Microtec produces many types of systems for the measurement of wood logs. In particular, Logeye 301 allows the acquisition of color images of the sides of logs. The project aims to use such color images to classify logs according to the number and size of knots on their surface. For image acquisition, it is possible to use one of our facilities in which a CT Log scanner is also installed. It is then possible to perform manual labeling of color images or take advantage of CT Log tomographic data for automatic labeling. In either case, the work involves the development of machine learning algorithms (preferably CNN-based) that can automatically classify logs.
Microtec produces many types of systems for the measurement of wood logs. In particular, Logeye 301 allows the acquisition of color images of the sides of logs. The project aims to use such color images to classify logs according to the number and size of knots on their surface. For image acquisition, it is possible to use one of our facilities in which a CT Log scanner is also installed. It is then possible to perform manual labeling of color images or take advantage of CT Log tomographic data for automatic labeling. In either case, the work involves the development of machine learning algorithms (preferably CNN-based) that can automatically classify logs.
Automatic detection of knots and wood logs classification using machine learning
ASHAQ, MARIAN NASHAAT ADLY
2022/2023
Abstract
Microtec produces many types of systems for the measurement of wood logs. In particular, Logeye 301 allows the acquisition of color images of the sides of logs. The project aims to use such color images to classify logs according to the number and size of knots on their surface. For image acquisition, it is possible to use one of our facilities in which a CT Log scanner is also installed. It is then possible to perform manual labeling of color images or take advantage of CT Log tomographic data for automatic labeling. In either case, the work involves the development of machine learning algorithms (preferably CNN-based) that can automatically classify logs.File | Dimensione | Formato | |
---|---|---|---|
Ashaq_Marian.pdf
Open Access dal 03/04/2024
Dimensione
6.27 MB
Formato
Adobe PDF
|
6.27 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/45141