Saliency-driven Black Point Compensation

Saliency-driven Black Point Compensation

A. Lindner; N. Bonnier; S. Süsstrunk 

We present a novel framework for automatically determining whether or not to apply black point compensation (BPC) in image reproduction. Visually salient objects have a larger influence on determining image quality than the number of dark pixels in an image, and thus should drive the use of BPC. We propose a simple and efficient algorithmic implementation to determine when to apply BPC based on low-level saliency estimation. We evaluate our algorithm with a psychophysical experiment on an image data set printed with or without BPC on a Canon printer. We find that our algorithm is correctly able to predict the observers’ preferences in all cases when the saliency maps are unambiguous and accurate.

Proceedings SPIE


IS&T / SPIE Electronic Imaging, Color Imaging XVI: Display, Processing, Hardcopy, and Applications, San Francisco, CA, USA, January 23-27, 2011.

DOI : 10.1117/12.872448


Images with ground truth

Saliency estimator

Comparison of our method against thresholding

simple threshold
Simple thresholding of percentage of dark pixels. Please remark that it is not possible to determine a threshold that causes many correct decisions.
saliency weighted
Normalized saliency difference of the dark and non-dark regions. A thresholding on this data yields a higher performance.