EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Tortoise plastron versus adulterants: identification and comparative study using image recognition technology

Haoyu Tu, Xiaoshun Wang, Zifang Wu, Zhen Huang, Xinyue Zhou, Jiaxin Zou, Yaodong Ping, Ling Xiao, Wentao Sheng, Lei Wang, Wenfeng Xu, Pengfei Jin und 2 weitere

Machine Vision and Applications · 2026-07 · 37 (4)

DOI: 10.1007/s00138-026-01838-5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Vision and Applications, online erschienen am 11.06.2026. Verfasst von Haoyu Tu und 13 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: China Health & Medical Development Foundation, The foundation of the NMPA Key Laboratory of Quality Control of Chinese Medicine.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Compared with botanical medicines, the intelligent identification of animal-derived medicines has developed relatively slowly and presents greater challenges due to species diversity, substantial morphological variations after processing, and the prevalence of adulteration. Tortoise plastron is a representative animal-derived medicine whose subtle morphological differences complicate reliable authentication. This study aimed to establish a standardized image-based framework to achieve accurate and reproducible identification of tortoise plastron and its common adulterants. An RGB image dataset covering Chinemys reevesii, Mauremys mutica, Ocadia sinensis, Malayemys subtrijuga, and Trachemys scripta elegans was constructed. Images were enhanced through geometric transformations, color jittering, and Gaussian blurring to simulate diverse acquisition conditions. Segmentation was performed using the SAM2 model to remove background noise and extract core regions, and classification was conducted using YOLO11 models of three scales (m, l, x). Training and validation were carried out on datasets with and without segmentation-based augmentation, each repeated three times, with average performance recorded. Statistical analysis included comparison of model performance metrics across datasets and model scales. The combined preprocessing–segmentation–classification workflow effectively captured both global and fine-grained features of tortoise plastron. YOLO11m with segmentation-based augmentation achieved the most balanced performance across accuracy and robustness. Eight technical modules, including attention-enhanced feature extraction and multi-scale pooling, contributed to improved classification precision. A practical recognition application was developed to facilitate user-friendly deployment. This study established a comprehensive digital framework for the objective identification of tortoise plastron and adulterants, transforming subjective trait-based evaluation into quantitative image analysis. The integration of advanced segmentation and multi-scale feature fusion provides a transferable paradigm for the intelligent identification of animal-derived medicines, with potential to enhance quality control and authenticity assurance in traditional Chinese medicine.

Förderung

  • China Health & Medical Development Foundation
  • The foundation of the NMPA Key Laboratory of Quality Control of Chinese Medicine

Zitieren

APA

Tu, H., Wang, X., Wu, Z., Huang, Z., Zhou, X., Zou, J., Ping, Y., Xiao, L., Sheng, W., Wang, L., Xu, W., Jin, P., Hu, H., & Wang, Z. (2026). Tortoise plastron versus adulterants: identification and comparative study using image recognition technology. Machine Vision and Applications, 37(4). https://doi.org/10.1007/s00138-026-01838-5

Vancouver

Tu H, Wang X, Wu Z, Huang Z, Zhou X, Zou J, et al. Tortoise plastron versus adulterants: identification and comparative study using image recognition technology. Machine Vision and Applications. 2026;37(4). doi:10.1007/s00138-026-01838-5

BibTeX
@article{Tu2026,
  author = {Tu, Haoyu and Wang, Xiaoshun and Wu, Zifang and Huang, Zhen and Zhou, Xinyue and Zou, Jiaxin and Ping, Yaodong and Xiao, Ling and Sheng, Wentao and Wang, Lei and Xu, Wenfeng and Jin, Pengfei and Hu, Hankun and Wang, Zhongyuan},
  title = {Tortoise plastron versus adulterants: identification and comparative study using image recognition technology},
  journal = {Machine Vision and Applications},
  year = {2026},
  volume = {37},
  number = {4},
  doi = {10.1007/s00138-026-01838-5}
}
Kostenlos starten →