Efficient Image Recognition and Retrieval on IoT-Assisted Energy-Constrained Platforms From Big Data Repositories

Irfan Mehmood, Amin Ullah, Khan Muhammad, Der Jiunn Deng, Weizhi Meng, Fadi Al-Turjman, Muhammad Sajjad, Victor Hugo C. De Albuquerque

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The advanced computational capabilities of many resource constrained devices, such as smartphones have enabled various research areas including image retrieval from big data repositories for numerous Internet of Things (IoT) applications. The major challenges for image retrieval using smartphones in an IoT environment are the computational complexity and storage. To deal with big data in IoT environment for image retrieval, this paper proposes a light-weighted deep learning-based system for energy-constrained devices. The system first detects and crops face regions from an image using Viola-Jones algorithm with additional face and nonface classifier to eliminate the miss-detection problem. Second, the system uses convolutional layers of a cost effective pretrained CNN model with defined features to represent faces. Next, features of the big data repository are indexed to achieve a faster matching process for real-time retrieval. Finally, Euclidean distance is used to find similarity between query and repository images. For experimental evaluation, we created a local facial images dataset, including both single and group facial images. This dataset can be used by other researchers as a benchmark for comparison with other real-time facial image retrieval systems. The experimental results show that our proposed system outperforms other state-of-the-art feature extraction methods in terms of efficiency and retrieval for IoT-assisted energy-constrained platforms.

Original languageEnglish
Article number8629991
Pages (from-to)9246-9255
Number of pages10
JournalIEEE Internet of Things Journal
Volume6
Issue number6
DOIs
Publication statusPublished - 2019 Dec

Fingerprint

Image recognition
Image retrieval
Smartphones
Crops
Feature extraction
Computational complexity
Classifiers
Internet of things
Big data
Costs

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Cite this

Mehmood, I., Ullah, A., Muhammad, K., Deng, D. J., Meng, W., Al-Turjman, F., ... De Albuquerque, V. H. C. (2019). Efficient Image Recognition and Retrieval on IoT-Assisted Energy-Constrained Platforms From Big Data Repositories. IEEE Internet of Things Journal, 6(6), 9246-9255. [8629991]. https://doi.org/10.1109/JIOT.2019.2896151
Mehmood, Irfan ; Ullah, Amin ; Muhammad, Khan ; Deng, Der Jiunn ; Meng, Weizhi ; Al-Turjman, Fadi ; Sajjad, Muhammad ; De Albuquerque, Victor Hugo C. / Efficient Image Recognition and Retrieval on IoT-Assisted Energy-Constrained Platforms From Big Data Repositories. In: IEEE Internet of Things Journal. 2019 ; Vol. 6, No. 6. pp. 9246-9255.
@article{5a878d6d3c9248c8aa976ea797c7d3d8,
title = "Efficient Image Recognition and Retrieval on IoT-Assisted Energy-Constrained Platforms From Big Data Repositories",
abstract = "The advanced computational capabilities of many resource constrained devices, such as smartphones have enabled various research areas including image retrieval from big data repositories for numerous Internet of Things (IoT) applications. The major challenges for image retrieval using smartphones in an IoT environment are the computational complexity and storage. To deal with big data in IoT environment for image retrieval, this paper proposes a light-weighted deep learning-based system for energy-constrained devices. The system first detects and crops face regions from an image using Viola-Jones algorithm with additional face and nonface classifier to eliminate the miss-detection problem. Second, the system uses convolutional layers of a cost effective pretrained CNN model with defined features to represent faces. Next, features of the big data repository are indexed to achieve a faster matching process for real-time retrieval. Finally, Euclidean distance is used to find similarity between query and repository images. For experimental evaluation, we created a local facial images dataset, including both single and group facial images. This dataset can be used by other researchers as a benchmark for comparison with other real-time facial image retrieval systems. The experimental results show that our proposed system outperforms other state-of-the-art feature extraction methods in terms of efficiency and retrieval for IoT-assisted energy-constrained platforms.",
author = "Irfan Mehmood and Amin Ullah and Khan Muhammad and Deng, {Der Jiunn} and Weizhi Meng and Fadi Al-Turjman and Muhammad Sajjad and {De Albuquerque}, {Victor Hugo C.}",
year = "2019",
month = "12",
doi = "10.1109/JIOT.2019.2896151",
language = "English",
volume = "6",
pages = "9246--9255",
journal = "IEEE Internet of Things Journal",
issn = "2327-4662",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

