Texture Synthesis based on image resolution enhancement using wavelet transforms

In this paper, we propose a Wavelet and Stationary domain normalization (WSDN) technique for texture synthesis. The proposed WSDN improve the image resolution by estimating the high frequency band information. The proposed technique is based on the idea of splitting the texture synthesis problem into three stages. In the first stage stationary and discrete wavelet transforms are applied on the original low resolution image. The LH, HL, HH subbands generated after applying DWT is interpolated. In the second stage, estimated LH, HL, HH subbands are generated by the normalization technique. In the third stage inverse DWT (IDWT) is applied to generate synthesized image. To test the efficacy of the proposed method PSNR values are calculated and compared with the existing methods. The experimental results clearly indicate the efficacy of the proposed method over the existing method. [PUBLICATION ABSTRACT]