[1]朱博文,吴永明,刘洋.卧床失能病人面部表情识别方法研究[J].智能系统学报,2026,21(4):952-962.[doi:10.11992/tis.202510015]
ZHU Bowen,WU Yongming,LIU Yang.Research on facial expression recognition method for bedridden patients[J].CAAI Transactions on Intelligent Systems,2026,21(4):952-962.[doi:10.11992/tis.202510015]
点击复制
ZHU Bowen,WU Yongming,LIU Yang.Research on facial expression recognition method for bedridden patients[J].CAAI Transactions on Intelligent Systems,2026,21(4):952-962.[doi:10.11992/tis.202510015]
卧床失能病人面部表情识别方法研究
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第4期
页码:
952-962
栏目:
学术论文—机器感知与模式识别
出版日期:
2026-07-05
- Title:
- Research on facial expression recognition method for bedridden patients
- Keywords:
- bedridden patients; facial expression recognition; YOLOv11; feature fusion; deep learning; attention mechanism; feature fusion; image classification; RAF-DB dataset
- 分类号:
- TP391.4
- 摘要:
- 针对卧床失能病人因面部僵硬、目光呆滞、表情钝化等因素，导致传统人脸识别方法难以准确有效捕捉病人复杂面部表情特征与变化的问题，研究一种基于YOLOv11的卧床失能病人面部表情识别方法。该方法针对性设计高效上卷积模块解决特征捕捉适配性不足问题、轻量特征融合模块强化多尺度特征复用、C2PSA-CAA（C2 position-sensitive attention-context-aware attention） 检测头模块提升复杂遮挡场景鲁棒性，通过三级模块协同优化检测准确性。对本文方法进行验证，实验结果显示：在公开数据集RAF-DB上，平均精度均值 mAP50和 mAP50-95分别达到87.83%和87.83%，与YOLOv11相比，分别提高8.46% 和 8.48%，参数量仅为 2.8×106；在自建卧床失能病人数据集上，mAP50 和 mAP50-95 分别达到87.21%和56.52%，与YOLOv11相比，分别提高3.21% 和 2.67%。实验结果表明，本文方法可更准确地实现卧床失能病人的面部表情识别，有助于实现卧床失能病人的智能监护。
- Abstract:
- To address the challenge that conventional facial recognition methods fail to accurately capture complex facial expression features and dynamics in bedridden patients with disabilities—who often present with facial stiffness, dull gaze, and flattened affect—this study proposes a YOLOv11-based facial expression recognition method specifically tailored for this patient population. This method is specifically designed with three hierarchical modules to collaboratively optimize detection accuracy: the efficient up-convolution block to address the deficiency of adaptability in feature capture, the lightweight feature fusion module to enhance multi-scale feature reuse, and the C2 position-sensitive attention-context-aware attention detection head module to improve robustness in complex occlusion scenarios. Evaluation of the proposed method demonstrated that on the public RAF-DB dataset, it achieved mean average precision (mAP) values of 87.83% for mAP50 and 87.83% for mAP50-95, representing improvements of 8.46% and 8.48% respectively, compared to YOLOv11, with a parameter count of only 2.8×106. On a self-constructed dataset of bedridden disabled patients, the method achieved mAP50 and mAP50-95 values of 87.21% and 56.52%, corresponding to increases of 3.21% and 2.67% over YOLOv11.The experimental results indicate that the proposed method enables more accurate facial expression recognition in bedridden disabled patients with disabilities, thereby contributing to intelligent care monitoring for this population.
- 参考文献/References:
-
[1] GAYA-MOREY F X, BUADES-RUBIO J M, PALANQUE P, et al. Deep learning-based facial expression recognition for the elderly: a systematic review[EB/OL]. (2025-02-04)[2025-10-15]. https://arxiv.org/abs/2502.02618.
[2] 王信, 汪友生. 基于深度学习与传统机器学习的人脸表情识别综述[J]. 应用科技, 2018(1): 65-72 WANG Xin, WANG Yousheng. Facial expression recognition based on deep learning and traditional machine learning[J]. Applied science and technology, 2018(1): 65-72
[3] 陈微, 祁郑晴, 李雪, 等. 失能老人居家护理需求的研究进展[J]. 当代护士(中旬刊), 2022, 29(11): 1-5 CHEN Wei, QI Zhengqing, LI Xue, et al. Research progress on home care needs of disabled elderly people[J]. Modern nurse, 2022, 29(11): 1-5
[4] 李钦云, 宋岳涛. 老年长期照护的国内外现状和展望[J]. 实用老年医学, 2023, 37(1): 83-86 LI Qinyun, SONG Yuetao. Present situation and prospect of long-term care for the elderly at home and abroad[J]. Practical geriatrics, 2023, 37(1): 83-86
[5] GHIMIRE D, LEE J. Geometric feature-based facial expression recognition in image sequences using multi-class AdaBoost and support vector machines[J]. Sensors, 2013, 13(6): 7714-7734
[6] 辛静. 基于帧间灰度差的动态表情识别[D]. 天津: 天津大学, 2009. XIN Jing. Dynamic facial expression recognition based on the gray difference of frames[D]. Tianjin: Tianjin University, 2009.
