Patricia Ladret

The blur effect: perception and estimation with a new no-reference perceptual blur metric

To achieve the best image quality, noise and artifacts are generally removed at the cost of a loss of details generating the blur effect. To control and quantify the emergence of the blur effect, blur metrics have already been proposed in the literature. By associating the blur effect with the edge spreading, these metrics are sensitive not only to the threshold choice to classify the edge, but also to the presence of noise which can mislead the edge detection. Based on the observation that we have difficulties to perceive differences between a blurred image and the same reblurred image, we propose a new approach which is not based on transient characteristics but on the discrimination between different levels of blur perceptible on the same picture. Using subjective tests and psychophysics functions, we validate our blur perception theory for a set of pictures which are naturally unsharp or more or less blurred through one or two-dimensional low-pass filters. Those tests show the robustness and the ability of the metric to evaluate not only the blur introduced by a restoration processing but also focal blur or motion blur. Requiring no reference and a low cost implementation, this new perceptual blur metric is applicable in a large domain from a simple metric to a means to fine-tune artifacts corrections.

Three factors that influence the overall quality of the stereoscopic 3D content: image quality, comfort, and realism

In todays context, where 3D content is more abundant than ever and its acceptance by the public is probably de_nitive, there are many discussions on controlling and improving the 3D quality. But what does this notion represent precisely? How can it be formalized and standardized? How can it be correctly evaluated? A great number of studies have investigated these matters and many interesting approaches have been proposed. Despite this, no universal 3D quality model has been accepted so far that would allow a uniform across studies assessment of the overall quality of 3D content, as it is perceived by the human observers. In this paper, we are making a step forward in the development of a 3D quality model, by presenting the results of an exploratory study in which we started from the premise that the overall 3D perceived quality is a multidimensional concept that can be explained by the physical characteristics of the 3D content. We investigated the spontaneous impressions of the participants while watching varied 3D content, we analyzed the key notions that appeared in their discourse and identi_ed correlations between their judgments and the characteristics of our database. The test proved to be rich in results. Among its conclusions, we consider of highest importance the fact that we could thus determine three di_erent perceptual attributes ( image quality, comfort and realism ( that could constitute a _rst simplistic model for assessing the perceived 3D quality.

A temporal mosquito noise corrector

Due to the required memory space and computing time, temporal processing is rarely used even in video processing. However, when the temporal aspect of a compression noise is major, it cannot be treated spatially only. The following article presents an example of such a noise: the mosquito noise. The equally spatial and temporal nature of the mosquito artifact is first explained through its definition. It is followed by the different ways already used to treat it. A spatio-temporal and compression-independent mosquito noise corrector is then introduced. Finally, the interest of a temporal corrector over purely spatial ones is shown through tests results.

The role of temporal aspects for quality assessment

For quality assessment, videos are often considered as series of images with, at best, a motion component. To study the role of temporal aspects in quality, we compare the perceived quality of two versions of a mosquito noise correction algorithm: one purely spatial and the other spatio-temporal. We set up a paired-comparison experiment specially adapted to the temporal aspects of video quality. Results prove the existence of a purely temporal aspect in video quality perception.

Blurred face recognition algorithm guided by a no-reference blur metric

Performance of face recognition systems drop drastically when blur effect is present on facial images. In this paper, we propose a new approach for blurred face recognition. Our method is based on a measure of the level of blur introduced in the image using a no-reference blur metric. The face recognition process can be performed with any facial feature descriptor to allow the combination of alternative methods for overcoming data acquisition problems introduced in an image. To assess its efficiency, the approach has been applied with Gabor wavelets, Local Binary Patterns (LBP) and Local Phase Quantization (LPQ) facial descriptors on the FERET data-set. Experimental results clearly show the strength of this method at overcoming the problem caused by various forms of blur whatever the facial feature descriptor are implemented.

The influence of the visualization task on the simulator sickness symptoms - A comparative SSQ study on 3DTV and 3D immersive glasses

The human factors are an essential aspect to take into consideration in order to explain the level of public acceptability of new stereoscopic devices. A study using the Simulator Sickness Questionnaire allowed us to illustrate the differences in symptoms after the visualization of 3D images on a 3DTV screen and on a pair of prototype immersive 3D glasses. Also, the results of our study showed that the visualization task influenced the exploration of the scenes, and therefore influenced the evolution of the simulator sickness symptoms.

Fully automated facial picture evaluation using high level attributes

People automatically and quickly judge a facial picture from its appearance. Thus, developing tools that can reproduce human judgments may help consumers in their picture selection process. Previous work mostly studied the position of facial keypoints to make predictions about specific traits: trustworthiness, likability, competence, etc. In this work, high level attributes (e.g. gender, age, smile) are automatically extracted using 3 different tools and are used to build models adapted to each trait. Models are validated on a set of synthetic images and it is shown that using attributes increases significantly the correlation between human and algorithmic evaluations. Then, a new dataset of 140 images is presented and used to demonstrate the relevance of high level attributes for evaluating faces with respect to likability and competence. A model combining both facial keypoints and attributes is finally proposed and applied to picture selection: which picture depicts the most likable face for a given person?

Measurement of compression-induced temporal artifacts in subjective and objective video quality assessment

Temporal pooling and temporal defects are the two dierences between image and video quality assessment. Whereas temporal pooling has been the object of two recent studies, this paper focuses on the rarely addressed topic of compression-induced temporal artifacts, such as mosquito noise. To study temporal aspects in subjective quality assessment, we compared the perceived quality of two versions of a mosquito noise corrector: one purely spatial and the other spatio-temporal. We set up a paired-comparison experiment and choose videos whose compression mainly creates temporal artifacts. Results proved the existence of a purely temporal aspect in video quality perception. We investigate the correlation between subjective results from the experiment and three video metrics (VQM, MOVIE, VQEM), as well as two temporally-pooled image metrics (SSIM and PSNR). SSIM and PSNR metrics nd the corrected sequences of better quality than the compressed ones but do not distinguish spatial and spatio-temporal processings. The confrontation of those results with the VQM and Movie objective metrics show that they do not account for this type of defects. A detailed study highlights that either they do not detect them or the response of their temporal component is masked by the one of their spatial components.