A deep convolutional neural network for food detection and recognition

Mohammed A. Subhi, Sawal Hamid Md Ali

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we propose a new deep convolutional neural network (CNN) configuration to detect and recognize local food images. Various types of food with different color and texture reflect the fact that the food image recognition is considered a challenging task. However, deep learning has been widely used as an efficient image recognition method, and CNN is the contemporary approach for deep learning to be implemented. CNN has been optimized to the tasks of food detection and recognition with few modifications. We present a new dataset of the most consumed local Malaysian food items which was collected from publicly available Internet sources including but not limited to, image search engines. For evaluation of recognition performance, CNN achieved significantly higher accuracy than traditional approaches with manually extracted features. Additionally, it was found out that convolution masks show that the features of food color dominate the features map. For the process of food detection, CNN also exhibited considerably higher accuracy than other conventional methods.

Original languageEnglish
Title of host publication2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages284-287
Number of pages4
ISBN (Electronic)9781538624715
DOIs
Publication statusPublished - 24 Jan 2019
Event2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Kuching, Malaysia
Duration: 3 Dec 20186 Dec 2018

Publication series

Name2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings

Conference

Conference2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018
CountryMalaysia
CityKuching
Period3/12/186/12/18

Fingerprint

food
Neural networks
Food
Image recognition
learning
Color
Learning
color
Search Engine
Masks
Search engines
Recognition (Psychology)
Convolution
convolution integrals
Internet
engines
masks
textures
Textures
evaluation

Keywords

  • Convolutional neural network
  • Deep learning
  • Food detection
  • Food recognition

ASJC Scopus subject areas

  • Biomedical Engineering
  • Medicine (miscellaneous)
  • Health Informatics
  • Instrumentation

Cite this

Subhi, M. A., & Md Ali, S. H. (2019). A deep convolutional neural network for food detection and recognition. In 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings (pp. 284-287). [08626720] (2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IECBES.2018.08626720

A deep convolutional neural network for food detection and recognition. / Subhi, Mohammed A.; Md Ali, Sawal Hamid.

2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 284-287 08626720 (2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Subhi, MA & Md Ali, SH 2019, A deep convolutional neural network for food detection and recognition. in 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings., 08626720, 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 284-287, 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018, Kuching, Malaysia, 3/12/18. https://doi.org/10.1109/IECBES.2018.08626720
Subhi MA, Md Ali SH. A deep convolutional neural network for food detection and recognition. In 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 284-287. 08626720. (2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings). https://doi.org/10.1109/IECBES.2018.08626720
Subhi, Mohammed A. ; Md Ali, Sawal Hamid. / A deep convolutional neural network for food detection and recognition. 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 284-287 (2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings).
@inproceedings{cc68cde0ab9641d894a26e009b35fb49,
title = "A deep convolutional neural network for food detection and recognition",
abstract = "In this paper, we propose a new deep convolutional neural network (CNN) configuration to detect and recognize local food images. Various types of food with different color and texture reflect the fact that the food image recognition is considered a challenging task. However, deep learning has been widely used as an efficient image recognition method, and CNN is the contemporary approach for deep learning to be implemented. CNN has been optimized to the tasks of food detection and recognition with few modifications. We present a new dataset of the most consumed local Malaysian food items which was collected from publicly available Internet sources including but not limited to, image search engines. For evaluation of recognition performance, CNN achieved significantly higher accuracy than traditional approaches with manually extracted features. Additionally, it was found out that convolution masks show that the features of food color dominate the features map. For the process of food detection, CNN also exhibited considerably higher accuracy than other conventional methods.",
keywords = "Convolutional neural network, Deep learning, Food detection, Food recognition",
author = "Subhi, {Mohammed A.} and {Md Ali}, {Sawal Hamid}",
year = "2019",
month = "1",
day = "24",
doi = "10.1109/IECBES.2018.08626720",
language = "English",
series = "2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "284--287",
booktitle = "2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings",
address = "United States",

}

TY - GEN

T1 - A deep convolutional neural network for food detection and recognition

AU - Subhi, Mohammed A.

AU - Md Ali, Sawal Hamid

PY - 2019/1/24

Y1 - 2019/1/24

N2 - In this paper, we propose a new deep convolutional neural network (CNN) configuration to detect and recognize local food images. Various types of food with different color and texture reflect the fact that the food image recognition is considered a challenging task. However, deep learning has been widely used as an efficient image recognition method, and CNN is the contemporary approach for deep learning to be implemented. CNN has been optimized to the tasks of food detection and recognition with few modifications. We present a new dataset of the most consumed local Malaysian food items which was collected from publicly available Internet sources including but not limited to, image search engines. For evaluation of recognition performance, CNN achieved significantly higher accuracy than traditional approaches with manually extracted features. Additionally, it was found out that convolution masks show that the features of food color dominate the features map. For the process of food detection, CNN also exhibited considerably higher accuracy than other conventional methods.

AB - In this paper, we propose a new deep convolutional neural network (CNN) configuration to detect and recognize local food images. Various types of food with different color and texture reflect the fact that the food image recognition is considered a challenging task. However, deep learning has been widely used as an efficient image recognition method, and CNN is the contemporary approach for deep learning to be implemented. CNN has been optimized to the tasks of food detection and recognition with few modifications. We present a new dataset of the most consumed local Malaysian food items which was collected from publicly available Internet sources including but not limited to, image search engines. For evaluation of recognition performance, CNN achieved significantly higher accuracy than traditional approaches with manually extracted features. Additionally, it was found out that convolution masks show that the features of food color dominate the features map. For the process of food detection, CNN also exhibited considerably higher accuracy than other conventional methods.

KW - Convolutional neural network

KW - Deep learning

KW - Food detection

KW - Food recognition

UR - http://www.scopus.com/inward/record.url?scp=85062796104&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062796104&partnerID=8YFLogxK

U2 - 10.1109/IECBES.2018.08626720

DO - 10.1109/IECBES.2018.08626720

M3 - Conference contribution

T3 - 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings

SP - 284

EP - 287

BT - 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -