(Department of Information Technology and Communication, Politeknik Mersing, Malaysia)(2) Ummi Raba'ah Hashim
(Centre for Advanced Computing Technology, Universiti Teknikal Malaysia Melaka (UTeM), Malaysia)(3) Sabrina Ahmad
(Centre for Advanced Computing Technology, Universiti Teknikal Malaysia Melaka (UTeM), Malaysia)(4) Lizawati Salahuddin
(Centre for Advanced Computing Technology, Universiti Teknikal Malaysia Melaka (UTeM), Malaysia)(5) Ngo Hea Choon
(Centre for Advanced Computing Technology, Universiti Teknikal Malaysia Melaka (UTeM), Malaysia)(6) Kasturi Kanchymalay
(Centre for Advanced Computing Technology, Universiti Teknikal Malaysia Melaka (UTeM), Malaysia)(7) Nur Haslinda Ismail
(Centre for Advanced Computing Technology, Universiti Teknikal Malaysia Melaka (UTeM), Malaysia)*corresponding author
AbstractThis study proposed a classification model for timber defect classification based on an artificial neural network (ANN). Besides that, the research also focuses on determining the appropriate parameters for the neural network model in optimizing the defect identification performance, such as the number of hidden layers nodes and the number of epochs in the neural network. The neural network's performance is compared with other standard classifiers such as Naïve Bayes, K-Nearest Neighbours, and J48 Decision Tree in finding their significant differences across the multiple timber species. The classifier's performance is measured based on the F-measure due to the imbalanced dataset of the timber species. The experimental results show that the proposed classification model based on the neural network outperforms the other standard classifiers in detecting many types of defects across multiple timber species with an F-measure of 84.01%. This research demonstrates that ANN can accurately classify the defects across multiple species while defining appropriate parameters (hidden layers and epochs) for the neural network model in optimizing defect identification performance.
KeywordsAutomated vision inspection; Defect identification; Neural network; Classification performance; Epoch
|
DOIhttps://doi.org/10.26555/ijain.v7i2.588 |
Article metricsAbstract views : 1772 | PDF views : 264 |
Cite |
Full Text Download
|
References
[1] U. Buehlmann and R. Edward Thomas, "Impact of human error on lumber yield in rough mills," Robot. Comput. Integr. Manuf., vol. 18, no. 3–4, pp. 197–203, Jun. 2002, doi: 10.1016/S0736-5845(02)00010-8.
[2] H. Yu, Y. Liang, H. Liang, and Y. Zhang, "Recognition of wood surface defects with near infrared spectroscopy and machine vision," J. For. Res., vol. 30, no. 6, pp. 2379–2386, Dec. 2019, doi: 10.1007/s11676-018-00874-w.
[3] H. Kim et al., "Visual Classification of Wood Knots Using k-Nearest Neighbor and Convolutional Neural Network," J. Korean Wood Sci. Technol., vol. 47, no. 2, pp. 229–238, 2019. Available at: Google Scholar.
[4] K. Kamal, R. Qayyum, S. Mathavan, and T. Zafar, "Wood defects classification using laws texture energy measures and supervised learning approach," Adv. Eng. Informatics, vol. 34, pp. 125–135, 2017, doi: 10.1016/j.aei.2017.09.007.
[5] A. Urbonas, V. Raudonis, R. Maskeliūnas, and R. Damaševičius, "Automated Identification of Wood Veneer Surface Defects Using Faster Region-Based Convolutional Neural Network with Data Augmentation and Transfer Learning," Appl. Sci., vol. 9, no. 22, p. 4898, Nov. 2019, doi: 10.3390/app9224898.
[6] M. Gao, D. Qi, H. Mu, and J. Chen, "A Transfer Residual Neural Network Based on ResNet-34 for Detection of Wood Knot Defects," Forests, vol. 12, no. 2, p. 212, Feb. 2021, doi: 10.3390/f12020212.
[7] M. Thilagavathi and S. Abirami, "Study of Neural Network Training Algorithms in Detection of Wood Surface Defects," Int. J. Autom. Smart Technol., vol. 9, no. 3, pp. 107–113, 2019, doi: 10.5875/ausmt.v9i3.1924.
[8] M. S. Packianather and B. Kapoor, "A wrapper-based feature selection approach using Bees Algorithm for a wood defect classification system," 2015 10th Syst. Syst. Eng. Conf. SoSE 2015, pp. 498–503, 2015, doi: 10.1109/SYSOSE.2015.7151902.
[9] U. R. Hashim, S. Z. Hashim, and A. K. Muda, "Image Collection for Non-Segmenting Approach of Timber Surface Defect Detection," Int. J. Adv. Soft Comput. Its Appl., vol. 7, no. 1, pp. 15–34, 2015. Available at: Google Scholar.
