Zhifang Liao
ABSTRACT
This paper focuses on the reconstruction of high resolution image blocks through low resolution image blocks, the reconstruction process takes advantage of the sharpness value of image has the property of scale invariance [1]. The image blocks with the same sharpness value are grouped into one class. For classes that are higher than a certain sharpness value will train coupling dictionary, then the sparse representation coefficient of the block is obtained by using the mapping function, Coupling dictionary and image feature blocks. Image super-resolution reconstruction will utilize coupling dictionary, mapping function and sparse representation coefficient. The class of have no training coupling dictionary, the corresponding block is reconstructed directly by using the same location of MR (middle resolution) image, MR image is obtained by the double cubic interpolation amplification of LR (lower resolution) image. The proposed algorithm is improved on the basis of [2]. With the image reconstruction performance basically unchanged, the time of image reconstruction is greatly reduced and the complexity of the algorithm is reduced.
- Dongwei Liu and Reinhard Klette. 2015. Sharpness and contrast measures on videos. In Proceedings of the International Conference on Image and Vision Computing New Zealand. IEEE, Auckland, New Zealand, 1-6. https://doi.org/10.1109/ivcnz.2015.7761556Google Scholar
- Awais Ahmed and Junaid Ahmed. 2019.Clustering Oriented Scale Invariant Dictionaries for Single Image Super-Resolution. In Proceedings of the International Conference on Computing, Mathematics and Engineering Technologies. IEEE, Boston, USA, 1-6. https://doi.org/ 10.1109/ICOMET.2019.8673396Google ScholarCross Ref
- J. L. Harris. 1964. Diffraction and resolving power. Journal of the optical society of America, Vol:54, Issue:7(1964),931-936. https://doi.org/10.1364/JOSA.54.000931Google Scholar
- Goodman, J. W. 2005. Introduction to Fourier optics. Roberts and Company Publishers. Greenwood Village, CO, United States.Google Scholar
- Jianchao Yang and John Wright. 2010. Image super-resolution via sparse representation. IEEE Transactions on Image Processing, Volume: 19, Issue: 11 (Nov. 2010), 2861–2873. https://doi.org/10.1109/TIP.2010.2050625Google ScholarDigital Library
- Emamnuel J. Candès. 2006. Compressive sensing. In Proceedings of the International Congress of Mathematicians. EMS, Madrid, Spain, 1433–1452. https://doi.org/10.4171/022-3/69Google Scholar
- Boaz Ophir and Michael Lustig. 2011. Multiscale dictionary learning using wavelets. IEEE Journal of Selected Topics in Signal Processing, Volume: 5, Issue: 5 (Sept. 2011), 1014–1024. https://doi.org/10.1109/JSTSP.2011.2155032Google Scholar
- K Zhang, X Gao, D Tao and X Li. 2012. Multi-scale dictionary for single image super-resolution. In Proceedings of the International Conference on Computer Vision and Pattern Recognition. IEEE, Providence, RI, USA, 1114–1121. https://doi.org/10.1109/CVPR.2012.6247791Google Scholar
- Weisheng Dong and Lei Zhang. 2011. Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Transactions on Image Processing, Volume: 20, Issue: 7 (July. 2011), 1838–1857. https://doi.org/10.1109/TIP.2011.2108306Google ScholarDigital Library
- Jianzhou Feng and Li Song. 2011. Learning dictionaries via subspace segmentation for sparse representation. In Proceedings of the International Conference on Image Processing. IEEE, Brussels, Belgium, 1245–1248. https://doi.org/10.1109/ICIP.2011.6115658Google ScholarCross Ref
- Guoshen Yu, Guillermo Sapiro and Stéphane Mallat. 2010. Image modelling and enhancement via structured sparse model selection. In Proceedings of the International Conference on Image Processing. IEEE, Hong Kong, China, 1641–1644. https://doi.org/10.1109/ICIP.2010.5653853Google Scholar
- Shuyuan Yang and Min Wang. 2012. Single image super-resolution reconstruction via learned geometric dictionaries and clustered sparse coding. IEEE Transactions on Image Processing, Volume: 21, Issue: 9 (Sept. 2012), 4016–4028. https://doi.org/10.1109/TIP.2012.2201491Google ScholarDigital Library
