iWarpGAN: Disentangling Identity and Style to Generate Synthetic Iris Images
iWarpGAN: Disentangling Identity and Style to Generate Synthetic Iris Images
复制标题
DOI：
10.1109/ijcb57857.2023.10449250
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Shivangi Yadav;A. Ross
中科院分区：
文献类型：
--
作者：
Shivangi Yadav;A. Ross
生成对抗网络（GAN）在近似合成图像生成的复杂分布方面取得了成功。但是，当前基于GAN生成生物特征图像（例如IRIS）的方法具有一定的局限性：（a）合成图像在训练数据集中通常非常类似于图像； （b）生成的图像在其中所代表的独特身份的数量方面缺乏多样性； （c）很难生成与相同身份有关的多个图像。为了克服这些问题，我们建议通过使用两种转换途径在虹膜模式的上下文中删除身份和样式：身份转换途径：身份转换途径从训练集中生成独特的身份，并从训练集中生成唯一的身份，并从参考中提取样式代码使用此样式图像并输出虹膜图像。通过串联转换的身份代码和参考样式代码，Iwarpgan生成了具有类间和内部变体的虹膜图像。使用ISO/IEC 29794-6标准质量指标和Ver-ieye Iris Matcher，对所提出的方法生成此类虹膜深效的功效既定性和定量评估。此外，通过提高基于深度学习的IRIS匹配器的性能，在训练过程中使用真实数据增强合成数据，可以证明合成生成的图像的实用性。
Generative Adversarial Networks (GANs) have shown success in approximating complex distributions for synthetic image generation. However, current GAN-based methods for generating biometric images, such as iris, have certain limitations: (a) the synthetic images often closely resemble images in the training dataset; (b) the generated images lack diversity in terms of the number of unique identities represented in them; and (c) it is difficult to generate multiple images pertaining to the same identity. To overcome these issues, we propose iWarpGAN that disentangles identity and style in the context of the iris modality by using two transformation pathways: Identity Transformation Pathway to generate unique identities from the training set, and Style Transformation Pathway to extract the style code from a reference image and output an iris image using this style. By concatenating the transformed identity code and reference style code, iWarpGAN generates iris images with both inter- and intra-class variations. The efficacy of the proposed method in generating such iris Deep-Fakes is evaluated both qualitatively and quantitatively using ISO/IEC 29794-6 Standard Quality Metrics and the Ver-iEye iris matcher. Further, the utility of the synthetically generated images is demonstrated by improving the performance of deep learning based iris matchers that augment synthetic data with real data during the training process.