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

Abstract

The remarkable developments in computer vision and machine learning have changed the methodologies of many scientific disciplines. They have also created a new research field in wood science called computer vision-based wood identification, which is making steady progress towards the goal of building automated wood identification systems to meet the needs of the wood industry and market. Nevertheless, computer vision-based wood identification is still only a small area in wood science and is still unfamiliar to many wood anatomists. To familiarize wood scientists with the artificial intelligence-assisted wood anatomy and engineering methods, we have reviewed the published mainstream studies that used or developed machine learning procedures. This review could help researchers understand computer vision and machine learning techniques for wood identification and choose appropriate techniques or strategies for their study objectives in wood science.

Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy

“…The images are then analyzed with image analysis tools to perform quantitative wood anatomical investigations ( Gärtner et al, 2015 ; Yeung et al, 2015 ; von Arx et al, 2016 ; Prendin et al, 2017 ; Peters et al, 2018 ). Despite the great advances in the procedures for wood sectioning and image acquisition, the actual feature recognition phase still requires human supervision ( Hwang and Sugiyama, 2021 ). In fact, traditional image analysis is often not able to overcome the artifacts generated by the sample processing: the great number of cells occurring in the sections, combined with a non-optimal image quality, is the reason why automated image analysis is often followed by a manual editing phase.…”

Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods

“…(1) Five fold cross-validation analysis was performed with label stratified folds and specimen level separation between the folds i.e., each specimen contributed images to exactly one fold. Specimen level mutual exclusivity between the folds is necessary for the valid evaluation of any machine learning based classifier for wood identification (e.g., Ravindran et al, 2019Ravindran et al, , 2021 and as discussed in Hwang and Sugiyama, 2021). Model predictions over the five folds were aggregated to compute the (top-1) prediction accuracy and a confusion matrix.…”

Geometric and Topological Bases of a New Classification of Wood Vascular Tissues Part 1: Shape and Arrangement Classifications of Vessels

“…A new field of research in wood science, in the field of machine learning, called computer-vision-based wood identification is progressing steadily towards the development of automated wood identification. It is currently just a minor topic in wood science and many wood anatomists are still inexperienced [17]. The majority of research has been on texture analysis techniques such as local binary pattern (LBP) or local phase quantization (LPQ) [18].…”