Kereste Kalite Kontrolünde Derin Öğrenme: YOLOv8 Mimarisi ile Gerçek Zamanlı Çok Sınıflı Yüzey Kusur Tespiti

Yıl 2025, Cilt: 21 Sayı: 2, 352 - 378, 30.12.2025

Uğur Şevik

https://doi.org/10.58816/duzceod.1814094

https://izlik.org/JA25RU62UJ

Öz

Ahşap ürünlerin kalite kontrolü, kereste endüstrisinin ekonomik sürdürülebilirliği ve son ürün güvenliği açısından kritik bir öneme sahiptir. Budak, çatlak ve reçine gibi doğal kusurlar, ahşabın mekanik özelliklerini ve estetik niteliklerini olumsuz etkileyerek ticari değerini doğrudan belirlemektedir. Yıllardır uygulanan geleneksel manuel denetim yöntemleri; insan faktörüne bağlı öznellik, yorgunluk kaynaklı tutarsızlıklar (genellikle %70-80 doğruluk), yavaşlık ve yüksek işgücü maliyeti gibi önemli dezavantajlar barındırmaktadır. Bu durum, modern kereste fabrikalarında otomatik, hızlı ve nesnel tespit sistemlerine olan ihtiyacı kaçınılmaz kılmaktadır. Bu çalışma, ahşap yüzeylerindeki budak ve diğer yaygın kusurların gerçek zamanlı, çok sınıflı tespiti için, hız ve doğruluk dengesiyle öne çıkan son teknoloji derin öğrenme modeli YOLOv8'in etkinliğini ve endüstriyel uygulanabilirliğini araştırmaktadır. Bu kapsamda, yedi farklı kusur sınıfını içeren, endüstriyel çeşitliliği yansıtan halka açık bir görüntü veri seti kullanılarak YOLOv8n (nano) modeli, transfer öğrenme yaklaşımıyla eğitilmiştir. Modelin performansı, mAP (ortalama kesinlik) gibi standart metrikler kullanılarak değerlendirilmiştir. NVIDIA A100 GPU donanımı üzerinde gerçekleştirilen testlerde, optimize edilmiş YOLOv8 modelinin mAP@50 metriğinde %89,5 gibi yüksek bir tespit doğruluğuna ulaştığı görülmüştür. Modelin rekabetçi doğruluğu ve tek aşamalı mimarisinin getirdiği yüksek işlem hızı (~625 FPS gerçek zamanlı tespit yeteneği), onu endüstriyel üretim hatlarına entegrasyon için güçlü bir aday yapmaktadır. Bu çalışma, YOLOv8 mimarisinin etkinliğini kanıtlamakta ve otomatik kereste derecelendirme ile akıllı kesim optimizasyonu için temel bir teknolojik altyapı sunmaktadır. Bu, Endüstri 4.0 vizyonu çerçevesinde akıllı kereste fabrikaları için uygun maliyetli, yüksek performanslı bir görsel denetim çözümüdür.

Anahtar Kelimeler

Ahşap Kusurları , Budak Tespiti , Derin Öğrenme , YOLOv8 , Gerçek Zamanlı Sistemler , Makine Görmesi , Görüntü İşleme , Kalite Kontrol.

Deep Learning in Lumber Quality Control: Real-Time Multi-Class Surface Defect Detection using YOLOv8 Architecture

https://izlik.org/JA25RU62UJ

Öz

Quality control of wood products is of critical importance for both the economic sustainability of the timber industry and end-product safety. Natural defects such as knots, cracks, and resin directly determine the commercial value of wood by adversely affecting its mechanical properties and aesthetic qualities. Traditional manual inspection methods, which have been applied for years, carry significant disadvantages such as subjectivity dependent on the human factor, fatigue-related inconsistencies (often 70-80% accuracy), slowness, and high labor costs. This situation makes the need for automated, fast, and objective detection systems inevitable in modern timber mills. This study investigates the effectiveness and industrial applicability of YOLOv8, a state-of-the-art deep learning model that stands out with its balance of speed and accuracy, for the real-time, multi-class detection of knots and other common defects on wood surfaces. In this context, the YOLOv8n (nano) model was trained using a transfer learning approach on a public image dataset that reflects industrial diversity and includes seven different defect classes. The model's performance was evaluated using standard metrics such as mAP (mean Average Precision). In tests performed on NVIDIA A100 GPU hardware, the optimized YOLOv8 model achieved a high detection accuracy of 89.5% in the mAP@50 metric. The model's competitive accuracy and the high processing speed (~625 FPS real-time detection capability) brought by its single-stage architecture make it a strong candidate for integration into industrial production lines. This study demonstrates the effectiveness of the YOLOv8 architecture and provides a fundamental technological infrastructure for automatic lumber grading and smart cutting optimization. This is a cost-effective, high-performance visual inspection solution for smart timber factories within the framework of the Industry 4.0 vision.

Anahtar Kelimeler

Wood Defects , Knot Detection , Deep Learning , YOLOv8 , Real-Time Systems , Machine Vision , Image Processing , Quality Control.

