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.
College of Engineering| College of Forest Resources
Department of Sustainable Bioproducts
Center for Advanced Vehicular Systems
wood identification, machine-learning, smartphone, macro lens, Inception-ResNet, convolutional neural networks (CNN)
Lopes, D.J. V; Burgreen, G.W.; Entsminger, E.D. North American Hardwoods Identification Using Machine-Learning. Forests 2020, 11(3), 298.