Food Calorie and Nutrition Analysis System based on Mask R-CNN

Chiang, Meng-Lin; Wu, Chia-An; Feng, Jian-Kai; Fang, Chiung‐Yao; Chen, Sei-Wang

doi:10.1109/iccc47050.2019.9064257

Cited by 10 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1: Meng-Lin Chiang, Jiankai Feng, Chia-An Wu, Chiung-Yao Fang, et al [4] To give health information on the food we eat, this paper introduces a system that takes advantage of the widespread use of mobile devices. To identify food classes, and food masks, and label food calories and nutrients, this work employs food photos as input to a system based on Mask R-CNN.…”

Section: Literature Reviewmentioning

confidence: 99%

Food Processing and Calorie Detection

Solanke

2024

IJSREM

View full text Add to dashboard Cite

Food is one of the most basic needs of all living things on Earth. People want the food they eat to be pure, fresh, and of a standard quality. The food processing industry's automation and standards-setting mechanisms ensure the quality of the food. Worldwide, people are becoming increasingly sensitive to food these days. An unbalanced diet can result in weight gain, obesity, diabetes, and other problems. As a result, numerous algorithms were developed to assess food images and calculate calories. This method proposes a powerful deep Convolutional Neural Network (CNN) architecture to locate and recognize local food photographs. Food is available in a wide range of flavors, textures, and shapes, which emphasizes how challenging it is to recognize food in pictures. Conversely, deep learning has become more and more well-liked as a successful picture-recognition method. We created a system for identifying foods and estimating calories, which uses a picture of a meal as input to determine a person's daily caloric intake. We provide a fresh dataset of the most well-liked foods, collected from publicly available web resources. Convolutional neural networks, or CNNs, are used as classifiers to identify foods, and we can determine a food's calorie content based on its gram weight. Keywords — Calorie estimation, deep learning, convolutional neural networks, and food detection and recognition.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Food Processing and Calorie Detection

Solanke

2024

IJSREM

View full text Add to dashboard Cite

show abstract

“…Chiang et al. [ 36 ] proposed a model based on a mask region-based convolutional neural network (Mask-RCNN) with a union post-processing technique.…”

Section: Related Workmentioning

confidence: 99%

“…Some studies have focused on simultaneous localization and recognition of foods using object detection models, like [34], which uses Fast-RCNN, and [35], which uses YOLO. Chiang et al [36] proposed a model based on a mask region-based convolutional neural network (Mask-RCNN) with a union post-processing technique.…”

Section: Segmentation Model For Food Imagementioning

confidence: 99%

mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments

Baban A Erep,

Chaari

2023

Sensors

View full text Add to dashboard Cite

Recent decades have witnessed the development of vision-based dietary assessment (VBDA) systems. These systems generally consist of three main stages: food image analysis, portion estimation, and nutrient derivation. The effectiveness of the initial step is highly dependent on the use of accurate segmentation and image recognition models and the availability of high-quality training datasets. Food image segmentation still faces various challenges, and most existing research focuses mainly on Asian and Western food images. For this reason, this study is based on food images from sub-Saharan Africa, which pose their own problems, such as inter-class similarity and dishes with mixed-class food. This work focuses on the first stage of VBDAs, where we introduce two notable contributions. Firstly, we propose mid-DeepLabv3+, an enhanced food image segmentation model based on DeepLabv3+ with a ResNet50 backbone. Our approach involves adding a middle layer in the decoder path and SimAM after each extracted backbone feature layer. Secondly, we present CamerFood10, the first food image dataset specifically designed for sub-Saharan African food segmentation. It includes 10 classes of the most consumed food items in Cameroon. On our dataset, mid-DeepLabv3+ outperforms benchmark convolutional neural network models for semantic image segmentation, with an mIoU (mean Intersection over Union) of 65.20%, representing a +10.74% improvement over DeepLabv3+ with the same backbone.

show abstract

“…Some studies have focused on simultaneous localization and recognition of foods using object detection models like [34] which uses Fast-RCNN and [35] which uses YOLO. Chiang et al [36] proposed a model based on Mask Region-based Convolutional Neural Network (Mask-RCNN) with a union post-processing technique.…”

Section: Segmentation Model For Food Imagementioning

confidence: 99%

mid-DeepLabv3+ : A Novel Approach for Image Semantic Segmentation applied to African Food Dietary Assessment

EREP,

CHAARI,

ELE

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent decades have seen the development of vision-based dietary assessment systems (VBDA). These systems generally consist of three main stages: food image analysis, portion estimation and nutrient derivation. The effectiveness of the initial step is highly dependent on the use of accurate segmentation and image recognition models, and the availability of high-quality training datasets. Food image segmentation still faces various challenges, while most existing research has focused mainly on Asian and Western food images. For this reason, this study is based on food images from sub-Saharan Africa, which pose their own problems, such as inter-class similarity and dishes presentation with mixed-class food. This work focuses on the first stage of VBDA, where we introduce two notable contributions. Firstly, we propose mid-DeepLabv3+, an enhanced food image segmentation model based on DeepLabv3+ with a ResNet50 backbone. Our approach involves adding a middle layer in the decoder path and SimAM attention mechanism after each extracted backbone features layers. Secondly, we present CamerFood10, the first food images dataset specifically designed for sub-Saharan African food segmentation. It includes 10 classes of most consumed food items in Cameroon. On our dataset, mid-DeepLabv3+ outperforms existing image segmentation benchmark models with an mIoU (mean Intersection over Union) of 65.20\%, representing more than +10.74\% improvement over the DeepLabv3+ with the same backbone.

show abstract

Food Calorie and Nutrition Analysis System based on Mask R-CNN

Cited by 10 publications

References 8 publications

Food Processing and Calorie Detection

Food Processing and Calorie Detection

mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments

mid-DeepLabv3+ : A Novel Approach for Image Semantic Segmentation applied to African Food Dietary Assessment

Contact Info

Product

Resources

About