Back to Search
Start Over
A Biologically Inspired Automatic System for Media Quality Assessment.
- Source :
-
IEEE Transactions on Automation Science & Engineering . Apr2016, Vol. 13 Issue 2, p894-902. 9p. - Publication Year :
- 2016
-
Abstract
- Photo aesthetic quality evaluation is a challenging task in artificial intelligence systems. In this paper, we propose a biologically inspired aesthetic descriptor that mimicks humans sequentially perceiving visually/semantically salientref refid="fnote1"/ id="fnote1" asterisk="no"paraIn general, visually salient regions are perceived by low-level visual features, such as the high contrast between the foreground and the background objects; while semantically salient regions are perceived by high-level visual features such as human faces.pararegions in a photo. In particular, a weakly supervised learning paradigm is developed to project the local image descriptors into a low-dimensional semantic space. Then, each graphlet can be described by multiple types of visual features, both in low-level and in high-level. Since humans usually perceive only a few salient regions in a photo, a sparsity-constrained graphlet ranking algorithm is proposed that seamlessly integrates both the low-level and the high-level visual cues. Top-ranked graphlets are those visually/semantically prominent local aesthetic descriptors in a photo. They are sequentially linked into a path that simulates humans actively viewing process. Finally, we learn a probabilistic aesthetic measure based on such actively viewing paths (AVPs) from the training photos. Experimental results show that: 1) the AVPs are 87.65% consistent with real human gaze shifting paths, as verified by the eye-tracking data and 2) our aesthetic measure outperforms many of its competitors. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 15455955
- Volume :
- 13
- Issue :
- 2
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Automation Science & Engineering
- Publication Type :
- Academic Journal
- Accession number :
- 114532781
- Full Text :
- https://doi.org/10.1109/TASE.2015.2418223