Bayesian deep learning for semantic segmentation of food images

Aguilar, Eduardo; Nagarajan, B.; Remeseiro, Beatriz; Radeva, Petia

doi:10.1016/j.compeleceng.2022.108380

Cited by 16 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main reason was the difficulty encountered in data processing using AI algorithms. Currently, the existing convolutional neural networks (CNNs), which are the central components of AI algorithms for food image processing, are almost all designed for rectangular images [ 38 , 43 , 46 , 47 , 48 , 49 ]. Although isolated studies have been conducted for circular images, e.g., [ 50 , 51 , 52 ], they require training using the same type of images, which are not widely available.…”

Section: Discussionmentioning

confidence: 99%

Improved Wearable Devices for Dietary Assessment Using a New Camera System

Sun

Jia

Chen

et al. 2022

Sensors

View full text Add to dashboard Cite

An unhealthy diet is strongly linked to obesity and numerous chronic diseases. Currently, over two-thirds of American adults are overweight or obese. Although dietary assessment helps people improve nutrition and lifestyle, traditional methods for dietary assessment depend on self-report, which is inaccurate and often biased. In recent years, as electronics, information, and artificial intelligence (AI) technologies advanced rapidly, image-based objective dietary assessment using wearable electronic devices has become a powerful approach. However, research in this field has been focused on the developments of advanced algorithms to process image data. Few reports exist on the study of device hardware for the particular purpose of dietary assessment. In this work, we demonstrate that, with the current hardware design, there is a considerable risk of missing important dietary data owing to the common use of rectangular image screen and fixed camera orientation. We then present two designs of a new camera system to reduce data loss by generating circular images using rectangular image sensor chips. We also present a mechanical design that allows the camera orientation to be adjusted, adapting to differences among device wearers, such as gender, body height, and so on. Finally, we discuss the pros and cons of rectangular versus circular images with respect to information preservation and data processing using AI algorithms.

show abstract

Section: Discussionmentioning

confidence: 99%

Improved Wearable Devices for Dietary Assessment Using a New Camera System

Sun

Jia

Chen

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Then, weight is estimated using shape template and area-based weight estimation for foods to extract the nutrient content for dietary monitoring and assessment. Aguilar et al [17] proposed Bayesian deep learning for food semantic segmentation and assessed the uncertainty in the predictions for the improvements of healthcare technologies and dietary monitoring. In this paper, Bayesian inference is approximated using the MC-dropout [18] method by placing a dropout layer after each residual block of the network.…”

Section: Related Workmentioning

confidence: 99%

Semantic food segmentation for health monitoring

Hussain

Ortis

Polosa

et al. 2023

Fifteenth International Conference on Machine Vision (ICMV 2022)

View full text Add to dashboard Cite

This paper presents semantic food segmentation to detect individual food items in an image. The presented approach has been developed in the context of the FoodRec project, which aims to study and develop an automatic framework to track and monitor the dietary habits of people, during their smoke quitting protocol. The goal of food segmentation is to train a model that can look at the images of food items and infer semantic information to recognize individual food items present in an image. In this contribution, we propose a novel Convolutional Deconvolutional Pyramid Network for food segmentation to understand the semantic information of an image at a pixel level. This network employs convolution and deconvolution layers to build a feature pyramid and achieves high-level semantic feature map representation. As a consequence, the novel semantic segmentation network generates a dense and precise segmentation map of the input food image. Furthermore, the proposed method demonstrated significant improvements on a well-known public benchmark dataset.

show abstract

“…Achieving on these datasets a mIoU of 71.79% and 65.13% respectively. A more recent work, [39] proposed a Bayesian version of DeepLabv3+ and GourmetNet [37] to perform multi-class segmentation of foods.…”

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

Bayesian deep learning for semantic segmentation of food images

Cited by 16 publications

References 8 publications

Improved Wearable Devices for Dietary Assessment Using a New Camera System

Improved Wearable Devices for Dietary Assessment Using a New Camera System

Semantic food segmentation for health monitoring

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

Contact Info

Product

Resources

About