[10] H. L. Tong, H. Ng, T. V. T. Yap, W. Ahmad, and M. F. A. Fauzi, "Evaluation of feature extraction and selection techniques for the classification of wood defect images," J. Eng. Appl. Sci, vol. 12, no. 3, pp. 602–608, 2017. Available at: Google Scholar.
[11] Y. Yang, X. Zhou, Y. Liu, Z. Hu, and F. Ding, "Wood Defect Detection Based on Depth Extreme Learning Machine," Appl. Sci., vol. 10, no. 21, p. 7488, Oct. 2020, doi: 10.3390/app10217488.
[12] J. Sandak, A. Sandak, A. Zitek, B. Hintestoisser, and G. Picchi, "Development of Low-Cost Portable Spectrometers for Detection of Wood Defects," Sensors, vol. 20, no. 2, p. 545, Jan. 2020, doi: 10.3390/s20020545.
[13] M. Tiitta, V. Tiitta, M. Gaal, J. Heikkinen, R. Lappalainen, and L. Tomppo, "Air-coupled ultrasound detection of natural defects in wood using ferroelectret and piezoelectric sensors," Wood Sci. Technol., vol. 54, no. 4, pp. 1051–1064, Jul. 2020, doi: 10.1007/s00226-020-01189-y.
[14] K. Kamal, R. Qayyum, S. Mathavan, and T. Zafar, "Wood defects classification using laws texture energy measures and supervised learning approach," Adv. Eng. Informatics, vol. 34, pp. 125–135, Oct. 2017, doi: 10.1016/j.aei.2017.09.007.
[15] D. T. Pham, A. J. Soroka, A. Ghanbarzadeh, E. Koc, S. Otri, and M. Packianather, "Optimising neural networks for identification of wood defects using the bees algorithm," in 2006 IEEE International Conference on Industrial Informatics, INDIN'06, 2007, pp. 1346–1351, doi: 10.1109/INDIN.2006.275855.
[16] T. He, Y. Liu, C. Xu, X. Zhou, Z. Hu, and J. Fan, "A fully convolutional neural network for wood defect location and identification," IEEE Access, vol. 7, pp. 123453–123462, 2019, doi: 10.1109/ACCESS.2019.2937461.
[17] N. Chen, X. Men, C. Hua, X. Wang, X. Han, and H. Chen, "Research on edge defects image recognition technology based on artificial neural network," Proc. 13th IEEE Conf. Ind. Electron. Appl. ICIEA 2018, pp. 1929–1933, 2018, doi: 10.1109/ICIEA.2018.8398024.
[18] S. Y. Jung, Y. H. Tsai, W. Y. Chiu, J.-S. S. Hu, and C.-T. T. Sun, "Defect detection on randomly textured surfaces by convolutional neural networks," in IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM, 2018, vol. 2018-July, pp. 1456–1461, doi: 10.1109/AIM.2018.8452361.
[19] C.-C. Huang and X.-P. Lin, "Study on machine learning based intelligent defect detection system," in MATEC Web of Conferences, 2018, vol. 201, p. 1010, doi: 10.1051/matecconf/201820101010.
[20] K. Hu, B. Wang, Y. Shen, J. Guan, and Y. Cai, "Defect identification method for poplar veneer based on progressive growing generated adversarial network and MASK R-CNN Model," BioResources, vol. 15, no. 2, pp. 3041–3052, 2020, doi: 10.15376/biores.15.2.3041-3052.
[21] T.-W. W. Tang, W.-H. H. Kuo, J.-H. H. Lan, C.-F. F. Ding, H. Hsu, and H.-T. T. Young, "Anomaly detection neural network with dual auto-encoders GAN and its industrial inspection applications," Sensors, vol. 20, no. 12, p. 3336, 2020, doi: 10.3390/s20123336.
[22] T. He, Y. Liu, Y. Yu, Q. Zhao, and Z. Hu, "Application of deep convolutional neural network on feature extraction and detection of wood defects," Measurement, vol. 152, p. 107357, 2020, doi: 10.1016/j.measurement.2019.107357.
[23] J. Shi, Z. Li, T. Zhu, D. Wang, and C. Ni, "Defect detection of industry wood veneer based on NAS and multi-channel mask R-CNN," Sensors, vol. 20, no. 16, p. 4398, 2020, doi: 10.3390/s20164398.
[24] X. Ji, H. Guo, and M. Hu, "Features extraction and classification of wood defect based on HU invariant moment and wavelet moment and BP neural network," ACM Int. Conf. Proceeding Ser., 2019, doi: 10.1145/3356422.3356459.
