期刊
COMPUTERS & GRAPHICS-UK
卷 98, 期 -, 页码 82-92出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.cag.2021.04.025
关键词
Small data assisting; Illumination normalization; Deep learning; Face recognition
This paper proposes a small data-assisted face image illumination normalization method, which improves generalization ability by training the network model on a small number of image pairs and using different network parameters for different face images. Experiments show that the method performs well in normalization even when only 500 face image pairs are used for training.
Image transfer based on deep learning methods can achieve good results in face illumination processing. However, data constraints and generalization ability restrict the further development of these methods in this field. In this paper, we propose small data assisting face image illumination normalization. For data constraints, we train the network model on a small number of image pairs. In terms of generalization ability, the proposed normalization network parameters are different for processing different face images. Small data learning can provide prior knowledge, and the reconstruction process can guide detail gen-eration. Therefore, the small data learning network and the reconstruction network are complementary to each other in image generating mode when only a small quantity of data is available. We use this network mode to normalize the illumination and reconstruct the super-resolution of face images. After illumination normalization, super-resolution reconstruction can obtain more precise face information and further improve the face recognition rate. Experiments show that the proposed method has good normal-ization performance when only 500 face image pairs are used for training. (C) 2021 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据