[7] AVANIJA J, MADHAVI K R, SUNITHA G, et al. Facial expression recognition using convolutional neural network[C]//2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition. Hyderabad: IEEE, 2022: 1-7.
[8] JIANG Qiqi, PENG Xiwei, CHEN Hanyu, et al. Facial expression recognition based on residual network[C]//2022 41st Chinese Control Conference. Hefei: IEEE, 2022: 7000-7006.
[9] 黎克迅, 高治军. LFSepNet: 融合Transformer的照明和面部特征解耦人脸识别方法[J]. 计算机工程与应用, 2026, 62(4): 201-209 LI Kexun, GAO Zhijun. LFSepNet: face recognition method with illumination and facial feature decoupling based on transformer[J]. Computer engineering and applications, 2026, 62(4): 201-209
[10] MA Hui, LEI Sen, CELIK T, et al. FER-YOLO-mamba: facial expression detection and classification based on selective state space[EB/OL]. (2024-05-03)[2025-10-15]. https://arxiv.org/abs/2405.01828.
[11] CHEN Yangbo, PENG Chunyan. Occlusion-aware facial expression recognition with dynamic feature weighting and block loss optimization[C]//Proceedings of International Conference on Image, Vision and Intelligent Systems 2025. Singapore: Springer, 2026: 197-207.
[12] LI Shan, DENG Weihong, DU Junping. Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2584-2593.
[13] SHARMA S, SHANMUGASUNDARAM K, RAMASAMY S K. FAREC: CNN based efficient face recognition technique using Dlib[C]//2016 International Conference on Advanced Communication Control and Computing Technologies. Ramanathapuram: IEEE, 2017: 192-195.
[14] RAHMAN M M, MUNIR M, MARCULESCU R. EMCAD: efficient multi-scale convolutional attention decoding for medical image segmentation[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 11769-11779.
[15] QIN Danfeng, LEICHNER C, DELAKIS M, et al. MobileNetV4: universal models for the mobile ecosystem[M]//Computer Vision–ECCV 2024. Cham: Springer Nature Switzerland, 2024: 78-96.
[16] CAI Xinhao, LAI Qiuxia, WANG Yuwei, et al. Poly kernel inception network for remote sensing detection[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 27706-27716.
[17] ASHISH V, NOAM S, NIKI P, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Auckland: NIPS, 2017: 6000–6010.
[18] SANDLER M, HOWARD A, ZHU Menglong, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4510-4520.
[19] LIU Zhuang, MAO Hanzi, WU Chaoyuan, et al. A ConvNet for the 2020s[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 11966-11976.
[20] MOU Xiangwei, XIE Liuping, SONG Yongfu, et al. Dynamic occlusion-aware facial expression recognition guided by AA-ViT[J]. Electronics, 2026, 15(4): 764
[21] LI Yong, ZENG Jiabei, SHAN Shiguang, et al. Occlusion aware facial expression recognition using CNN with attention mechanism[J]. IEEE transactions on image processing, 2019, 28(5): 2439-2450
[22] ZHAO Zengqun, LIU Qingshan, WANG Shanmin. Learning deep global multi-scale and local attention features for facial expression recognition in the wild[J]. IEEE transactions on image processing, 2021, 30: 6544-6556
[23] MA Hui, CELIK T, LI Hengchao. Lightweight attention convolutional neural network through network slimming for robust facial expression recognition[J]. Signal, image and video processing, 2021, 15(7): 1507-1515
[24] LIU Ping, LIN Yuewei, MENG Zibo, et al. Point adversarial self-mining: a simple method for facial expression recognition[J]. IEEE transactions on cybernetics, 2022, 52(12): 12649-12660
[25] LIU Hanwei, CAI Huiling, LIN Qingcheng, et al. Adaptive multilayer perceptual attention network for facial expression recognition[J]. IEEE transactions on circuits and systems for video technology, 2022, 32(9): 6253-6266
