典型文献
Multi-scale fusion residual encoder-decoder approach for low illumination image enhancement
文献摘要：
The sensing light source of the line scan camera cannot be fully exposed in a low light environment due to the extremely small number of photons and high noise,which leads to a reduction in image quality.A multi-scale fusion residual encoder-decoder(FRED)was proposed to solve the problem.By directly learning the end-to-end mapping between light and dark images,FRED can enhance the image's brightness with the details and colors of the original image fully restored.A residual block(RB)was added to the network structure to increase feature diversity and speed up network training.Moreover,the addition of a dense context feature aggregation module(DCFAM)made up for the deficiency of spatial information in the deep network by aggregating the context's global multi-scale features.The experimental results show that the FRED is superior to most other algorithms in visual effect and quantitative evaluation of peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM).For the factor that FRED can restore the brightness of images while representing the edge and color of the image effectively,a satisfactory visual quality is obtained under the enhancement of low-light.
文献关键词：
中图分类号：
作者姓名：
Pan Xiaoying;Wei Miao;Wang Hao;Jia Fengzhu
作者机构：
School of Computer Science and Technology,Xi'an University of Posts and Telecommunications,Xi'an 710121,China;Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing,Xi'an University of Posts and Telecommunications,Xi'an 710121,China;School of Software,Northwestern Polytechnical University,Xi'an 710072,China
文献出处：
引用格式：
[1]Pan Xiaoying;Wei Miao;Wang Hao;Jia Fengzhu-.Multi-scale fusion residual encoder-decoder approach for low illumination image enhancement)[J].中国邮电高校学报（英文版）,2022(02):63-72
A类：
FRED,DCFAM
B类：
Multi,scale,fusion,residual,encoder,decoder,approach,low,illumination,enhancement,sensing,light,source,line,scan,camera,cannot,fully,exposed,environment,due,extremely,small,number,photons,high,noise,which,leads,reduction,quality,multi,was,proposed,solve,problem,By,directly,learning,end,mapping,between,dark,images,brightness,details,colors,original,restored,block,RB,added,network,structure,increase,diversity,speed,training,Moreover,addition,dense,context,aggregation,module,made,deficiency,spatial,information,deep,by,aggregating,global,features,experimental,results,show,that,superior,most,other,algorithms,visual,quantitative,evaluation,peak,signal,ratio,PSNR,structural,similarity,measure,SSIM,For,while,representing,edge,effectively,satisfactory,obtained,under
AB值：
0.561855
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
