Performance Enhancement of Automatic Wood Classification of Korean Softwood by Ensembles of Convolutional Neural Networks

Abstract

In our previous study, the LeNet3 model successfully classified images from the transverse surfaces of five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch). However, a practical limitation exists in our system stemming from the nature of the training images obtained from the transverse plane of the wood species. In real-world applications, it is necessary to utilize images from the longitudinal surfaces of lumber. Thus, we improved our model by training it with images from the longitudinal and transverse surfaces of lumber. Because the longitudinal surface has complex but less distinguishable features than the transverse surface, the classification performance of the LeNet3 model decreases when we include images from the longitudinal surfaces of the five Korean softwood species. To remedy this situation, we adopt ensemble methods that can enhance the classification performance. Herein, we investigated the use of ensemble models from the LeNet and MiniVGGNet models to automatically classify the transverse and longitudinal surfaces of the five Korean softwoods. Experimentally, the best classification performance was achieved via an ensemble model comprising the LeNet2, LeNet3, and MiniVGGNet4 models trained using input images of 128 × 128 × 3 pixels via the averaging method. The ensemble model showed an F1 score greater than 0.98. The classification performance for the longitudinal surfaces of Korean pine and Korean red pine was significantly improved by the ensemble model compared to individual convolutional neural network models such as LeNet3.

Computer Vision-Based Wood Identification: A Review

“…The identification accuracy obtained was 99.3%. The authors reported that the software weight of the CNN created is small enough for installation on a mobile device such as a smartphone; -Maintaining the objective of ensuring field applicability, Kwon et al [133] acknowledged the real-world limitations of not including longitudinal wood surfaces. Using mobile device cameras to obtain macroscopic images, they applied a combination of models, obtaining the best results with LeNet2, LeNet3 and MiniVGGNet4.…”

Convolutional neural network performance and the factors affecting performance for classification of seven Quercus species using sclereid characteristics in the bark

“…Kwon et al (2017) reported the possibility and performance of softwood species classification using CNN-based models, such as LeNet and miniVGGNet. Kwon et al (2019) improved the performance of automated species classification by using a CNN with ensemble methods. Yang et al (2019) also employed a CNN with ensemble methods for classifying Korean softwood species using datasets from near-infrared spectra (NIR) analysis results and macroscopic images of radial sections.…”

Evaluation Of Test Specimen Surface Preparation On Macroscopic Computer Vision Wood Identification

“…In traditional macroscopic wood identification (Panshin and de Zeeuw 1980;Hoadley 1990;Wheeler and Baas 1998;Ruffinatto et al 2015), experts with extensive training view anatomical features on the transverse, and often radial and/or tangential surface(s), and make taxonomical determinations based on the size, frequency, combinations, and/or patterns of features they observe (Miller et al 2002;Wiedenhoeft 2011;Ar evalo et al 2020;Ar evalo and Wiedenhoeft 2022). In CVWID, images with relevant wood anatomical features are processed by a model to make an identification (Khalid et al 2008;Esteban et al 2009;Filho et al 2014;Kwon et al 2017Kwon et al , 2019Rosa da Silva et al 2017;Barmpoutis et al 2018;Figueroa-Mata et al 2018;Tang et al 2018;Damayanti et al 2019;de Andrade et al 2020;He et al 2020;Lens et al 2020;Souza et al 2020;Fabija nska et al 2021;Wu et al 2021). While a taxonomic determination can be based on microscopic or macroscopic features in the wood specimen, the focus of this study is macroscopic wood identification, and CVWID will refer to imagebased macroscopic wood identification.…”