A lion-optimized efficientnet framework for non-destructive and rapid plant species identification in palm-leaf manuscripts
Source abstract
Abstract
Abstract Palm-leaf manuscripts (PLMs), essential Asian cultural artifacts, necessitate accurate species identification for their preservation. Traditional destructive analysis or manual inspection prone to errors hampers large-scale conservation efforts. To address this, we present PLNet, a lightweight framework integrating Lion-optimized EfficientNetB2 with domain-specific augmentation strategies. Lion optimizer enhances training stability, while task-driven augmentation simulates manuscript degradation. PLNet achieves exceptional performance on a diverse test set: 99.07% accuracy and 99.21% F1-score, outperforming ResNet50, DenseNet169, and YOLOv11-cls. Crucially, PLNet operates with high efficiency, utilizing only 7.7 million parameters and processing a folio in 0.31 s. To enable practical application, we developed PLNet-GUI for large-scale identification. Validated on 142,679 PLMs from 8 countries, the framework demonstrates robust real-world applicability, reveals regional species distribution patterns, and establishes a method shift in heritage conservation by replacing destructive practices with AI-driven preservation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Wood and Agarwood Research · Handwritten Text Recognition Techniques · Species Distribution and Climate Change
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (42)
Show source-provided references
1. Lawson, P. Palm leaf books and their conservation. Libr. Conserv. N. 16, 5–7 (1987).
2. Suryawanshi, D., Sinha, P. & Agrawal, O. Basic studies on the properties of palm leaf. Restaurator 15, 65–78 (1994).
3. Cai, M. Research on the cataloging items of the Beiyejing in the main collection databases of the UK. Libr. J. Shandong. 6, 75–83 (2020).
4. Xu, Z. & Liu, H. Palm leaves Buddhism Sutra culture of Xishuangbanna Dai and plant diversity. Biodiv. Sci. 3, 174–179 (1995).10.17520/biods.1995031 ↗
5. Nishanthi, M., Kumara, H. & Konpola, K. Research conception of palm leaf manuscript conservation: Bibliometric Analysis of Scopus database. Int. J. Multidiscip. Stud. 10, 13–28 (2023).
6. Cabral, U. & Rathnabahu, R. N. Report on the best practices for conservation of Palm-Leaf Manuscripts in Sri Lankan Libraries. Sri Lankan J. Librariansh. Inf. Manag. 1, 1–4 (2021).
7. Zhang, M., Song, X., Wang, J. & Lyu, X. Preservation characteristics and restoration core technology of palm leaf manuscripts in Potala Palace. Arch. Sci. 22, 501–519 (2022).10.1007/s10502-021-09383-y ↗
8. Nichols, K. An alternative approach to loss compensation in palm leaf manuscripts. Pap. Conserv. 28, 105–109 (2004).10.1080/03094227.2004.9638646 ↗
9. Crowley, A. S. Repair and conservation of palm-leaf manuscripts. Restaurator 1, 105–114 (1970).
10. Van Dyke, Y. Sacred leaves: the conservation and exhibition of early Buddhist manuscripts on palm leaves. Book Pap. Group Annu. 28, 83–97 (2009).
11. Zysk, K. G. Conjugal love in India: Ratiâsåastra and ratiramaòna: text, translation, and notes. Brill, Leiden (2002).10.1163/9789004502703 ↗
12. de Bernon, O., Sopheap, K. & An, L. K. Provisional inventory of Cambodian manuscripts, Part Two. EFEO, Bangkok (2018).
13. Aid, M. B. The documentary heritage of Myanmar: selected case studies. UNESCO, Paris (2018).
14. Tomlinson, P. B. The uniqueness of palms. Bot. J. Linn. Soc. 151, 5–14 (2006).10.1111/j.1095-8339.2006.00520.x ↗
15. ICOMOS. Principles for the preservation of historic timber structures. ICOMOS, Paris (1999).
16. Alvisi, C. Un’anima per il diritto: andare più in alto. Mucchi Editore, Modena (2023).
17. Glassman, S. Systematic studies in the leaf anatomy of palm genus Syagrus. Am. J. Bot. 59, 775–788 (1972).10.1002/j.1537-2197.1972.tb10152.x ↗
18. Sharma, D., Krist, G. & Velayudhan, N. M. Structural characterisation of 18th century Indian palm leaf manuscripts of India. Int. J. Conserv. Sci. 9, 257–264 (2018).
19. Hundius, H. & Wharton, D. The digital library of Lao manuscripts: Making the literary heritage of Laos available via the Internet. Microform Digit. Rev. 39, 142–144 (2010).
