Enhanced image saliency model based on blur identification

Abstract

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.

Eye movements during change detection: the role of depth of field

“…The results showed that the depth of field or the amount of blur could influence the allocation of viewers’ attention, which were consistent with the previous research [18, 19]. More specifically, small depth of field made viewers put more attention in the sharp area; however, the areas which got attention were larger than that in the scene with large depth of field.…”

Saliency-based framework for facial expression recognition

“…We conducted a visual experiment with the help of an eye-tracker and recorded the fixations and saccades of human observers as they watch the collection of videos showing six universal facial expressions. It is known that eye gathers most of the information during fixations [10,11]. Eye fixations describe the way in which visual attention is directed towards salient regions in a given stimulus.…”

Depth of Field Affects Perceived Depth in Stereographs

“…Depth of field is an important aspect of vision, and there has been significant research on the effects of depth of field in nonstereo photographs over the past few years. For example, it has been shown that depth of field can be used to direct viewers' attention [Baveye et al 2012;Hamerly and Dvorak 1981;Hillaire et al 2008;Khan et al 2010], and it may also influence the aesthetic appreciation of images [Datta et al 2006]. Other research has directly assessed its effects on the perceived distance from the observer to objects and the perceived distances between objects in the scene [Held et al 2010;Mather 1996;Mather and Smith 2000;Pentland 1987;Vishwanath and Blaser 2010;Watt et al 2005].…”