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.

Natural image categorisation and retrieval is the main challenge for image indexing. With the increase of available images and video databases, there is a real need to, first, organise the database automatically according to different semantic groups, and secondly, to take into account these large databases where most of the data is stored in a compressed form. The global distribution of orientation features is a very powerful tool to semantically organise the database into groups, such as outdoor urban scenes, indoor scenes, 'closed' landscapes (valleys, mountains, forests, etc.) and 'open' landscapes (deserts, fields, beaches, etc.). The constraint of a JPEG compressed database is completely integrated with an efficient implementation of an orientation estimator in the DCT (Discrete Cosinus Transform) domain. The proposed estimator is analysed from different points of view (accuracy and discrimination power). The images are then globally characterised by a set of a few parameters (two or three), allowing a fast scenes categorisation and organisation which is very robust to the quantisation effect, up to a quality factor of 10 in the JPEG format.

No abstract

International audiencePicture selection is a time-consuming task for humans and a real challenge for machines, which have to retrieve complex and subjective information from image pixels. An automated system that infers human feelings from digital portraits would be of great help for profile picture selection, photo album creation or photo editing. In this work, two models of facial pictures evaluation are defined. The first one predicts the overall aesthetic quality of a facial image, and the second one answers the question " Among a set of facial pictures of a given person, on which picture does the person look like the most friendly? ". Aesthetic quality is evaluated by the computation of 15 features that encode low-level statistics in different image regions (face, eyes, mouth). Relevant features are automatically selected by a feature ranking technique, and the outputs of 4 learning algorithms are fused in order to make a robust and accurate prediction of the image quality. Results are compared with recent works and the proposed algorithm obtains the best performance. The same pipeline is considered to evaluate the likability of a facial picture, with the difference that the estimation is based on high-level attributes such as gender, age, smile. Performance of these attributes is compared with previous techniques that mostly rely on facial keypoints positions, and it is shown that it is possible to obtain likability predictions that are close to human perception. Finally, a combination of both models that selects a likable facial image of good quality for a given person is described

Nowadays, images can be obtained in various ways such as capturing photos in single-exposure mode, applying Multiple Exposure Fusion algorithms to generate an image from multiple shoots of the same scene, mapping High Dynamic Range images to Standard Dynamic Range (SDR) images, converting raw formats to displayable formats, or applying post-processing techniques to enhance image quality, aesthetic quality,.. . When looking at some photos, one might have a feeling of unnaturalness. This paper deals with the problem of developing a model firstly to estimate if an image looks natural or not to humans and the second purpose is to try to understand how the unnaturalness feeling is induced by a photo: Are there specific unnaturalness clues or is unnaturalness a general feeling when looking at a photo? The study focuses on SDR images, especially on tonemapped images. The first contribution of the paper is the setting of an experiment gathering human naturalness opinions on 1,900 SDR images mainly obtained from tone mapping operators. Based on the collected data, the second contribution of the paper is to study the efficiency of different feature types including handcrafted features and learned features for image naturalness analysis. A binary classification model is then developed based on the determined features to classify if an image looks natural or unnatural.

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.

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 of 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 to various forms of blur whatever the facial feature descriptor algorithm implemented.

Abstract-This paper presents a new model of human attention that allows salient areas to be extracted from video frames. As automatic understanding of video semantic content is still far from being achieved, attention model tends to mimic the focus of the human visual system. Most existing approaches extract the saliency of images in order to be used in multiple applications but they are not compared to human perception.The model described here is achieved by the fusion of a static model inspired by the human system and a model of moving object detection. The static model is divided into two steps: a "retinal" filtering followed by a "cortical" decomposition. The moving object detection is carried out by a compensation of camera motion. Then we compare the attention model output for different videos with human judgment. A psychophysical experiment is proposed to compare the model with visual human perception and to validate it. The experimental results indicate that the model achieves about 88% of precision. This shows the usefulness of the scheme and its potential in future applications.