Abstract
A novel method of improving the spatial resolution of scanned images, by means of neural networks, is presented in this paper. Images of different resolution, originating from scanner, successively train a neural network, which learns to improve resolution from 25 to 50 pixels-per-inch (ppi), then from 100 to 200 ppi and finally, from 50 to 100 ppi. Thus, the network is provided with consistent knowledge regarding the point spread function (PSF) of the scanner, whilst it gains the generalization ability to reconstruct finer resolution images unfamiliar to it. The novelty of the proposed image-resolution-enhancement technique lies in the successive training of the neural structure with images of increasing resolution. Comparisons with the image scanned at 400 ppi demonstrate the superiority of our method to conventional interpolation techniques.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Lehmann TM, Gonner C, Spitzer K (1999) Survey: interpolation methods in medical image processing. IEEE Trans Med Imaging 18:1049–1075
Go J, Sohn K, Lee Ch (2000) Interpolation using neural networks for digital still cameras. IEEE Trans Consum Electr 46:610–616
Skoneczny S, Szostakowski J (2001) Classical and neural methods of image sequence interpolation. Proc SPIE 4535:191–204
Tekalp AM (1995) Digital video processing. Prentice-Hall, USA
Salari E, Zhang S (2003) Integrated recurrent neural network for image resolution enhancement from multiple image frames. IEE Proc 150:299–305
Tsagaris V, Panagiotopoulou A, Anastassopoulos V (2004) Interpolation in multispectral data using neural networks. Proc SPIE 5573:460–470
Valdes M del C, Inamura M (1998) Spatial resolution improvement of a low spatial resolution thermal infrared image by backpropagated neural networks. IEICE Trans Inf Syst E81–D:872–880
Valdes M del C, Inamura M (2000) Spatial resolution improvement of remotely sensed images by a fully interconnected neural network approach. IEEE Trans Geosc Rem Sens 38:2426–2430
Ahmed F, Gustafson SC, Karim MA (1996) Image interpolation with adaptive receptive field-based Gaussian radial basis functions. Microw Opt Techn Lett 13:197–202
Plaziac N (1999) Image interpolation using neural networks. IEEE Trans Image Process 8:1647–1651
Davila CA, Hunt BR (2000) Superresolution of binary images with a nonlinear interpolative neural network. Appl Opt 39:2291–2299
Sekiwa D, Taguchi A (2001) Enlargement of digital images by using multi-neural networks. Electr Commun Jpn 84:61–69
Pan F, Zhang L (2003) New image super-resolution scheme based on residual error restoration by neural networks. Opt Eng 42:3038–3046
Hu H, Hofman PM, Haan G (2004) Image interpolation using classification-based neural networks. IEEE Intern Symp Consum Electr 1:133–137
Pu H-C, Lin C-T, Liang S-F, Kumar N (2003) A novel neural-network-based image resolution enhancement. IEEE Intern Conf Fuzz Syst 2:1428–1433
Collins M, Jong M (2004) Neuralizing target superresolution algorithms. IEEE Geosc Rem Sens Lett 1:318–321
Ahmed MN, Cooper BE, Love ST (2001) Document resizing using a multi-layer neural network. NIP17: Intern Conf Dig Print Techn:792–796
Craubner S (2002) Optoelectronic image scanning with high spatial resolution and reconstruction fidelity. Opt Eng 41:381–394
Shen H-L, Xin JH (2004) Spectral characterization of a color scanner by adaptive estimation. J Opt Soc Am 21:1125–1130
Patterson DW (1996) Artificial neural networks: theory and applications. Prentice-Hall, Singapore
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Panagiotopoulou, A., Anastassopoulos, V. Scanned images resolution improvement using neural networks. Neural Comput & Applic 17, 39–47 (2008). https://doi.org/10.1007/s00521-007-0106-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-007-0106-x