Chinese Herbal Classification Based on Image Segmentation and Deep Learning Methods

Liu, Shupeng; Chen, Weiyang; Zhao, Li; Xiang, Dong

doi:10.1007/978-3-030-89698-0_28

Cited by 2 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[19] Dong used image segmentation and deep learning (DL) techniques to classify Chinese herbal medicine plants. [20] Abdollahi used CNN-based techniques for identifying medicinal plants, emphasizing biodiversity preservation [21] Lozada and co-workers investigated the effectiveness of image filters for plant identification, [22] while Gao proposed a detached feature extraction strategy for traditional Chinese medicine formulas. [23] Chen et al developed an auto ML model for the identification of 315 traditional herbs.…”

Section: Research Gaps and Motivationsmentioning

confidence: 99%

Identification of Spices and their Adulterants by Integrating Machine Learning and Analytical Techniques: A Representative Study

Naman,

Sharma,

Baldi

2024

Int. J. Pharm. Sci. Drug Res.

View full text Add to dashboard Cite

The adulteration of spices presents a substantial risk to public health and the authenticity of culinary customs. This article introduces a comprehensive interdisciplinary strategy to tackle this problem, by combining traditional and advanced techniques to authenticate spices in simple manner.The machine learning and artificial intelligence, has shown shows significant promise in diverse area based on their ability to differentiate on the basis of distinct morphological features. This article oversees the possibility to explore machine learning to check the quality of the spices and to identify their adulterants. As a representative case study, machine learning models for spice recognition, including transfer learning with pre-existing models such as MobileNetV2 is reported for the selected spice (Capsicum annum) demonstrating 97.97% accuracy. In addition, the study examines several conventional and analytical methodologies viz., qualitative tests, microscopy, colorimetry, density measurement, and spectroscopy. Furthermore, quantitative method based on high-performance liquid chromatography was developed and reported here briefly for analysing the capsaicin concentration, which is essential for assessing the quality of C. annum. This comprehensive study focuses on important areas of research that have not been well explored. The results may open a new vista in determining the quality of spices and identification of their adulterations using the artificial intelligence.

show abstract

Section: Research Gaps and Motivationsmentioning

confidence: 99%

Identification of Spices and their Adulterants by Integrating Machine Learning and Analytical Techniques: A Representative Study

Naman,

Sharma,

Baldi

2024

Int. J. Pharm. Sci. Drug Res.

View full text Add to dashboard Cite

show abstract

“…These networks have been widely used in image classification tasks, including plant classification [17,18]. For instance, Liu et al [19] utilized GoogLeNet to classify complex background images of 50 Chinese herbal medicines under natural conditions. This model has significant application value as it can be effectively used for fine-grained recognition of Chinese herbs, leading to improved accuracy and stability of recognition.…”

Section: Introductionmentioning

confidence: 99%

Origin Identification of Saposhnikovia divaricata by CNN Embedded with the Hierarchical Residual Connection Block

Yang

Yao

et al. 2023

Agronomy

View full text Add to dashboard Cite

This paper proposes a method for recognizing the origin of Saposhnikovia divaricata using the IResNet model to achieve computer vision-based classification. Firstly, we created a small sample dataset and applied data augmentation techniques to enhance its diversity. After that, we introduced the hierarchical residual connection block in the early stage of the original model to expand the perceptual field of the neural network and enhance the extraction of scale features. Meanwhile, a depth-separable convolution operation was adopted in the later stage of the model to replace the conventional convolution operation and further reduce the time cost of the model. The experimental results demonstrate that the improved network model achieved a 5.03% improvement in accuracy compared to the original model while also significantly reducing the number of parameters required for the model. In our experiments, we compared the accuracy of the proposed model with several classical convolutional neural network models, including ResNet50, Resnest50, Res2net50, RepVggNet_B0, and ConvNext_T. The results showed that our proposed model achieved an accuracy of 93.72%, which outperformed ResNet50 (86.68%), Resnest50 (89.38%), Res2net50 (91.83%), RepVggNet_B0 (88.68%), and ConvNext_T (92.18%). Furthermore, our proposed model achieved the highest accuracy among the compared models, with a transmission frame rate of 158.9 fps and an inference time of only 6.29 ms. The research methodology employed in this study has demonstrated the ability to reduce potential errors caused by manual observation, effectively improving the recognition ability of Saposhnikovia divaricata based on existing data. Furthermore, the findings of this study provide valuable reference and support for future efforts to develop lightweight models in this area.

show abstract

Chinese Herbal Classification Based on Image Segmentation and Deep Learning Methods

Cited by 2 publications

References 15 publications

Identification of Spices and their Adulterants by Integrating Machine Learning and Analytical Techniques: A Representative Study

Identification of Spices and their Adulterants by Integrating Machine Learning and Analytical Techniques: A Representative Study

Origin Identification of Saposhnikovia divaricata by CNN Embedded with the Hierarchical Residual Connection Block

Contact Info

Product

Resources

About