[26] CAI Jie, MENG Zibo, KHAN A S, et al. Probabilistic attribute tree structured convolutional neural networks for facial expression recognition in the wild[J]. IEEE transactions on affective computing, 2023, 14(3): 1927-1941
[27] LIU Yang, ZHANG Xingming, KAUTTONEN J, et al. Uncertain facial expression recognition via multi-task assisted correction[J]. IEEE transactions on multimedia, 2024, 26: 2531-2543
[28] ZHANG Ziyang, TIAN Xiang, ZHANG Yuan, et al. Enhanced discriminative global-local feature learning with priority for facial expression recognition[J]. Information sciences, 2023, 630: 370-384
[29] 侯海燕, 谭玉枚, 宋树祥, 等. 头部姿态鲁棒的面部表情识别[J]. 广西师范大学学报(自然科学版), 2024, 42(6): 126-137 HOU Haiyan, TAN Yumei, SONG Shuxiang, et al. Head pose-robust facial expression recognition[J]. Journal of Guangxi normal university (natural science edition), 2024, 42(6): 126-137
[30] TAO Huanjie, DUAN Qianyue. Hierarchical attention network with progressive feature fusion for facial expression recognition[J]. Neural networks, 2024, 170: 337-348
[31] ZHOU Haoliang, HUANG Shucheng, ZHANG Feifei, et al. CEPrompt: cross-modal emotion-aware prompting for facial expression recognition[J]. IEEE transactions on circuits and systems for video technology, 2024, 34(11): 11886-11899
[32] MAO Jiawei, XU Rui, YIN Xuesong, et al. POSTER++: a simpler and stronger facial expression recognition network[J]. Pattern recognition, 2025, 157: 110951
[33] 黎豊玮, 谭玉枚, 宋树祥, 等. 基于注意力引导的遮挡感知面部表情识别[J/OL]. 广西师范大学学报(自然科学版) (2025-07-28)[2025-10-15]. https://doi.org/10.16088/j.issn.1001-6600.2024120301. LI Fengwei, TAN Yumei, SONG Shuxiang, et al. Haiyingoocclusion-aware facial expression recognition based on attention guidance[J/OL]. Journal of Guangxi Normal University(natural science edition)(2025-07-28)[2025-10-15]. https://doi.org/10.16088/j.issn.1001-6600.2024120301.
[34] 党宏社, 孟饶辰, 高宛蓉. 基于双流特征交叉融合Efficient Transformer的人脸表情识别[J]. 计算机工程与应用, 2025, 61(15): 251-257 DANG Hongshe, MENG Raochen, GAO Wanrong. Facial expression recognition based on dual-stream feature cross-fusion efficient transformer[J]. Computer engineering and applications, 2025, 61(15): 251-257
[35] ZHOU Bolei, KHOSLA A, LAPEDRIZA A, et al. Learning deep features for discriminative localization[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 2921-2929.
[36] CHATTOPADHAY A, SARKAR A, HOWLADER P, et al. Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks[C]//2018 IEEE Winter Conference on Applications of Computer Vision. Lake Tahoe: IEEE, 2018: 839-847.
- 相似文献/References:
-
[1]张一鸣,欧宗瑛,王 虹.基于C均值K近邻算法的面部表情识别[J].智能系统学报,2008,3(1):57.
ZHANG Yi-ming,OU Zong-ying,WANG Hong.Facial expression recognition based on Cmeans and K-nearest neighbor algorithms[J].CAAI Transactions on Intelligent Systems,2008,3():57.
[2]孔英会,崔文婷,张珂,等.融合关键区域信息的双流网络视频表情识别[J].智能系统学报,2025,20(3):658.[doi:10.11992/tis.202401031]
KONG Yinghui,CUI Wenting,ZHANG Ke,et al.Two-stream network video expression recognition by fusing key region information[J].CAAI Transactions on Intelligent Systems,2025,20():658.[doi:10.11992/tis.202401031]
备注/Memo
收稿日期:2025-10-15。
作者简介:朱博文，硕士研究生，主要研究方向为机器视觉、智能制造。E-mail：1643928725@qq.com。;吴永明，博士，教授，主要研究方向为智能制造、绿色制造。主持广东省产学研重点项目4项，参与科技部国际合作项目1项和省部级科研项目多项，获广东省科技进步二等奖1项，获国家专利授权3项，发表学术论文60余篇。E-mail：ymwu@gdut.edu.cn。;刘洋，硕士研究生，主要研究方向为机器视觉、智能制造。E-mail：2051248370@qq.com。
通讯作者:吴永明. E-mail：ymwu@gdut.edu.cn
更新日期/Last Update:
1900-01-01