Abstract
Image super-resolution (SR) is the process of generating a high-resolution (HR) image using one or more low-resolution (LR) inputs. Many SR methods have been proposed, but generating the small-scale structure of an SR image remains a challenging task. We hence propose a single-image SR algorithm that combines the benefits of both internal and external SR methods. First, we estimate the enhancement weights of each LR-HR image patch pair. Next, we multiply each patch by the estimated enhancement weight to generate an initial SR patch. We then employ a method to recover the missing information from the high-resolution patches and create that missing information to generate a final SR image. We then employ iterative back-projection to further enhance visual quality. The method is compared qualitatively and quantitatively with several state-of-the-art methods, and the experimental results indicate that the proposed framework provides high contrast and better visual quality, particularly for non-smooth texture areas.
Similar content being viewed by others
References
Aharon M, Elad M, Bruckstein A (2006) K-SVD: An algorithm for designing over-complete dictionaries for sparse representation. IEEE T Signal Process 54:4311–4322
Babacan SD, Molina R, Katsaggelos AK (2011) Variational Bayesian super resolution. IEEE T Image Process 20:984–999
Cao F, Cai M, Tan Y, Zhao J (2016) Image super-resolution via adaptive regularization and sparse representation. IEEE T Neural Netw Learn Syst 27:1550–1561
Dong C, Loy C, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. CVPR:184–199
Farsiu S, Robinson D, Elad M, Milanfar P (2003) Fast and robust super resolution. Proc. IEEE Int’l Conf. Image Processing. IEEE, Barcelona, pp 14–1–217
Fattal R (2007) Image upsampling via imposed edge statistics. ACM T Graph 26:1–95
Freeman WT, Jones TR, Pasztor EC (2002) Example-based super-resolution. IEEE Comput Graph 22:56–65
Glasner D, Bagon S, Irani M (2009) Super-resolution from a single image. IEEE ICCV:349–356
Gong W, Hu L, Li J, Li W (2015) Combining sparse representation local rank constraint for single image superresolution. Inform Sci 325:1–19
Hou HS, Andrews HC (1978) Cubic splines for image interpolation and digital filtering. IEEE T Acoust Speech 26:508–517
Keys RG (1981) Cubic convolution interpolation for digital image processing. IEEE T Acoust Speech ASSP-29:1153–1160
Kim K, Kwon Y (2010) Single-image super resolution using sparse regression and natural image prior. IEEE T Pattern Anal 32:1127–1133
Li X, Orchard MT (2001) New edge-directed interpolation. IEEE T Image Process 10:1521–1527
Lin FJ (2015) Super-resolution from learning the enhancement ratio and texture/residual dictionary. Proc. IEEE Int’l Conf. Image Processing. IEEE, Quebec City, pp 2135–2139
Park SC, Park MK, Kang MG (2003) Super resolution image reconstruction: A technical overview. IEEE Signal Process Mag 20:21–36
Permuter H, Francos J, Jermyn I (2006) A study of Gaussian mixture models of color and texture features for image classification and segmentation. Pattern Recog 39:695–706
Protter M, Elad M, Takeda H, Milanfar P (2009) Generalizing the nonlocal-means to super-resolution reconstruction. IEEE T Image Process 18:36–51
Shan Q, Li Z, Jia J, Tang CK (2008) Fast image/video upsampling. ACM T Graph 27:1–5
Thanh MN, Wu QMJ, Ahuja S (2010) An extension of the standard mixture model for image segmentation. IEEE T Neural Networ 21:1326–1338
Timofte R, De Smet V, Van Gool L (2013) Anchored neighborhood regression for fast example-based super resolution. ICCV. https://doi.org/10.1109/ICCV.2013.241
Timofte R, De Smet V, Van Gool L (2014) A+: Adjusted anchored neighborhood regression for fast super-resolution. ACCV. https://doi.org/10.1007/978-3-319-16817-3_8
Timofte R, Rothe R, Van Gool L (2016) Seven ways to improve example-based single image super resolution. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2016), June 2016, US. pp 1865–1873
Yang J, Wright J, Huang T, Ma Y (2010) Image super-resolution via sparse representation. IEEE T Image Process 19:2861–2873
Yang J, Wang Z, Lin Z, Cohen S, Huang TS (2012) Coupled dictionary training for image superresolution. IEEE T Image Process 21:3467–3478
Zeyde R, Elad M, Protter M (2012) On Single Image Scale-Up Using Sparse-Representations. In: Boissonnat J-D, Chenin P, Cohen A, Gout C, Lyche T, Mazure M-L, Schumaker L (eds) Curves and Surfaces. Lecture Notes in Computer Science, vol 6920. Springer, Berlin, Heidelberg, pp 711–730
Zhang H, Zhang Y, Li H, Huang TS (2012) Generative Bayesian image super resolution with natural image prior. IEEE T Image Process 21:4054–4067
Zhang K, Tao D, Gao X et al (2015) Learning multiple linear mappings for efficient single image super-resolution. IEEE T Image Process 24:846–861
Zibetti M, Mayer J (2007) A robust and computationally efficient simultaneous superresolution scheme for image sequences. IEEE T Circ Syst Vid 17:1288–1300
Zuo W, Zhang L, Song C, Zhang D, Gao H (2014) Gradient histogram estimation and preservation for texture enhanced image denoising. IEEE T Image Process 23:2459–2472
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lin, FJ., Chuang, JH. Image super-resolution by estimating the enhancement weight of self example and external missing patches. Multimed Tools Appl 77, 19071–19087 (2018). https://doi.org/10.1007/s11042-017-5350-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-5350-1