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.
N1 - Funding Information:
Manuscript received January 9, 2019; accepted January 15, 2019. Date of publication January 30, 2019; date of current version December 11, 2019. This work was supported by the National Research Foundation of Korea through the Korea Government (Ministry of Science and ICT) under Grant 2018R1C1B5086294. (Corresponding author: Muhammad Sajjad.) I. Mehmood and K. Muhammad are with the Department of Software, School of Electronics and Information Engineering, Sejong University, Seoul 143-747, South Korea (e-mail: irfanmehmood@ieee.org; khan.muhammad@ieee.org).
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 -