Kaynakça

• Affonso, C., Rossi, A. L. D., Vieira, F. H. A. ve de Leon Ferreira, A. C. P. (2017). Deep learning for biological image classification. Expert Systems with Applications, 85, 114–122. https://doi.org/10.1016/j.eswa.2017.05.039
• Al Hagrey, S. A. (2006). Electrical resistivity imaging of tree trunks. Near Surface Geophysics, 4(3), 179–187. https://doi.org/10.3997/1873-0604.2005043
• Alapuranen, P. ve Westman, T. (1992). Automatic visual inspection of wood surfaces. Proceedings of the 11th IAPR international conference on pattern recognition, Vol. 3, 371–374.
• Alsabhan, W. ve Alotaiby, T. (2022). Automatic building extraction on satellite images using Unet and ResNet50. Computational Intelligence and Neuroscience, 2022, 5008854. https://doi.org/10.1155/2022/5008854
• Andersson, H. (2008). Automatic classification of wood defects using support vector machines [Yüksek lisans tezi, Chalmers University of Technology].
• Andreu, J. P. ve Rinnhofer, A. (2003). Modeling of internal defects in logs for value optimization based on industrial CT scanning. Fifth international conference on image processing and scanning of wood 23–26.
• Augustauskas, R., Lipnickas, A. ve Surgailis, T. (2021). Segmentation of Drilled Holes in Texture Wooden Furniture Panels Using Deep Neural Network. Sensors, 21(11), 3633. https://doi.org/10.3390/s21113633
• Badrinarayanan, V., Kendall, A. ve Cipolla, R. (2017). SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), 2481–2495. https://doi.org/10.1109/TPAMI.2016.2644615
• Bai, T., Nguyen, D., Wang, B., Nguyen, T., Ravishankar, S. ve Ye, J. C. (2021). Deep High-Resolution Network for Low Dose X-ray CT Denoising. arXiv. https://doi.org/10.48550/arxiv.2102.00599
• Bardak, T. ve Bardak, S. (2017). Prediction of wood density by using red-green-blue (RGB) color and fuzzy logic techniques. Politeknik Dergisi, 20(4), 979–984.
• Batrakhanov, D., Zolotarev F., Eerola T., Lensu L. and Kälviäinen H., "Virtual sawing using generative adversarial networks," 2021 36th International Conference on Image and Vision Computing New Zealand (IVCNZ), Tauranga, New Zealand, 2021, pp. 1-6, https://doi.org/10.1109/IVCNZ54163.2021.9653436.
• Bauer, E. ve Kohavi, R. (1999). An empirical comparison of voting classification algorithms: Bagging, boosting, and variants. Machine Learning, 36(1-2), 105–142. https://doi.org/10.1023/A:1007515423169
• Bay, H., Ess, A., Tuytelaars, T. ve Van Gool, L. (2008). Speeded-up robust features (SURF). Computer Vision and Image Understanding, 110(3), 346–359. https://doi.org/10.1016/j.cviu.2007.09.014
• Bengio, Y., Courville, A. ve Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8), 1798–1828. https://doi.org/10.1109/TPAMI.2013.50
• Besl, P. ve McKay, N. D. (1992). A method for registration of 3-d shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2), 239–256. https://doi.org/10.1109/34.121791
• Bond, B. H. (1998). Characterization of Wood Features Using Color, Shape, and Density Parameters [Doktora tezi, Virginia Tech].
• Boukadida, H., Longuetaud, F., Colin, F., Mothe, F. ve Cuny, H. (2012). PithExtract: A robust algorithm for pith detection in computer tomography images of wood Application to 125 logs from 17 tree species. Computers and Electronics in Agriculture, 85, 90–98. https://doi.org/10.1016/j.compag.2012.03.012
• Braović, M., Šerić, L., Ivanda, A. ve Plos, M. (2021). Evaluation of Transfer Learning Methods for Wood Knot Detection. 2021 44th international convention on information, communication and electronic technology (MIPRO) 930–935.
• Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140. https://doi.org/10.1007/BF00058655
• Cavalin, P. R., Kapp, M. N., Martins, J. ve Oliveira, L. E. (2013). A multiple feature vector framework for forest species recognition. Proceedings of the 28th annual ACM symposium on applied computing 16–20.
• Cetiner, I., Var, A. A. ve Cetiner, H. (2016). Classification of knot defect types using wavelets and KNN. Elektronika Ir Elektrotechnika, 22(6), 67–72. https://doi.org/10.5755/j01.eie.22.6.17227
• Chacon, M. I. ve Alonso, G. R. (2006). Wood defects classification using a SOM/FFP approach with minimum dimension feature vector. International symposium on neural networks 1105-1110.
• Chang, S. J. ve Gazo, R. (2009). Measuring the effect of internal log defect scanning on the value of lumber produced. Forest Products Journal, 59(11/12), 56-59. https://doi.org/10.13073/0015-7473-59.11.56
• Chen, H., Hu, Q., Zhai, B., Chen, H. ve Liu, K. (2020). A robust weakly supervised learning of deep Conv-Nets for surface defect inspection. Neural Computing and Applications, 32(15), 11229–11244. https://doi.org/10.1007/s00521-019-04677-1
• Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K. ve Yuille, A. L. (2014). Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv. https://doi.org/10.48550/arXiv.1412.7062
• Chen, L. C., Zhu, Y., Papandreou, G., Schroff, F. ve Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European conference on computer vision (ECCV) 801–818.
• Cortes, C. ve Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1007/BF00994018
• Couceiro, J., Lin, C. feng, Hansson, L., Schleicher, F., Svensson, M., Jones, D., … Sandberg, D. (2016). Use of X-ray computed tomography for real-time studies of the fire progress in wood. Wood Material Science & Engineering, 18(6), 2150–2152. https://doi.org/10.1080/17480272.2023.2269539
• Cristhian, A. C., Sanchez, R. ve Baradit, E. (2008). Detection of knots using X-ray tomographies and deformable contours with simulated annealing. Wood Research, 53(4), 57–66.
• Csurka, G., Dance, C.R., Fan, L., Willamowski, J.K., & Bray, C. (2004). Visual categorization with bags of keypoints. European Conference on Computer Vision.
• Cui, Y., Lu, S. ve Liu, S. (2023). Real-time detection of wood defects based on SPP-improved YOLO algorithm. Multimedia Tools and Applications, 82(14), 21031–21044. https://doi.org/10.1007/s11042-023-14588-7
• Dalal, N. ve Triggs, B. (2005). Histograms of oriented gradients for human detection. 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05) Vol. 1, 886–893).
• De Ligne, L., De Muynck, A., Caes, J., Van Acker, J., Van den Bulcke, J. ve Boone, M. N. (2022). Studying the spatio-temporal dynamics of wood decay with X-ray CT scanning. Holzforschung, 76(5), 408–420. https://doi.org/10.1515/hf-2021-0167
• Deng, J., Dong, W., Socher, R., Li, L. J., Li, K. ve Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. 2009 IEEE conference on computer vision and pattern recognition. 248–255.
• Ding, F., Zhuang, Z., Liu, Y., Jiang, D., Yan, X. ve Wang, Z. (2020). Detecting Defects on Solid Wood Panels Based on an Improved SSD Algorithm. Sensors, 20(18), 5315. https://doi.org/10.3390/s20185315
• Dlamini, S., Chen, Y. H. ve Kuo, J. C. F. (2023). Complete fully automatic detection, segmentation and 3D reconstruction of tumor volume for non-small cell lung cancer using YOLOv4 and region-based active contour model. Expert Systems with Applications, 212, 118661. https://doi.org/10.1016/j.eswa.2022.118661
• Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E. ve Darrell, T. (2014). DeCAF: A deep convolutional activation feature for generic visual recognition. International conference on machine learning 647–655.
• Estevez, P. A., Perez, C. A. ve Goles, E. (2003). Genetic input selection to a neural classifier for defect classification of radiata pine boards. Forest Products Journal, 53(7/8), 87–94.
• FAO. (2020). Forest product statistics. Food and Agriculture Organization of the United Nations. http://www.fao.org/forestry/statistics/80938@180723/en/
• Feio, A. ve Machado, J. S. (2015). In-situ assessment of timber structural members: combining information from visual strength grading and NDT/SDT methods a review. Construction and Building Materials, 101, 1157–1165. https://doi.org/10.1016/j.conbuildmat.2015.06.027
• Fredriksson, M. (2014). Log sawing position optimization using computed tomography scanning. Wood Material Science & Engineering, 9(2), 110–119. https://doi.org/10.1080/17480272.2014.904430
• FSS (Föoreningen Svenska Sägverksmän). (1999). Nordiskt trä: sorteringsreglar. Markaryds Grafiska.
• Funt, B. V. ve Bryant, E. C. (1987). Detection of internal log defects by automatic interpretation of computer tomography images. Forest Products Journal, 37(1), 56–62.
• Gao, M., Chen, J., Mu, H. ve Qi, D. (2021a). A transfer residual neural network based on ResNet-34 for detection of wood knot defects. Forests, 12(2), 212. https://doi.org/10.3390/f12020212
• Gao, M., Song, P., Wang, F., Liu, J., Mandelis, A. ve Qi, D. (2021b). A Novel Deep Convolutional Neural Network Based on ResNet-18 and Transfer Learning for Detection of Wood Knot Defects. Journal of Sensors, 2021, 4428964. https://doi.org/10.1155/2021/4428964
• Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V. ve Garcia-Rodriguez, J. (2018). A survey on deep learning techniques for image and video semantic segmentation. Applied Soft Computing, 70, 41–65.
• Gergel, T., Bucha, T., Gejdoš, M., Danihelová, Z., Merganič, J., Gaff, M. ve Klímek, P. (2019). Computed tomography log scanning-high technology for forestry and forest based industry. Central European Forestry Journal, 65(1-2), 51–59. https://doi.org/10.2478/forj-2019-0003
• Giovannini, S., Boschetto, D., Vicario, E., Cossi, M., Busatto, A., Ghidoni, S. ve Ursella, E. (2019). Improving knot segmentation using Deep Learning techniques. Proceedings, 21st international nondestructive testing and evaluation of wood symposium, 40-47
• Girshick, R., Donahue, J., Darrell, T. ve Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition 580–587.
• Grönlund, U. (1995). Quality improvements in forest products industry [Doktora tezi, Luleå University of Technology].
• Gu, I. Y. H., Andersson, H. ve Vicen, R. (2010). Wood defect classification based on image analysis and support vector machines. Wood Science and Technology, 44(4), 693–704. https://doi.org/10.1007/s00226-009-0287-9
• Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J. ve Chen, T. (2017). Recent advances in convolutional neural networks. Pattern Recognition, 77, 354–377. https://doi.org/10.1016/j.patcog.2017.10.013
• Halabe, U. B., Agrawal, S. ve Gopalakrishnan, B. (2009). Nondestructive evaluation of wooden logs using ground penetrating radar. Nondestructive Testing and Evaluation, 24(4), 329–346. https://doi.org/10.1080/10589750802474344
• Haralick, R. M., Shanmugam, K. ve Dinstein, I. H. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6), 610–621. https://doi.org/10.1109/TSMC.1973.4309314
• He, K., Zhang, X., Ren, S. ve Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition 770–778.
• He, T., Liu, Y., Xu, C., Zhou, X., Hu, Z. ve Fan, J. (2019). A fully convolutional neural network for wood defect location and identification. IEEE Access, 7, 123453–123462. https://doi.org/10.1109/ACCESS.2019.2938138
• Hermanson, J. C. ve Wiedenhoeft, A. C. (2011). A brief review of machine vision in the context of automated wood identification systems. IAWA Journal, 32(2), 233–250. https://doi.org/10.1163/22941932-90000059
• Hinton, G. E., Osindero, S. ve Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527–1554. https://doi.org/10.1162/neco.2006.18.7.1527
• Hittawe, M. M., Muddamsetty, S. M., Sidibé, D. ve Mériaudeau, F. (2015, September). Multiple features extraction for timber defects detection and classification using SVM. 2015 IEEE international conference on image processing (ICIP) 427–431.
• Hou, Z. ve Parker, J. M. (2005). Texture Defect Detection Using Support Vector Machines with Adaptive Gabor Wavelet Features. IEEE workshop on applications of computer vision Vol. 1, 275–280.
• Howard, A., Sandler, M., Chu, G., Chen, L. C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., Le, Q. V. ve Adam, H. (2019). Searching for mobilenetv3. Proceedings of the IEEE/CVF international conference on computer vision 1314–1324.
• Hu, J., Song, W., Zhang, W., Zhao, Y. ve Yilmaz, A. (2019). Deep learning for use in lumber classification tasks. Wood Science and Technology, 53(2), 505–517. https://doi.org/10.1007/s00226-019-01089-3
• Huber, H. A., McMillin, C. W. ve McKinney, J. P. (1985). Lumber defect detection abilities of furniture rough mill employees. Forest Products Journal, 35(11/12), 79–82.
• Hwang, S. W., Lee, T., Kim, H., Chung, H., Choi, J. G. ve Yeo, H. (2022). Classification of wood knots using artificial neural networks with texture and local feature-based image descriptors. Holzforschung, 76(1), 1–13. https://doi.org/10.1515/hf-2021-0051
• Image Systems. (2013). 2013 annual report. http://mb.cision.com/Main/7480/9570148/233985.pdf
• Jocher, G. (2020). YOLOv5 by Ultralytics. GitHub. https://github.com/ultralytics/yolov5
• Jocher, G., Chaurasia, A. ve Qiu, J. (2023). YOLO by Ultralytics. GitHub. https://github.com/ultralytics/ultralytics
• Kamal, K., Qayyum, R., Mathavan, S. ve Zafar, T. (2017). Wood defects classification using laws texture energy measures and supervised learning approach. Advanced Engineering Informatics, 34, 125–135. https://doi.org/10.1016/j.aei.2017.10.003
• Kauppinen, H. ve Silvén, O. (1996). The effect of illumination variations on color-based wood defect classification. Proceedings of International conference on pattern recognition (ICPR 1996) Vol. 4, 828–832.
• Khazem, S., Richard, A., Fix, J. ve Pradalier, C. (2023). Deep learning for the detection of semantic features in tree X-ray CT scans. Artificial Intelligence in Agriculture, 7, 13–26. • https://doi.org/10.1016/j.aiia.2022.12.001
• Kim, H., Kim, M., Park, Y., Yang, S. Y., Chung, H., Kwon, O. ve Yeo, H. (2019). Visual classification of wood knots using k-nearest neighbor and convolutional neural network. Journal of the Korean Wood Science and Technology, 47(2), 229–238. https://doi.org/10.5658/WOOD.2019.47.2.229
• Kim, H. ve Kang, M. (2020). A comparison of methods to reduce overfitting in neural networks. International Journal of Advanced Smart Convergence, 9(2), 173–178.
• Kontzer, T. (2019). Going against the grain: How Lucidyne is revolutionizing lumber grading with deep learning. NVIDIA Blog. https://blogs.nvidia.com/blog/2019/04/18/lucidyne-gradescan-lumber-grading/
• Krähenbühl, A., Kerautret, B. ve Debled-Rennesson, I. (2013). Knot Segmentation in Noisy 3D Images of Wood. Discrete geometry for computer imagery 383–394.
• Krähenbühl, A., Kerautret, B., Debled-Rennesson, I., Mothe, F. ve Longuetaud, F. (2014). Knot segmentation in 3D CT images of wet wood. Pattern Recognition, 47(12), 3852–3869. https://doi.org/10.1016/j.patcog.2014.05.015
• Krizhevsky, A., Sutskever, I. ve Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems 25. ACM 60, 6, 84–90. https://doi.org/10.1145/3065386
• Lampinen, J., Smolander, S. ve Korhonen, M. (1998). Wood surface inspection system based on generic visual features. F. F. Soulie ve P. Gallinari (Ed.), Industrial applications of neural networks 35–42.
• Lazarescu, C., Watanabe, K. ve Avramidis, S. (2010). Density and moisture profile evolution during timber drying by CT scanning measurements. Drying Technology, 28(4), 460–467. https://doi.org/10.1080/07373931003613478
• LeCun, Y., Bengio, Y. ve Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
• Lemley, J., Bazrafkan, S. ve Corcoran, P. (2017). Deep learning for consumer devices and services: Pushing the limits for machine learning, artificial intelligence, and computer vision. IEEE Consumer Electronics Magazine, 6(2), 48–56. https://doi.org/10.1109/MCE.2016.2640698
• Lens, F., Liang, C., Guo, Y., Tang, X., Jahanbanifard, M., da Silva, F. S. C., Ceccantini, G. ve Verbeek, F. J. (2020). Computer-assisted timber identification based on features extracted from microscopic wood sections. IAWA Journal, 41(4), 660–680. https://doi.org/10.1163/22941932-bja10033
• Li, D. J., Zhang, Z. Y., Wang, B. S. ve Zhang, Y. X. (2022). Detection method of timber defects based on target detection algorithm. Measurement, 203-208 111937. https://doi.org/10.1016/j.measurement.2022.111937
• Li, G., Wang, X., Feng, H. ve Wiedenbeck, J. (2014). Analysis of wave velocity patterns in black cherry trees and its effect on internal decay detection. Computers and Electronics in Agriculture, 104, 32–39. https://doi.org/10.1016/j.compag.2014.03.008
• Li, S. L., Li, D. J. ve Yuan, W. Q. (2019). Wood Defect Classification Based on Two-Dimensional Histogram Constituted by LBP and Local Binary Differential Excitation Pattern. IEEE Access, 7, 145829–145842. https://doi.org/10.1109/ACCESS.2019.2945763
• Lin, T. Y., Goyal, P., Girshick, R., He, K. ve Dollár, P. (2017). Focal loss for dense object detection. Proceedings of the IEEE international conference on computer vision 2980–2988.
• Lin, T. Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C. L. ve Dollár, P. (2015). Microsoft COCO: Common objects in context. arXiv https://doi.org/10.48550/arXiv.1405.0312
• Liu, C., Yuen, J. ve Torralba, A. (2010). Sift flow: Dense correspondence across scenes and its applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5), 978–994. https://doi.org/10.1109/TPAMI.2010.147
• Liu, S., Qi, L., Qin, H., Shi, J. ve Jia, J. (2018). Path aggregation network for instance segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition 8759–8768.
• Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y. ve Berg, A. C. (2016). SSD: Single shot multibox detector. European conference on computer vision 21–37.
• Longuetaud, F., Mothe, F., Kerautret, B., Krähenbühl, A., Hory, L., Leban, J. M. ve Debled-Rennesson, I. (2012). Automatic knot detection and measurements from X-ray CT images of wood: a review and validation of an improved algorithm on softwood samples. Computers and Electronics in Agriculture, 85, 77–89. https://doi.org/10.1016/j.compag.2012.03.013
• Lopes, D. J. V., Bobadilha, G. D. S. ve Grebner, K. M. (2020). A fast and robust artificial intelligence technique for wood knot detection. BioResources, 15(4), 9351–9361.
• Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91–110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
• Lundahl, C. G. ve Grönlund, A. (2010). Increased yield in sawmills by applying alternate rotation and lateral positioning. Forest Products Journal, 60(4), 331-338. https://doi.org/10.13073/0015-7473-60.4.331
• Mahram, A., Shayesteh, M. G. ve Jafarpour, S. (2012). Classification of wood surface defects with hybrid usage of statistical and textural features. 2012 35th international conference on telecommunications and signal processing (TSP) 749–752.
• Mikołajczyk, A. ve Grochowski, M. (2018). Data augmentation for improving deep learning in image classification problem. 2018 International Interdisciplinary PhD Workshop (IIPhDW) 117–122.
• Mohan, S. ve Venkatachalapathy, K. (2012). Wood knot classification using bagging. International Journal of Computer Applications, 51(18), 50–53.
• Mohsin, M., Balogun, O. S., Haataja, K. ve Toivanen, P. (2022). Real-Time Defect Detection and Classification on Wood Surfaces Using Deep Learning. Image processing: Algorithms and systems, Society for Imaging Science and Technology, XX, Vol. 34, No. 10, 382/1-382/6.
• Nasir, V. ve Cool, J. (2018). A review on wood machining: Characterization, optimization, and monitoring of the sawing process. Wood Material Science & Engineering, 15(1), 1–18. https://doi.org/10.1080/17480272.2018.1465465
• Nasir, V. ve Cool, J. (2020). Intelligent wood machining monitoring using vibration signals combined with self-organizing maps for automatic feature selection. The International Journal of Advanced Manufacturing Technology, 108(5), 1811–1825. https://doi.org/10.1007/s00170-020-05459-0
• Nguyen, V.-T., Kerautret, B., Debled-Rennesson, I., Colin, F., Piboule, A., & Constant, T. (2016). Segmentation of defects on log surface from terrestrial lidar data. International Conference on Pattern Recognition, 3168–3173. https://doi.org/10.1109/ICPR.2016.7900122
• Norlander, R., Grahn, J. ve Maki, A. (2015). Wooden Knot Detection Using ConvNet Transfer Learning. R. R. Paulsen ve K. S. Pedersen (Ed.), Image analysis. SCIA 2015. lecture notes in computer science, vol 9127 263–274. https://doi.org/10.1007/978-3-319-19665-7_22
• Ojala, T., Pietikäinen, M. ve Harwood, D. (1996). A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 29(1), 51–59. https://doi.org/10.1016/0031-3203(95)00067-4
• Osborne, N. L. ve Maguire, D. A. (2015). Modeling knot geometry from branch angles in Douglas-fir (Pseudotsuga menziesii). Canadian Journal of Forest Research, 46(2), 215–224. https://doi.org/10.1139/cjfr-2015-0145
• Parajuli, R. ve Zhang, D. (2016). Price linkages between spot and futures markets for softwood lumber. Forest Science, 62(4), 482–489. https://doi.org/10.5849/forsci.16-019
• Patrício, D. I. ve Rieder, R. (2018). Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review. Computers and Electronics in Agriculture, 153, 69–81. https://doi.org/10.1016/j.compag.2018.08.001
• Perez, L. ve Wang, J. (2017). The effectiveness of data augmentation in image classification using deep learning. arXiv. https://doi.org/10.48550/arXiv.1712.04621
• Pham, D. T., Muhamad, Z., Mahmuddin, M., Ghanbarzadeh, A., Koc, E. ve Otri, S. (2007). Using the bees algorithm to optimise a support vector machine for wood defect classification. IPROMS 2007 Innovative Production Machines and Systems Virtual Conference, 454–461.
• Pölzleitner, W. ve Schwingshakl, G. (1992). Real-time surface grading of profiled wooden boards. Industrial Metrology, 2(3-4), 283–298.
• Qayyum, R., Kamal, K., Zafar, T. ve Mathavan, S. (2016). Wood defects classification using GLCM based features and PSO trained neural network. 2016 22nd International conference on automation and computing (ICAC) 273–277.
• Qiao, Y., Hu, Y., Zheng, Z., Liu, D., Tian, Y. ve Chen, G. (2022). A diameter measurement method of red jujubes trunk based on improved PSPNet. Agriculture, 12(8), 1140. https://doi.org/10.3390/agriculture12081140
• Qiu, Q., Qin, R., Lam, J. H. M., Leung, C. K. M. ve Lau, D. (2019). An innovative tomographic technique integrated with acoustic-laser approach for detecting defects in tree trunk. Computers and Electronics in Agriculture, 156, 129–137. https://doi.org/10.1016/j.compag.2018.11.017
• Quinlan, J. R. (1996). Bagging, boosting, and C4.5. Proceedings of the thirteenth national conference on artificial intelligence 725–730.
• Rais, A., Ursella, E., Vicario, E. ve Giudiceandrea, F. (2017). The use of the first industrial x-ray ct scanner increases the lumber recovery value: case study on visually strength-graded douglas-fir timber. Annals of Forest Science, 74(2), 28. https://doi.org/10.1007/s13595-017-0630-5
• Redmon, J., Divvala, S., Girshick, R. ve Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE conference on computer vision and pattern recognition (CVPR) 779–788. https://doi.org/10.48550/arXiv.1506.02640
• Redmon, J. ve Farhadi, A. (2016). YOLO9000: Better, Faster, Stronger. arXiv. https://doi.org/10.48550/arXiv.1612.08242
• Redmon, J. ve Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv. https://doi.org/10.48550/arXiv.1804.02767
• Reich, B., Kunda, M., Zolotarev, F., Eerola, T., Zemčík, P. ve Kauppi, T. (2025). Multimodal surface defect detection from wooden logs for sawing optimization. arXiv. https://doi.org/10.48550/arXiv.2503.21367
• Ren, S., He, K., Girshick, R. ve Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Advances in Neural Information Processing Systems 28.
• Roboflow. (2025, 29 Ekim). Homepage. https://roboflow.com
• Rocha, M. F. V., Costa, L. R., Costa, L. J., Araujo, A. C. C., Soares, B. C. D. ve Hein, P. R. G. (2018). Wood knots influence the modulus of elasticity and resistance to compression. Floresta e Ambiente, 25(4), e20170906. https://doi.org/10.1590/2179-8087.090617
• Ronneberger, O., Fischer, P. ve Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical image computing and computer-assisted intervention – MICCAI 2015 234–241.
• Ross, R. J., Zerbe, J. I., Wang, X. ve Pellerin, R. F. (2005). Stress wave nondestructive evaluation of Douglas-fir peeler cores. Forest Products Journal, 55(3), 90–94.
• Roussel, J. R., Mothe, F., Krahenbühl, A., Cuny, H., Colin, F., Constant, T. ve Leban, J. M. (2014). Automatic knot segmentation in CT images of wet softwood logs using a tangential approach. Computers and Electronics in Agriculture, 104, 46–56. https://doi.org/10.1016/j.compag.2014.03.004
• Rudakov, N. (2018). Detection of Mechanical Damages in Sawn Timber Using Convolutional Neural Networks [Yüksek lisans tezi, Lappeenranta University of Technology].
• Rummukainen, H., Makkonen, M. ve Uusitalo, J. (2019). Economic value of optical and X-ray CT scanning in bucking of Scots pine. Wood Material Science & Engineering, 16(3), 178–187. https://doi.org/10.1080/17480272.2019.1672787
• Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C. ve Fei-Fei, L. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211–252. https://doi.org/10.1007/s11263-015-0816-y
• Ruz, G. A., Estévez, P. A. ve Perez, C. A. (2005). A neurofuzzy color image segmentation method for wood surface defect detection. Forest Products Journal, 55(4), 52-58.
• Sandak, J., Sandak, A., Zitek, A., Hintestoisser, B. ve Picchi, G. (2020). Development of low-cost portable spectrometers for detection of wood defects. Sensors, 20(2), 545. https://doi.org/10.3390/s20020545
• Sarigul, E., Abbott, A. L. ve Schmoldt, D. L. (2003). Rule-driven defect detection in CT images of hardwood logs. Computers and Electronics in Agriculture, 41(1-3), 101–119. https://doi.org/10.1016/S0168-1699(03)00046-2
• Schafer, M. E. (2000). Ultrasound for defect detection and grading in wood and lumber. In 2000 IEEE ultrasonics symposium proceedings Vol. 1, 771–778.
• Schmoldt, D. L., Li, P. ve Abbott, A. L. (1997). Machine vision using artificial neural networks with local 3D neighborhoods. Computers and Electronics in Agriculture, 16(3), 255–271. https://doi.org/10.1016/S0168-1699(97)00002-1
• Seferbekov, S., Iglovikov, V., Buslaev, A. ve Shvets, A. (2018). Feature pyramid network for multi-class land segmentation. 2018 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW) 4321-4324. https://doi.org/10.48550/arXiv.1806.03510
• Siddique, N., Paheding, S., Elkin, C. P. ve Devabhaktuni, V. (2021). U-net and its variants for medical image segmentation: A review of theory and applications. IEEE Access, 9, 82031–82057. https://doi.org/10.1109/ACCESS.2021.3086020
• Silven, O. ve Kauppinen, H. (1996). Recent developments in wood inspection. International Journal of Pattern Recognition and Artificial Intelligence, 10(1), 83–95.
• Silven, O., Niskanen, M. ve Kauppinen, H. (2003). Wood inspection with non-supervised clustering. Machine Vision and Applications, 13(5-6), 275–285. https://doi.org/10.1007/s00138-002-0084-z
• Simonyan, K. ve Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv. https://doi.org/10.48550/arXiv.1409.1556
• Song, L., Chen, Y., Liu, S., Yu, H., Zhou, J. ve Ma, Y. (2023). SLWE-Net: An improved lightweight U-Net for Sargassum extraction from GOCI images. Marine Pollution Bulletin, 194, 115349. https://doi.org/10.1016/j.marpolbul.2023.115349
• Stängle, S. M., Brüchert, F., Heikkila, A., Usenius, T., Usenius, A. ve Sauter, U. H. (2015). Potentially increased sawmill yield from hardwoods using x-ray computed tomography for knot detection. Annals of Forest Science, 72(1), 57–65. https://doi.org/10.1007/s13595-014-0385-1
• Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V. ve Rabinovich, A. (2015). Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition 1–9.
• Terven, J., Córdova-Esparza, D. M. ve Romero-González, J. A. (2023). A comprehensive review of yolo architectures in computer vision: From YOLOv1 to YOLOv8 and beyond. Machine Learning and Knowledge Extraction, 5(4), 1680–1716. https://doi.org/10.3390/make5040083
• Todoroki, C., Lowell, E. ve Dykstra, D. (2010). Automated knot detection with visual post-processing of Douglas-fir veneer images. Computers and Electronics in Agriculture, 70(1), 163–171. https://doi.org/10.1016/j.compag.2009.10.002
