SAR Image segmentation based on convolutional-wavelet neural network and markov random field

作者：

Highlights：

• Convolutional neural network (CNN) is good at learning features from raw data automatically.

• A wavelet constrained pooling layer is designed to replace the conventional pooling.

• The wavelet pooling is plugged into the original CNN to generate the new network architecture named CWNN.

• Two labeling strategies (i.e., a superpixel approach and a MRF approach) are used to refine the segmentation results.

摘要

•Convolutional neural network (CNN) is good at learning features from raw data automatically.•A wavelet constrained pooling layer is designed to replace the conventional pooling.•The wavelet pooling is plugged into the original CNN to generate the new network architecture named CWNN.•Two labeling strategies (i.e., a superpixel approach and a MRF approach) are used to refine the segmentation results.

论文关键词：Convolutional Neural Network,Wavelet transform,Markov Random Filed,SAR image segmentation

论文评审过程：Received 27 March 2016, Revised 5 October 2016, Accepted 16 November 2016, Available online 18 November 2016, Version of Record 29 November 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.11.015