20. Mehta, R. V. K. & Challa, N. P. Facilitating enhanced user access through Palm-leaf manuscript digitization—Challenges and solutions. 2017 Second International Conference on Electrical, Computer and Communication Technologies (ICECCT). 1-4, (2017).10.1109/ICECCT.2017.8117838 ↗
21. Wu, Q., Zhou, C. & Wang, C. Feature extraction and automatic recognition of plant leaf using artificial neural network. Adv. Artif. Intell. 3, 5–12 (2006).
22. Wu, S. G. et al. A leaf recognition algorithm for plant classification using probabilistic neural network. 2007 IEEE international symposium on signal processing and information technology. 11-16, (2007).10.1109/ISSPIT.2007.4458016 ↗
23. Prasad, S., Kudiri, K. M. & Tripathi, R. Relative sub-image based features for leaf recognition using support vector machine. Proceedings of the 2011 International Conference on Communication, Computing & Security. 343-346, (ICCCS, 2011).10.1145/1947940.1948012 ↗
24. Priya, C. A., Balasaravanan, T. & Thanamani, A. S. An efficient leaf recognition algorithm for plant classification using support vector machine. International conference on pattern recognition, informatics and medical engineering. 428-432, (PRIME, 2012).10.1109/ICPRIME.2012.6208384 ↗
25. Caglayan, A., Guclu, O. & Can, A. B. A plant recognition approach using shape and color features in leaf images. Int. Conf. Image Anal. Process. 8157, 161–170 (2013).
26. Munisami, T., Ramsurn, M., Kishnah, S. & Pudaruth, S. Plant leaf recognition using shape features and colour histogram with K-nearest neighbour classifiers. Procedia Comput. Sci. 58, 740–747 (2015).10.1016/j.procs.2015.08.095 ↗
27. Jeon, W. S. & Rhee, S. Y. Plant leaf recognition using a convolution neural network. Int. J. Fuzzy Log. Intell. Syst. 17, 26-34 (2017).10.5391/IJFIS.2017.17.1.26 ↗
28. Shah, M. P., Singha, S. & Awate, S. P. Leaf classification using marginalized shape context and shape+ texture dual-path deep convolutional neural network. 2017 IEEE International Conference on Image Processing, 860-864, (ICIP, 2017).10.1109/ICIP.2017.8296403 ↗
29. Beikmohammadi, A., Faez, K. & Motallebi, A. SWP-LeafNET: a novel multistage approach for plant leaf identification based on deep CNN. Expert Syst. Appl. 202, 117470 (2022).10.1016/j.eswa.2022.117470 ↗
30. Tan, M. & Le, Q. Efficientnet: rethinking model scaling for convolutional neural networks. Int. Conf. Mach. Learn. 97, 6105–6114 (2019).
31. Buslaev, A. et al. Albumentations: fast and flexible image augmentations. Information 11, 125 (2020).10.3390/info11020125 ↗
32. Müller, R., Kornblith, S. & Hinton, G. E. When does label smoothing help?. Adv. Neural Inf. Process. Syst. 32, 4694–4703 (2019).
33. Szegedy, C. et al. Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2818-2826 (CVPR, 2016).10.1109/CVPR.2016.308 ↗
34. Chen, X. et al. Symbolic discovery of optimization algorithms. Adv. Neural Inf. Process. Syst. 36, 2931–2950 (2024).
35. Shannon, C. E. A mathematical theory of communication. Bell Syst. Tech. J. 27, 379–423 (1948).10.1002/j.1538-7305.1948.tb01338.x ↗
36. Selvaraju, R. R. et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE international conference on computer vision (ICCV), 618-626, (2017).10.1109/ICCV.2017.74 ↗
37. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition, 770-778, (CVPR, 2016).10.1109/CVPR.2016.90 ↗
38. Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2261-2269, (CVPR, 2017).10.1109/CVPR.2017.243 ↗
39. Jocher, G., Qiu, J. & Chaurasia, A. YOLOv11 by Ultralytics. GitHub repository https://github.com/ultralytics/ultralytics (2023).
40. Snoek, J., Larochelle, H. & Adams, R. P. Practical Bayesian optimization of machine learning algorithms. Adv. Neural Inf. Process. Syst. 25, 2960–2968 (2012).
41. Eagleton, G. E. Persistent pioneers; Borassus L. and Corypha L. in Malesia. Biodiversitas 17, 716–732 (2016).
42. Gabriel, A. A. & Mardhiyyah, Y. S. Utilization of Siwalan (Borassus Flabellifer L.) plantation waste for kraft paper production. J. Teknol. Ind. Pertan. Indones. 11, 1–5 (2019).10.17969/jtipi.v11i1.12111 ↗