Alexandre Ninassi

Does where you Gaze on an Image Affect your Perception of Quality? Applying Visual Attention to Image Quality Metric

The aim of an objective image quality assessment is to find an automatic algorithm that evaluates the quality of pictures or video as a human observer would do. To reach this goal, researchers try to simulate the Human Visual System (HVS). Visual attention is a main feature of the HVS, but few studies have been done on using it in image quality assessment. In this work, we investigate the use of the visual attention information in their final pooling step. The rationale of this choice is that an artefact is likely more annoying in a salient region than in other areas. To shed light on this point, a quality assessment campaign has been conducted during which eye movements have been recorded. The results show that applying the visual attention to image quality assessment is not trivial, even with the ground truth.

Pseudo No Reference image quality metric using perceptual data hiding

Regarding the important constraints due to subjective quality assessment, objective image quality assessment has recently been extensively studied. Such metrics are usually of three kinds, they might be Full Reference (FR), Reduced Reference (RR) or No Reference (NR) metrics. We focus here on a new technique, which recently appeared in quality assessment context: data-hiding-based image quality metric. Regarding the amount of data to be transmitted for quality assessment purpose, watermarking based techniques are considered as pseudo noreference metric: A little overhead due to the embedded watermark is added to the image. Unlike most existing techniques, the proposed embedding method exploits an advanced perceptual model in order to optimize both the data embedding and extraction. A perceptually weighted watermark is embedded into the host image, and an evaluation of this watermark allows to assess the host images quality. In such context, the watermark robustness is crucial; it must be suffciently robust to be detected after very strong distortions, but it must also be suffciently fragile to be degraded along with the host image. In other words, the watermark distortion must be proportional to the images distortion. Our work is compared to existing standard RR and NR metrics in terms of both the correlation with subjective assessment and of data overhead induced by the mark.

A Study of Content based Watermarking using an Advanced HVS Model

A key point of image watermarking schemes is to select the image pixels or transformed coefficients where an embedded watermark would reach the optimal invisibility versus robustness trade-off. Human visual system (HVS) based JND masks are thus useful to optimally adapt the watermark strength right below the visibility threshold. Most of the perceptual masks created so far for watermarking purpose are based on the empirical assumption that edges and/or textures allow the best watermark visual masking and thus ensures good invisibility properties. Nevertheless, although invisibility control in smooth areas is challenging, it could be interesting to extend the watermark in such areas since the robustness performances might increase. The goal of this paper is to use an advanced HVS model to manage invisibility in order to evaluate the robustness of watermarks embedded in smooth areas only, edges/textured areas only or in both areas. This study is further to the one presented in (F. Autrusseau and P. Le Callet, 2007). The robustness was tested against 89 attacked images (using Stirmark), results showed that including smooth areas in the JND mask increases the robustness while preserving good invisibility properties.