SISR Reconstruction Method of Image Structure Perception Based on Hidden Topic Probability Model

被引：0
作者：
Ma L. [1 ]
Wang X. [1 ]
Tian J. [2 ]
Zhang Y. [3 ]
机构：
[1] School of Electronics & Information Engineering, South China University of Technology, Guangzhou, 510640, Guangdong
[2] Institute of System Science, National University of Singapore
[3] Institute of Computer Application Engineering, South China University of Technology, Guangzhou, 510640, Guangdong
来源：
Huanan Ligong Daxue Xuebao/Journal of South China University of Technology (Natural Science) | 2019年 / 47卷 / 04期
基金：
中国国家自然科学基金;
关键词：
Manifold constraint; Node regression mapping; Structure perception; Super-resolution reconstruction; Topic probability model;
D O I：
10.12141/j.issn.1000-565X.180321
中图分类号：
学科分类号：
摘要：
In the process of single image super-resolution reconstruction(SISR)based on learning from examples, the mapping relation was assumed one-to-one from a low-resolution(LR)input to a high-resolution(HR)image patch. But in fact, one LR patch may relate to many HR patches, and thus leads to matching errors. To solve the mismatch problem of restored patch, the probability model of LR patch topic pattern was derived to express new observation information for hidden topics in LR signals. Then a structure-aware recovery mechanism with topic differences and context maximum probability was proposed, and LR manifold description was formed by relating topic modes to LR neighbor contents. The HR signal was accurately distinguished and reconstructed from similar LR manifold signals via an adaptive selection of topic decision trees and regression matrix of nodes. The topic mo-del optimization experiment demonstrates that the peak signal-to-noise ratio(PSNR)of our topic constraint SISR method is improved by 0.25dB compared to that of the decision tree based SISR algorithm without introducing hidden topics. In the comparative experiment of five algorithms, the average PSNR value of our SISR approach is improved by 0.92dB compared to that of the sparse dictionary based SISR method. So the introduced hidden topic information and topic-manifold structure identification are feasible. © 2019, Editorial Department, Journal of South China University of Technology. All right reserved.
引用
收藏
页码：1 / 9
页数：8
相关论文
共 16 条
  • [1] Zeyde R., Elad M., Protter M., On single image scale-up using sparse-representations, Proceedings of IEEE Conference on Curves and Surfaces, pp. 711-730, (2010)
  • [2] Chen X., Qi C., Low-rank neighbor embedding for single image super-resolution, Journal of IEEE Signal Process Letters, 21, 1, pp. 79-82, (2014)
  • [3] Dong W., Zhang L., Shi G., Et al., Nonlocal centralized sparse representation for image restoration, Journal of IEEE Transactions on Image Processing, 22, 4, pp. 1620-1630, (2013)
  • [4] Li Y., Dong W., Xie X., Et al., Image super-resolution with parametric sparse model learning, Journal of IEEE Transactions on Image Processing, 27, 9, pp. 4638-4650, (2018)
  • [5] Ma L.-H., Huang Y., Li J.-H., Improved SCSR algorithm on the basis of flexible LBP texture dictionary and multi-feature description, Journal of South China University of Technology(Natural Science Edition), 43, 3, pp. 57-65, (2015)
  • [6] Chang H., Yeung D., Xiong Y., Super-resolution through neighbor embedding, Proceedings of International Conference on Computer Vision and Pattern Recognition, pp. 275-282, (2004)
  • [7] Timoft R., Smet D., Anchored neighborhood regression for fast example-based super-resolution, Procee-dings of IEEE Conference on Computer Vision, pp. 1920-1927, (2013)
  • [8] Timoft R., Smet D., A+: adjusted anchored neighborhood regression for fast super-resolution, Proceedings of Asian Conference on Computer Vision, pp. 111-126, (2014)
  • [9] Schuitr S., Leistner C., Bischor H., Fast and accurate image upscaling with super-resolution forests, Proceedings of IEEE Computer Vision and Pattern Recognition, pp. 3791-3799, (2016)
  • [10] Huang J., Liu T., SRHRF+: self-example enhanced single image super-resolution using hierarchical random forests, Proceedings of IEEE Computer Vision and Pattern Recognition, pp. 1067-1075, (2017)
12