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

Somdip Dey, Suman Saha, Amit Singh, Klaus D. Mcdonald-Maier

Research output: Other contributionpeer-review

Abstract

Fruit and vegetable classification using Convolutional Neural Networks (CNNs) has become apopular application in the agricultural industry, however, to the best of our knowledge no pre-viously recorded study has designed and evaluated such an application on a mobile platform. Inthis paper, we propose a power-efficient CNN model, FruitVegCNN, to perform classification offruits and vegetables in a mobile multi-processor system-on-a-chip (MPSoC). We also evaluatedthe 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 efficacyand power efficiency of our proposed CNN architecture
Original languageEnglish
Number of pages19
DOIs
Publication statusPublished - 23 Jul 2020

Fingerprint

Dive into the research topics of 'FruitVegCNN: Power- and Memory-Efficient Classification of Fruits & Vegetables Using CNN in Mobile MPSoC'. Together they form a unique fingerprint.

Cite this