CVApr 19, 2017

FSITM: A Feature Similarity Index For Tone-Mapped Images

arXiv:1704.05624v1120 citations
Originality Incremental advance
AI Analysis

This work addresses the need for better quality assessment metrics for tone-mapped images, which is important for researchers and practitioners in image processing, though it is incremental as it builds on existing methods like TMQI.

The authors tackled the problem of objectively evaluating tone-mapped images by proposing FSITM, a new index based on local phase information, which outperformed the state-of-the-art TMQI on two standard databases and achieved even higher performance when combined with TMQI.

In this work, based on the local phase information of images, an objective index, called the feature similarity index for tone-mapped images (FSITM), is proposed. To evaluate a tone mapping operator (TMO), the proposed index compares the locally weighted mean phase angle map of an original high dynamic range (HDR) to that of its associated tone-mapped image calculated using the output of the TMO method. In experiments on two standard databases, it is shown that the proposed FSITM method outperforms the state-of-the-art index, the tone mapped quality index (TMQI). In addition, a higher performance is obtained by combining the FSITM and TMQI indices. The MATLAB source code of the proposed metric(s) is available at https://www.mathworks.com/matlabcentral/fileexchange/59814.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes