Proceedings of the 1st International Multi-Disciplinary Conference Theme: Sustainable Development and Smart Planning, IMDC-SDSP 2020, Cyperspace, 28-30 June 2020

Research Article

Cloud-Based ImageNet Object Recognition For Mobile Devices

Download476 downloads
  • @INPROCEEDINGS{10.4108/eai.28-6-2020.2297916,
        author={Akram  Saeed and Dan  Schonfeld},
        title={Cloud-Based ImageNet Object Recognition For Mobile Devices},
        proceedings={Proceedings of the 1st International Multi-Disciplinary Conference Theme: Sustainable Development and Smart Planning, IMDC-SDSP 2020, Cyperspace, 28-30 June 2020},
        publisher={EAI},
        proceedings_a={IMDC-SDSP},
        year={2020},
        month={9},
        keywords={cloud computing convolutional neural network object recognition},
        doi={10.4108/eai.28-6-2020.2297916}
    }
    
  • Akram Saeed
    Dan Schonfeld
    Year: 2020
    Cloud-Based ImageNet Object Recognition For Mobile Devices
    IMDC-SDSP
    EAI
    DOI: 10.4108/eai.28-6-2020.2297916
Akram Saeed1,*, Dan Schonfeld2
  • 1: Ninevah University
  • 2: Ninevah University1, University of Illinois at Chicago2
*Contact email: akram.saeed@uoninevah.edu.iq

Abstract

User reliance on real-time applications is continuously increasing as the use of smartphone devices has tremendously increased in day to day life within the past few years. Smartphone devices computation power has significantly increased as well, however, there are still some scalability, performance challenges and some complications with real-time application such as limited computation capabilities and battery life of mobile devices. In this paper, we propose a cloud-based object recognition through task offloading to a high-speed server. We explore this design extensively and demonstrate a real-time solution for object recognition framework on mobile devices using a Convolution neural network (CNN) leveraging the ImageNet dataset and by optimizing the offloading process to minimize the time and energy needed. This framework use the emerging the Android operating system as a platform to connect with an object recognition server where the CNN deep learning resides and process received images. Using this method will overcome the design limited capacity of mobile devices since object recognition algorithms require high-speed calculations