[25] A. Paulauskaite-Taraseviciene, K. Sutiene, and L. Pipiras, "Wooden dowels classification using convolutional neural network," Proc. Rom. Acad. Ser. A-Mathematics Phys. Tech. Sci. Inf. Sci., vol. 20, no. 4, pp. 401–408, 2019. Available at: Google Scholar.
[26] Y. Huang, C. Qiu, X. Wang, S. Wang, and K. Yuan, "A compact convolutional neural network for surface defect inspection," Sensors (Switzerland), vol. 20, no. 7, pp. 1–19, 2020, doi: 10.3390/s20071974.
[27] Z.-N. N. Ke, Q.-J. J. Zhao, C.-H. H. Huang, P. Ai, and J.-G. G. Yi, "Detection of wood surface defects based on particle swarm-genetic hybrid algorithm," in 2016 International Conference on Audio, Language and Image Processing (ICALIP), 2016, pp. 375–379, doi: 10.1109/ICALIP.2016.7846635.
[28] Y. Li, H. Feng, X. Du, and Y. Fang, "Using PT-Kriging Method for Stress Wave Three Dimensional Imaging of Wood Internal Defects," in 2017 International Conference on Computer Technology, Electronics and Communication (ICCTEC), 2017, pp. 671–675, doi: 10.1109/ICCTEC.2017.00150.
[29] T. Hau Lee, N. Hu, T. Y. Tzen Vun, W. A. Wan Siti Halimatul Munirah, and A. F. Mohammad Faizal, "Evaluation of feature extraction and selection techniques for the classification of wood defect images," J. Eng. Appl. Sci., vol. 12, pp. 602–608, 2017. Available at: Google Scholar.
[30] M. S. Packianather and B. Kapoor, "A wrapper-based feature selection approach using Bees Algorithm for a wood defect classification system," in 2015 10th System of Systems Engineering Conference (SoSE), 2015, pp. 498–503, doi: 10.1109/SYSOSE.2015.7151902.
[31] A. K. Patel, V. N. Mandhala, D. K. Anguraj, and S. R. Nayak, "Surface defect detection using SVM‐based machine vision system with optimized feature," Mach. Vis. Insp. Syst. Vol. 2 Mach. Learn. Approaches, pp. 109–127, 2021. doi: 10.1002/9781119786122.ch6
[32] U. R. Hashim, S. Z. Hashim, and A. K. Muda, "Image collection for non-segmenting approach of timber surface defect detection," Int. J. Adv. Soft Comput. its Appl., vol. 7, no. 1, pp. 15–34, 2015. Available at: Google Scholar.
[33] U. R. ah Hashim, S. Z. M. Hashim, A. K. Muda, K. Kanchymalay, I. E. A. Jalil, and M. H. Othman, "Single class classifier using FMCD based non-metric distance for timber defect detection," Int. J. Adv. Soft Comput. its Appl., vol. 9, no. 3, pp. 199–216, 2017. doi: 10.26555/ijain.v3i2.94
[34] D. Wu and N. Ye, "Wood defect recognition based on affinity propagation clustering," in 2010 Chinese Conference on Pattern Recognition (CCPR), 2010, vol. 96, no. 5, pp. 1–5. doi: 10.1109/CCPR.2010.5659314
[35] Z. Chang, J. Cao, and Y. Zhang, "A novel image segmentation approach for wood plate surface defect classification through convex optimization," J. For. Res., vol. 29, no. 6, pp. 1789–1795, 2018, doi: 10.1007/s11676-017-0572-7. doi: 10.1007/s11676-017-0572-7
[36] V. T. Nguyen, T. Constant, B. Kerautret, I. Debled-Rennesson, and F. Colin, "A machine-learning approach for classifying defects on tree trunks using terrestrial LiDAR," Comput. Electron. Agric., vol. 171, no. February, 2020, doi: 10.1016/j.compag.2020.105332.
[37] T. Pahlberg, M. Thurley, D. Popovic, and O. Hagman, "Crack detection in oak flooring lamellae using ultrasound-excited thermography," Infrared Phys. Technol., vol. 88, pp. 57–69, 2018, doi: 10.1016/j.infrared.2017.11.007.
[38] D. D. Bhavani, A. Vasavi, and P. T. Keshava, "Machine learning: a critical review of classification tehnique," Int. J. Adv. Res. Comput. Commun. Eng., vol. 3, no. 11, pp. 17–23, 2014, doi: 10.17148/ijarcce.
[39] N. D. Abdullah, U. R. Hashim, S. Ahmad, and L. Salahuddin, "Analysis of texture features for wood defect classification," Bull. Electr. Eng. Informatics, vol. 9, no. 1, pp. 121–128, 2020, doi: 10.11591/eei.v9i1.1553.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0