Vol. 18, No. 8, August 31, 2024
10.3837/tiis.2024.08.003,
Download Paper (Free):
Abstract
Chinese herbal slices (CHS) automated recognition based on computer vision plays a critical role in the practical application of intelligent Chinese medicine. Due to the complexity and similarity of herbal images, identifying Chinese herbal slices is still a challenging task. Especially, easily-confused CHS have higher inter-class and intra-class complexity and similarity issues, the existing deep learning models are less adaptable to identify them efficiently. To comprehensively address these problems, a novel tiny easily-confused CHS dataset has been built firstly, which includes six pairs of twelve categories with about 2395 samples. Furthermore, we propose a ResNeSt-CHS model that combines multilevel perception fusion (MPF) and perceptive sparse fusion (PSF) blocks for efficiently recognizing easily-confused CHS images. To verify the superiority of the ResNeSt-CHS and the effectiveness of our dataset, experiments have been employed, validating that the ResNeSt-CHS is optimal for easily-confused CHS recognition, with 2.1% improvement of the original ResNeSt model. Additionally, the results indicate that ResNeSt-CHS is applied on a relatively small-scale dataset yet high accuracy. This model has obtained state-of-the-art easily-confused CHS classification performance, with accuracy of 90.8%, far beyond other models (EfficientNet, Transformer, and ResNeSt, etc) in terms of evaluation criteria.
Statistics
Show / Hide Statistics
Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.
Cite this article
[IEEE Style]
Q. Zhang, J. Ou, H. Zhou, "Efficient Recognition of Easily-confused Chinese Herbal Slices Images Using Enhanced ResNeSt," KSII Transactions on Internet and Information Systems, vol. 18, no. 8, pp. 2103-2118, 2024. DOI: 10.3837/tiis.2024.08.003.
[ACM Style]
Qi Zhang, Jinfeng Ou, and Huaying Zhou. 2024. Efficient Recognition of Easily-confused Chinese Herbal Slices Images Using Enhanced ResNeSt. KSII Transactions on Internet and Information Systems, 18, 8, (2024), 2103-2118. DOI: 10.3837/tiis.2024.08.003.
[BibTeX Style]
@article{tiis:101091, title="Efficient Recognition of Easily-confused Chinese Herbal Slices Images Using Enhanced ResNeSt", author="Qi Zhang and Jinfeng Ou and Huaying Zhou and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2024.08.003}, volume={18}, number={8}, year="2024", month={August}, pages={2103-2118}}