Articles producció científica> Enginyeria Informàtica i Matemàtiques

Hierarchical Approach to Classify Food Scenes in Egocentric Photo-Streams

  • Identification data

    Identifier: imarina:6170416
    Authors:
    Martinez, Estefania TalaveraLeyva-Vallina, MariaSarker, Md. Mostafa KamalPuig, DomenecPetkov, NicolaiRadeva, Petia
    Abstract:
    Recent studies have shown that the environment where people eat can affect their nutritional behavior [1]. In this paper, we provide automatic tools for personalized analysis of a person's health habits by the examination of daily recorded egocentric photo-streams. Specifically, we propose a new automatic approach for the classification of food-related environments, that is able to classify up to 15 such scenes. In this way, people can monitor the context around their food intake in order to get an objective insight into their daily eating routine. We propose a model that classifies food-related scenes organized in a semantic hierarchy. Additionally, we present and make available a new egocentric dataset composed of more than 33 000 images recorded by a wearable camera, over which our proposed model has been tested. Our approach obtains an accuracy and F-score of 56% and 65%, respectively, clearly outperforming the baseline methods.
  • Others:

    Author, as appears in the article.: Martinez, Estefania Talavera; Leyva-Vallina, Maria; Sarker, Md. Mostafa Kamal; Puig, Domenec; Petkov, Nicolai; Radeva, Petia;
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Puig Valls, Domènec Savi
    Keywords: Visualization Tools Semantics Scenes classification Recognition Monitoring Lifestyle Informatics Food scenes Feature extraction Egocentric vision Eating habits Cameras
    Abstract: Recent studies have shown that the environment where people eat can affect their nutritional behavior [1]. In this paper, we provide automatic tools for personalized analysis of a person's health habits by the examination of daily recorded egocentric photo-streams. Specifically, we propose a new automatic approach for the classification of food-related environments, that is able to classify up to 15 such scenes. In this way, people can monitor the context around their food intake in order to get an objective insight into their daily eating routine. We propose a model that classifies food-related scenes organized in a semantic hierarchy. Additionally, we present and make available a new egocentric dataset composed of more than 33 000 images recorded by a wearable camera, over which our proposed model has been tested. Our approach obtains an accuracy and F-score of 56% and 65%, respectively, clearly outperforming the baseline methods.
    Thematic Areas: Medical informatics Mathematical & computational biology Health information management Health informatics General medicine Engenharias iv Electrical and electronic engineering Educação física Computer science, interdisciplinary applications Computer science, information systems Computer science applications Ciência da computação Biotechnology
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    ISSN: 21682208
    Author's mail: domenec.puig@urv.cat
    Author identifier: 0000-0002-0562-4205
    Record's date: 2023-07-31
    Papper version: info:eu-repo/semantics/acceptedVersion
    Papper original source: Ieee Journal Of Biomedical And Health Informatics. 24 (3): 866-877
    APA: Martinez, Estefania Talavera; Leyva-Vallina, Maria; Sarker, Md. Mostafa Kamal; Puig, Domenec; Petkov, Nicolai; Radeva, Petia; (2020). Hierarchical Approach to Classify Food Scenes in Egocentric Photo-Streams. Ieee Journal Of Biomedical And Health Informatics, 24(3), 866-877. DOI: 10.1109/JBHI.2019.2922390
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2020
    Publication Type: Journal Publications
  • Keywords:

    Biotechnology,Computer Science Applications,Computer Science, Information Systems,Computer Science, Interdisciplinary Applications,Electrical and Electronic Engineering,Health Informatics,Health Information Management,Mathematical & Computational Biology,Medical Informatics
    Visualization
    Tools
    Semantics
    Scenes classification
    Recognition
    Monitoring
    Lifestyle
    Informatics
    Food scenes
    Feature extraction
    Egocentric vision
    Eating habits
    Cameras
    Medical informatics
    Mathematical & computational biology
    Health information management
    Health informatics
    General medicine
    Engenharias iv
    Electrical and electronic engineering
    Educação física
    Computer science, interdisciplinary applications
    Computer science, information systems
    Computer science applications
    Ciência da computação
    Biotechnology
  • Documents:

  • Cerca a google

    Search to google scholar