Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture Features
Identifying wood accurately and rapidly is one of the best ways to prevent wood product fakes and adulterants in forestry products. Wood identification traditionally relies heavily on special experts that spend extensive time in the laboratory. A new method is proposed that uses near-infrared (NIR)...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/12/11/1527 |
| _version_ | 1797510233693618176 |
|---|---|
| author | Xi Pan Kang Li Zhangjing Chen Zhong Yang |
| author_facet | Xi Pan Kang Li Zhangjing Chen Zhong Yang |
| author_sort | Xi Pan |
| collection | DOAJ |
| description | Identifying wood accurately and rapidly is one of the best ways to prevent wood product fakes and adulterants in forestry products. Wood identification traditionally relies heavily on special experts that spend extensive time in the laboratory. A new method is proposed that uses near-infrared (NIR) spectra at a wavelength of 780–2300 nm incorporated with the gray-level co-occurrence (GLCM) texture feature to accurately and rapidly identify timbers. The NIR spectral features were determined by principal component analysis (PCA), and the digital image features extracted with the GLCM were used to create a support vector machine (SVM) model to identify the timbers. The results from fusion features of raw spectra and four GLCM features of 25 timbers showed that identification accuracy by the model was 99.43%. A sample anisotropy and heterogeneity comparative analysis revealed that the wood identification information from the transverse surface had more characteristics than that from the tangential and radial surfaces. Furthermore, short-wavelength pre-processed NIR bands of 780–1100 nm and 1100–2300 nm realized high identification accuracy of 99.43% and 100%, respectively. The four GLCM features were effective for improving identification accuracy by improving the data spatial clustering features. |
| first_indexed | 2024-03-10T05:29:41Z |
| format | Article |
| id | doaj.art-8e35ca9b5e8746fbad7f53359b86a264 |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-10T05:29:41Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-8e35ca9b5e8746fbad7f53359b86a2642023-11-22T23:25:01ZengMDPI AGForests1999-49072021-11-011211152710.3390/f12111527Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture FeaturesXi Pan0Kang Li1Zhangjing Chen2Zhong Yang3Research Institute of Wood Industry, Chinese Academy of Forestry, Beijing 100091, ChinaResearch Institute of Wood Industry, Chinese Academy of Forestry, Beijing 100091, ChinaDepartment of Sustainable Biomaterials, Virginia Polytechnic Institute and State University, Blacksburg, VA 24060, USAResearch Institute of Wood Industry, Chinese Academy of Forestry, Beijing 100091, ChinaIdentifying wood accurately and rapidly is one of the best ways to prevent wood product fakes and adulterants in forestry products. Wood identification traditionally relies heavily on special experts that spend extensive time in the laboratory. A new method is proposed that uses near-infrared (NIR) spectra at a wavelength of 780–2300 nm incorporated with the gray-level co-occurrence (GLCM) texture feature to accurately and rapidly identify timbers. The NIR spectral features were determined by principal component analysis (PCA), and the digital image features extracted with the GLCM were used to create a support vector machine (SVM) model to identify the timbers. The results from fusion features of raw spectra and four GLCM features of 25 timbers showed that identification accuracy by the model was 99.43%. A sample anisotropy and heterogeneity comparative analysis revealed that the wood identification information from the transverse surface had more characteristics than that from the tangential and radial surfaces. Furthermore, short-wavelength pre-processed NIR bands of 780–1100 nm and 1100–2300 nm realized high identification accuracy of 99.43% and 100%, respectively. The four GLCM features were effective for improving identification accuracy by improving the data spatial clustering features.https://www.mdpi.com/1999-4907/12/11/1527near-infrared (NIR) spectragray-level co-occurrence matrix (GLCM)wood identificationfeature fusionsupport vector machine (SVM) |
| spellingShingle | Xi Pan Kang Li Zhangjing Chen Zhong Yang Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture Features Forests near-infrared (NIR) spectra gray-level co-occurrence matrix (GLCM) wood identification feature fusion support vector machine (SVM) |
| title | Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture Features |
| title_full | Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture Features |
| title_fullStr | Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture Features |
| title_full_unstemmed | Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture Features |
| title_short | Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture Features |
| title_sort | identifying wood based on near infrared spectra and four gray level co occurrence matrix texture features |
| topic | near-infrared (NIR) spectra gray-level co-occurrence matrix (GLCM) wood identification feature fusion support vector machine (SVM) |
| url | https://www.mdpi.com/1999-4907/12/11/1527 |
| work_keys_str_mv | AT xipan identifyingwoodbasedonnearinfraredspectraandfourgraylevelcooccurrencematrixtexturefeatures AT kangli identifyingwoodbasedonnearinfraredspectraandfourgraylevelcooccurrencematrixtexturefeatures AT zhangjingchen identifyingwoodbasedonnearinfraredspectraandfourgraylevelcooccurrencematrixtexturefeatures AT zhongyang identifyingwoodbasedonnearinfraredspectraandfourgraylevelcooccurrencematrixtexturefeatures |