Weighted Vector Quantization for Super Resolution Algorithm by Using Consistent Distance Metric

論文翻譯標題: 使用一致性距離度量於權重式向量量化之超解析演算法
  • 周 郁倫

學生論文: Master's Thesis

摘要

Super resolution technology is generating a high-resolution (HR) image from a low-resolution (LR) image to get a better visual quality In this thesis a vector quantization (VQ) based super resolution algorithm is proposed Training a proper codebook is one of the significant factors in VQ To let the distance metric in training codebooks consistent with that in image reconstruction procedure the proposed method utilizes correlation coefficient as a new distance metric to generate a new kind of codebooks Since the new codebooks contain unit vectors the normalizing parameter will be multiplied by the selected code vectors in image reconstruction procedure Experimental results show that the proposed algorithm truly improve the visual quality with “natural detail”
獎項日期2015 七月 28
原文English
監督員Shen-Chuan Tai (Supervisor)

引用此

Weighted Vector Quantization for Super Resolution Algorithm by Using Consistent Distance Metric
郁倫, 周. (Author). 2015 七月 28

學生論文: Master's Thesis