当前位置: X-MOL 学术IEEE Trans. Neural Netw. Learn. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Noise Robust Face Hallucination Based on Smooth Correntropy Representation.
IEEE Transactions on Neural Networks and Learning Systems ( IF 10.4 ) Pub Date : 2021-04-22 , DOI: 10.1109/tnnls.2021.3071982
Licheng Liu , Qiying Feng , C. L. Philip Chen , Yaonan Wang

Face hallucination technologies have been widely developed during the past decades, among which the sparse manifold learning (SML)-based approaches have become the popular ones and achieved promising performance. However, these SML methods always failed in handling noisy images due to the least-square regression (LSR) they used for error approximation. To this end, we propose, in this article, a smooth correntropy representation (SCR) model for noisy face hallucination. In SCR, the correntropy regularization and smooth constraint are combined into one unified framework to improve the resolution of noisy face images. Specifically, we introduce the correntropy induced metric (CIM) rather than the LSR to regularize the encoding errors, which admits the proposed method robust to noise with uncertain distributions. Besides, the fused LASSO penalty is added into the feature space to ensure similar training samples holding similar representation coefficients. This encourages the SCR not only robust to noise but also can well exploit the inherent typological structure of patch manifold, resulting in more accurate representations in noise environment. Comparison experiments against several state-of-the-art methods demonstrate the superiority of SCR in super-resolving noisy low-resolution (LR) face images.

中文翻译:

基于光滑熵表示的噪声鲁棒人脸幻觉。

在过去的几十年中,面部幻觉技术得到了广泛的发展,其中基于稀疏流形学习(SML)的方法已成为流行的方法并取得了令人鼓舞的性能。但是,由于它们用于误差近似的最小二乘回归(LSR),这些SML方法始终无法处理嘈杂的图像。为此,我们在本文中提出了一种用于嘈杂的面部幻觉的平滑熵表示(SCR)模型。在SCR中,将熵的正则化和平滑约束组合到一个统一的框架中,以提高嘈杂的人脸图像的分辨率。具体来说,我们引入了熵诱导度量(CIM)而不是LSR来规范化编码错误,这使所提出的方法对不确定分布的噪声具有鲁棒性。除了,将融合的LASSO罚分添加到特征空间中,以确保具有相似表示系数的相似训练样本。这鼓励SCR不仅对噪声具有鲁棒性,而且可以很好地利用膜片歧管的固有类型结构,从而在噪声环境中获得更准确的表示。针对几种最先进方法的对比实验证明了SCR在超分辨带噪低分辨率(LR)人脸图像中的优越性。
更新日期:2021-04-22
down
wechat
bug