计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 250200066-6.doi: 10.11896/jsjkx.250200066
陈平安1, 邓琦1,2
CHEN Ping’an1, DENG Qi1,2
摘要： 人脸识别与表情检测是计算机视觉和深度学习领域的热门研究方向,广泛应用于各种场景。然而,传统的表情检测方法在非受限条件下的表现差,深度学习方法则面临特征区分度低和识别精度容易受到姿势和表情变化影响等问题。对此,提出了基于SSD的网络模型重构与中心损失优化算法(IML-SSD),以提升面部表情检测的准确性和鲁棒性。首先,提出了一种基于网络重构优化的SSD面部表情快速检测算法,通过重构SSD算法模型中的基础层和辅助层,提高了识别速度、准确率和鲁棒性。随后,结合中心损失函数对SSD算法进行了进一步优化,使得同一类别的表情特征更加聚合,不同类别的特征则更加分离,从而增强了面部表情特征的判别能力。测试结果表明,所提算法优于对比算法,且在数据集FERPlus上的mAP值提升了约6.5个百分点。
中图分类号:
| [1]LI X,YANG M,DU Y T. Occlusion face recognition based on partition selection and gabor wavelet[J].Microelectronics & Computer,2023,40(5):39-46. [2]ZHOU H,LIU J H,LIU Z W,et al.Rotate-and-render unsupervised photorealistic face rotation from single-view images[C]//Proceedings of International Conference on Computer Vision and Pattern Recognition.Amsterdam:Elsevier.2020. [3]ZHANG Y S,NIE Z Y,SUI L L.Deep Learning-based Facial Recognition in Complex Mining Areas[J].Energy Science and Technology,2022,20(5):3-8. [4]WEI Y,LIU M,WANG H,et al.Learning flow-based feature warping for face frontalization with illumination inconsistent supervision[C]//Proceedings of European Conference on Compu-ter Vision.Berlin:Springer,2020. [5]ZHANG R R,MIN G,LUO T,et al.Face Recognition Algorithm Based on Deep Neural Networks Model Introducing Image Denoising Processing Mechanism[J].Digital Printing,2022(5):26-36. [6]YAO H X,DENG W H,LIUH H,et al. An overview of research development of affective computing and understanding[J].Journal of image and graphics,2022,27(6):2008-2035. [7]WANG K,PENG X J,YANG J F,et al.Suppressing Uncertainties for Large-Scale Facial Expression Recognition[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020. [8]ZHAO Z Q,LIU Q S,ZHOU F.Robust Lightweight Facial Expression Recognition Network with Label Distribution Training[C]//AAAI-21 Technical Tracks 4.2021. [9]ZENG D,LIN Z,YAN X,et al.Face2exp:Combating data biases for facial expression recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:20291-20300. [10]XIA M,ZHENG H,PENG H,et al.Enhanced multi-Scale Dynamic Facial Expression Recognition via Conditional Random Fields[J].The Visual Computer,2024,10:1-12. [11]LI J, LIU Z,WANG Z,et al.FERmc:Facial expression recognition framework based on multi-branch fusion and depthwise separable convolution[J].Information Fusion,2025,124:103416-103416. [12]JIAO Z,FU B,MAO Y,et al.Emotion Recognition MethodBased on Multiscale Attention Residual Network[J].Pattern Recognition and Image Analysis,2025,34(4):1000-1006. [13]PENG C,SUN M,ZOU K,et al.Facial Expression Recognition-You Only Look Once-Neighborhood Coordinate Attention Mamba:Facial Expression Detection and Classification Based on Neighbor and Coordinates Attention Mechanism[J].Sensors,2024,24(21):912-6912. [14]GOODFELLOW I J,ERHAN D,CARRIER P L,et al.Challenges in Representation Learning:A Report on Three Machine Learning Contests[J].Lecture Notes in Computer Science,2013,8228(1):125-132. [15]LUCEY P,COHN J F,KANADE T,et al.The Extended Cohn-Kanade Dataset (RAF-DB ):A complete dataset for action unit and emotion-specified expression[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops(CVPRW 2010).2010. [16]FARZANEH A H,QI X.Facial expression recognition in thewild via deep attentive center loss[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.2021:2402-2411. [17]ZHANG Y,WANG C,DENG W.Relative uncertainty learning for facial expression recognition[J].Advances in Neural Information Processing Systems,2021,34:17616-17627. [18]SHE J,HU Y,SHI H,et al.Dive into ambiguity:Latent distrib ution mining and pairwise uncertainty estimation for facial expression recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:6248-6257. |
|
||
首页