Corporate Research and Development Center, Toshiba Corporation, 1 Komukaitoshiba-cho, Saiwai-ku, Kawasaki 212-8582, Japan.
IEEE Trans Pattern Anal Mach Intell. 2011 Apr;33(4):838-45. doi: 10.1109/TPAMI.2010.203.
This paper proposes a novel method for recognizing faces degraded by blur using deblurring of facial images. The main issue is how to infer a Point Spread Function (PSF) representing the process of blur on faces. Inferring a PSF from a single facial image is an ill-posed problem. Our method uses learned prior information derived from a training set of blurred faces to make the problem more tractable. We construct a feature space such that blurred faces degraded by the same PSF are similar to one another. We learn statistical models that represent prior knowledge of predefined PSF sets in this feature space. A query image of unknown blur is compared with each model and the closest one is selected for PSF inference. The query image is deblurred using the PSF corresponding to that model and is thus ready for recognition. Experiments on a large face database (FERET) artificially degraded by focus or motion blur show that our method substantially improves the recognition performance compared to existing methods. We also demonstrate improved performance on real blurred images on the FRGC 1.0 face database. Furthermore, we show and explain how combining the proposed facial deblur inference with the local phase quantization (LPQ) method can further enhance the performance.
本文提出了一种利用人脸图像去模糊来识别模糊人脸的新方法。主要问题是如何推断代表人脸模糊过程的点扩散函数 (PSF)。从单个人脸图像推断 PSF 是一个不适定问题。我们的方法使用从模糊人脸训练集中学到的先验信息，使问题更易于处理。我们构建了一个特征空间，使得由相同 PSF 退化的模糊人脸彼此相似。我们在这个特征空间中学习代表预定义 PSF 集的先验知识的统计模型。对未知模糊的查询图像与每个模型进行比较，并选择最接近的模型进行 PSF 推断。使用对应于该模型的 PSF 对查询图像进行去模糊，然后即可进行识别。在 FERET 大型人脸数据库（人工聚焦或运动模糊）上的实验表明，与现有方法相比，我们的方法显著提高了识别性能。我们还在 FRGC 1.0 人脸数据库上的真实模糊图像上展示并解释了如何结合所提出的人脸去模糊推断和局部相位量化 (LPQ) 方法来进一步提高性能。
