WOOD RESEARCH Volume 64, Number 5, 2019
Widyanto Dwi Nugroho, Rini Pujiarti, and Novena Puteri Tiyasa

Wood anatomical characteristics of agarwood-producing species (Aquilaria sp.)

Aquilaria sp. is one of the tree species that produce agarwood. Agarwood is a kind of wood that has high content of fragrant resin and high economic values. Sufficient information about wood anatomical characteristic of agarwood-producing species is essential in agarwood trading, especially for identification and verification of wood. Therefore, this research aims to observe wood anatomical features of Aquilaria sp. and to observe its cell morphology. Five trees and five seedlings of Aquilaria sp. were used for the experiment. The results showed that the wood of Aquilaria sp. can be determined according to IAWA List of Hardwood for Identification with anatomical features nos. 2, 5, 10, 13, 22, 24, 29, 30, 40, 48, 49, 52, 58, 62, 66, 68, 71, 79, 92, 97, 105/104, 112, 115 and 134. Furthermore, seedling and trees of Aquilaria sp. have similar anatomical features but they have some differences on the cells morphology.

WOOD RESEARCH Volume 66, Number 1, 2021
Tao He, Shibiao Mu, Houkui Zhou, and Junguo Hu

Wood species identification based on an ensemble of deep convolution neural networks

Our paper proposed an ensemble framework of combining three deep convolution neural networks (CNN). This method was inspired by network in network. Transfer learning used to accelerate training and deeper layers of network. Nine different CNN architectures were trained and evaluated in two wood macroscopic images datasets. After two times of 30 epochs training, our proposed network obtained 100% test rate in our dataset, which including 8 kinds of wood species and 918 images. The proposed method achieved 98.81% test recognition rate after three times training with 30 epochs in other dataset, which including 41 kinds of wood species and 11,984 images. Results showed that magnification macroscopic images can be instead of microscopic images in wood species identification, and our proposed ensemble of deep CNN can be used for wood species identification.

WOOD RESEARCH Volume 66, Number 2, 2021
Yan Yang, He Sun, Shuang Yang, Aifeng Wang, Rui Zhao, Wei Wang, Yiming He, Bin Li, Binxin Zhang, and Qian Wu

Internal cause analysis of damage of wooden components in danxia temple ancient architectures: Tree species

In the study, part of degraded wooden components of Danxia Temple ancient architectures in China were indentified through the bright field microscope, and chemical compositions in cell walls were observed using polarized and fluorescence lights, respectively. The results showed that samples were belonged to Quercus spp., Ulmus spp., Salix spp., and Populus spp., respectively. Cellulose composition in Quercus spp. was seriously consumed by brown decay fungi, cellulose and lignin compositions in Ulmus spp. were consumed by white decay fungi under polarized and fluorescence light observations. All of these four kind of tree species themselves were easily vulnerable to be attacked by insects.