i-manager Publications

A Novel Approach for Image Super Resolution Problems with Convolution Neural Networks

Chidadala Janardhan*, K. V. Ramanaiah**, K.Babulu***

* Research Scholar, JNTUK University, Kakinada, India.

** Associate Professor & Head, Department of Electronics and Communication Engineering, Yogivemana University, Proddatur, India.

*** Professor, Department of Electronics and Communication Engineering, JNTUK University, Kakinada, India.

Periodicity:September - November'2017
DOI : https://doi.org/10.26634/jit.6.4.13846

Abstract

The High Resolution Images (HRI) are more attractive in order to process the tasks like patient health monitoring, Machine inspection in industry, identify the missing objects location with the help of satellite images, missing number plate reorganization, criminal fingerprint identification, and many more. Images are degraded because of insufficient sensor resolution of the acquisition device, moving of object or camera and during transmission, processing and storing. Over the decades many researchers have proposed different approaches to solve these problems. The process of constructing High Resolution image from cluster of low resolution pictures or single low resolution image is named image super resolution. In this paper, the authors have evaluated various classes of super resolution algorithms, such as Iterative Back Projection (IBP), Sparse Representation (SR), and Convolution Neural Networks (CNN) with their performances. After evaluation Super Resolution with Deep Convolution networks can give best results over the state of the methods in terms of PSNR and quality of the image. This paper also gives some directions to future researchers to solve more ill posed problems.

Keywords

Super Resolution, Convolution Networks, Sparse Representation, Image Restoration, Interpolation

How to Cite this Article?

janardhan, C., Ramanaiah, K. V., and Babulu, K. (2017). A Novel Approach for Image Super Resolution Problems with Convolution Neural Networks. i-manager’s Journal on Information Technology, 6(4), 15-22. https://doi.org/10.26634/jit.6.4.13846

References

[1]. Bareja, M. N. & Modi, C. K. (2012, May). An effective iterative back projection based single image super resolution approach. In Communication Systems and Network Technologies (CSNT), 2012 International Conference on (pp. 95-99). IEEE.

[2]. Dong, C., Loy, C. C., He, K., & Tang, X. (2016). Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(2), 295-307.

[3]. Ducournau, A., & Fablet, R. (2016, December). Deep learning for ocean remote sensing: An application of convolutional neural networks for super-resolution on satellite-derived SST data. In Pattern Recognition in Remote Sensing (PRRS), 2016 9^th IAPR Workshop on (pp. 1- 6). IEEE.

[4]. Freeman, W. T., Jones, T. R., & Pasztor, E. C. (2002). Example-based super-resolution. IEEE Computer Graphics and Applications, 22(2), 56-65.

[5]. Huang, J. B., Singh, A., & Ahuja, N. (2015). Single image super-resolution from transformed self-exemplars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5197-5206).

[6]. Huang, B., Wang, W., Bates, M., & Zhuang, X. (2008). Three-dimensional super-resolution imaging by stochastic optical reconstruction microscopy. Science, 319(5864), 810-813.

[7]. Irani, M. & Peleg, S. (1991). Improving resolution by image registration. CVGIP: Graphical Models and Image Processing, 53(3), 231-239.

[8]. Iyanda, C. A., Yaakob, S. N. B., & Nawir, M. (2016, August). Uniqueness of iterative back projection in super resolution techniques. In Electronic Design (ICED), 2016 3^rd International Conference on (pp. 501-506). IEEE.

[9]. Jia, K., Wang, X., & Tang, X. (2013). Image transformation based on learning dictionaries across image spaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(2), 367-380.

[10]. Kim, J., Kwon Lee, J., & Mu Lee, K. (2016). Deeplyrecursive convolutional network for image superresolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1637- 1645).

[11]. Li, X., Zhu, M., Cui, Z., & Zhu, X. (2015, August). A super-resolution algorithm based on adaptive sparse representation. In Fuzzy Systems and Knowledge Discovery (FSKD), 2015 12^th International Conference on (pp. 1834-1838). IEEE.

