Computer-assisted timber identification based on features extracted from microscopic wood sections

Abstract

Wood anatomy is one of the most important methods for timber identification. However, training wood anatomy experts is time-consuming, while at the same time the number of senior wood anatomists with broad taxonomic expertise is declining. Therefore, we want to explore how a more automated, computer-assisted approach can support accurate wood identification based on microscopic wood anatomy. For our exploratory research, we used an available image dataset that has been applied in several computer vision studies, consisting of 112 — mainly neotropical — tree species representing 20 images of transverse sections for each species. Our study aims to review existing computer vision methods and compare the success of species identification based on (1) several image classifiers based on manually adjusted texture features, and (2) a state-of-the-art approach for image classification based on deep learning, more specifically Convolutional Neural Networks (CNNs). In support of previous studies, a considerable increase of the correct identification is accomplished using deep learning, leading to an accuracy rate up to 95.6%. This remarkably high success rate highlights the fundamental potential of wood anatomy in species identification and motivates us to expand the existing database to an extensive, worldwide reference database with transverse and tangential microscopic images from the most traded timber species and their look-a-likes. This global reference database could serve as a valuable future tool for stakeholders involved in combatting illegal logging and would boost the societal value of wood anatomy along with its collections and experts.

WorldForestID: Addressing the need for standardized wood reference collections to support authentication analysis technologies; a way forward for checking the origin and identity of traded timber

“…(2020) provide a table of the proportion of the 7,371 anatomical descriptions in InsideWood with each anatomical character, and this gives a good indication of which ones have particular diagnostic value singly and in combination. As with macroscopy, expertise is necessary, and machine learning and other neural network methods are being investigated to aid or reduce the need for human expertise in order to improve point‐of‐contact identification of suspect wood (e.g., Lens et al., 2020; Martins et al., 2013; Silva et al., 2017). These developments do not eliminate the need for expert wood anatomists but provide alternative methods of identification in the current reality of the declining population of expert anatomists despite the increased global trade in wood products.…”

Computer vision-based wood identification and its expansion and contribution potentials in wood science: A review

“…In a comparative study of DL and conventional ML models [ 55 ], CNN-based models, Inception-v3 [ 165 ], SqueezeNet [ 164 ], ResNet [ 25 ], and DenseNet [ 166 ], all models achieved better performance than k-NN models trained with LBP or LPQ features. Lens et al [ 72 ] also reported that VGG16 and ResNet101 models had better classification performance for the UFPR dataset than those trained with texture features. The CNN with residual connections proposed by Fabijańska et al [ 65 ] identified 14 European trees better than other popular CNN architectures.…”

“…All wood image types can be used as data for identification. The most commonly used image types are macroscopic images [50,54,[62][63][64][65], X-ray computed tomographic (CT) images [66,67], stereograms [20,21,26,68,69], and micrographs [47,[70][71][72] (Fig. 2a).…”

“…In micrographs that provide microscopic information such as wood fibers, local features for extracting morphological characteristics of cells were preferred [48,74,79], and statistics related to the size, shape, and distribution of cells were also used for identification [27,59,61,80]. In contrast, convolutional neural networks (CNNs) were employed regardless of image type [29,65,72,81].…”

“…These characteristics make it suitable for wood identification. ANN has been used with large datasets [72,97,128], which supports DL methods such as CNN that are able to build more sophisticated models with larger amounts of data [53,55,64,96].…”