Abstract
The implementation of Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES) to combat illegal logging and associated trade necessitates accurate and efficient field screening of wood species. In this study, a total of 10,237 images of 15 Dalbergia and 11 Pterocarpus species were collected from the transverse surfaces of 417 wood specimens. Three deep learning models were then constructed, trained, and tested with these images to discriminate between timber species. The optimal parameters of the deep learning model were analyzed, and the representative wood anatomical features that were activated by the deep learning models were visualized. The results demonstrated that the overall accuracies of the 26-class, 15-class, and 11-class models were 99.3, 93.7, and 88.4%, respectively. It is suggested that at least 100 high-quality images per species with minimum patch sizes of 1000 × 1000 from more than 10 wood specimens were needed to train reliable and applicable deep learning models. The feature visualization indicated that the vessel groupings and axial parenchyma were the main wood anatomical features activated by the deep learning models. The combination of the state-of-the-art deep learning models, parameter configuration, and feature visualization provide a time- and cost-effective tool for the field screening of wood species to support effective CITES designation and implementation.
Funding source: Chinese Academy of Forestry
Award Identifier / Grant number: CAFYBB2017ZE003
Funding source: National Special Support Plan of China
Award Identifier / Grant number: W02020331
Acknowledgments
We would like to acknowledge Mr. Zhiyuan Zou for his assistance to model development, Dr. Prabu Ravindran, Dr. Richard Soares and Dr. Alex C. Wiedenhoeft of Forest Products Laboratory, USDA for their contributions to image collection and data curation. We also would like to acknowledge Dr. Bo Liu, Dr. Juan Guo, Dr. Shan Li of Chinese Academy of Forestry, Dr. Alexandre Bahia Gontijoa of Forest Products Laboratory of Brazil and Dr. Volker Haag of Thünen Institute of Germany for their assistance with the wood image identification tests.
Author contributions: Tuo He: conceptualization, data curation, investigation, methodology, software, visualization, writing (original draft); Yang Lu: data curation, investigation, validation; Lichao Jiao: formal analysis, resources; Yonggang Zhang: data curation, resources; Xiaomei Jiang: investigation; Yafang Yin: funding acquisition, supervision, writing-review and editing.
Research funding: This work was supported by the Project of Chinese Academy of Forestry (CAFYBB2017ZE003) and National Special Support Plan of China (no. W02020331).
Employment or leadership: None declared.
Honorarium: None declared.
References
Barlow, J., Lennox, G. D., Ferreira, J., Berenguer, E., Lees, A. C., Nally, R. M., Thomson, J. R., Ferraz, S. F. B., Louzada, J., Oliveira, V. H. F., et al. (2016). Anthropogenic disturbance in tropical forests can double biodiversity loss from deforestation. Nature 535: 144–147, https://doi.org/10.1038/nature18326.Search in Google Scholar PubMed
Barrett, M. A., Brown, J. L., Morikawa, M. K., Labat, J., and Yoder, A. D. (2010). CITES designation for endangered rosewood in Madagascar. Science 328: 1109–1110, https://doi.org/10.1126/science.1187740.Search in Google Scholar PubMed
Bogucki, R., Cygan, M., Khan, C. B., Klimek, M., Milczek, J. K., and Mucha, M. (2018). Applying deep learning to right whale photo identification. Conserv. Biol. 33: 676–684, https://doi.org/10.1111/cobi.13226.Search in Google Scholar PubMed PubMed Central
Brancalion, P. H. S., Almeida, D. R. A., Vidal, E., Molin, P. G., Sontag, V. E., Souza, S. E., and Schulze, M. D. (2018). Fake legal logging in the Brazilian Amazon. Science Advances 4: eaa1192, https://doi.org/10.1126/sciadv.aat1192.Search in Google Scholar PubMed PubMed Central
Canteiro, C., Barcelos, L., Filardi, F., Forzza, R., Green, L., Lanna, J., Leitman, P., Milliken, W., Morim, M. P., Patmore, K., et al. (2019). Enhancement of conservation knowledge through increased access to botanical information. Conserv. Biol. 33: 523–533. https://doi.org/10.1111/cobi.13291.Search in Google Scholar PubMed PubMed Central
Cerardo, C., Ehrilich, P. R., Barnosky, A. D., Garcia, A., Pringle, R. M., and Palmer, T. M. (2015). Accelerated modern human–induced species losses: Entering the sixth mass extinction. Sci. Adv. 1: e1400253, https://doi.org/10.1126/sciadv.1400253.Search in Google Scholar PubMed PubMed Central
CITES. (2019). Decisions made on proposals to amend Appendices I and II at CoP18. Available at: https://www.cites.org/eng/updates_decisions_cop18_species_proposals (Accessed 12 September 2019).Search in Google Scholar
Dormontt, E. E., Boner, M., Braun, B., Breulmann, G., Degen, B., Espinoza, E., Garden, S., Guilley, P., Hermanson, J. C., Koch, G., et al. (2015). Forensic timber identification: it's time to integrate disciplines to combat illegal logging. Biol. Conserv. 191: 790–798, https://doi.org/10.1016/j.biocon.2015.06.038.Search in Google Scholar
Dyrmann, M., Karstoft, H., and Midtiby, H. S. (2016). Plant species classification using deep convolutional neural network. Biosyst. Eng. 151: 72–80, https://doi.org/10.1016/j.biosystemseng.2016.08.024.Search in Google Scholar
Dumenu, W. K. (2019). Assessing the impact of felling/export ban and CITES designation on exploitation of African rosewood (Pterocarpus erinaceus). Biol. Conserv. 236: 124–133, https://doi.org/10.1016/j.biocon.2019.05.044.Search in Google Scholar
Ellwood, E. R., Soltis, P. S., and Klein, M. L. (2019). Conservation Focus: New insights for conservation from expansion of physical-collection digital data. Conserv. Biol. 33: 498–499. https://doi.org/10.1111/cobi.13287.Search in Google Scholar PubMed
Espinoza, E. O., Wiemann, M. C., Barajas-Morales, J., Chavarria, G. D., and McClure, P. J. (2015). Forensic analysis of CITES-protected Dalbergia timber from the Americas. IAWA J. 36: 311–325, https://doi.org/10.1163/22941932-20150102.Search in Google Scholar
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., and Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature 542: 115–118, https://doi.org/10.1038/nature21056.Search in Google Scholar PubMed PubMed Central
Figueroa-Mata, G., Mata-Montero, E., Valverde-Ot´arola, J. C., and Arias-Aguilar, D. (2018). Automated image-based identification of forest species: challenges and opportunities for 21st century xylotheques. International Work Conference on Bioinspired Intelligence. IEEE, San Carlos, Costa Rica, https://doi.org/10.1109/IWOBI.2018.8464206.Search in Google Scholar
Filho, P. L. P., Oliveira, L. S., Nisgoski, S., and Britto, A. S. (2014). Forest species recognition using macroscopic images. Mach. Vis. Applic. 25: 1019–1031, https://doi.org/10.1007/s00138-014-0592-7.Search in Google Scholar
Gasson, P. (2011). How precise can wood identification be? Wood anatomy's role in support of the legal timber trade, especially CITES. IAWA J. 32: 137–154, https://doi.org/10.1163/22941932-90000049.Search in Google Scholar
Gasson, P., Miller, R., Stekel, D. J., Whinder, F., and Ziemińska, K. (2010). Wood identification of Dalbergia nigra (CITES Appendix I) using quantitative wood anatomy, principal components analysis and Naïve Bayes classification. Ann. Bot. 105: 45–56, https://doi.org/10.1093/aob/mcp270.Search in Google Scholar PubMed PubMed Central
Hartvig, I., Czako, M., Kjær, E. D., Nielsen, L. R., and Theilade, I. (2015). The use of DNA barcoding in identification and conservation of rosewood (Dalbergia spp.) PLoS One 10: e0138231, https://doi.org/10.1371/journal.pone.0138231.Search in Google Scholar PubMed PubMed Central
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Las Vegas, USA, pp. 770–778.10.1109/CVPR.2016.90Search in Google Scholar
He, T., Jiao, L., Wiedenhoeft, A. C., and Yin, Y. (2019). Machine learning approaches outperform distance- and tree-based methods for DNA barcoding of Pterocarpus wood. Planta 249: 1617–1625, https://doi.org/10.1007/s00425-019-03116-3.Search in Google Scholar PubMed
Houghton, R. A., Byers, B., and Nassikas, A. A. (2015). A role for tropical forests in stabilizing atmospheric CO2. Nat. Clim. Change 5: 1022–1023, https://doi.org/10.1038/nclimate2869.Search in Google Scholar
