Performance Analysis Using CNN for Detecting Wood Knots

Abstract

This study proposes a Convolutional Neural Network (CNN) model to quickly and accurately detect wood deformations. The performance of the CNN was enhanced by extracting structural deformation features, optimizing training parameters, and improving datasets. Experimental analyses demonstrate that the CNN achieved high accuracy rates and is an effective method for deformation detection. The CNN model was designed to identify various wood deformations. Its layered architecture was optimized to analyze deformations at different scales and levels of detail. Minimal preprocessing was applied to the images used during training, and data augmentation techniques were employed to enhance dataset diversity. The model was trained on a training dataset and tested on a validation dataset. Metrics such as loss function and accuracy were monitored throughout the training process. The CNN achieved an accuracy rate of 99.90% on the training dataset. This study highlights that the CNN model is an effective method for non-destructive detection of wood deformations. The proposed CNN model has potential applications in wood deformation detection and quality control processes.

Keywords

• Wood Deformation
• Deep Learning
• Convolutional Neural Network
• Performance Analysis

References

1. Görgün H V, “Budak tipleri ve değerlendirme farklılıkları,” Artvin Çoruh Üniversitesi Orman Fakültesi Dergisi, 24(1) (2023) 96-105; doi:10.17474/artvinofd.1177307.
2. As N, Dündar T, Büyüksarı Ü, “Budakların Odunun Fiziksel ve Mekanik Özellikleri Üzerine Etkileri”, Journal of the Faculty of Forestry Istanbul University, 58(2) (2008) 1-13; https://doi.org/10.17099/jffiu.76055.
3. Doğu D, Koç H, As N, Atik C, Aksu B, Erdinler S, “Türkiye’de Yetişen Endüstriyel Öneme Sahip Ağaçların Temel Kimlik Bilgileri ve Kullanıma Yönelik Genel Değerlendirme”, Journal of the Faculty of Forestry Istanbul University, 51(2) (2014) 69-84; https://doi.org/10.17099/jffiu.33874.
4. Özkan S, “Kayın (Fagus Orientalis L.) Kerestesinde Eğilme Özelliklerinin Tahribatsiz Yöntemle Tespiti”, Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü , Isparta, 2012.
5. Yılmaz, M, Şahin, H, Yıldız, A, “Sectoral Application Analysis of Studies Made with Deep Learning Models”, Electronic Letters on Science & Engineering,17(2) (2021) 126-140.
6. Özgür S. B., “Algoritmalar, Yapay Zeka, Makine Öğrenmesi, Derin Öğrenme ve Uygulamaları: Beşeri Fayda Üretiminin Yazılımlar Tarafından Karşılanması”, Ekonomi ve Yönetim Araştırmaları Dergisi, 10(1) (2021) 1-29.
7. Eker R, Alkiş KC, Uçar Z, Aydın A, “Ormancılıkta makine öğrenmesi kullanımı”, Turkish Journal of Forestry | Türkiye Ormancılık Dergisi, 24(2) (2023), 150-177; doi: 10.18182/tjf.1282768.
8. Çetiner H, Çetiner İ, “Classification of Cataract Disease with a DenseNet201 Based Deep Learning Model”, Journal of the Institute of Science and Technology, 12(3) (2022) 1264-1276; doi:10.21597/jist.1098718.

9. Gurkan, C, Kozalioglu, S, Palandoken, M, “Real Time Mask Detection, Social Distance and Crowd Analysis using Convolutional Neural Networks and YOLO Architecture Designs”, Academic Perspective Procedia, 4(1) (2021) 195-204, doi: 10.33793/acperpro.04.01.29.
10. Elkıran, H, “OCC-OPENCV Kütüphanesi için Blok Tabanlı Programlama Aracı,”, Yüksek Lisans Tezi, İstanbul Sabahattin Zaim Üniversitesi Fen Bilimleri Enstitüsü, 2020.
11. Shukla N, Fricklas K, “Machıne Learnig with Tensorflow”, (2nd Ed.), Manning, USA,2018.
12. Primandani Arsi and Retno Waluyo, “Analisis Sentimen Wacana Pemindahan Ibu Kota Indonesia Menggunakan Algoritma Support Vector Machine (SVM)”, Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), 8(1) (2021) 147-156; doi: 10.25126/jtiik.202183944.
13. Baita, A, Yoga P, Cahyono N “Analisis Sentimen Mengenai Vaksin Sinovac Menggunakan Algoritma Support Vector Machine (SVM) dan K-Nearest Neighbor (KNN)”, Information System Journel (INFOS), 4(2) (2021) 42-46; https://doi.org/10.24076/infosjournal.2021v4i2.687.
14. Çavuşlu MA, Becerikli Y, Karakuzu C, “Levenberg-Marquardt Algoritması ile YSA Eğitiminin Donanımsal Gerçeklenmesi Hardware Implementation of Neural Network Training with Levenberg-Marquardt Algorithm,” Türkiye Bilişim Vakfı Bilgisayar Bilimleri Ve Mühendisliği Dergisi, 5(1) (2016) 1.
15. Kayalı N Z, Omurca İS, “Konvolüsyonel Sinir Ağları (CNN) ile Çin Sayı Örüntülerinin Sınıflandırması,” Journal of Computer Science,Sep. IDAP 2021(1) (2021) 184 – 191; doi: 10.53070/bbd.989668.
16. Aalami N, “Hierarchical Convolutional Neural Networks for Fashion Image Classification”, Expert Systems with Applications, 116(1) (2019) 328-339; doi: 10.1016/j.eswa.2018.09.022.
17. Samtaş G, Gülesin M, “Sayısal Görüntü İşleme ve Farklı Alanlardaki Uygulamaları”, Electronic Journal of Vocatinal Collages, 2(1) (2011) 85 - 97.
18. Ide H, Kurita T, “Improvement of Learning for CNN with ReLU Activation by Sparse Regularization,” in Proceedings of the International Joint Conference on Neural Networks, Anchorage, AK, USA, 2017, 2684-2691; doi: 10.1109/IJCNN.2017.7966185.
19. Cengil E, Çınar A, “A New Approach for Image Classification: Convolutional Neural Network,” European Journal of Technic EJT, 6(2) (2016) 96 - 103.