• Uddin MS, Mazumder MKA, Prity AJ, Mridha MF, Alfarhood S, Safran M and Che D (2024) Cauli-Det: enhancing cauliflower disease detection with modified YOLOv8. Frontiers in Plant Science, 15:1373590. https://doi.org/10.3389/fpls.2024.1373590
• Urbonas, A., Raudonis, V., Maskeliūnas, R. ve Damaševičius, R. (2019). Automated Identification of Wood Veneer Surface Defects Using Faster Region-Based Convolutional Neural Network with Data Augmentation and Transfer Learning. Applied Sciences, 9(22), 4898. https://doi.org/10.3390/app9224898
• Wang, A., Qian, W., Li, A., Xu, Y., Hu, J., Xie, Y. ve Zhang, L. (2024). NVW-YOLOv8s: An improved YOLOv8s network for real-time detection and segmentation of tomato fruits at different ripeness stages. Computers and Electronics in Agriculture, 219, 108833. https://doi.org/10.1016/j.compag.2024.108833
• Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., Liu, W. ve Xiao, B. (2021). Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10), 3349–3364. https://doi.org/10.1109/TPAMI.2020.2983686
• Wang, J. ve Liu, X. (2021). Medical image recognition and segmentation of pathological slices of gastric cancer based on Deeplab v3+ neural network. Computer Methods and Programs in Biomedicine, 207, 106210. https://doi.org/10.1016/j.cmpb.2021.106210
• Wang, J., Zhao, J., Sun, H., Zhou, G., Chen, H., Yan, J. ve Fu, L. (2022). Satellite remote sensing identification of discolored standing trees for pine wilt disease based on semi-supervised deep learning. Remote Sensing, 14(23), 5936. https://doi.org/10.3390/rs14235936
• Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M. ve Solomon, J. M. (2019). Dynamic graph CNN for learning on point clouds. arXiv. https://doi.org/10.48550/arXiv.1801.07829
• Watanabe, K., Lazarescu, C., Shida, S. ve Avramidis, S. (2012). A novel method of measuring moisture content distribution in timber during drying using ct scanning and image processing techniques. Drying Technology, 30(3), 256–262. https://doi.org/10.1080/07373937.2011.634977
• Wen, L., Li, X. ve Gao, L. (2020). A transfer convolutional neural network for fault diagnosis based on ResNet-50. Neural Computing and Applications, 32(10), 6111–6124. https://doi.org/10.1007/s00521-019-04099-w
• Wood defect Dataset by 666. (2025, 29 Ekim). Roboflow. https://universe.roboflow.com/666-fpagy/v4-bokmf/dataset/1
• Xie, G., Wang, L., Williams, R. A., Li, Y., Zhang, P. ve Gu, S. (2024). Segmentation of wood CT images for internal defects detection based on CNN: A comparative study. Computers and Electronics in Agriculture, 224, 109244. https://doi.org/10.1016/j.compag.2024.109244
• Xie, Y. H. ve Wang, J. C. (2015). Study on the identification of the wood surface defects based on texture features. Optik, 126(19), 2231–2235. https://doi.org/10.1016/j.ijleo.2015.05.084
• Yosinski, J., Clune, J., Bengio, Y. ve Lipson, H. (2014). How transferable are features in deep neural networks? In Advances in Neural Information Processing Systems 27.
• Zhang, W., Li, X., Jia, X., Ma, H., Luo, Z. ve Li, X. (2020). Machinery fault diagnosis with imbalanced data using deep generative adversarial networks. Measurement, 152, 107377. https://doi.org/10.1016/j.measurement.2019.107377
• Zhang, W., Zhou, F., Liu, Y., Sun, P., Chen, Y. ve Wang, L. (2022). Object defect detection based on data fusion of a 3d point cloud and 2d image. Measurement Science and Technology, 34(2), 025002. https://doi.org/10.1088/1361-6501/ac93a3
• Zhang, Y., Xu, C., Li, C., Yu, H. ve Cao, J. (2015). Wood defect detection method with PCA feature fusion and compressed sensing. Journal of Forestry Research, 26(3), 745–751. https://doi.org/10.1007/s11676-015-0062-8
• Zhao, Z., Ge, Z., Jia, M., Liu, Y., Xu, K. ve Gao, Z. (2022). A particleboard surface defect detection method research based on the deep learning algorithm. Sensors, 22(20), 7733. https://doi.org/10.3390/s22207733
• Zhao, Z., Yang, X., Zhou, Y., Sun, J. ve Ge, Z. (2021). Real-time detection of particleboard surface defects based on improved YOLOv5 target detection. Scientific Reports, 11(1), 21777. https://doi.org/10.1038/s41598-021-01084-x
• Zhong, Y., Ren, H. Q., Lou, W. L. ve Li, X. Z. (2012). The effect of knots on bending modulus of elasticity of dimension lumber. Key Engineering Materials, 517, 677–682. https://doi.org/10.4028/www.scientific.net/KEM.517.677
• Zolotarev, F., Eerola, T., Lensu, L., Kälviäinen, H., Helin, T., Haario, H., Kauppi, T. ve Heikkinen, J. (2020). Modelling internal knot distribution using external log features. Computers and Electronics in Agriculture, 179, 105795. https://doi.org/10.1016/j.compag.2020.105795