基于主客观联合评价判据的红外超分辨率重建方法研究
投稿时间:2019-04-25  修订日期:2019-05-06  点此下载全文
引用本文:
摘要点击次数: 140
全文下载次数: 0
作者单位E-mail
邵保泰 中国科学院上海技术物理研究所 shaobaotai@sina.com 
汤心溢 中国科学院上海技术物理研究所 gq227@mail.sitp.ac.cn 
张宁 中国科学院上海技术物理研究所  
基金项目:国家十三五国防预研项目(HJJ2017-0083/YYAB3007),中国科学院青年创新促进会(2014216)
中文摘要:在红外超分辨率成像应用中,提高主观视觉效果有着很现实的需求。当前基于深度学习的图像超分辨率重建方法大多以客观评价指标为损失函数进行训练和优化,主观评价方法因量化困难而难以应用,为此本文着重研究了主观评价和各种可量化的客观评价指标的相关性,发现相位一致性特征与主观评价结果关联度高。据此设计了基于主客观联合评价的损失函数,应用于红外图像超分辨率重建算法,实验表明本方法在保持客观质量评价的同时,更好地提高了图像的主观视觉效果。
中文关键词:超分辨率重建  红外图像  主客观联合评价、损失函数
 
Research on infrared super-resolution based on criterion of subjectivity and objectivity joint evaluation
Abstract:In the application of infrared super-resolution imaging, it is actual demand to improve the subjective visual effects of images. At present, most of the image super-resolution reconstruction methods based on deep learning are trained and optimized with objective evaluation index as loss function. The subjective evaluation method is difficult to apply because of the difficulty of quantification. Therefore, this paper focuses on the correlation between subjective evaluation and quantifiable objective evaluation indexes, and finds that the characteristics of phase consistency are highly correlated with subjective evaluation results. Based on this, a loss function based on subjective and objective joint evaluation is designed and applied to the super-resolution reconstruction algorithm of infrared image. Experiments show that this method can improve the subjective visual effect of image while maintaining the objective evaluation score.
keywords:super-resolution reconstruction  infrared image  subjective and objective joint evaluation, loss function
  HTML  查看/发表评论  下载PDF阅读器

版权所有:《红外与毫米波学报》编辑部