Repository logo
 
Publication

Comparison of Image Processing and Classification Methods for a Better Diet Decision-Making

2023-06-29Book part Restricted access
Simple item page
dc.contributor.authorAbbasi, Maryam
dc.contributor.authorCardoso, Filipe
dc.contributor.authorMartins, Pedro
dc.date.accessioned2024-01-09T13:25:10Z
dc.date.available2024-01-09T13:25:10Z
dc.date.issued2023-06-29
dc.description.abstractThis paper aims to explore the use of different deep learning techniques, specifically convolutional neural networks (CNNs), for dietary assessment through image food recognition and compare their performance to the human visual system (HVS). Currently, there are three main techniques for using CNNs in this task: training a network from scratch; using an off-the-shelf pre-trained network; and performing unsupervised pre-training with supervised adjustments. In this study, the authors evaluate the performance of three CNN models with varying numbers of parameters (5,000 to 160 million) based on dataset size and spatial image context. The authors also consider human knowledge and classification to compare the performance of the CNNs to the HVS. They find that while the CNNs make errors across different food classes, the HVS tends to make semantic errors with specific food classes. As a result, the HVS shows more consistency in its answers. Overall, the findings suggest that the HVS is more accurate when the dataset is diverse, while the CNN performs better when the dataset is focused on a particular niche. In conclusion, this study provides empirical evidence that machine learning can be more efficient than the HVS in certain tasks but also highlights the strengths and limitations of both approaches. The authors suggest that combining CNNs with other classification techniques, such as bagof-words, may be a promising approach for improving the accuracy of dietary assessment through image food recognition.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationAbbasi, M., Cardoso, F. & Martins, P. (2023). Comparison of image processing and classification methods for a better diet decision-making In: I. Rojas, O. Valenzuela, F. Ruiz Rojas, L.J. Herrera & F. Ortuño (Eds), Bioinformatics and Biomedical Engineering. IWBBIO 2023. Lecture Notes in Computer Science, vol 13919 (pp.309-403). Springer. doi: https://doi.org/10.1007/978-3-031-34953-9_31pt_PT
dc.identifier.doi10.1007/978-3-031-34953-9_31pt_PT
dc.identifier.isbn978-3-031-34952-2
dc.identifier.urihttp://hdl.handle.net/10400.15/4668
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherSpringerpt_PT
dc.subjectComparept_PT
dc.subjectImage processingpt_PT
dc.subjectMachine learningpt_PT
dc.subjectImage Classificationpt_PT
dc.subjectGoogLeNetpt_PT
dc.subjectInception-v3pt_PT
dc.subjectResNetpt_PT
dc.subjectBag-of-wordspt_PT
dc.titleComparison of Image Processing and Classification Methods for a Better Diet Decision-Makingpt_PT
dc.typebook part
dspace.entity.typePublication
oaire.citation.conferencePlaceCham, Switzerlandpt_PT
oaire.citation.endPage403pt_PT
oaire.citation.startPage390pt_PT
oaire.citation.titleComparison of Image Processing and Classification Methods for a Better Diet Decision-Makingpt_PT
oaire.citation.volume13919pt_PT
person.familyNameGonçalves Cardoso
person.givenNameFilipe
person.identifier19-AQJEAAAAJ
person.identifier.ciencia-id8219-19E8-C070
person.identifier.orcid0000-0002-3916-5182
person.identifier.scopus-author-id57486516500
rcaap.rightsrestrictedAccesspt_PT
rcaap.typebookPartpt_PT
relation.isAuthorOfPublicationf108cbea-41e4-459d-86e3-3225c293e4a6
relation.isAuthorOfPublication.latestForDiscoveryf108cbea-41e4-459d-86e3-3225c293e4a6

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2023_iwbbio___How_Well_Can_Deep_Learning_and_Human_Visual_System_Recognize_Food_Images (1).pdf
Size:
1.46 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections