PROJECT TITLE :

High Dynamic Range Image Compression by Optimizing Tone Mapped Image Quality Index - 2015

ABSTRACT:

Tone mapping operators (TMOs) aim to compress high dynamic vary (HDR) pictures to low dynamic range (LDR) ones therefore as to visualize HDR images on standard displays. Most existing TMOs were demonstrated on specific examples while not being totally evaluated using well-designed and subject-validated image quality assessment models. A recently proposed tone mapped image quality index (TMQI) made one amongst the primary attempts on objective quality assessment of tone mapped pictures. Here, we tend to propose a substantially totally different approach to design TMO. Rather than using any predefined systematic computational structure for tone mapping (like analytic image transformations and/or specific contrast/edge enhancement), we tend to directly navigate within the area of all pictures, looking out for the image that optimizes an improved TMQI. In particular, we have a tendency to first improve the 2 building blocks in TMQI-structural fidelity and statistical naturalness components-resulting in a TMQI-II metric. We tend to then propose an iterative algorithm that alternatively improves the structural fidelity and statistical naturalness of the resulting image. Numerical and subjective experiments demonstrate that the proposed algorithm consistently produces better quality tone mapped images even when the initial images of the iteration are created by the foremost competitive TMOs. Meanwhile, these results additionally validate the prevalence of TMQI-II over TMQI.