for training a single CNN. For the two types of datasets, we use multiple-dish food photos annotated with bounding boxes and single-dish food photos with food calories. Our results showed that our multi-task method achieved higher accuracy, higher speed and smaller network size than a sequential model of food detection and food calorie estimation.
ER -