Mehmood, I, Ullah, A, Muhammad, K, Deng, DJ, Meng, W, Al-Turjman, F, Sajjad, M & De Albuquerque, VHC 2019, 'Efficient Image Recognition and Retrieval on IoT-Assisted Energy-Constrained Platforms From Big Data Repositories', IEEE Internet of Things Journal, vol. 6, no. 6, 8629991, pp. 9246-9255. https://doi.org/10.1109/JIOT.2019.2896151

Efficient Image Recognition and Retrieval on IoT-Assisted Energy-Constrained Platforms From Big Data Repositories. / Mehmood, Irfan; Ullah, Amin; Muhammad, Khan; Deng, Der Jiunn; Meng, Weizhi; Al-Turjman, Fadi; Sajjad, Muhammad; De Albuquerque, Victor Hugo C.

In: IEEE Internet of Things Journal, Vol. 6, No. 6, 8629991, 12.2019, p. 9246-9255.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Efficient Image Recognition and Retrieval on IoT-Assisted Energy-Constrained Platforms From Big Data Repositories

AU - Mehmood, Irfan

AU - Ullah, Amin

AU - Muhammad, Khan

AU - Deng, Der Jiunn

AU - Meng, Weizhi

AU - Al-Turjman, Fadi

AU - Sajjad, Muhammad

AU - De Albuquerque, Victor Hugo C.

PY - 2019/12

Y1 - 2019/12

N2 - The advanced computational capabilities of many resource constrained devices, such as smartphones have enabled various research areas including image retrieval from big data repositories for numerous Internet of Things (IoT) applications. The major challenges for image retrieval using smartphones in an IoT environment are the computational complexity and storage. To deal with big data in IoT environment for image retrieval, this paper proposes a light-weighted deep learning-based system for energy-constrained devices. The system first detects and crops face regions from an image using Viola-Jones algorithm with additional face and nonface classifier to eliminate the miss-detection problem. Second, the system uses convolutional layers of a cost effective pretrained CNN model with defined features to represent faces. Next, features of the big data repository are indexed to achieve a faster matching process for real-time retrieval. Finally, Euclidean distance is used to find similarity between query and repository images. For experimental evaluation, we created a local facial images dataset, including both single and group facial images. This dataset can be used by other researchers as a benchmark for comparison with other real-time facial image retrieval systems. The experimental results show that our proposed system outperforms other state-of-the-art feature extraction methods in terms of efficiency and retrieval for IoT-assisted energy-constrained platforms.

AB - The advanced computational capabilities of many resource constrained devices, such as smartphones have enabled various research areas including image retrieval from big data repositories for numerous Internet of Things (IoT) applications. The major challenges for image retrieval using smartphones in an IoT environment are the computational complexity and storage. To deal with big data in IoT environment for image retrieval, this paper proposes a light-weighted deep learning-based system for energy-constrained devices. The system first detects and crops face regions from an image using Viola-Jones algorithm with additional face and nonface classifier to eliminate the miss-detection problem. Second, the system uses convolutional layers of a cost effective pretrained CNN model with defined features to represent faces. Next, features of the big data repository are indexed to achieve a faster matching process for real-time retrieval. Finally, Euclidean distance is used to find similarity between query and repository images. For experimental evaluation, we created a local facial images dataset, including both single and group facial images. This dataset can be used by other researchers as a benchmark for comparison with other real-time facial image retrieval systems. The experimental results show that our proposed system outperforms other state-of-the-art feature extraction methods in terms of efficiency and retrieval for IoT-assisted energy-constrained platforms.

UR - http://www.scopus.com/inward/record.url?scp=85071283999&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071283999&partnerID=8YFLogxK

U2 - 10.1109/JIOT.2019.2896151

DO - 10.1109/JIOT.2019.2896151

M3 - Article

AN - SCOPUS:85071283999

VL - 6

SP - 9246

EP - 9255

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

SN - 2327-4662

IS - 6

M1 - 8629991

ER -