Eric Dinet

Visual attention: Effects of blur

The detection of salient regions in images is of great interest for a lot of computer vision applications as adaptive content delivery, smart resizing and auto-cropping, content based image retrieval or visually impaired people assistance. In this paper we focus on the effect of blurriness on human visual attention when observers see images with no prior knowledge. We investigate the hypothesis that sharp objects tend to capture attention irrespective of intensity, color or contrast. Eye movements of 17 subjects were recorded with an eye-tracker in free viewing conditions. Observers were asked to watch a collection of 122 color and grayscale images selected according to criteria driven by basic features of visual perception. The results of the experimental study clearly demonstrate the influence of the sharp/blur aspect of an image part on its saliency. These results indicate that blur information might be integrated in models of attention to efficiently improve the extraction of salient regions.

Enhanced image saliency model based on blur identification

Detection of visual saliency is of great interest for a lot of computer vision applications in particular for content-based image retrieval. The work presented in this paper is devoted to develop an algorithm of saliency detection that performs adequately in predicting human fixations for stimuli containing blur and sharp regions. This work is based on an experimental study on the effect of blurriness on visual attention when observers see images with no prior knowledge in free viewing conditions. A ground-truth has been derived from this experimental study to test the saliency model we developed.

COLOUR IMAGE COMPARISON AND VISUAL PERCEPTION : A PROCESS FOR DESCRIPTOR VALIDATION

In some specific problems, a gray scale analysis is unfortunately not sufficient: color is necessarily required. Generally in these kinds of problems it is necessary to be able to quantify the quality of an image in accordance with a reference one and the quality of a process in accordance with another one (for example to evaluate degradations introduced when compressing color images). Such quantifications must provide results correlated with human vision since color image quality is generally evaluated by human observers. In a first time we have developed objective local descriptors for the evaluation of quality of color images. Then we have established a process to validate the accuracy and the correlation of these descriptors with human visual perception. The goal of this paper is to expose how we determine during an experimental process whether retained descriptors are correlated with a visual classification of color images based on their quality. We describe the whole experimental process used to study this correlation. We also expose results obtained through the experimental process.

Moving object detection for unconstrained low-altitude aerial videos, a pose-independant detector based on Artificial Flow

Automatic detection of moving objects is an important task for aerial surveillance. It has been a popular and well-studied subject for the computer vision community, but is still a challenge. The method we introduce targets surveillance low-altitude mini and micro-UAVs. We take advantage of the inherent image motion on footage captured by such aerial vehicles. Our method confronts Optical Flow vectors and an estimated Flow in order to detect independently moving pixels. This motion-based approach is robust to operational conditions and to the geometric properties of the scene. The efficiency of the method was computed on the VIVID database. The moving areas detected will make the tracking task more robust and efficient.

Influence of color on visual saliency in short videos

The architecture of computational models of visual attention designed for videos is generally the result of a direct extension of techniques dedicated to static images. These models try to extract the salient areas of dynamic scenes (i.e. areas that may capture visual attention) by fusing static saliency maps computed frame per frame with saliency maps independently obtained from dynamic features. The problem is that there is no evidence for assuming that visual saliency of videos can be accurately identified from such a fusion process. In addition, there is no guarantee that visual saliency is the same for still and dynamic scenes. Then we propose to investigate this issue for short videos from the perspective of color information that has been clearly identified as an important salient property in static images.

Contribution of Augmented Reality Solutions to Assist Visually Impaired People in Their Mobility

The study is dedicated to analyze opportunities of augmented reality eyewear solutions for visually impaired people in a context of mobility. In order to perfectly understand the needs of low vision individuals, their expectation towards visual aids, and to clearly define crucial requirements, an experimental study has been carried out in a re-adaptation clinic. 58 patients with different visual pathologies have been carefully selected by vision-care professionals. During experiments and interviews, professional techniques developed for teaching patients to efficiently use their visual residual capabilities have been analyzed. One of the main objectives was to show the usefulness and the importance to put in the loop all actors to be able to derive relevant knowledge essential to success in the design and in the development of new visual aids dedicated to facilitate mobility of low vision people. The first results are encouraging and they tend to demonstrate the interest to use embedded augmented reality systems in order to propose helpful solutions easily adaptable to the specificities of the different visual troubles affecting mobility.

Image quality assessment for the visually impaired

In recent years, image enhancement methods have been developed to assist visually impaired people in the everyday life. These methods are promising but they currently suffer from the problem of their correct adjustment according to the specificities of each patient. To address such a problem, an objective quality metric could be used to quantify if enhancement schemes do not introduce artifacts that could be perceived as troublesome by visually deficient persons. As all existing metrics were designed to assess the image quality for observers with normal or corrected to normal vision, they are not appropriate in the context of low vision. Then an alternate framework is presented in this paper. This framework combines three distinct quality attributes that were identified as important features for the visually impaired in image quality assessment and it has been developed to adapt to the different types of visual pathologies.

Stroke extraction method for offline recognition of Chinese characters

A structural method for analysis of Chinese characters is presented, with the purpose of handwritten character recognition. Firstly, a line following and thinning process is used to obtain the thinned shape of the character. This process includes a specific treatment of singular regions allowing the detection of the branching points. In a second stage, an extended direction code is assigned to each point of the thinned line. Then, median filtering of extended codes eliminates much of the quantization noise, without altering significant direction changes. This leads to split up the character into a list of straight line segments, which are characterized by a main direction attribute. In a third stage, strokes are extracted by bringing together adjoining segments having neighboring directions. To compare two characters, firstly, we try to associate to each stroke of the first character the nearest stroke of the second one. Then, the distance between both characters is obtained from the sum of the distances between strokes, associated by pairs. This distance takes into account the possible presence of non- paired strokes in both characters.