Abstract
Wood recognition based on computer technology relies on a large number of computing services provided by cloud services, which makes it unable to be used in recognition scenarios without a network and cannot run on some low performance devices. These shortcomings limit the application of computer algorithms in wood recognition. The photographs of 13 types of wood that are in circulation in Yunnan Province are taken as the research objects. Based on the gray-level co-occurrence matrix, the wood texture features are extracted, and the extreme learning machine (ELM) is used as the feature classifier, and a method of quickly identifying wood is proposed. Experiments show that compared with traditional machine vision algorithms and deep learning-based wood recognition methods, this method has the characteristics of strong generalization and low energy consumption, and can quickly recognize wood on low-performance hardware. This method can make the recognition model run on some low-performance devices, such as Arduino and Raspberry Pi, which provides a solution for some wood recognition scenarios where the cloud platform cannot be used without a network.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.