Automatic Wood Species Identification of Korean Softwood Based on Convolutional Neural Networks

Abstract

Automatic wood species identification systems have enabled fast and accurate identification of wood species outside of specialized laboratories with well-trained experts on wood species identification. Conventional automatic wood species identification systems consist of two major parts: a feature extractor and a classifier. Feature extractors require hand-engineering to obtain optimal features to quantify the content of an image. A Convolutional Neural Network (CNN), which is one of the Deep Learning methods, trained for wood species can extract intrinsic feature representations and classify them correctly. It usually outperforms classifiers built on top of extracted features with a hand-tuning process.We developed an automatic wood species identification system utilizing CNN models such as LeNet, MiniVGGNet, and their variants. A smartphone camera was used for obtaining macroscopic images of rough sawn surfaces from cross sections of woods. Five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch) were under classification by the CNN models. The highest and most stable CNN model was LeNet3 that is two additional layers added to the original LeNet architecture. The accuracy of species identification by LeNet3 architecture for the five Korean softwood species was 99.3%. The result showed the automatic wood species identification system is sufficiently fast and accurate as well as small to be deployed to a mobile device such as a smartphone.

Using Deep Learning to Identify Costa Rican Native Tree Species From Wood Cut Images

“…Below is an overview of the most recent publications in this field. Kwon et al (2017) proposed six different CNN models (variants of LeNet and MiniVGGNet architetures) to identify five softwood species from Korea. A smartphone camera was used for obtaining macroscopic wood images.…”

Geometric and Topological Bases of a New Classification of Wood Vascular Tissues, Part 2: Classification of Vessels According to Their Grouping

“…The classification of wood species using texture characteristics of transverse cross-section microscopic images is the focus of the current study. Some authors, such as [6,7], use the images as inputs for convolutional neural network (CNN), where the features are extracted by the classifier. Other authors explore and extract features using standard texture methods such as Local Binary Patterns (LBP) [2,8], Local Phase Quantization (LPQ) [9], gray level co-occurrence matrix [10] or Mathematical morphological operation and K-L divergence [11].…”

“…This classifier can be combined with BP neural network and Mahalanobis distance (MD) to perform hardwood species classification [11]. In recent years, a deep learning classifier, such as CNN architectures, has started to be exploited [6,7,12].…”

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

“…Recently, CNNs have been employed to classify wood species using datasets containing wood images. 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.…”