Microstructure identification based on vessel pores feature extraction of high-value hardwood species

Abstract

Because of the diversity of vessel pores in different hardwood species, they are important for wood species identification. In this paper, a Micro CT was used to collect wood images. The experiment was based on six wood types, Pterocarpus macrocarpus, Pterocarpus erinaceus, Dalbergia latifolia, Dalbergia frutescens var. tomentosa, Pterocarpus indicus, and Pterocarpus soyauxii. One-thousand cross-sectional images of 2042 px × 1640 px were collected for each species. One pixel represents 1.95 µm of the real physical dimension. The level set geometric active contour model was used to obtain the contour of the vessel pores. Combined with a variety of morphological processing methods, the binary images of the vessel pores were obtained. The features of the binary images were extracted for classification. Classifiers such as BP neural network and support vector machine were used, the number, roundness, area, perimeter, and other characteristic parameters of the vessel pores were classified, and the accuracy rate was more than 98.9%. The distribution and arrangement of the vessel pores of six kinds of hardwood were obtained through the level set geometric active contour model and image morphology. Then BP neural network and support vector machine were used for realizing the classification of hardwood species.

Rapid Identification for the Pterocarpus Bracelet by Three-Step Infrared Spectrum Method

“…The existing methods of wood recognition are mainly based on anatomy, genetic biology and chemotaxonomical analysis. Traditional anatomy identification is well-established and most frequently used, which distinguishes wood samples by comparing their macroscopic and microscopic anatomical features [ 8 , 9 , 10 ], but it cannot accurately discriminate wood samples at the species scale [ 11 , 12 ]. Although the genetic method of DNA barcoding has been demonstrated to be effective in wood recognition even at the species scale, its wide application is limited by some technological challenges concerning DNA extraction, barcode selection and reference database [ 13 , 14 , 15 ], whereas the chemotaxonomical analysis exhibits more flexibility and potential for efficient identification, which is mainly based on various qualitative and quantitative fingerprint information of wood samples or their extractives obtained by chemical characterization techniques involving mass spectrometry [ 3 ], fluorescence [ 16 , 17 ], nuclear magnetic resonance spectroscopy [ 18 ], Fourier transform infrared spectroscopy (FTIR) [ 19 , 20 ] or a specific combination of some of the above [ 21 , 22 , 23 ].…”