期刊文献+

边缘融合的多字典超分辨率图像重建算法 被引量:25

Image super-resolution reconstruction based on multi-dictionary and edge fusion
下载PDF
导出
摘要 由于煤矿井下特殊的环境导致井下图像一般比较模糊和边缘特征比较弱,而目前基于字典学习的图像超分辨率重建算法通常是将全部图像块利用训练的单一字典进行重建,忽视了各图像块之间的差异性,不利于重建边缘不清晰的矿井图像。结合矿井图像特征提出一种边缘融合的多字典超分辨率图像重建方法,该算法根据各图像块的梯度统计信息将图像块进行分类并训练对应的字典库,重建时将不同字典重建的图像块融合成完整的高分辨率图像;此外为了提高图像的边缘信息,预处理阶段低分辨率图像进行边缘融合以增强边缘特征,重建的高分辨率图像利用学习的先验知识进行边缘融合以修正重建过程中出现的误差。实验表明,该算法的重建效果优于其它基于字典学习的超分辨率图像重建方法,能够很好地重建图像的边缘细节,并抑制重建过程中产生的重影和振铃效应,平均PSNR值提高1.19 d B。 Due to the special environment of coal mine, the images are generally blurred and have weak edges, and the image super-resolution reconstruction algorithm based on dictionary learning is usually that all blocks are reconstructed by single dictionary, ignoring the differences among them and being bad for reconstructing the mine images. Combined with the characteristics of mine images, this paper proposes a multi-dictionary learning image super-resolution method with edge fusion. In the method, all image blocks are classified according to the gradient statistics and dictionary librar- ies are trained. Finally, the image blocks reconstructed by different dictionaries are merged into a complete high resolu- tion image. In order to perfect the edge information, the preprocessing stage of the low-resolution image performs edge fusion to enhance their features. The high-resolution image reconstructed by dictionary learning uses the prior knowl- edge to fuse the edge information, thus correct the errors in the reconstruction process. The experiment shows that the effect of this method is improved compared with other super-resolution image reconstruction methods based on dictiona- ry learning, which can reconstruct the edge details of the image well and suppress the ghosting and ringing effect, and the value of average PSNR is increased by 1.19 dB.
作者 程德强 陈亮亮 蔡迎春 游大磊 屠屹磊 CHENG Deqiang;CHEN Liangliang;CAI Yingchun;YOU Dalei;TU Yilei(School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 211116,China)
出处 《煤炭学报》 EI CAS CSCD 北大核心 2018年第7期2084-2090,共7页 Journal of China Coal Society
基金 国家自然科学基金资助项目(51774281) 江苏省"六大人才高峰"高层次人才培养资助项目(2015-ZBZZ-009) 徐州市重点研发资助项目(KC16GZ013)
关键词 超分辨率 边缘融合 多字典 梯度统计 super-resolution edge fusion multi-dictionary gradient statistics
  • 相关文献

参考文献2

二级参考文献75

  • 1袁亮.淮南矿区煤巷稳定性分类及工程对策[J].岩石力学与工程学报,2004,23(z2):4790-4794. 被引量:36
  • 2何满潮,谢和平,彭苏萍,姜耀东.深部开采岩体力学研究[J].岩石力学与工程学报,2005,24(16):2803-2813. 被引量:2018
  • 3康红普.煤巷锚杆支护成套技术研究与实践[J].岩石力学与工程学报,2005,24(21):3959-3964. 被引量:285
  • 4彭苏萍,高云峰,杨瑞召,陈华靖,陈信平.AVO探测煤层瓦斯富集的理论探讨和初步实践——以淮南煤田为例[J].地球物理学报,2005,48(6):1475-1486. 被引量:120
  • 5陆阳,郭智奇,韩江洪,杨晴晴.矿井机车运输监控系统调度联锁过程的Petri网建模[J].煤炭学报,2007,32(11):1216-1223. 被引量:23
  • 6PARK S C,PARK M K,KANG M G. Super-resolution im-age reconstruction : a technical overview [ J ]. IEEE signal processing magazine, special issue of super-resolution image reconstruction, 2003,20 ( 3 ) : 21-36.
  • 7TSAI R Y,HUANG T S,TSAI R Y,et al. Muhiframe image restoration and registration [ C ]//Advances in Computer Vi- sion and Image Processing. [ S. 1.] :IEEE, 1984:317-339.
  • 8ZHOU F,YANG W, LIAO Q. A coarse-to-fine subpixel registration method to recover local perspective deformation in the application of image super - resolution [ J ]. IEEE transactions on image processing, 2012, 21 ( 1 ) :53-66.
  • 9MILCHEVSKI A, IVANOVSKI Z, MUSTAFA B. Machine learning based supper-resolution algorithm robust to regis- tration errors [ C ]//Digital Signal Processing Workshop and IEEE Signal Processing Education Workshop (DSP/SPE). [S. 1. ] :IEEE,2011:326-331.
  • 10VRIGKAS M, NIKOU C, KONDI L P. On the improvement of image registration for high accuracy super- resolution [ C ]//IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . [ S. 1. ] : IEEE, 2011 : 981-984.

共引文献360

同被引文献287

引证文献25

二级引证文献186

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