Image recognition of traditional Chinese medicine based on deep learning

Miao, Jianjun; Huang, Yanan; Wang, Zhaoshun; Wu, Zeqing; Lv, Jianhui

doi:10.3389/fbioe.2023.1199803

Cited by 11 publications

(7 citation statements)

References 42 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al enhanced ConvNeXt and devised a classification model for ginseng grades, addressing the issue of low variability between features in ginseng grade classification [ 25 ]. Miao et al amalgamated ConvNeXt with the ACMix network, augmenting ConvNeXt’s feature extraction performance and establishing a model for classifying traditional Chinese herbs [ 26 ]. These studies collectively substantiate the efficacy of ConvNeXt and its modified iterations in the domain of food detection.…”

Section: Methodsmentioning

confidence: 99%

A Non-Destructive Detection and Grading Method of the Internal Quality of Preserved Eggs Based on an Improved ConvNext

Tang,

Zhang,

Chen

et al. 2024

Foods

View full text Add to dashboard Cite

As a traditional delicacy in China, preserved eggs inevitably experience instances of substandard quality during the production process. Chinese preserved egg production facilities can only rely on experienced workers to select the preserved eggs. However, the manual selection of preserved eggs presents challenges such as a low efficiency, subjective judgments, high costs, and hindered industrial production processes. In response to these challenges, this study procured the transmitted imagery of preserved eggs and refined the ConvNeXt network across four pivotal dimensions: the dimensionality reduction of model feature maps, the integration of multi-scale feature fusion (MSFF), the incorporation of a global attention mechanism (GAM) module, and the amalgamation of the cross-entropy loss function with focal loss. The resultant refined model, ConvNeXt_PEgg, attained proficiency in classifying and grading preserved eggs. Notably, the improved model achieved a classification accuracy of 92.6% across the five categories of preserved eggs, with a grading accuracy of 95.9% spanning three levels. Moreover, in contrast to its predecessor, the refined model witnessed a 24.5% reduction in the parameter volume, alongside a 3.2 percentage point augmentation in the classification accuracy and a 2.8 percentage point boost in the grading accuracy. Through meticulous comparative analysis, each enhancement exhibited varying degrees of performance elevation. Evidently, the refined model outshone a plethora of classical models, underscoring its efficacy in discerning the internal quality of preserved eggs. With its potential for real-world implementation, this technology portends to heighten the economic viability of manufacturing facilities.

show abstract

Section: Methodsmentioning

confidence: 99%

A Non-Destructive Detection and Grading Method of the Internal Quality of Preserved Eggs Based on an Improved ConvNext

Tang,

Zhang,

Chen

et al. 2024

Foods

View full text Add to dashboard Cite

show abstract

“…The edge server ES j selects a random number n 0 , calculates EI j = H ID j ||n 0 , and sends it to CSC. (2) After receiving {EI j }, CSC selects the random number s 1 to calculate DI j = H EI j ||s 1 ||s and SI j = EI j ⊕ ID c , and returns them to ES j . Finally, CSC stores {EI j , s 1 }.…”

Section: Edge Server Registrationmentioning

confidence: 99%

“…The proliferation of IoT devices connecting to the Internet has led to a substantial surge in network data and processes. The updates of various information technologies have driven the upgrading of devices; image recognition, vehicle networks, industrial internet, and other time sensitive and computationally intensive businesses continue to emerge [2,3]. Currently available devices have limited computing power due to their hardware and size, which cannot guarantee the normal operation of such services.…”

Section: Introductionmentioning

confidence: 99%

A Trusted Internet of Things Access Scheme for Cloud Edge Collaboration

Zhu,

Zhou,

Jiang

2024

Electronics

View full text Add to dashboard Cite

With the rapid popularization of current Internet of Things (IoT) technology and 5G networks, as well as the continuous updating of new service lifestyles and businesses, the era of big data processing for the IoT has arrived. However, centralizing all data for processing in the cloud can lead to issues such as communication latency and privacy breaches. To solve these problems, edge computing, as a new network architecture close to terminal data sources and supporting low latency services, has gradually emerged. In this context, cloud edge collaborative computing has become an important network architecture. With the changing security requirements and communication methods of cloud edge collaborative network architecture, traditional authentication key agreement protocols are no longer applicable. Therefore, a new IoT authentication and key agreement protocol needs to be designed to solve this problem. This study proposes an IoT accessible solution for cloud edge collaboration. This scheme adopts a chaotic mapping algorithm to achieve efficient authentication. It ensures the anonymity and untraceability of users. Following this, we conducted strict security verification using BAN logic and Scyther tools. Through experimental comparative analysis, the research results show that the protocol performs better than other schemes while ensuring security. This indicates that the protocol can achieve efficient authentication and key negotiation in cloud edge collaborative network architecture, providing a secure and reliable solution for the accessibility of the IoT.

show abstract

“…Traditional Chinese tongue diagnosis heavily relies on the subjective judgment and clinical experience of TCM practitioners, resulting in outcomes that lack objective indicators Miao et al (2023) . The adoption of computer-aided tongue feature recognition models allows for an objective and quantitative diagnosis of tongue conditions, establishing a quantifiable relationship between tongue features and diseases Zhang et al (2006) .…”

Section: Introductionmentioning

confidence: 99%

Tongue feature recognition to monitor rehabilitation: deep neural network with visual attention mechanism

Yi,

Lai,

Sun

et al. 2024

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

ObjectiveWe endeavor to develop a novel deep learning architecture tailored specifically for the analysis and classification of tongue features, including color, shape, and coating. Unlike conventional methods based on architectures like VGG or ResNet, our proposed method aims to address the challenges arising from their extensive size, thereby mitigating the overfitting problem. Through this research, we aim to contribute to the advancement of techniques in tongue feature recognition, ultimately leading to more precise diagnoses and better patient rehabilitation in Traditional Chinese Medicine (TCM).MethodsIn this study, we introduce TGANet (Tongue Feature Attention Network) to enhance model performance. TGANet utilizes the initial five convolutional blocks of pre-trained VGG16 as the backbone and integrates an attention mechanism into this backbone. The integration of the attention mechanism aims to mimic human cognitive attention, emphasizing model weights on pivotal regions of the image. During the learning process, the allocation of attention weights facilitates the interpretation of causal relationships in the model’s decision-making.ResultsExperimental results demonstrate that TGANet outperforms baseline models, including VGG16, ResNet18, and TSC-WNet, in terms of accuracy, precision, F1 score, and AUC metrics. Additionally, TGANet provides a more intuitive and meaningful understanding of tongue feature classification models through the visualization of attention weights.ConclusionIn conclusion, TGANet presents an effective approach to tongue feature classification, addressing challenges associated with model size and overfitting. By leveraging the attention mechanism and pre-trained VGG16 backbone, TGANet achieves superior performance metrics and enhances the interpretability of the model’s decision-making process. The visualization of attention weights contributes to a more intuitive understanding of the classification process, making TGANet a promising tool in tongue diagnosis and rehabilitation.

show abstract

Image recognition of traditional Chinese medicine based on deep learning

Cited by 11 publications

References 42 publications

A Non-Destructive Detection and Grading Method of the Internal Quality of Preserved Eggs Based on an Improved ConvNext

A Non-Destructive Detection and Grading Method of the Internal Quality of Preserved Eggs Based on an Improved ConvNext

A Trusted Internet of Things Access Scheme for Cloud Edge Collaboration

Tongue feature recognition to monitor rehabilitation: deep neural network with visual attention mechanism

Contact Info

Product

Resources

About