View in EDS

Research on texture features classification of multilayered wood flooring using global image structure method.

Saved in:
Bibliographic Details
Title: Research on texture features classification of multilayered wood flooring using global image structure method.
Authors: Yang, Bo-kai1 (AUTHOR), Li, Rong-rong1 (AUTHOR) rongrong.li@njfu.edu.cn, Meng, Yuan1 (AUTHOR), Xu, Ze-yu1 (AUTHOR)
Source: Wood Material Science & Engineering. Apr2026, Vol. 21 Issue 2, p790-802. 13p.
Subjects: Flooring, Surface texture, Gabor filters, Support vector machines, Boosting algorithms, Dimensional reduction algorithms, Feature extraction
Abstract: The manual classification method based on grain batch in multilayer wood-flooring-production line is inefficient and has a high false detection rate. In this study, a new algorithm combining the global-image structure (GIST) feature extraction technique with the Adaboost strategy integrated support vector Machine (SVM) is proposed. After preprocessing the image acquired by the CCD linear array camera, 12 groups of Gabor filters with different scales and directions were used, and the feature vector of the image was compressed by the average pooling method. Then the local linear embedding (LLE) algorithm was used to further reduce the feature dimension. Finally, the Adaboost strategy was used to integrate 10 support vector machines (SVMs) as classifiers, and the particle swarm optimization algorithm (PSO) was used for the hyperparameters of each SVMs. The accuracy of this method was 98.93%, and the three main evaluation parameters of F1 Score, Precision and Recall reached 99%, 100% and 98%, respectively. The texture feature-classification method adopted in this study effectively solves challenges caused by abnormal surface colour and complex texture, achieving remarkable results in multilayer solid-wood composite-flooring-texture classification. [ABSTRACT FROM AUTHOR]
Copyright of Wood Material Science & Engineering is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:The manual classification method based on grain batch in multilayer wood-flooring-production line is inefficient and has a high false detection rate. In this study, a new algorithm combining the global-image structure (GIST) feature extraction technique with the Adaboost strategy integrated support vector Machine (SVM) is proposed. After preprocessing the image acquired by the CCD linear array camera, 12 groups of Gabor filters with different scales and directions were used, and the feature vector of the image was compressed by the average pooling method. Then the local linear embedding (LLE) algorithm was used to further reduce the feature dimension. Finally, the Adaboost strategy was used to integrate 10 support vector machines (SVMs) as classifiers, and the particle swarm optimization algorithm (PSO) was used for the hyperparameters of each SVMs. The accuracy of this method was 98.93%, and the three main evaluation parameters of F1 Score, Precision and Recall reached 99%, 100% and 98%, respectively. The texture feature-classification method adopted in this study effectively solves challenges caused by abnormal surface colour and complex texture, achieving remarkable results in multilayer solid-wood composite-flooring-texture classification. [ABSTRACT FROM AUTHOR]
ISSN:17480272
DOI:10.1080/17480272.2025.2453625