J Shanghai Jiaotong Univ Sci ›› 2021, Vol. 26 ›› Issue (6): 857-868.doi: 10.1007/s12204-020-2235-7

• Automation, Image Processing • Previous Articles    

Poisson Image Restoration via Transformed Network

XU Xiaoling (徐晓玲), ZHENG Haiyu (郑海玉), ZHANG Fengqin (张凤芹),LI Hechen (李赫辰), ZHANG Minghui∗ (张明辉)   

  1. (School of Electronic Information Engineering, Nanchang University, Nanchang 330031, China)
  • Received:2020-01-30 Online:2021-11-28 Published:2021-12-01

Abstract: There is a Poisson inverse problem in biomedical imaging, fluorescence microscopy and so on. Sincethe observed measurements are damaged by a linear operator and further destroyed by Poisson noise, recoveringthe approximate original image is difficult. Motivated by the decouple scheme and the variance-stabilizing transformation(VST) strategy, we propose a method of transformed convolutional neural network (CNN) to restorethe observed image. In the network, the Conv-layers play the role of a linear inverse filter and the distributiontransformation simultaneously. Furthermore, there is no batch normalization (BN) layer in the residual block ofthe network, which is devoted to tackling with the non-Gaussian recovery procedure. The proposed method iscompared with state-of-the-art Poisson deblurring algorithms, and the experimental results show the effectivenessof the method.

Key words: deconvolution, Poisson noise, transformed network, decouple scheme, variance-stabilizing transformation(VST)

CLC Number: