PROJECT TITLE :

Satellite Image Resolution Enhancement Using Dual - 2015

ABSTRACT:

Resolution enhancement (RE) schemes (which aren't primarily based on wavelets) suffer from the downside of losing high-frequency contents (which ends up in blurring). The discrete-wavelet-transform-based (DWT) RE theme generates artifacts (due to a DWT shift-variant property). A wavelet-domain approach primarily based on dual-tree complex wavelet remodel (DT-CWT) and nonlocal means that (NLM) is proposed for RE of the satellite pictures. A satellite input image is decomposed by DT-CWT (that is almost shift invariant) to get high-frequency subbands. The high-frequency subbands and the low-resolution (LR) input image are interpolated using the Lanczos interpolator. The high-frequency subbands are more matured an NLM filter to cater for the artifacts generated by DT-CWT (despite of its nearly shift invariance). The filtered high-frequency subbands and the LR input image are combined using inverse DT-CWT to obtain a resolution-enhanced image. Objective and subjective analyses reveal superiority of the proposed technique over the standard and state-of-the-art RE techniques.