DOI QR코드

DOI QR Code

Performance Enhancement of Automatic Wood Classification of Korean Softwood by Ensembles of Convolutional Neural Networks

  • Kwon, Ohkyung (National Instrumentation Center for Environmental Management (NICEM), Seoul National University) ;
  • Lee, Hyung Gu (National Instrumentation Center for Environmental Management (NICEM), Seoul National University) ;
  • Yang, Sang-Yun (Department of Forest Sciences, Seoul National University) ;
  • Kim, Hyunbin (Department of Forest Sciences, Seoul National University) ;
  • Park, Se-Yeong (Department of Forest Sciences, Seoul National University) ;
  • Choi, In-Gyu (Department of Forest Sciences, Seoul National University) ;
  • Yeo, Hwanmyeong (Department of Forest Sciences, Seoul National University)
  • 투고 : 2019.02.18
  • 심사 : 2019.04.24
  • 발행 : 2019.05.25

초록

In our previous study, the LeNet3 model successfully classified images from the transverse surfaces of five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch). However, a practical limitation exists in our system stemming from the nature of the training images obtained from the transverse plane of the wood species. In real-world applications, it is necessary to utilize images from the longitudinal surfaces of lumber. Thus, we improved our model by training it with images from the longitudinal and transverse surfaces of lumber. Because the longitudinal surface has complex but less distinguishable features than the transverse surface, the classification performance of the LeNet3 model decreases when we include images from the longitudinal surfaces of the five Korean softwood species. To remedy this situation, we adopt ensemble methods that can enhance the classification performance. Herein, we investigated the use of ensemble models from the LeNet and MiniVGGNet models to automatically classify the transverse and longitudinal surfaces of the five Korean softwoods. Experimentally, the best classification performance was achieved via an ensemble model comprising the LeNet2, LeNet3, and MiniVGGNet4 models trained using input images of $128{\times}128{\times}3pixels$ via the averaging method. The ensemble model showed an F1 score greater than 0.98. The classification performance for the longitudinal surfaces of Korean pine and Korean red pine was significantly improved by the ensemble model compared to individual convolutional neural network models such as LeNet3.

키워드

HMJGBP_2019_v47n3_265_f0001.png 이미지

Fig. 1. A confusion matrix and their meaning.

HMJGBP_2019_v47n3_265_f0002.png 이미지

Fig. 2. Comparison of diagonal elements of confusion matrix from LeNet-type and MiniVGGNet-type models for different sizes of input images.

HMJGBP_2019_v47n3_265_f0003.png 이미지

Fig. 3. Normalized diagonal values from confusion matrices by ensemble models for input images of 64 ×64 × 3.

HMJGBP_2019_v47n3_265_f0004.png 이미지

Fig. 4. Normalized diagonal values from confusion matrices by ensemble models for input images of 128 ×128 × 3.

HMJGBP_2019_v47n3_265_f0005.png 이미지

Fig. 5. Confusion matrices and F1 scores of several ensemble models by the averaging method.

Table 1. Class name and its designated index for species and surface combination

HMJGBP_2019_v47n3_265_t0001.png 이미지

Table 2. The architecture of LeNet models.

HMJGBP_2019_v47n3_265_t0002.png 이미지

Table 3. The architecture of MiniVGGNet models.

HMJGBP_2019_v47n3_265_t0003.png 이미지

Table 4. The best results by SNR-like measure from ensemble sets for input image of 64 × 64 × 3.

HMJGBP_2019_v47n3_265_t0004.png 이미지

Table 5. The best results by SNR-like measure from ensemble sets for input image of 128 × 128 × 3.

HMJGBP_2019_v47n3_265_t0005.png 이미지

Table 6. Performance measures of LeNet2-LeNet3-MiniVGGNet4 ensemble model by the averaging method.

HMJGBP_2019_v47n3_265_t0006.png 이미지

Table 7. Performance measures (F1 scores) of the best ensemble model (LeNet2, LeNet3, and MiniVGGNet4) by the averaging method and individual CNN models (LeNet3 and MiniVGGNet3).

