Research on bamboo defect segmentation and classification based on improved u-net network

In this paper, computer vision technology is used to quickly and accurately identify and classify the surface defects of processed bamboo, which overcomes the low efficiency of manual identification. The datasets consist of 6360 defective bamboo mat images of four categories taken by the author at the same position, which are split at a ratio of 8:2 for training and testing. In this experiment, we improved the U-net to segment the datasets and use VGG16, GoogLeNet and ResNet50 with attention mechanism for classification and comparison. The experimental results show that the accuracy of this method is 5.65% higher than the commonly used neural network method. The highest accuracy rate is 99.2%.

Degradation features of archaeological wood surface to deep inside a case study on wooden boards of marquis of haihun’s outer coffin

Although researches have been carried on the bio-chemical deterioration of archaeological wood, still the degradation of archaeological wood is so complicated to fully understand. One essential question is how archaeological wood of large volume would degrade from surface to deep inside and why. The recently unearthed outer coffin of Marquis of Haihun, buried for over 1800 years, gave us a great opportunity to investigate this question. The degradation features were analyzed with methods of optical microscopy, Fourier Transform Infrared Spectroscopy (FT-IR), X-ray diffraction (XRD), viscosimetry, and determination of physical properties of wood. The results, including the microstructures of wood fibers, wood components, degree of polymerization and crystallinity of cellulose, and shrinkage of wood, unanimously show that the sapwood of the board is worst degraded, the surface layer of the heartwood is degraded to a higher extent than the inner part, and it tends to degrade more easily along the axial direction.

Alterations in the anatomy and chemical structure of archaeological wood from a tomb of northern china due to different fungal rots

This paper aims to identify the decay types and investigate the chemical alterations in the three types of fungal decayed archaeological wood from Dongshan Han Tomb M6 (ca. 200-100 B.C.) in Taiyuan City, China. Microscopy, FT-IR, 13C NMR and XPS were adopted to reveal the features of the samples. The results show that from the microscopic and chemical perspectives, these samples are consistent with the characteristics of brown-rot, white-rot and soft-rot. However, all the samples show the accumulation of carboxylic acids or carboxylate salts from extensive oxidation of lignin, which were not observed in artificial fungal decayed wood. Moreover, different fungal decay types and pH values of the samples corresponding to the alternative forms of carboxylic acid or carboxylate salt are considered to be influenced by combined factors, such as the position in the tomb, groundwater level, moisture content, oxygen availability, etc. This study may provide a reference for the deterioration and conservation of fungal decayed wooden artifacts in the tomb of northern China where alkaline loess is the main soil type.