Search

This study aims to verify the wood classification performance of convolutional neural networks (CNNs), such as VGG16, ResNet50, GoogLeNet, and basic CNN architectures, and to investigate the factors affecting classification performance. A dataset from 10 softwood species consisted of 200 cross-sectional micrographs each from the total part, earlywood, and latewood of each species. We used 80% and 20% of each dataset for training and testing, respectively. To improve the performance of the architectures, the dataset was augmented, and the differences in classification performance before and after augmentation were compared. The four architectures showed a high classification accuracy of over 90% between species, and the accuracy increased with increasing epochs. However, the starting points of the accuracy, loss, and training speed increments differed according to the architecture. The latewood dataset showed the highest accuracy. The epochs and augmented datasets also positively affected accuracy, whereas the total part and non-augmented datasets had a negative effect on accuracy. Additionally, the augmented dataset tended to derive stable results and reached a convergence point earlier. In the present study, an augmented latewood dataset was the most important factor affecting classification performance and should be used for training CNNs. [ABSTRACT FROM AUTHOR]

The quantitative anatomical characteristics of Quercus variabilis virgin cork grown in Korea were observed by scanning electron microscopy and compared with Quercus suber reproduction cork from Portugal to obtain basic data for further utilization of domestic cork resources in Korean cork industries. Q. variabilis virgin cork showed a smaller growth ring width and higher latecork percentage than Q. suber reproduction cork. Q. variabilis showed a smaller proportion of cork cells and a higher proportion of lenticular channels than Q. suber, whereas sclereid and dark-brown zones were found only in Q. variabilis. The frequency of pentagonal cork cells in the transverse and radial sections was higher in the cork of Q. suber than in Q. variabilis. In the tangential section, Q. variabilis displayed a lower frequency of heptagonal cells and a higher frequency of pentagonal cells than Q. suber.Q. variabilis cork had a smaller cell width, lumen diameter, cell wall thickness, prism base edge and area, total cell volume, and solid volume of the cell wall than Q. suber cork. The fractional solid volume and number of cells per cm3 were higher in Q. variabilis than Q. suber. [ABSTRACT FROM AUTHOR]