HMJGBP_2019_v47n3_265_t0007.png 이미지

참고문헌

  1. Eom, Y., Park, B. 2018. Wood Species Identification of Documentary Woodblocks of Songok Clan of the Milseong Park, Gyeongju, Korea. Journal of the Korean Wood Science and Technology 46(3):270-277. https://doi.org/10.5658/WOOD.2018.46.3.270
  2. Hafemann, L.G., Oliveira, L.S., Cavalin, P. 2014. Forest Species Recognition Using Deep Convolutional Neural Networks. 22nd International Conference on Pattern Recognition (ICPR), pp. 1103-1107.
  3. Hermanson, J.C., 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/10.1163/22941932-90000054
  4. Hermanson, J., Wiedenhoeft, A.C., Gardner, S. 2013. A machine vision system for automated field-level wood identification. Global Timber Tracking Network. Presentation at Regional Workshop for Asia, Pacific and Oceania on identification of timber species and origins, Beijing, China.
  5. Khalid, M., Lee, E.L.Y., Yusof, R., Nadaraj, M. 2008. Design of an intelligent wood species recognition system. International Journal of Simulation System, Science and Technology 9(3): 9-19.
  6. Kim, S.C., Choi, J. 2016. Study on Wood Species Identification for Daeungjeon Hall of Jeonghyesa Temple, Suncheon. Journal of the Korean Wood Science and Technology 44(6): 897-902. https://doi.org/10.5658/WOOD.2016.44.6.897
  7. Kwon, O., Lee, H.G., Lee, M.-R., Jang, S., Yang, S.-Y., Park, S.-Y., Choi, I.-G., Yeo, H. 2017. Automatic Wood Identification of Korean Softwood Based on Convolutional Neural Networks. Journal of Korean Wood Science and Technology 45(6): 797-808. https://doi.org/10.5658/WOOD.2017.45.6.797
  8. Lecun, Y., Bottou, L., Bengio, Y., Haffner, P. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11):2278-2324. https://doi.org/10.1109/5.726791
  9. Lee, K., Seo, J., Han, G. 2018. Dating Wooden Artifacts Excavated at Imdang-dong Site, Gyeongsan, Korea and Interpreting the Paleoenvironment according to the Wood Identification. Journal of the Korean Wood Science and Technology 46(3): 241-252. https://doi.org/10.5658/WOOD.2018.46.3.241
  10. Park, J.H., Oh, J.E., Hwang, I.S., Jang, H.U., Choi, J.W., Kim, S.C. 2018. Study on Species Identification for Pungnammun Gate (Treasure 308) in Jeonju, Korea. Journal of the Korean Wood Science and Technology 46(3): 278-284. https://doi.org/10.5658/WOOD.2018.46.3.278
  11. Park, S.Y., Kim, J.C., Kim, J.H., Yang, S.Y., Kwon, O., Yeo, H., Cho, K., Choi, I.G. 2017. Possibility of Wood Classification in Korean Softwood Species Using Near-infrared Spectroscopy Based on Their Chemical Compositions. Journal of the Korean Wood Science and Technology 45(2): 202-212. https://doi.org/10.5658/WOOD.2017.45.2.202
  12. Ravindran, P., Costa, A., Soares, R., Wiedenhoeft, A.C. 2018. Classification of CITES-listed and other neotropical Meliaceae wood images using convolutional neural networks. Plant Methods 14:25 https://doi.org/10.1186/s13007-018-0292-9
  13. Rosebrock, A. 2017. Deep Learning for Computer Vision with Python: Practitioner Bundle. PyImageSearch, pp. 73-83.
  14. Simonyan, K., Zisserman, A. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv.org. cs.CV.
  15. Tang, X.J., Tay, Y.H., Siam, N.A., Lim, S.C. 2017. Rapid and Robust Automated Macroscopic Wood Identification System using Smartphone with Macro-lens. arXiv:1709.08154v1 [cs.CY]
  16. Tou, J.Y., Lau, P.Y., Tay, Y.H. 2007. Computer visionbased wood recognition system. In Proceedings of International workshop on advanced image technology.
  17. Yang, S.Y., Park, Y., Chung, H., Kim, H., Park, S.Y., Choi, I.G., Kwon, O., Yeo, H. 2017. Soft Independent Modeling of Class Analogy for Classifying Lumber Species Using Their Near-infrared Spectra. Journal of the Korean Wood Science and Technology 47(1): 101-109. https://doi.org/10.5658/WOOD.2019.47.1.101
  18. Yang, S.Y. 2019. Classification of Wood Species using Near-infrared Spectroscopy and Artificial Neural Networks, Doctoral dissertation, Seoul National University