arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.03565cs.CV
收藏

NIR-VIS异构人脸识别中的互谱人脸补全

Cross-spectral Face Completion for NIR-VIS Heterogeneous Face Recognition

National Laboratory of Pattern Recognition, CASIA(中国科学院自动化研究所模式识别国家重点实验室);Center for Research on Intelligent Perception and Computing, CASIA(中国科学院自动化研究所智能感知与计算研究中心);Center for Excellence in Brain Science and Intelligence Technology, CAS(中国科学院脑科学与智能技术卓越创新中心);University of Chinese Academy of Sciences(中国科学院大学)

Ran He, Jie Cao, Lingxiao Song, Zhenan Sun, Tieniu Tan

摘要:

近红外-可见光(NIR-VIS)异构人脸识别是指将近红外和可见光人脸图像进行匹配的过程。当前的异构方法试图通过从NIR图像合成VIS图像来将VIS人脸识别方法扩展到NIR光谱。然而,由于自遮挡和传感间隙,近红外人脸图像丢失了一些可见光的内容,使他们总是不完整的VIS人脸图像相比。本文将高分辨率异构人脸合成建模为两个组件的互补组合,即纹理修复组件和姿态校正组件。修复组件从NIR图像纹理合成和修复VIS图像纹理。校正组件将NIR图像中的任何姿态映射到VIS图像中的正面姿态,从而产生成对的NIR和VIS纹理。开发了一个翘曲过程,将这两个组件集成到端到端的深度网络中。分别设计了细粒度的类内方差和基于小波变换的类内方差和视觉质量监控算法。为了保证合成结果,采用了一次UV损失、两次对抗损失和一次像素损失。我们证明,通过附加的校正组件,我们可以简化异构人脸合成从一对多的不成对的图像翻译到一对一的成对图像翻译,并尽量减少异构识别过程中的光谱和姿态差异。大量的实验结果表明,我们的网络不仅产生高分辨率的VIS人脸图像,而且还有利于提高异构人脸识别的准确性。

英文摘要:

Near infrared-visible (NIR-VIS) heterogeneous face recognition refers to the process of matching NIR to VIS face images. Current heterogeneous methods try to extend VIS face recognition methods to the NIR spectrum by synthesizing VIS images from NIR images. However, due to self-occlusion and sensing gap, NIR face images lose some visible lighting contents so that they are always incomplete compared to VIS face images. This paper models high resolution heterogeneous face synthesis as a complementary combination of two components, a texture inpainting component and pose correction component. The inpainting component synthesizes and inpaints VIS image textures from NIR image textures. The correction component maps any pose in NIR images to a frontal pose in VIS images, resulting in paired NIR and VIS textures. A warping procedure is developed to integrate the two components into an end-to-end deep network. A fine-grained discriminator and a wavelet-based discriminator are designed to supervise intra-class variance and visual quality respectively. One UV loss, two adversarial losses and one pixel loss are imposed to ensure synthesis results. We demonstrate that by attaching the correction component, we can simplify heterogeneous face synthesis from one-to-many unpaired image translation to one-to-one paired image translation, and minimize spectral and pose discrepancy during heterogeneous recognition. Extensive experimental results show that our network not only generates high-resolution VIS face images and but also facilitates the accuracy improvement of heterogeneous face recognition.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