MyWood-ID: Automated Macroscopic Wood Identification System using Smartphone and macro-lens

Wood serves as raw material for countless industries due to its unique material characteristics. As such, different types of wood are traded and valued accordingly based on their supply and demand. Hence, the correct identification of wood based on trading name is important in commercial trading. Macroscopic level wood identification that has been practiced by wood anatomists for decades can identify wood up to family level in some cases but mostly up to the genera level. However, the skill on wood identification is hardly transferable due to the complexity and variation of wood structures. In this paper, we proposed a rapid and robust macroscopic wood identification system using machine vision with deep learning method using smartphone and retrofitted macro-lens as effective image acquisition device. With cloud hosting, our system is cost effective, easily accessible, fast and scalable at the same time provides great accuracy on identification. This system is trained to identify 100 commonly trading wood types found in Malaysia with Top-1 accuracy of 77.52% and Top-2 accuracy of 87.29%. A beta version of the application can be downloaded from Apple Appstore.