Just Noticeable Difference Estimation for Screen Content Images

0
343
Just Noticeable Difference Estimation for Screen Content Images

Just Noticeable Difference Estimation for Screen Content Images

Abstract of Just Noticeable Difference Estimation for Screen Content

Just Noticeable Difference Estimation for Screen Content Images,We propose a novel just noticeable difference (JND) model for a screen content image (SCI).In particular, we decompose each edge profile into its luminance, contrast, and structure,
and then evaluate the visibility threshold in different ways. The edge luminance adaptation, contrast masking, and structural distortion sensitivity are studied in subjective experiments,
Extensive experiments are conducted to verify the proposed JND model, which confirm that it is accurate in predicting the JND profile, and outperforms the state-of-the-art schemes in terms of the distortion masking ability.Furthermore, we explore the applicability of the proposed JND model in the scenario of perceptually lossless SCI compression,

Conclusion

Just Noticeable Difference Estimation for Screen Content Images,We have proposed a JND model that is specifically designed for screen content images.

 The novelty of the model lies in computing the JND at a finer scale by introducing a parametric edge model, which provides a feasible way to estimate the visibility thresholds of three conceptually independent components including luminance, contrast and structure.

We demonstrate the effectiveness of the JND model and compare it with conventional schemes by subjective testing.

The SCI JND model can play a variety of roles in the transport of screen visuals.