Image interpolation by estimation and deconvolution of Haar wavelet approximate subband

Author

Yasuno, H. ; Chiracharit, W. ; Chamnongthai, K.

Author_Institution

Dept. of Electron. & Telecommun. Eng., King Mongkut´´s Univ. of Technol. Thonburi, Bangkok

Volume

1

fYear

2008

fDate

14-17 May 2008

Firstpage

501

Lastpage

504

Abstract

A backward wavelet transform (BWT) based image interpolation method, which consists of the estimation of an undecimated approximate subband and the deconvolution operation to the estimation result by solving simultaneous linear equations (SLE), is described in this paper. Our BWT means that the inverse step of wavelet transform (WT) by convolution operation and down sampling is utilized obtaining high resolution image, and inverse wavelet transform (IWT) is not utilized. For confirming the possibility and the effectiveness of this method, we concentrate on Haar wavelet, and the best result in peak-signal- to-noise-ratio (PSNR) is 38.31 dB with cubic spline interpolation.

Keywords

Haar transforms; deconvolution; image recognition; interpolation; wavelet transforms; Haar wavelet approximate subband; backward wavelet transform; cubic spline interpolation; deconvolution operation; high resolution image; image interpolation; inverse wavelet transform; linear equations; peak-signal- to-noise-ratio; Convolution; Deconvolution; Digital TV; Equations; Image resolution; Image sampling; Interpolation; PSNR; Spline; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, 2008. ECTI-CON 2008. 5th International Conference on

Conference_Location

Krabi

Print_ISBN

978-1-4244-2101-5

Electronic_ISBN

978-1-4244-2102-2

Type

conf

DOI

10.1109/ECTICON.2008.4600480

Filename

4600480