TechRxiv
guide.pdf (2.9 MB)
Download file

FruitVegCNN: Power- and Memory-Efficient Classification of Fruits & Vegetables Using CNN in Mobile MPSoC

Download (2.9 MB)
preprint
posted on 23.07.2020, 14:24 authored by Somdip DeySomdip Dey, Suman Saha, Amit Singh, Klaus D. Mcdonald-Maier

Fruit and vegetable classification using Convolutional Neural Networks (CNNs) has become a popular application in the agricultural industry, however, to the best of our knowledge no previously recorded study has designed and evaluated such an application on a mobile platform. In this paper, we propose a power-efficient CNN model, FruitVegCNN, to perform classification of fruits and vegetables in a mobile multi-processor system-on-a-chip (MPSoC). We also evaluated the efficacy of FruitVegCNN compared to popular state-of-the-art CNN models in real mobile plat- forms (Huawei P20 Lite and Samsung Galaxy Note 9) and experimental results show the efficacy and power efficiency of our proposed CNN architecture.

Funding

Robust remote sensing for multi-modal characterisation in nuclear and other extreme environments

Engineering and Physical Sciences Research Council

Find out more...

National Centre for Nuclear Robotics (NCNR)

Engineering and Physical Sciences Research Council

Find out more...

nosh/agri-tech-000001

History

Email Address of Submitting Author

somdip.dey@essex.ac.uk

ORCID of Submitting Author

0000-0001-6161-4637

Submitting Author's Institution

University of Essex

Submitting Author's Country

United Kingdom