TY - GEN
T1 - Roundwood Tracking from the Forest to the Sawmill using filter approaches to highlight the annual ring pattern
AU - Wimmer, G.
AU - Schraml, R.
AU - Uhl, A.
AU - Petutschnigg, A.
N1 - Conference code: 186237
Export Date: 14 December 2023
Correspondence Address: Wimmer, G.; University of Salzburg, Austria; email: [email protected]
Funding details: Austrian Science Fund, FWF, I 3653
Funding text 1: This work is partially funded by the Austrian Science Fund (FWF) under Project Number I 3653.
References: Homepage of the Forest Stewardship Council, , www.fsc.org, fsc, [online]. Available; Homepage of the Programme for the Endorsement of Forest Certification, , www.pefc.at, pefc, [online]. Available; Tzoulis, I., Andreopoulou, Z., Emerging traceability technologies as a tool for quality wood trade (2013) Procedia Technology, 8, pp. 606-611. , https://www.sciencedirect.com/science/article/pii/S2212017313001497, 6th International Conference on Information and Communication Technologies in Agriculture, Food and Environment (haicta 2013) [online]. Available; Chiorescu, S., Grönlund, A., The fingerprint approach: using data generated by a 2-axis log scanner to accomplish traceability in the sawmill's log yard (2003) Forest Products Journal, 53, pp. 78-86; Chiorescu, S., Grönlund, A., The fingerprint method: Using over-bark and under-bark log measurement data generated by three-dimensional log scanners in combination with radiofrequency identification tags to achieve traceability in the log yard at the sawmill (2004) Scandinavian Journal of Forest Research, 19 (4), pp. 374-383; Flodin, J., Oja, J., Grönlund, A., Fingerprint traceability of logs using the outer shape and the tracheid effect (2008) Forest Products Journal, 58 (4), pp. 21-27; Barrett, W., (2007) Biometrics of Cut Tree Faces, 1, pp. 562-565; Schraml, R., Petutschnigg, A., Uhl, A., Validation and reliability of the discriminative power of geometric wood log end features (2015) Proceedings of the IEEE International Conference on Image Processing (ICIP'15); Schraml, R., Hofbauer, H., Petutschnigg, A., Uhl, A., Tree log identification based on digital cross-section images of log ends using fingerprint and iris recognition methods (2015) Proceedings of the 16th International Conference on Computer Analysis of Images and Patterns (CAIP'15), ser. lncs, pp. 752-765. , Springer Verlag; Schraml, R., Charwat-Pessler, J., Petutschnigg, A., Uhl, A., Towards the applicability of biometric wood log traceability using digital log end images (2015) Computers and Electronics in Agriculture, 119, pp. 112-122; Schraml, R., Hofbauer, H., Petutschnigg, A., Uhl, A., On rotational pre-alignment for tree log end identification using methods inspired by fingerprint and iris recognition (2016) Machine Vision and Applications, 27 (8), pp. 1289-1298; Wimmer, G., Schraml, R., Hofbauer, H., Petutschnigg, A., Uhl, A., Two-stage cnn-based wood log recognition (2021) Computational Science and Its Applications-ICCSA 2021, ser. lncs, 12955, pp. 115-125. , Cham: Springer International Publishing; Wimmer, G., Schraml, R., Lamminger, L., Petutschnigg, A., Uhl, A., Cross-modality wood log tracing (2021) 2021 IEEE International Symposium on Multimedia (ISM), pp. 191-195; Wimmer, G., Schraml, R., Hofbauer, H., Petutschnigg, A., Uhl, A., An analysis of the use of hyperspectral data for roundwood tracking (2022) Computational Science and Its Applications-ICCSA 2022 Workshops, pp. 294-307. , Cham: Springer International Publishing; Schraml, R., Charwat-Pessler, J., Entacher, K., Petutschnigg, A., Uhl, A., Roundwood tracking using log end biometrics (2016) Proceedings of the Annual GIL Meeting (GIL'2016), ser. lni. Gesellschaft für Informatik, pp. 189-192; He, K., Gkioxari, G., Dollar, P., Girshick, R., Mask r-CNN (2017) 2017 IEEE International Conference on Computer Vision (ICCV), , oct; Schraml, R., Uhl, A., Pith estimation on rough log end images using local fourier spectrum analysis (2013) Proceedings of the 14th Conference on Computer Graphics and Imaging (CGIM'13), , Innsbruck, AUT, Feb; Schroff, F., Kalenichenko, D., Philbin, J., Facenet: A unified embedding for face recognition and clustering (2015) 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815-823. , June; Iandola, F.N., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J., Keutzer, K., Squeezenet: Alexnet-level accuracy with 50x fewer parameters and 1mb model size (2016) CoRR, , http://arxiv.org/abs/1602.07360, vol. abs/1602.07360, [online]. Available; Kingma, D.P., Ba, J., Adam: A method for stochastic optimization (2015) CoRR, , vol. abs/1412.6980; Huang, G., Liu, Z., Maaten Der, L.Van, Weinberger, K.Q., Densely connected convolutional networks (2017) 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261-2269
PY - 2022
Y1 - 2022
N2 - The proof of origin of wood logs is becoming more and more important. In the context of Industry 4.0 and to combat illegal logging, there is an increased interest to track each individual log. In order to track roundwood from the forest to the sawmill, this work applies log recognition based on log end images from 100 logs that were captured first in the forest and later at the sawmill. The log images are segmented from the background, then preprocessed using a novel filtering approach and features are extracted using two CNN-based methods. In this work we show that using filtering approaches that improve the visibility of the annual ring pattern and suppress unwanted image information like the saw cut pattern clearly improve the recognition results. © 2022 IEEE.
AB - The proof of origin of wood logs is becoming more and more important. In the context of Industry 4.0 and to combat illegal logging, there is an increased interest to track each individual log. In order to track roundwood from the forest to the sawmill, this work applies log recognition based on log end images from 100 logs that were captured first in the forest and later at the sawmill. The log images are segmented from the background, then preprocessed using a novel filtering approach and features are extracted using two CNN-based methods. In this work we show that using filtering approaches that improve the visibility of the annual ring pattern and suppress unwanted image information like the saw cut pattern clearly improve the recognition results. © 2022 IEEE.
KW - CNN
KW - filter bank
KW - forest
KW - roundwood tracking
KW - sawmill
KW - Forestry
KW - Image enhancement
KW - Information filtering
KW - Sawing
KW - Sawmills
KW - Wood products
KW - Annual ring
KW - Filter approach
KW - Filters bank
KW - Forest
KW - Illegal logging
KW - Image information
KW - Ring patterns
KW - Roundwood tracking
KW - Roundwoods
KW - Filter banks
U2 - 10.1109/ISM55400.2022.00056
DO - 10.1109/ISM55400.2022.00056
M3 - Conference contribution
SN - 978-1-6654-7173-2
SP - 249
EP - 256
BT - 2022 IEEE International Symposium on Multimedia (ISM)
T2 - 24th IEEE International Symposium on Multimedia, ISM 2022
Y2 - 5 December 2022 through 7 December 2022
ER -