Hwang, S. W., Kobayashi, K., Zhai, S., and Sugiyama, J. (2018). Automated identification of Lauraceae by scale-invariant feature transform. J. Wood Sci. 64: 69–77, https://doi.org/10.1007/s10086-017-1680-x.Search in Google Scholar
IAWA Committee. (2016). Index Xylariorum 4.1. Available at: https://www.iawawebsite.org/uploads/soft/Abstracts/Index%20Xylariorum%204.1.pdf.Search in Google Scholar
Irwin, A. (2019). Cops and Loggers: innovative technologies could turn the tide on illegal logging. Nature 568: 19–21. Available at: https://media.nature.com/original/magazine-assets/d41586-019-01035-7/d41586-019-01035-7.pdf (Accessed 19 October 2019).10.1038/d41586-019-01035-7Search in Google Scholar PubMed
Jiao, L., Yu, M., Wiedenhoeft, A. C., He, T., Li, J., Liu, B., Jiang, X., and Yin, Y. (2018). DNA barcode authentication and library development for the wood of six commercial Pterocarpus species: the critical role of Xylarium specimens. Sci. Rep. 8: 1945, https://doi.org/10.1038/s41598-018-20381-6.Search in Google Scholar PubMed PubMed Central
Koch, G., Haag, V., Heinz, I., Richter, H., and Schmitt, U. (2015). Control of international traded timber-the role of macroscopic and microscopic wood identification against illegal logging. J. Forensic Res. 6: 317, https://doi.org/10.4172/2157-7145.1000317.Search in Google Scholar
Kovashka, A., Russakovsky, O., Li, F., and Grauman, K. (2016). Crowdsourcing in computer vision. Found. Trends Comput. Graphics Vis. 10: 177–243, https://doi.org/10.1561/0600000071.Search in Google Scholar
Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems. NIPS, Lake Tahoe, pp. 1097–1105.Search in Google Scholar
Laurance, W. F., Wang, G., Innes, J.L., Wu, S. W., Dai, S., and Lei, J. (2008). The need to cut China's illegal timber imports. Science 319: 1184–1185, https://doi.org/10.1126/science.319.5867.1184b.Search in Google Scholar PubMed
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature 521: 436–444, https://doi.org/10.1038/nature14539.Search in Google Scholar PubMed
Lee, S. H., Chan, C. S., Wilkin, P., and Remagnino, P. (2015). Deep-plant: plant identification with convolutional neural networks. IEEE International Conference on Image Processing (ICIP). IEEE, Quebec City, Canada, pp. 452–456.10.1109/ICIP.2015.7350839Search in Google Scholar
Lewis, S. L., Edwards, D. P., and Galbraith, D. (2015). Increasing human dominance of tropical forests. Science 349: 827–832, https://doi.org/10.1126/science.aaa9932.Search in Google Scholar PubMed
Lim, C. L., Prescott, G. W., Alban, J. D. T., Ziegler, A. D., and Webb, E. L. (2017). Untangling the proximate causes and underlying drivers of deforestation and forest degradation in Myanmar. Conserv. Biol. 31: 1362–1372, https://doi.org/10.1111/cobi.12984.Search in Google Scholar PubMed
Lowe, A. J., Dormontt, E. E., Bowie, M. J., Degen, B., Gardner, S., Thomas, D., Clarke, C., Rimbawanto, A., Wiedenhoeft, A., Yin, Y., et al. (2016). Opportunities for improved transparency in the timber trade through scientific verification. Bioscience 66: 990–998, https://doi.org/10.1093/biosci/biw129.Search in Google Scholar
Mabberley, D. J. (2009). Mabberley's plant-book: a portable dictionary of plants, their classification and uses. 3rd ed. Cambridge University Press, Cambridge.Search in Google Scholar
Martins, J., Oliveira, L. S., Nisgoski, S., and Sabourin, R. (2013). A database for automatic classification of forest species. Mach. Vis. Applic. 24: 567–578, https://doi.org/10.1007/s00138-012-0417-5.Search in Google Scholar
Ng, K. K. S., Lee, S. L., Tnah, L. H., Nurul-Farhanah, Z. N., Ng, C. H., Lee, C. T., Tani, N., Diway, B., Lai, P. S., and Khoo, E. (2016). Forensic timber identification: a case study of a CITES listed species, Gonystylus bancanus (Thymelaeaceae). Forensic Sci. Int. Genet. 23: 197–209, https://doi.org/10.1016/j.fsigen.2016.05.002.Search in Google Scholar PubMed
Nualart, N., Ibáñez, N., Soriano, I., and López-Pujol, J. (2017). Assessing the relevance of herbarium collections as tools for conservation biology. Bot. Rev. 83: 303–325, https://doi.org/10.1007/s12229-017-9188-z.Search in Google Scholar
