Journal of South China University of Technology (Natural Science Edition) ›› 2015, Vol. 43 ›› Issue (3): 57-65.doi: 10.3969/j.issn.1000-565X.2015.03.009

• Electronics, Communication & Automation Technology • Previous Articles     Next Articles

Improved SCSR Algorithm on the Basis of Flexible LBP Texture Dictionary and Multi-Feature Description

Ma Li-hong Huang Yin Li Jian-hui   

  1. School of Electronic and Information Engineering∥National Engineering Techonology Ｒesearch Center for Mobile Ultrasonic Detection，South China University of Technology，Guangzhou 510640，Guangdong，China
  • Received:2014-08-21 Revised:2014-12-08 Online:2015-03-25 Published:2015-02-10
  • Contact: 马丽红(1965-)，女，博士，教授，主要从事图像视频信号处理、容错编码和数据隐藏、模式识别研究． E-mail:eelhma@scut.edu.cn
  • About author:马丽红(1965-)，女，博士，教授，主要从事图像视频信号处理、容错编码和数据隐藏、模式识别研究．
  • Supported by:
    Supported by the National Natural Science Foundation of China(NSFC)(61471173)

PDF

781

Abstract: A multi-feature joint dictionary (MFJD) is suggested to improve the structural distinction in dictionary training and to accelerate the atom matching in sparse reconstruction． Firstly，two dictionaries branched respectively for edge-and texture-descriptions are created using gradient and LBP operators． Secondly，tree structures are intro-duced to represent the hierarchical clustering of atoms，which leads to a quick atom searching． Then，bilateral total variation (BTV) regularization is employed to achieve the optimal resolution． Experimental results show that，in comparison with the sparse coding super-resolution reconstruction (SCSＲ) algorithm，MFJD averagely improves the PSNR，MSSIM and FSIM of an image by 0． 2424dB，0． 0043 and 0． 0056，respectively，and reduces the recon-struction time to approximately 22．77% of that of SCSＲ algorithm owing to the reduction of dictionary dimensionality．

Key words: super-resolution reconstruction, structure classification, multi-feature description, LBP texture, bilateral total variation

CLC Number: