Title

End-grain of 10 North American hardwoods

Abstract

This technical note determines the feasibility of using an InceptionV4_ResNetV2 convolutional neural network (CNN) to correctly identify hardwood species from macroscopic images. The method is composed of a commodity smartphone fitted with a 14× macro lens for photography. The end-grains of ten different North American hardwood species were photographed to create a dataset of 1709 images. The stratified 5-fold cross-validation machine-learning method was used, in which the number of testing samples varied from 341 to 342. Data augmentation was performed on-the-fly for each training set by rotating, zooming, and flipping images. It was found that the CNN could correctly identify hardwood species based on macroscopic images of its end-grain with an adjusted accuracy of 92.60%. With the current growing of machine-learning field, this model can then be readily deployed in a mobile application for field wood identification.

Publisher

Forests

First Page

298

Publication Date

3-7-2020

College

College of Forest Resources| College of Engineering

Department

Department of Sustainable Bioproducts

Research Center

Center for Advanced Vehicular Systems

Keywords

wood identification, machine-learning, smartphone, macro lens, Inception-ResNet, convolutional neural networks (CNN)

This document is currently not available here.

Share

COinS