[1]杨欣,费树岷,周大可,等.基于分类预测器及退化模型的图像超分辨率快速重建[J].东南大学学报(自然科学版),2013,43(1):35-38.[doi:10.3969/j.issn.1001-0505.2013.01.007]
 Yang Xin,Fei Shumin,Zhou Dake,et al.Image fast super-resolution reconstruction based on class predictor and degradation model[J].Journal of Southeast University (Natural Science Edition),2013,43(1):35-38.[doi:10.3969/j.issn.1001-0505.2013.01.007]
点击复制

基于分类预测器及退化模型的图像超分辨率快速重建()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
43
期数:
2013年第1期
页码:
35-38
栏目:
机械工程
出版日期:
2013-01-20

文章信息/Info

Title:
Image fast super-resolution reconstruction based on class predictor and degradation model
作者:
杨欣12费树岷2周大可1唐庭阁1
1南京航空航天大学自动化学院, 南京210016; 2东南大学自动化学院, 南京210096
Author(s):
Yang Xin12 Fei Shumin2 Zhou Dake1 Tang Tingge1
1 College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
2 School of Automation, Southeast University, Nanjing 210096, China
关键词:
超分辨率重建 分类预测器 退化模型 特征提取 邻域嵌套
Keywords:
super-resolution reconstruction class predictor degradation model feature extraction neighbor embedding
分类号:
TH457
DOI:
10.3969/j.issn.1001-0505.2013.01.007
摘要:
对基于学习的领域嵌套超分辨率重建方法进行了有效改进,提出了一种基于分类预测器以及退化模型的图像超分辨率重建技术.首先,利用退化模型得到图像训练集,并基于邻域嵌套进行分块;其次,根据图像各自特点提取灰度和梯度特征,并进行特征融合,从而实现了训练过程中噪声信息的有效抑制及图像中边缘信息的锐化;然后,引入分类预测器的思想,设计了一种离线的分类预测器,对预测器进行离线训练,得出优化参数,从而大幅度减少了优化时间;最后,利用L2范数对低分辨率图像分块进行分类,将分块送入相应子预测器中进行快速超分辨率重建.实验结果表明,该算法具有良好的实时性和有效性.
Abstract:
Super-resolution(SR)reconstruction technology based on neighbor embedding is effectively improved and a novel image SR reconstruction method using class predictor and degradation model is proposed. First, according to image degradation model, training set is obtained and cut into patches based on neighbor embedding. Secondly, in order to suppress noise and smoothen regions, gray and gradient information is extracted and combined to feature vector according to each patch character. Thirdly, the idea of class predictor is introduced and a novel off-line predictor is designed. Optimal parameters are obtained through off-line training and the optimization time is substantially reduced. Finally, in the light of L2 norm, each low resolution(LR)patch is classed and then put into corresponding sub-predictor with fast SR reconstruction. The experimental results exhibit the good real-time performance and effectiveness of the proposed algorithm.

参考文献/References:

[1] Chaudhuri S. Super-resolution imaging [M]. Norwell, MA, USA: Kluwer Academic, 2001: 100-125.
[2] 杨欣,费树岷,周大可. 基于MAP的自适应图像配准及超分辨率重建[J].仪器仪表学报, 2011, 32(8):1771-1775.
  Yang Xin, Fei Shumin, Zhou Dake. Self-adapting weighted technology for simultaneous image registration and super-resolution reconstruction based on MAP [J]. Chinese Journal of Scientific Instrument, 2011, 32(8): 1771-1775.(in Chinese)
[3] 杨欣,王从庆,费树岷. 基于最大后验概率的SAR图像自适应超分辨率盲重建[J]. 宇航学报, 2010,31(1):217-221.
  Yang Xin, Wang Chongqing, Fei Shumin. An adaptive technology for SAR image blind super-resolution based on MAP [J]. Journal of Astronautics, 2010, 31(1):217-221.(in Chinese)
[4] Shen H, Zhang L, Huang B,et al. A MAP approach for joint motion estimation, segmentation, and super resolution [J]. IEEE Transaction on Image Processing, 2007, 16(2): 479-490.
[5] Freeman W T, Jones T R, Pasztor E C. Example-based super-resolution [J]. IEEE Computer Graphics and Applications, 2002, 22(2): 56-65.
[6] Chen M, Qiu G, Lam K M. Example selective and order independent learning-based image super-resolution [C]//International Symposium on Intelligent Signal Processing and Communication Systems. Hong Kong, China, 2005: 77-80.
[7] Chang H, Yeung D Y, Xiong Y. Super-resolution through neighbor embedding [C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington DC, USA, 2004: 275-282.
[8] Wei F, Yeung D Y. Image hallucination using neighbor embedding over visual primitive manifolds [C]//IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, Minnesota, USA, 2007: 201-205.
[9] Chan T M, Zhang J, Pu J, et al. Neighbor embedding based super-resolution algorithm through edge detection and feature selection [J]. Pattern Recognition Letters, 2009, 30(2): 494-502.
[10] 杨欣, 姜斌, 周大可. 基于退化模型和邻域嵌套的彩色图像超分辨率自适应重建[J]. 东南大学学报:自然科学版, 2011,41(6):1193-1196.
  Yang Xin, Jiang Bin, Zhou Dake. Degradation model and neighbor embedding based color image adaptive super-resolution reconstruction [J]. Journal of Southeast University:Natural Science Edition, 2011, 41(6):1193-1196.(in Chinese)

相似文献/References:

[1]杨欣,姜斌,周大可.基于退化模型和邻域嵌套的彩色图像超分辨率自适应重建[J].东南大学学报(自然科学版),2011,41(6):1193.[doi:10.3969/j.issn.1001-0505.2011.06.013]
 Yang Xin,Jiang Bin,Zhou Dake.Degradation model and neighbor embedding based color image adaptive super-resolution reconstruction[J].Journal of Southeast University (Natural Science Edition),2011,41(1):1193.[doi:10.3969/j.issn.1001-0505.2011.06.013]
[2]姚佳丽,李中源,吴华珍,等.基于字典学习的超分辨率显微CT图像重建[J].东南大学学报(自然科学版),2016,46(5):957.[doi:10.3969/j.issn.1001-0505.2016.05.010]
 Yao Jiali,Li Zhongyuan,Wu Huazhen,et al.Super-resolution image reconstruction for micro-CT based on dictionary learning[J].Journal of Southeast University (Natural Science Edition),2016,46(1):957.[doi:10.3969/j.issn.1001-0505.2016.05.010]

备注/Memo

备注/Memo:
作者简介: 杨欣(1978—),男,博士,副教授,yangxin@nuaa.edu.cn.
基金项目: 国家自然科学基金资助项目(60905009,61172135)、高等学校博士学科点专项科研基金资助项目(20093218120015 )、北京师范大学遥感科学国家重点实验室开放基金资助项目(2009KFJJ012)、南京航空航天大学基本科研业务费专项科研资助项目(NS2010081).
引文格式: 杨欣,费树岷,周大可,等.基于分类预测器及退化模型的图像超分辨率快速重建[J].东南大学学报:自然科学版,2013,43(1):35-38. [doi:10.3969/j.issn.1001-0505.2013.01.007]
更新日期/Last Update: 2013-01-20