期刊
PATTERN RECOGNITION
卷 111, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2020.107639
关键词
Complex-valued operations; Convolutional neural network; Image denoising; Deep learning
资金
- National Natural Science Foundation of China [61872151, U1611461]
- Natural Science Foundation of Guangdong Province [2020A1515011128]
- Science and Technology Program of Guangzhou [201802010055]
- Singapore MOE AcRF [MOE2017-T2-2-156]
This study investigates the potentials of complex-valued convolutional neural networks for image denoising. Experimental results show competitive performance of the proposed complex-valued denoising CNN against existing state-of-the-art real-valued denoising CNNs, with better robustness to possible inconsistencies of noise models. Complex-valued CNNs provide another promising deep-learning-based approach to image denoising and other image recovery tasks.
While complex-valued transforms have been widely used in image processing and have their deep connections to biological vision systems, complex-valued convolutional neural networks (CNNs) have not seen their applications in image recovery. This paper aims at investigating the potentials of complex valued CNNs for image denoising. A CNN is developed for image denoising with its key mathematical operations defined in the complex number field to exploit the merits of complex-valued operations, including the compactness of convolution given by the tensor product of 1D complex-valued filters, the nonlinear activation on phase, and the noise robustness of residual blocks. The experimental results show that, the proposed complex-valued denoising CNN performs competitively against existing state-of-the-art real-valued denoising CNNs, with better robustness to possible inconsistencies of noise models between training samples and test images. The results also suggest that complex-valued CNNs provide another promising deep-learning-based approach to image denoising and other image recovery tasks. (C) 2020 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