Identifying Images of Invasive Hydrangea Using Pre-Trained Deep Convolutional Neural Networks

International Journal of Academic Engineering Research (IJAER), 3(3), 28-36, March 2019

9 Pages Posted: 8 May 2019

See all articles by Belal A . M. Ashqar

Belal A . M. Ashqar

Al-Azhar University, Gaza

Samy S. Abu-Naser

Al-Azhar University, Gaza

Date Written: March 2019

Abstract

Invasive species are threatening habitats of native species in many countries around the world. The current methods of monitoring them depend on expert knowledge. Trained scientists visit designated areas and take note of the species inhabiting them. Using such a highly qualified workforce is expensive, time inefficient and insufficient since humans cannot cover large areas when sampling. In this paper, machine learning based approach is presented for identifying images of invasive hydrangea (a beautiful invasive species original of Asia) with a dataset that contains approximately 3,800 images taken in a Brazilian national forest and in some of the pictures there is Hydrangea. A deep learning technique that extensively applied to image recognition was used. Our trained model achieved an accuracy of 99.71% on a held-out test set, demonstrating the feasibility of this approach.

Keywords: Invasive Species, Classification, Deep Learning

Suggested Citation

Ashqar, Belal A . M. and Abu-Naser, Samy S., Identifying Images of Invasive Hydrangea Using Pre-Trained Deep Convolutional Neural Networks (March 2019). International Journal of Academic Engineering Research (IJAER), 3(3), 28-36, March 2019. Available at SSRN: https://ssrn.com/abstract=3369016

Belal A . M. Ashqar

Al-Azhar University, Gaza ( email )

Jamal A. El Naser St.
Gaza, P.O. Box 1
Palestine

Samy S. Abu-Naser (Contact Author)

Al-Azhar University, Gaza ( email )

Jamal A. El Naser St.
Gaza, P.O. Box 1
Palestine

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
52
Abstract Views
218
rank
407,628
PlumX Metrics