Pavlovich, M. J., Musselman, B., and Hall, A. B. (2016). Direct analysis in real time-Mass spectrometry (DART-MS) in forensic and security applications. Mass Spectr. Rev. 37: 1–17, https://doi.org/10.1002/mas.21509.Search in Google Scholar PubMed
Ravindran, P., Costa, A., Soares, R., and 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.Search in Google Scholar PubMed PubMed Central
Saatchi, S. S., Harris, N. L., Brown, S., Lefsky, M., Mitchard, E. T. A., Salas, W., Zutta, B. R., Buermann, W., Lewis, S. L., Hagen S, et al. (2011). Benchmark map of forest carbon stocks in tropical regions across three continents. Proc. Natl. Acad. Sci U.S.A. 108: 9899–9904, 10.1073/pnas.1019576108.10.1073/pnas.1019576108Search in Google Scholar PubMed PubMed Central
Silva, D. C., Pastore, T. C. M., Soares, L. F., Barros, F. A. S., Bergo, M. C. J., Coradin, V. T. H., Gontijo, A. B., Sosa, M. H., Chacón, C. B., and Braga, J. W. B. (2018). Determination of the country of origin of true mahogany (Swietenia macrophylla King) wood in five Latin American countries using handheld NIR devices and multivariate data analysis. Holzforschung 72: 521–530, https://doi.org/10.1515/hf-2017-0160.Search in Google Scholar
Siriwat, P. and Nijiman, V. (2018). Using online media-sourced seizure data to assess the illegal wildlife trade in Siamese rosewood. Environ. Conserv. 45: 352–360, https://doi.org/10.1017/S037689291800005X.Search in Google Scholar
Snel, F. A., Braga, J. W. B., Silva, D. C., Wiedenhoeft, A. C., Costa, A., Soares, R., Coradin, V. T. R., and Pastore, T. C. M. (2018). Potential field-deployable NIRS identification of seven Dalbergia species listed by CITES. Wood Sci. Technol. 52: 1411–1427, https://doi.org/10.1007/s00226-018-1027-9.Search in Google Scholar
Treanor, N. B. (2015). China's Hongmu Consumption Boom: analysis of the Chinese rosewood trade and links to illegal activity in tropical forested countries. Forest Trends Report Series: Forest Trade and Finance. Available at: https://www.forest-trends.org/ documents/files/doc_5057.pdf (Accessed 12 November 2018).Search in Google Scholar
Ugochukwu, A. I., Hobbs, J. E., Phillips, P. W. B., and Kerr, W. A. (2018). Technological solutions to authenticity issues in international trade: the case of CITES listed endangered species. Ecol. Econ. 146: 730–739, https://doi.org/10.1016/j.ecolecon.2017.12.021.Search in Google Scholar
Ullman, S., Assif, L., Fetaya, E., and Harari, D. (2016). Atoms of recognition in human and computer vision. Proc. Nat. Acad. Sci. U.S.A. 113: 2744–2749. https://doi.org/10.1073/pnas.1513198113.Search in Google Scholar PubMed PubMed Central
Wäldchen, J. and Mäder, P. (2018). Plant species identification using computer vision techniques: a systematic literature review. Arch. Comput. Methods Eng. 25: 507–543, https://doi.org/10.1007/s11831-016-9206-z.Search in Google Scholar PubMed PubMed Central
Wäldchen, J., Rzanny, M., Seeland, M., and Mäder, P. (2018). Automated plant species identification-trends and future directions. PLoS Comput. Biol. 14: e1005993, https://doi.org/10.1371/journal.pcbi.1005993.Search in Google Scholar PubMed PubMed Central
Wiedenhoeft, A. C., Simeone, J., Smith, A., Parker-Forney, M., Soares, R., and Fishman, A. (2019). Fraud and misrepresentation in retail forest products exceeds U.S. forensic wood science capacity. PLoS ONE 14: e0219917, https://doi.org/10.1371/journal.pone.0219917.Search in Google Scholar PubMed PubMed Central
Yu, M., Jiao, L., Guo, J., Wiedenhoeft, A. C., He, T., Jiang, X., and Yin, Y. (2017). DNA barcoding of vouchered xylarium wood specimens of nine endangered Dalbergia species. Planta 246: 1165–1176, https://doi.org/10.1007/s00425-017-2758-9.Search in Google Scholar PubMed
Zhang, M., Zhao, G., Liu, B., He, T., Guo, J., Jiang, X., and Yin, Y. (2019). Wood discrimination analyses of Pterocarpus tinctorius and endangered Pterocarpus santalinus using DART-FTICR-MS coupled with multivariate statistics. IAWA J. 40: 58–74, https://doi.org/10.1163/22941932-40190224.Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
