Analysis of Texture Features for Wood Defect Classification

Nur Dalila Abdullah, Ummi Raba'ah Hashim, Sabrina Ahmad

Abstract


Selecting important features in classifying wood defects remains a challenging issue to the automated visual inspection domain. This study aims to address the extraction and analysis of features based on statistical texture on images of wood defects. A series of procedures including feature extraction using the Grey Level Dependence Matrix (GLDM) and feature analysis were executed in order to investigate the appropriate displacement and quantisation parameters that could significantly classify wood defects. Samples were taken from the Kembang Semangkuk (KSK), Meranti and Merbau wood species. Findings from visual analysis and classification accuracy measures suggest that the feature set with the displacement parameter, d=2, and quantisation level, q=128, shows the highest classification accuracy. However, to achieve less computational cost, the feature set with quantisation level, q=32, shows acceptable performance in terms of classification accuracy.Selecting important features in classifying wood defects remains a challenging issue to the automated visual inspection domain. This study aims to address the extraction and analysis of features based on statistical texture on images of wood defects. A series of procedures including feature extraction using the Grey Level Dependence Matrix (GLDM) and feature analysis were executed in order to investigate the appropriate displacement and quantisation parameters that could significantly classify wood defects. Samples were taken from the Kembang Semangkuk (KSK), Meranti and Merbau wood species. Findings from visual analysis and classification accuracy measures suggest that the feature set with the displacement parameter, d=2, and quantisation level, q=128, shows the highest classification accuracy. However, to achieve less computational cost, the feature set with quantisation level, q=32, shows acceptable performance in terms of classification accuracy.

Keywords


GLDM;texture;feature extraction;defect detection;automated vision inspection

References


Hongbo Mu, Dawei Qi, Nan Hu, and Mingming Zhang. Edge Extraction of Wood Image with Rot Based on Gray Transformation. 2010 International Conference on Computer Application and System Modeling. 2010; 2:605-608.

R. Qayyum, K. Kamal, T. Zafar, and S. Mathavan. Wood Defects Classification Using GLCM Based Features And PSO Trained Neural Network. 22nd International Conference on Automation and Computing. 2016: 3–7.

U. R. Hashim, A. K. Muda, S. Z. Hashim, and M. B. Bonab. Rotation Invariant Texture Feature based on Spatial Dependence Matrix for Timber Defect Detection. 13th International Conference on Intelligent Systems Design and Applications (ISDA). 2013: 307–312.

U. R. Hashim, S. Z. Hashim, and A. K. Muda. Performance Evaluation of Multivariate Texture Descriptor for Classification Of Timber Defect. International Journal for Light and Electron Optics. 2016; 127(15): 6071–6080.

M. M. Hittawe, S. M. Muddamsetty, D. Sidibe, and F. Meriaudeau. Multiple Features Extraction for Timber Defects Detection and Classification using SVM. International Conference on Image Processing. 2015: 427-431.

A. Mahram, M. G. Shayesteh, and S. Jafarpour. Classification of Wood Surface Defects with Hybrid Usage of Statistical and Textural Features. 35th International Conference on Telecommunications and Signal Processing. 2012: 749-752.

A. Fahrurozi, S. Madenda, Ernastuti, and D. Kerami. Wood Texture Features Extraction by Using GLCM Combined With Various Edge Detection Methods. Journal of Physics: Conference Series. 2016; 725:1-11.

P. Cavalin, L. S. Oliveira, A. L. Koerich, A. S. Britto, A. S. B. Jr, and A. S. B. Jr. Wood Defect Detection using Grayscale Images and An Optimized Feature Set. Industrial Electronics Conference. 2006: 3408–3412.

M. Khalid, E. Lew Yi Lee, R. Yusof, and M. Nadaraj. Design of an Intelligent Wood Species Recognition System. International Journal of Simulation Systems, Science & Technology. 2008; 9(3): 9-19.

R. Athilakshmi. Defect Identification of Lumber Through Correlation Technique with Statistical and Textural Feature Extraction Method. International Conference on Communication and Computational Intelligence. 2010: 524–528.

P. Barmpoutis, I. Barboutis, and P. Lefakis. Detection of Various Characteristics on Wooden Surfaces , Using Scanner and Image Processing Techniques. 27th International Conference on Wood Modification and Technology. 2016: 7–13.

X. YongHua and W. Jin-Cong. Study on The Identification of The Wood Surface Defects Based on Texture Features. International Journal for Light and Electron Optics. 2015; 126(19): 2231–2235.

Z. Y. Xiang, Z. Y. Qin, L. Ying, J. L. Quan, and C. Z. Wei. Identification of Wood Defects Based on LBP Features. 35th Chinese Control Conference. 2016: 4202–4205.

W. Song, T. Chen, Z. Gu, W. Gai, W. Huang, and B. Wang. Wood Materials Defects Detection Using Image Block Percentile Color Histogram and Eigenvector Texture Feature. International Conference on Information Sciences, Machinery, Materials and Energy. 2015: 780–784.

U. R. Hashim, S. Z. Hashim, and A. K. Muda, “Image Collection for Non-Segmenting Approach of Timber Surface Defect Detection. International Journal of Advances in Soft Computing and its Application. 2015; 7(1): 15–34.

M. Petrou and P. G. Sevilla. Image Processing : Dealing with Texture. Wiley. 2006.

L. K. Soh and C. Tsatsoulis. Texture Analysis of SAR Sea Ice Imagery Using Gray Level Co-Occurrence Matrices. IEEE Transactions on Geoscience and Remote Sensing. 1999; 37(2): 780–795.

D. A. Clausi. An Analysis of Co-Occurrence Texture Statistics as A Function Of Grey Level Quantization. Canadian Journal of Remote Sensing. 2002; 28(1): 45–62.

J. Ma, Z. Zhang, C. Wang, and Z. Chen. Classifier-Based Feature Fusion for Texture Discrimination. International Conference on Information Engineering and Computer Science. 2009: 1-4.



Refbacks

  • There are currently no refbacks.


Bulletin of EEI Stats