期刊文献+

基于高频信息特征融合的超分辨率对抗网络研究

Research on Super Resolution Countermeasures Network Based on High Frequency Information Feature Fusion
下载PDF
导出
摘要 基于高频信息特征融合的超分辨率对抗网络,通过将局部和全局信息进行分离并融合,以达到提高图像的超分辨率的目的,同时避免过度平滑或者失真现象的发生。本次研究中,相关工作人员基于马尔科夫判别器和离散小波变换等概念,实现对于图像高频信息特征的提取与融合,搭建网络整体架构并引入损失函数。实验结果表明,该方法在图像重建、清晰度和结构方面都优于其他基线模型,并且具有较强的泛化能力和鲁棒性。 A super-resolution adversarial network based on high-frequency information feature fusion aims to improve the super-resolution of images by separating and fusing local and global information,while avoiding excessive smoothing or distortion.In this research,relevant staff realized the extraction and fusion of high-frequency information features of images,built the overall network architecture and introduced loss function based on concepts such as Markov discriminator and discrete wavelet transform.The experimental results show that this method outperforms other baseline models in image reconstruction,clarity,and structure,and has strong generalization ability and robustness.
作者 王永红 WANG Yonghong(Zhengzhou Institute of Finance and Technology,Zhengzhou Henan 450000,China)
出处 《信息与电脑》 2023年第11期103-105,共3页 Information & Computer
关键词 高频特征 特征融合 损失函数 high-frequency features feature fusion loss function
  • 相关文献

参考文献7

二级参考文献52

  • 1张新曼,韩九强,王勇.一种遗传搜索块寻优的不同聚焦点图像融合算法[J].电子与信息学报,2006,28(11):2054-2057. 被引量:6
  • 2赵永强,潘泉,张洪才.一种新的全色图像与光谱图像融合方法研究[J].光子学报,2007,36(1):180-183. 被引量:13
  • 3胡春海,丁志秀.基于模糊算法的多聚焦图像融合效果评价研究[J].传感技术学报,2007,20(4):885-888. 被引量:5
  • 4Yang A Y, Maji S, Hong K, et al. Distributed compression and fusion of nonnegative sparse signals for multiple-view object recognition[ C]// 12th International Conference on Information Fusion. Piscataway, NJ, USA: IEEE, 2009:1867 -1874.
  • 5Praveen K, Ankush M, Padam K. Addressing uncertainty in multi-modal fusion for improved object detection in dynamic environment [ J ~. In- formation Fusion, 2010, 11(4) : 311 -324.
  • 6Pizzi M N, Bruix S A, Calabria H C, et al. Image fusion of gated SPECT and CT angiography in coronary artery disease[J]. Revista Espanola de Medicina Nuclear, 2010, 29 (6) : 299 - 303.
  • 7Bai X Z, Zhou F G, Xue B D. Image fusion through local feature extraction by using muhi-scale top-hat by reconstruction operators[J]. Op- tik, 2013, 124(18) : 3198 -3203.
  • 8McAlpin D, Meyer F J. Multi-sensor data fusion for remote sensing of post-eruptive deformation and depositional features at Redoubt Volcano [ DB/OL]. (2012 - 08 - 23 ) [ 2013 - 09 - 15 ]. http ://www. elsevier, com/locate/jvolgeores.
  • 9Dong Z Y, Wang Z M, Liu D W, et al. SPOT5 multi-spectral (MS) and panchromatic (PAN) image fusion using an improved wavelet method based on local algorithm[ DB/OL]. (2013 -07 -13) [2013 -09 -15]. http://www, elsevier, com/locate/cageo. 141.
  • 10Zhao H, Li Q, Feng H J. Multi-focus color image fusion in the HSI space using the sum-modified-Laplacian and a coarse edge map[J]- Image and Vision Computing, 2008, 26(9) : 1285 -1295.

共引文献13

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部