Esaliency (Extended Saliency): Meaningful Attention Using Stochastic Image Modeling

Computer-vision attention processes allocate computational resources to different parts of visual input and can lead to faster object recognition and image analysis. This paper proposes a new bottom-up attention mechanism. Rather than taking the traditional approach, which tries to model human attention, we propose to use a validated stochastic model to estimate the probability that an image part is of interest. We refer to this probability as saliency and thus specify the saliency in a mathematically well-defined sense. The model quantifies several intuitive observations such as the greater likelihood of correspondence between visually similar image regions and the likelihood that only a small number of interesting objects will be present in the scene. The latter observation, which implies that such objects are (relaxed) global exceptions, replaces the traditional preference to local contrast. The algorithm starts by a rough pre-attentive segmentation and then uses a graphical mod...

• Type: Journal
• Year: 2010
• Where: PAMI
• Authors: Tamar Avraham, Michael Lindenbaum
• Keywords: Bottom-up Attention Mechanism, Model, PAMI 2010, Validated Stochastic Model