MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle East

<p>Automatic food recognition systems have been receiving increasing attention in the research community with the advancements in inductive learning (e.g., classification in computer vision) due to their applicability in the healthcare and hospitality industry. However, food recognition is cha...

Full description

Saved in:
Bibliographic Details
Main Author: Mohammed Yusuf Ansari (16904523) (author)
Other Authors: Marwa Qaraqe (10135172) (author)
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513560852299776
author Mohammed Yusuf Ansari (16904523)
author2 Marwa Qaraqe (10135172)
author2_role author
author_facet Mohammed Yusuf Ansari (16904523)
Marwa Qaraqe (10135172)
author_role author
dc.creator.none.fl_str_mv Mohammed Yusuf Ansari (16904523)
Marwa Qaraqe (10135172)
dc.date.none.fl_str_mv 2023-01-05T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2023.3234519
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/MEFood_A_Large-Scale_Representative_Benchmark_of_Quotidian_Foods_for_the_Middle_East/24056235
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Data management and data science
Machine learning
Benchmark testing
Feature extraction
Neural networks
Task analysis
Deep learning
Computer vision
Computational modeling
Food recognition
Benchmark dataset
Middle Eastern cuisine
dc.title.none.fl_str_mv MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle East
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Automatic food recognition systems have been receiving increasing attention in the research community with the advancements in inductive learning (e.g., classification in computer vision) due to their applicability in the healthcare and hospitality industry. However, food recognition is challenging due to its fine-grained nature and its high correlation with culture, geo-location, and language. To make food recognition systems feasible for the Middle Eastern region, we present a large-scale dataset (MEFood) of commonly consumed food items in the Middle East, thereby providing a dataset for current development and establishing a benchmark for future research. We have also thoroughly examined the MEFood dataset highlighting its challenging aspects and its real-world nature. Additionally, we have conducted a thorough experimental study benchmarking the mainstream computer vision and mobile networks on classification, runtime, and resource utilization metrics. Our results highlight that EfficientNet-V2 achieves performance closer to the best-performing individual model on the MEFood dataset while having the least resource utilization and minimal inference times. Finally, we have performed a thorough error analysis study to glean additional insights about the networks and MEFood dataset.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3234519" target="_blank">https://dx.doi.org/10.1109/access.2023.3234519</a></p>
eu_rights_str_mv openAccess
id Manara2_822791d47bacda7da87642c6d1a03e02
identifier_str_mv 10.1109/access.2023.3234519
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24056235
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle EastMohammed Yusuf Ansari (16904523)Marwa Qaraqe (10135172)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationData management and data scienceMachine learningBenchmark testingFeature extractionNeural networksTask analysisDeep learningComputer visionComputational modelingFood recognitionBenchmark datasetMiddle Eastern cuisine<p>Automatic food recognition systems have been receiving increasing attention in the research community with the advancements in inductive learning (e.g., classification in computer vision) due to their applicability in the healthcare and hospitality industry. However, food recognition is challenging due to its fine-grained nature and its high correlation with culture, geo-location, and language. To make food recognition systems feasible for the Middle Eastern region, we present a large-scale dataset (MEFood) of commonly consumed food items in the Middle East, thereby providing a dataset for current development and establishing a benchmark for future research. We have also thoroughly examined the MEFood dataset highlighting its challenging aspects and its real-world nature. Additionally, we have conducted a thorough experimental study benchmarking the mainstream computer vision and mobile networks on classification, runtime, and resource utilization metrics. Our results highlight that EfficientNet-V2 achieves performance closer to the best-performing individual model on the MEFood dataset while having the least resource utilization and minimal inference times. Finally, we have performed a thorough error analysis study to glean additional insights about the networks and MEFood dataset.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3234519" target="_blank">https://dx.doi.org/10.1109/access.2023.3234519</a></p>2023-01-05T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2023.3234519https://figshare.com/articles/journal_contribution/MEFood_A_Large-Scale_Representative_Benchmark_of_Quotidian_Foods_for_the_Middle_East/24056235CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240562352023-01-05T00:00:00Z
spellingShingle MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle East
Mohammed Yusuf Ansari (16904523)
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Data management and data science
Machine learning
Benchmark testing
Feature extraction
Neural networks
Task analysis
Deep learning
Computer vision
Computational modeling
Food recognition
Benchmark dataset
Middle Eastern cuisine
status_str publishedVersion
title MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle East
title_full MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle East
title_fullStr MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle East
title_full_unstemmed MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle East
title_short MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle East
title_sort MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle East
topic Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Data management and data science
Machine learning
Benchmark testing
Feature extraction
Neural networks
Task analysis
Deep learning
Computer vision
Computational modeling
Food recognition
Benchmark dataset
Middle Eastern cuisine