Development of robust neighbor embedding based super-resolution scheme

详细信息    查看全文

• 作者：Deepasikha Mishra ; ^{deepasikhame@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; ^{512cs606@nitrkl.ac.in" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Banshidhar Majhi ^{bmajhi@nitrkl.ac.in" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Pankaj Kumar Sa ^{pankajksa@nitrkl.ac.in" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Ratnakar Dash ^{ratnakar@nitrkl.ac.in" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Super-resolution ; Histogram matching ; Global neighborhood selection ; Locally linear embedding ; Robust principal component analysis ; Robust locally linear embedding
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：19 August 2016
• 年：2016
• 卷：202
• 期：Complete
• 页码：49-66
• 全文大小：3961 K

文摘

In this paper, we propose a robust neighbor embedding super-resolution (RNESR) scheme to generate a super-resolution (SR) image from a single low-resolution (LR) image. It utilizes histogram matching for selection of best training pair of images. This helps to learn co-occurrence prior to high-resolution (HR) image reconstruction. The global neighborhood size is computed from local neighborhood size, which avoids the over-fitting and under-fitting problem during neighbor embedding. Robust locally linear embedding (RLLE) is used in place of locally linear embedding (LLE) to generate HR image. To validate the scheme, exhaustive simulation has been carried out on standard images. Comparative analysis with respect to different measures like peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and feature similarity index (FSIM) reveals that the RNESR scheme generates high-quality SR image from a LR image as compared to existing schemes.