For more effective image sampling, compressive sensing (CS) imaging methods based on saliency have been proposed in recent years. Those assign higher measurement rates to salient regions, but lower rate non-salient regions improve the performance of CS imaging. However, those are block-based, which difficult apply actual as each photodiode should strictly correspond a block scene. In our work, ...

Stimulus salience depends both on behavioral context and on other factors such as novelty and frequency of occurrence. The temporo-parietal junction (TPJ) responds preferentially to behaviorally relevant stimuli and is thought to play a general role in detecting salient stimuli. If so, it should respond preferentially to novel or infrequent events, even in a neutral behavioral context. To test ...

A novel method for distinguishing classes of viewers from their aggregated eye movements is described. The probabilistic framework accumulates uniformly sampled gaze as Gaussian point spread functions (heatmaps), and measures the distance of unclassified scanpaths to a previously classified set (or sets). A similarity measure is then computed over the scanpath durations. The approach is used to...

The fundamental problem of computer vision is caused by the translation of a three-dimensional world onto one or more two-dimensional planes. As a result, methods for extracting regions of interest (ROIs) have certain limitations that cannot be overcome with traditional techniques that only utilize a single projection of the image. For example, while it is difficult to distinguished two overlap...

A major problem in Content-Based Image Retrieval (CBIR) is the unsupervised iden-tiication of perceptually salient regions in images. We contend that this problem can be tackled by mapping the pixels into various feature-spaces, whereupon they are subjected to a grouping-algorithm. In this paper we develop a robust and versatile non-parametric clustering algorithm that is able to handle the unb...

Grouping operations offer an effective mechanism by which to structure complex visual scenes. Among the various principles that support element integration, closure may be regarded as a main factor in shape extraction. In five experiments, we investigated the impact of grouping by closure on search for target configurations made up of collinearly arranged corner junctions. Systematic variations...

The majority of content based image retrieval systems use low-level features for similarity assessment of image content. However, low-level descriptors are often not sufficient for encoding stably more complex image information. This paper proposes an intermediate level descriptor which captures the organization of the image scene based on salient regions of the image. The descriptors are invar...