A novel saliency model is proposed in this paper to automatically process images in the similar way as the human visual system which focuses on conspicuous regions that catch human beings’ attention. The model combines a hypergraph representation and a partitioning process with potential region-of-interest (p-ROI) approximation and validation. Experimental results demonstrate that the proposed ...

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...

We present a multi-scale representation of grey-level shape, called scale-space primal sketch, that makes explicit features in scale-space as well as the relations between features at different levels of scale. The representation gives a qualitative description of the image structure that allows for extraction of significant image structure — stable scales and regions of interest — in a solely ...

This contribution introduces a new Intensity-based technique that leads to local 3D-reconstruction of a stenosis from many angiographic views. We examine the reconstruction of a local region of a non-rigidly moving heart with unknown motion, using methods of reconstruction of rigid objects and without using ECG-information. Our basic idea is to assume rigidity for the ROI, and to fixate it by c...

Displaying panoramic and wide angle views on a flat 2D display surface is necessarily prone to distortions. Perspective projections are limited to fairly narrow view angles. Cylindrical and spherical projections can show full 360◦ panoramas, but at the cost of curving straight lines, interfering with the perception of salient shapes in the scene. In this paper, we introduce locally-adapted proj...

A new feature detection technique is presented that utilises local radial symmetry to identify regions of interest within a scene. This transform is significantly faster than existing techniques using radial symmetry and offers the possibility of real-time implementation on a standard processor. The new transform is shown to perform well on a wide variety of images and its performance is tested...

We propose a novel concept for comparing fMRI activations of brain regions of interest (ROI) across subjects. Each individual activation pattern is compared with a group activation model, rather than comparing the activations directly, e.g. on a voxel–level basis. Meaningful mappings of functional activations are based on correspondences in the respective modal eigenspaces. First results on aud...

Technological advances during the last decade have provided huge possibilities to support e-learning. However, there are still concerns regarding Return-on-Investment (ROI) of e-learning, its sustainability within organizational boundaries and effectiveness across potential learner groups. Much previous research has concentrated on learners’ motivation, satisfaction, and retention. This leaves ...

Different algorithms have been proposed in the last few years for discovering different types of behaviors in trajectory data. Existing approaches, in general, deal only with the outliers, and do not consider the standards routes and regions of interest. In this paper we propose a new algorithm for trajectory outlier detection between regions of interest. We show with two experiments on real da...