信息安全研究2024，Vol.10Issue(1)：25-33,9.DOI:10.12379/j.issn.2096-1057.2024.01.05
融合卷积神经网络和Transformer的人脸欺骗检测模型
Face Spoofing Detection Model with Fusion of Convolutional Neural Network and Transformer
摘要
Abstract
In the field of face anti-spoofing,the methods based on Convolutional Neural Network(CNN)can learn feature representation with fewer parameters,yet their receptive fields remain local.In contrast,Transformer-based methods offer global perception but entail an impractical volume of parameters and computations,hindering widespread deployment on mobile or edge devices.To address these challenges,this paper proposed a face spoofing detection model that integrates CNN and Transformer,aiming to achieve a balance between the amount of parameters and accuracy while maintaining the ability to extract global and local features.Firstly,local face images are cropped and selected as input to effectively avoid overfitting.Secondly,the feature extraction module based on coordinate attention is designed.Finally,the fusion of CNN and Transformer modules are designed to extract local and global features of images through local-global-local information exchange.The experimental results show that the model achieved an accuracy of 99.31％and an average error rate of 0.54％on the CASIA-SURF(Depth modality)dataset;Moreover zero error rate is achieved on the CASIA-FASD and Replay-Attack datasets,and the model parameters are only 0.59MB,much smaller than the Transformer series models.关键词
人脸欺骗检测/CNN/Transformer/模型融合/注意力机制Key words
face spoofing detection/CNN/Transformer/model fusion/attention mechanisy分类
信息技术与安全科学引用本文复制引用
黄灵,何希平,贺丹,杨楚天,旷奇弦..融合卷积神经网络和Transformer的人脸欺骗检测模型[J].信息安全研究,2024,10(1):25-33,9.基金项目
重庆市教育委员会科学技术研究项目(KJZD-K20220080) （KJZD-K20220080）
重庆工商大学研究生科研创新项目(yjscxx2022-112-180) （yjscxx2022-112-180）
