PROJECT TITLE :

Naturalness Preserved Image Enhancement Using a Priori Multi-Layer Lightness Statistics - 2018

ABSTRACT:

The enhancement of non-uniformly illuminated images typically suffers from over-enhancement and produces unnatural results. This Project presents a naturalness preserved enhancement technique for non-uniformly illuminated pictures, using a priori multi-layer lightness statistics acquired from high-quality images. This Project makes three important contributions: coming up with a completely unique multi-layer image enhancement model; deriving the multi-layer lightness statistics of high-quality outdoor pictures, which are incorporated into the multi-layer enhancement model; and showing that the general quality rating of enhanced images is in step with a mix of contrast enhancement and naturalness preservation. Two separate human observer analysis studies were conducted on naturalness preservation and overall image quality. The results showed the proposed method outperformed four compared state-of-the-art enhancement strategies.