Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (3): 137-143.DOI: 10.3778/j.issn.1002-8331.1911-0143

Previous Articles     Next Articles

Low-Resolution Face Recognition Based on Self-Normalizing Neural Network

SHI Zhengyu, CHEN Renwen, HUANG Bin   

  1. State Key Laboratory of Mechanics and Control of Mechanical Structures, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
  • Online:2021-02-01 Published:2021-01-29



  1. 南京航空航天大学 机械结构力学及控制国家重点实验室,南京 210016


Traditional face recognition algorithms tend to decline when it occurs to low resolution face images. In order to solve this problem, a Light Discriminative Self-normalizing Neural Network(LDSNN) model is proposed, which extracts discriminative features from High-Resolution(HR) images and corresponding Low-Resolution(LR) images, and learns a coupled mapping which transforms the features to a common subspace. While the property of self-normalizing resulting from scaled exponential linear units accelerates the training stage. A loss function is designed to minimize intraclass distances and enlarge interclass distances based on not only the discriminability of HR-LR features, but also the similarity between them. Thus features from the same subject are more compacted together. The recognition rate of the proposed LDSNN model on a standard and two surveillance databases are 95.57%, 94.10%, and 84.56% respectively, better than other algorithms, which demonstrates that the proposed method works well with uncontrolled low-resolution face recognition.

Key words: face recognition, self-normalizing neural network, coupled mapping, sub-space, intraclass distances, interclass distances



关键词: 人脸识别, 自归一化神经网络, 耦合映射, 子空间, 类内距, 类间距