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.

Ripeness classification is one of the most challenging tasks in the postharvest management of mulberry fruit. The risks of microbial contamination and human error in manual sorting are significant; it may result in quality degradation and wasting of processed products. Due to advanced developments in computer vision and machine learning, automated sorting became possible. This study presents the results of developing and testing a computer vision-based application using convolutional neural networks (CNNs) for the classification of mulberry fruit ripening stages. To reduce the training cost and improve the accuracy of classification, transfer learning was used to fine-tune the CNN models. The CNN models in the test include DenseNet, Inception-v3, ResNet-18, ResNet-50, and AlexNet. Transfer learning was used to fine-tune the models and improve the accuracy of classification. The AlexNet and ResNet-18 networks exhibited the best performance with 98.32% and 98.65% overall accuracy for classifying the ripeness of white and black mulberries, respectively. Moreover, the performance of the models did not change when the data sets of both genotypes were mixed. The ResNet-18 was able to classify both genotype and ripeness from 600 fruit images in 2.36 min with an overall accuracy of 98.03%, which was superior to other architectures. It indicates that the model could be used for precise classification of the ripening stages of mulberries and other horticultural products, as a part of an automated sorting system.INDEX TERMS Convolutional neural network, computer vision, online detection, ripening classification, transfer learning.

The typical black coloured ebony wood (Diospyros, Ebenaceae) is desired as a commercial timber because of its durable and aesthetic properties. Surprisingly, a comprehensive wood anatomical overview of the genus is lacking, making it impossible to fully grasp the diversity in microscopic anatomy and to distinguish between CITES protected species native to Madagascar and the rest. We present the largest microscopic wood anatomical reference database for ebony woods and reconstruct evolutionary patterns in the microscopic wood anatomy within the family level using an earlier generated molecular phylogeny. Wood samples from 246 Diospyros species are described based on standardised light microscope observations. For the ancestral state reconstruction, we selected eight wood anatomical characters from 88 Ebenaceae species (including 29 Malagasy Diospyros species) that were included in the most recently reconstructed family phylogeny. Within Diospyros, the localisation of prismatic crystals (either in axial parenchyma or in rays) shows the highest phylogenetic value and appears to have a biogeographical signal. The molecular defined subclade Diospyros clade IX can be clearly distinguished from other ebony woods by its storied structure. Across Ebenaceae, Lissocarpa is distinguishable from the remaining genera by the combined presence of scalariform and simple vessel perforation plates, and Royena typically has silica bodies instead of prismatic crystals. The local deposition of prismatic crystals and the presence of storied structure allow identifying ebony wood species at the subgeneric level, but species-level identification is not possible. In an attempt to improve the identification accuracy of the CITES protected Malagasy woods, we applied computer vision algorithms based on microscopic images from our reference database (microscopic slides from ca. 1000 Diospyros specimens) and performed chemical profiling based on DART TOFMS.