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 language | English |
|---|---|
| Article number | 8629991 |
| Pages (from-to) | 9246-9255 |
| Number of pages | 10 |
| Journal | IEEE Internet of Things Journal |
| Volume | 6 |
| Issue number | 6 |
| DOIs | |
| Publication status | Published - 2019 Dec |
Fingerprint
All Science Journal Classification (ASJC) codes
- Signal Processing
- Information Systems
- Hardware and Architecture
- Computer Science Applications
- Computer Networks and Communications
Cite this
}
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 journal › Article
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 -