Abstract
Single image super-resolution is one of the evolving areas in the field of image restoration. It involves reconstruction of a high-resolution image from available low-resolution image. Although lot of researches are available in this field, still there are many issues related to existing problems those are still unresolved. Here, this research work focuses on two aspects of image super-resolution. The first aspect is that the process of dictionary formation is improved by using lesser number of images while preserving maximum structural variations. The second aspect is that pixel value estimation of high-resolution image is improved by considering only those overlapping patches which are more relevant from the characteristics of image point of view. For this, all overlapping pixels corresponding to a particular location are classified whether they are part of smooth region or an edge. Simulation results clearly prove the efficacy of the algorithm proposed in this paper.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aharon M, Elad M, Bruckstein A (2006) The K-SVD: an algorithm for designing of over-complete dictionaries for sparse representation. IEEE Trans Signal Process 54(11), 4311–4322
Berkeley dataset (1868) https://www2.eecs.berkeley.edu
Bevilacqua M, Roumy A, Guillemot C, Morel M.-L. A (2014) Single-image super-resolution via linear mapping of interpolated self-examples. In: IEEE Transactions on Image Processing, vol. 23(12), pp 5334–5347
Chang H, Yeung DY, Xiong Y (2004) Super-resolution through neighbor embedding. In: IEEE conference on computer vision and pattern recognition, vol. 1, pp 275–282
Choi JS, Kim M (2017) Single image super-resolution using global regression based on multiple local linear mappings. In: IEEE transactions on image processing, vol. 26(3)
Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2), 295–307
Egiazarian K, Katkovnik V (2015) Single image super-resolution via BM3D sparse coding. In: 23rd European signal processing conference, pp 2899–2903
Freeman W, Jones T, Pasztor E (2002) Example-Based Super-Resolut. IEEE Comput Graph Appl 22(2), 56–65
Liu ZS, Siu WC, Huang JJ (2017) Image super-resolution via weighted random forest. In: 2017 IEEE international conference on industrial technology (ICIT). IEEE
Liu C, Chen Q, Li H (2017) Single image super-resolution reconstruction technique based on a single hybrid dictionary. Multimedia Tools Appl 76(13), 14759–14779
Pandey G, Ghanekar U (2018) A compendious study of super-resolution techniques by single image. Optik 166:147–160
Pandey G, Ghanekar U (2020) Variance based external dictionary for improved single image super-resolution. Pattern Recognit Image Anal 30:70–75
Pandey G, Ghanekar U (2020) Classification of priors and regularization techniques appurtenant to single image super-resolution. Visual Comput 36:1291–1304. doi: 10.1007/s00371-019-01729-z
Pandey G, Ghanekar U (2021) Input image-based dictionary formation in super-resolution for online image streaming. In: Hura G, Singh A, Siong Hoe L (eds) Advances in communication and computational technology. Lecture notes in electrical engineering, vol 668. Springer, Singapore
Park SC, Park MK, Kang MG (2003) Super-resolution image reconstruction: a technical overview. IEEE Signal Process Magz 20(3), 21–36
Singh A, Ahuja N (2014) Super-resolution using sub-band self-similarity. In:’ Asian conference on computer vision, pp 552–5684
Wang Z, Bovik A, Sheikh H, Simoncelli E (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4), 600–612
Yang J, Wright J, Huang TS, Ma Y (2010) Image Super-Resolution via Sparse Representation. IEEE Trans Image Process 19(11), 2861–2873
Yang W, Zhang X, Tian Y, Wang W, Xue J-H, Liao Q (2019) Deep learning for single image super-resolution: a brief review. IEEE Trans Multimedia 21(12), 3106–3121
Zhang Z, Qi C, Hao Y (2016) Locality preserving partial least squares for neighbor embedding-based face hallucination. In: IEEE conference on image processing, pp 409–413
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Pandey, G., Ghanekar, U. (2021). Improved Single Image Super-resolution Based on Compact Dictionary Formation and Neighbor Embedding Reconstruction. In: Verma, G.K., Soni, B., Bourennane, S., Ramos, A.C.B. (eds) Data Science. Transactions on Computer Systems and Networks. Springer, Singapore. https://doi.org/10.1007/978-981-16-1681-5_7
Download citation
DOI: https://doi.org/10.1007/978-981-16-1681-5_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1680-8
Online ISBN: 978-981-16-1681-5
eBook Packages: Computer ScienceComputer Science (R0)