Image Super Resolution Using Fractional Discrete Wavelet Transformand Fractional Fast Fourier Transform

Super-resolution (SR) technique reconstructs a higher-resolution image or sequence from the observed LR images. In various image processing fields super resolution is playing a very crucial part. The single-frame as well as multi-frame both the methods in SR are widely used in multiple day to day applications and systems from last few years. In this work, we are proposing an Image resolution enhancement technique which has its basis on interpolation of the high-frequency sub-band images obtained by fractional discrete wavelet transform (FDWT). HereFDWT is used to decompose an input low-resolution image into different subbands. Then, interpolation between the high-frequency subband images and the input image takes place, followed by combining all these images to generate a new high-resolution image by using inverse FDWT. Directional selectivity which is provided by FDWT actually produces resolution enhancement, where the high-frequency subbands in different directions contribute to the sharpness of the high-frequency details such as edges. The quantitative peak signal-to-noise ratio (PSNR) and visual results show the superiority of the proposed technique over the conventional bicubic interpolation image resolution enhancement techniques.