Multitask Analysis Method for Tongue Image Based on Edge Computing

In response to the application scenarios of modernized Traditional Chinese Medicine (TCM) diagnostic and treatment equipment moving towards the user end, an effort has been made to enhance the user-friendliness of TCM diagnostic and treatment devices. This involves introducing the concept of edge co...

Full description

Saved in:
Bibliographic Details
Main Authors: Tingting Song, Bin Liu, Fengen Yuan, Yunfeng Wang, Kang Yu, Hao Yang, Qiuyan Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10480706/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849304241698504704
author Tingting Song
Bin Liu
Fengen Yuan
Yunfeng Wang
Kang Yu
Hao Yang
Qiuyan Li
author_facet Tingting Song
Bin Liu
Fengen Yuan
Yunfeng Wang
Kang Yu
Hao Yang
Qiuyan Li
author_sort Tingting Song
collection DOAJ
description In response to the application scenarios of modernized Traditional Chinese Medicine (TCM) diagnostic and treatment equipment moving towards the user end, an effort has been made to enhance the user-friendliness of TCM diagnostic and treatment devices. This involves introducing the concept of edge computing into the mobile tongue diagnosis instrument, shifting the tasks of tongue image acquisition and analysis to portable auxiliary diagnostic devices. To improve the efficiency of edge computing devices in handling tongue image analysis tasks, a multi-task network model based on a lightweight network backbone is proposed. The model utilizes the lightweight feature extraction backbone of MobileNet to provide feature encoding for both the semantic segmentation branch and the multi-label classification branch. The semantic segmentation branch adopts a skip-layer connection structure with multi-scale feature maps, and an attention mechanism is incorporated into the classification branch to fuse the feature maps from the segmentation branch. This achieves tongue segmentation and multi-label classification tasks in a computationally efficient environment. The model achieves a pixel accuracy of 85.3% in semantic segmentation and an accuracy of 95.6% in multi-label classification. The network’s forward propagation speed on edge computing platforms reaches 7 frames per second (FPS). The proposed lightweight network backbone multi-task network model ensures a significant improvement in processing efficiency while maintaining the accuracy of segmentation and classification tasks. Additionally, the model exhibits advantages in terms of quantity and scale, saving both storage and computational resources. It not only enhances the accuracy and efficiency of tongue image real-time analysis in edge computing scenarios but also reduces the processing time, providing excellent precision and inference speed.
format Article
id doaj-art-01e88ca2b632431a84e2162c4f688df3
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-01e88ca2b632431a84e2162c4f688df32025-08-20T03:55:48ZengIEEEIEEE Access2169-35362025-01-011312408612409510.1109/ACCESS.2024.338230310480706Multitask Analysis Method for Tongue Image Based on Edge ComputingTingting Song0Bin Liu1https://orcid.org/0009-0006-6860-5745Fengen Yuan2Yunfeng Wang3https://orcid.org/0000-0003-2738-8706Kang Yu4Hao Yang5https://orcid.org/0000-0002-9564-4815Qiuyan Li6Chinese Academy of Sciences, Institute of Microelectronics, Beijing, ChinaChinese Academy of Sciences, Institute of Microelectronics, Beijing, ChinaChinese Academy of Sciences, Institute of Microelectronics, Beijing, ChinaChinese Academy of Sciences, Institute of Microelectronics, Beijing, ChinaChinese Academy of Sciences, Institute of Microelectronics, Beijing, ChinaChinese Academy of Sciences, Institute of Microelectronics, Beijing, ChinaXiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaIn response to the application scenarios of modernized Traditional Chinese Medicine (TCM) diagnostic and treatment equipment moving towards the user end, an effort has been made to enhance the user-friendliness of TCM diagnostic and treatment devices. This involves introducing the concept of edge computing into the mobile tongue diagnosis instrument, shifting the tasks of tongue image acquisition and analysis to portable auxiliary diagnostic devices. To improve the efficiency of edge computing devices in handling tongue image analysis tasks, a multi-task network model based on a lightweight network backbone is proposed. The model utilizes the lightweight feature extraction backbone of MobileNet to provide feature encoding for both the semantic segmentation branch and the multi-label classification branch. The semantic segmentation branch adopts a skip-layer connection structure with multi-scale feature maps, and an attention mechanism is incorporated into the classification branch to fuse the feature maps from the segmentation branch. This achieves tongue segmentation and multi-label classification tasks in a computationally efficient environment. The model achieves a pixel accuracy of 85.3% in semantic segmentation and an accuracy of 95.6% in multi-label classification. The network’s forward propagation speed on edge computing platforms reaches 7 frames per second (FPS). The proposed lightweight network backbone multi-task network model ensures a significant improvement in processing efficiency while maintaining the accuracy of segmentation and classification tasks. Additionally, the model exhibits advantages in terms of quantity and scale, saving both storage and computational resources. It not only enhances the accuracy and efficiency of tongue image real-time analysis in edge computing scenarios but also reduces the processing time, providing excellent precision and inference speed.https://ieeexplore.ieee.org/document/10480706/Edge computingmulti-task networksemantic segmentationtongue diagnosisclassification
spellingShingle Tingting Song
Bin Liu
Fengen Yuan
Yunfeng Wang
Kang Yu
Hao Yang
Qiuyan Li
Multitask Analysis Method for Tongue Image Based on Edge Computing
IEEE Access
Edge computing
multi-task network
semantic segmentation
tongue diagnosis
classification
title Multitask Analysis Method for Tongue Image Based on Edge Computing
title_full Multitask Analysis Method for Tongue Image Based on Edge Computing
title_fullStr Multitask Analysis Method for Tongue Image Based on Edge Computing
title_full_unstemmed Multitask Analysis Method for Tongue Image Based on Edge Computing
title_short Multitask Analysis Method for Tongue Image Based on Edge Computing
title_sort multitask analysis method for tongue image based on edge computing
topic Edge computing
multi-task network
semantic segmentation
tongue diagnosis
classification
url https://ieeexplore.ieee.org/document/10480706/
work_keys_str_mv AT tingtingsong multitaskanalysismethodfortongueimagebasedonedgecomputing
AT binliu multitaskanalysismethodfortongueimagebasedonedgecomputing
AT fengenyuan multitaskanalysismethodfortongueimagebasedonedgecomputing
AT yunfengwang multitaskanalysismethodfortongueimagebasedonedgecomputing
AT kangyu multitaskanalysismethodfortongueimagebasedonedgecomputing
AT haoyang multitaskanalysismethodfortongueimagebasedonedgecomputing
AT qiuyanli multitaskanalysismethodfortongueimagebasedonedgecomputing