A DAC-CLGD-Danet network based method for defaced image segmentation  

作　　者：Pengbo Li Gang Li Yibin He Ling Zhang Yuanjin Sun Fayun Guo 

机构地区：[1]College of Software,Taiyuan University of Technology,Taiyuan 030024,China [2]Information Technology Department,Shanxi Taisen Technology Co.Ltd.,Taiyuan 030082,China

出　　处：《Intelligent and Converged Networks》2022年第3期294-308,共15页智能与融合网络（英文）

基　　金：supported by the Central Leading Local Special Foundation of Shanxi Province(Nos.YDZJSX2021C004 and YDZJSX2022A016);the Natural Science Foundation of Shanxi Province(No.20210302124554)。

摘　　要：Based on the problems of high noise,lower contrast,and complex features in defaced images and the low accuracy of existing defaced image segmentation techniques,this paper proposes a defaced image segmentation algorithm based on DAC-CLGD-Danet.Firstly,a CBDNet asymmetric blind denoising network is used for noise-containing defaced images,and natural and synthetic images are trained together to model the image noise and enhance the denoising ability of natural noise.Secondly,Danet is used as the base network.A Dense Atrous Convolution module(DAC)is added to the dual attention mechanism module to extend the perceptual domain of deep convolution,reduce image feature loss,and enhance the representation of global information and edge features of defaced images;Cross-Level Gating Decoder module(CLGD)is introduced to lighten the segmentation network,enhance image context aggregation,and produce accurate semantic segmentation.The experimental results demonstrated that the method in this paper has a significant effect on the HRF dataset and Cityscapes dataset,with a significant improvement compared with FCN,UNet,and SETR models,with Intersection over Union(IoU)improved by 9.81%and Mean Intersection over Union(mIoU)improved by 3.01%compared with UNet.

关 键 词：image segmentation Danet deep learning neural networks defaced images 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]