摘要：

为解决人脸识别技术中隐私保护与识别性能间的矛盾, 提出一种结合生成和嵌入网络的人脸隐私保护识别方法。首先利用卷积神经网络(CNN)生成模型对人脸图像像素值进行随机扰动, 生成无法被人类视觉识别但可由特定深度神经网络识别的失真人脸图像, 形成可撤销人脸模板; 随后通过预训练的FaceNet嵌入网络模型提取特征进行识别。在训练过程中, 为保证人脸模板的可识别性, 在生成网络模型中利用残差结构, 从原始图像中有效地提取关键特征, 增强图像的表现力, 并在一定程度上减少信息丢失。为增大原始图像和生成图像之间的差异并提高生成图像的多样性, 引入生成混合损失函数和多样性损失函数。为提高识别准确率, 利用改进的三元损失函数来优化模型。研究结果显示, 该方法不仅提升了人脸模板的隐私安全性, 还通过多样性损失函数增强了生成图像间的差异性, 提高了模型鲁棒性。在Aberdeen、GT和LFW数据集上的实验结果表明, 改进的三元损失函数在余弦嵌入空间中获得了更具代表性的特征表示, 识别准确率分别达到了99.87%、99.29%和98.59%。

关键词: 人脸识别, 隐私保护, 卷积神经网络, 可撤销模板, 生成网络, 嵌入网络

Abstract:

To address the contradiction between privacy protection and recognition performance in face recognition technology, a face privacy protection and recognition method combining generative and embedding networks is proposed. First, a Convolutional Neural Network (CNN)-based generative model is employed to randomly perturb the pixel values of face images, generating distorted face images that are unrecognizable to human vision but can be identified by specific deep neural networks, thereby forming cancelable face templates. Subsequently, features are extracted using a pretrained FaceNet embedding network model for recognition. During the training process, to ensure the recognition of face templates, a residual structure is utilized in the generative network model to effectively extract key features from the original images, enhance the expressiveness of the images, and reduce information loss to a certain extent. To increase the differences between the original and generated images and improve the diversity of the generated images, generative hybrid loss and diversity loss functions are introduced. To enhance the recognition accuracy, an improved triplet loss function is employed to optimize the model. The research results demonstrate that this method not only improves the privacy security of face templates but also enhances the differences among generated images using the diversity loss function, thereby improving model robustness. Experimental results on the Aberdeen, GT, and LFW datasets indicate that the improved triplet loss function achieves more representative feature representations in the cosine-embedding space, with recognition accuracy rates of 99.87%, 99.29%, and 98.59%, respectively.

Key words: face recognition, privacy protection, Convolutional Neural Network (CNN), cancelable template, generator network, embedding network