[12]. Liu, D., Wang, Z., Nasrabadi, N., & Huang, T. (2016, November). Learning a Mixture of Deep Networks for Single Image Super-Resolution. In Asian Conference on Computer Vision (pp. 145-156). Springer, Cham.

[13]. Liu, D., Wang, Z., Wen, B., Yang, J., Han, W., & Huang, T. S. (2016). Robust single image super-resolution via deep networks with sparse prior. IEEE Transactions on Image Processing, 25(7), 3194-3207.

[14]. Moustafa, M., Ebeid, H. M., Helmy, A., Nazamy, T. M., & Tolba, M. F. (2015, December). Super-resolution: Sparse dictionary design method using quantitative comparison. In Intelligent Computing and Information Systems (ICICIS), 2015 IEEE Seventh International Conference on (pp. 383- 389). IEEE.

[15]. Noh, H., Hong, S., & Han, B. (2015). Learning deconvolution network for semantic segmentation. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1520-1528).

[16]. Panda, S. S., Prasad, M. S. R., & Jena, G. (2011). POCS based super-resolution image reconstruction using an adaptive regularization parameter. arXiv preprint arXiv:1112.1484. 8(5).

[17]. Park, S. C., Park, M. K., & Kang, M. G. (2003). Superresolution image reconstruction: a technical overview. IEEE Signal Processing Magazine, 20(3), 21-36.

[18]. Rasti, P., Demirel, H., & Anbarjafari, G. (2013, September). Iterative back projection based image resolution enhancement. In Machine Vision and Image Processing (MVIP), 2013 8^th Iranian Conference on (pp. 237-240). IEEE.

[19]. Schulter, S., Leistner, C., & Bischof, H. (2015). Fast and accurate image upscaling with super-resolution forests. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3791-3799).

[20]. Shoji, H. & Gohshi, S. (2015, November). Limitations of learning-based Super-Resolution. In Intelligent Signal Processing and Communication Systems (ISPACS), 2015 International Symposium on (pp. 646-651). IEEE.

[21]. Song, H., He, X., Chen, W., & Sun, Y. (2010, June). An improved iterative back-projection algorithm for video super-resolution reconstruction. In Photonics and Optoelectronic (SOPO), 2010 Symposium on (pp. 1-4). IEEE.

[22]. Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. In AAAI (pp. 4278- 4284).

[23]. Tang, Z., Deng, M., Xiao, C., & Yu, J. (2011, August). Projection onto convex sets super-resolution image reconstruction based on wavelet bi-cubic interpolation. In Electronic and Mechanical Engineering and Information Technology (EMEIT), 2011 International Conference on (Vol. 17(2), pp. 351-354). IEEE.

[24]. Vandewalle, P., Süsstrunk, S., & Vetterli, M. (2006). A frequency domain approach to registration of aliased images with application to super-resolution. EURASIP Journal on Applied Signal Processing, 233-233.

[25]. Yang, J., Wang, Z., Lin, Z., Cohen, S., & Huang, T. (2012). Coupled dictionary training for image superresolution. IEEE Transactions on Image Processing, 21(8), 3467-3478.

[26]. Yang, J., Wright, J., Huang, T. S., & Ma, Y. (2010). Image super-resolution via sparse representation. IEEE Transactions on Image Processing, 19(11), 2861-2873.

[27]. Zeng, K., Yu, J., Wang, R., Li, C., & Tao, D. (2017). Coupled deep autoencoder for single image super-resolution. IEEE Transactions on Cybernetics, 47(1), 27-37.

A Novel Approach for Image Super Resolution Problems with Convolution Neural Networks

Abstract

Keywords

How to Cite this Article?

References

If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Options for accessing this content:

	North Americas,UK, Middle East,Europe		India	Rest of world
	USD	EUR	INR	USD-ROW
Pdf	35	35	200	20
Online	35	35	200	15
Pdf & Online	35	35	400	25