- Fahime Farhadifard and Elham Abar. 2014. Single image super-resolution based on sparse representation via directionally structured dictionaries. In Proceedings of the Signal Processing Communication Applications Conference. IEEE, Trabzon, Turkey,1718–1721. https://doi.org/10.1109/SIU.2014.6830580Google ScholarCross Ref
- Michael Elad and Michal Aharon. 2006. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Transactions on Image Processing, Volume: 15, Issue: 12 (Dec. 2006), 3736–3745. https://doi.org/10.1109/TIP.2006.881969Google ScholarDigital Library
- Jianchao Yang, Zhaowen Wang and Zhe Lin. 2012. Coupled dictionary training for image super-resolution. IEEE Transactions on Image Processing, Volume: 21, Issue: 8 (Aug. 2012), 3467–3478. https://doi.org/10.1109/TIP.2012.2192127Google ScholarDigital Library
- Jian Xu, Chun Qi and Zhiguo Chang. 2014. Coupled K-SVD dictionary training for super-resolution. In Proceedings of the International Conference on Image Processing. IEEE, Paris, France, 3910–3914. https://doi.org/10.1109/ICIP.2014.7025794Google ScholarCross Ref
- Jayant Kumar, Francine Chen and David Doermann. 2012. Sharpness estimation for document and scene images. In Proceedings of the International Conference on Patter Recognition, IEEE, Tsukuba, Japan, 3292–3295. https://ieeexplore.ieee.org/document/6460868Google Scholar
- Jian Sun, Jian Sun and Zongben Xu. 2011. Gradient profile prior and its applications in image super-resolution and enhancement. IEEE Transactions on Image Processing, Volume: 20, Issue: 6(June. 2011) ,1529–1542. https://doi.org/10.1109/TIP.2010.2095871Google ScholarDigital Library
- F Yeganli, M Nazzal and H Ozkaramanli. 2015. Image super-resolution via sparse representation over multiple learned dictionaries based on edge sharpness and gradient phase angle. Signal, Image and Video Processing volume 9(2015) ,285–293. https://link.springer.com/article/10.1007/s11760-015-0816-yGoogle ScholarCross Ref
- Junaid Ahmed and Madad Ali Shah . 2016. Single image super-resolution by directionality structured coupled dictionary learning. EURASIP Journal on Image and Video Processing, Article number: 36 (2016). https://link.springer.com/article/10.1186/s13640-016-0141-6Google Scholar
- Shenlong Wang, Lei Zhang and Yan Liang. 2012. Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis. In Proceedings of the International Conference on Computer Vision and Pattern Recognition. IEEE, Providence, RI, USA, 2216–2223. https://doi.org/10.1109/CVPR.2012.6247930Google Scholar
- Trevor Hastie, Iain Johnstone and Robert Tibshirani. 2004. Least angle regression. Annals of statistics, Volume 32, Number 2 (2004), 407-499. https://projecteuclid.org/euclid.aos/1083178935Google Scholar
- Meng Yang, Lei Zhang and Jian Yang. 2010. Metaface learning for sparse representation based face recognition. In Proceedings of the International Conference on Image Processing. IEEE, Hong Kong, China, 1601–1604. https://doi.org/10.1109/ICIP.2010.5652363Google ScholarCross Ref
- Zhou Wang, A.C. Bovik and H.R. Sheikh. 2004. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, Volume: 13, Issue: 4, (April. 2004), 600 – 612. https://doi.org/10.1109/TIP.2003.819861Google ScholarDigital Library
Recommendations
Hyperspectral image super-resolution through clustering-based sparse representation
AbstractPromoting the spatial resolution of hyperspectral sensors is expected to improve computer vision tasks. However, due to the physical limitations of imaging sensors, the hyperspectral image is often of low spatial resolution. In this paper, we ...
Dictionary learning-based image super-resolution for multimedia devices
AbstractIn multimedia devices such as mobile phones, surveillance cameras, and web cameras, image sensors have limited spatial resolution. As a result, the image captured from these devices misses high-frequency content and exhibits visual artifacts. ...
Image super-resolution using multi-dictionary sparse representation
ICMIP '20: Proceedings of the 5th International Conference on Multimedia and Image ProcessingImage super-resolution (SR) is of great significance in image processing field by providing an alternative approach to overcome the resolution limitations of devices. Many sparse representation based methods use a single pair of dictionaries for image ...
Comments