A review of the automated timber defect identification approach

Abstract

Timber quality control is undoubtedly a very laborious process in the secondary wood industry. Manual inspections by operators are prone to human error, thereby resulting in poor timber quality inspections and low production volumes. The automation of this process using an automated vision inspection (AVI) system integrated with artificial intelligence appears to be the most plausible approach due to its ease of use and minimal operating costs. This paper provides an overview of previous works on the automated inspection of timber surface defects as well as various machine learning and deep learning approaches that have been implemented for the identification of timber defects. Contemporary algorithms and techniques used in both machine learning and deep learning are discussed and outlined in this review paper. Furthermore, the paper also highlighted the possible limitation of employing both approaches in the identification of the timber defect along with several future directions that may be further explored.

A Comparative Analysis of Oak Wood Defect Detection Using Two Deep Learning (DL)-Based Software

“…Under this appellation, all knots, regardless of health, size, or shape, are included. In a study conducted in 2020 [39], machine learning techniques were employed to classify knots and cracks in oak, spruce, and TMT spruce-sawn timber within the wood industry. The findings indicated that a support vector machine (SVM) attained a defect identification accuracy of 75.8%.…”

“…The previously mentioned analysis [36] showed that the level of recognition of knots (sound and dead) is, on average, about 90% for the wood species Xyloma congestum. The majority of researchers focused on knots, as they are the most commonly encountered defect in timber, influencing both the structural integrity of the wood and the overall quality of the final product [39]. Additional improvements could be attained comparing the results obtained with the researched software.…”

Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey

“…In the last decade, several surveys and reviews focusing on image-based DL for industrial surface defects inspection have been published. However, the available works are either confined to a specialized application domain (such as metallurgical [18], [19], fabric and electronic [20], [21], [22], wood [23], and textile manufacturing [24], [25], [26]), or to a specific type of learning strategy (e.g., unsupervised methods [27]), or a specific architecture (e.g., Generative Adversarial Networks [28]), or else consider one single technique (e.g., transfer learning [29]) or requirement (e.g., lowering the number of labelled data for training [30]).…”

“…In addition to the cited works [18], [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29], [30], the related literature counts other reviews not specialised in the inspected material, employed architecture, or supervision level used for training. For instance, Czimmermann et al [31] explore visible and palpable defects and traditional feature extraction methods, characterizing supervised and unsupervised automatic approaches.…”

Frequency Domain Improvements to Texture Discrimination Algorithms

“…Because of the rapid progress of technology, materials in factories are produced faster and faster. Flat surfaced products such as wood [5], fabric [6] and metal [7] require machine vision systems to detect production defects. Unfortunately, high-speed production of these goods combined with the availability of high-resolution cameras put great strain on the network and the computers that process those images in real time.…”