Abstract

This paper presents a technique for enhancing resolution of images by interpolating high frequency sub-bands generated using lifting wavelet transform (LWT) and spatial information of input low resolution (LR) image. Stationary wavelet transform (SWT) is used at intermediate stage for edge enhancement. The input image is decomposed using LWT in order to generate high frequency (HF) sub-bands. The generated HF sub-bands are interpolated further.

Different high frequency sub-bands obtained through SWT are added to correct the estimated HF sub-bands. The input LR image is interpolated in parallel. All these sub-bands and estimated LR image are reconstructed by inverse lifting wavelet transformation (ILWT) to produce high resolution image. The qualitative, quantitative and visual images of the described technique show the superiority of the proposed method over conventional and state-of-the-art methods.