How best to evaluate a saliency model's ability to predict where humans look in images is an open research question. The choice of evaluation metric depends on how saliency is defined and how the ground truth is represented. Metrics differ in how they rank saliency models, and this results from how false positives and false negatives are treated, whether viewing biases are accounted for, whether spatial deviations are factored in, and how the saliency maps are pre-processed. In this paper, we provide an analysis of 8 different evaluation metrics and their properties. With the help of systematic experiments and visualizations of metric computations, we add interpretability to saliency scores and more transparency to the evaluation of saliency models. Building off the differences in metric properties and behaviors, we make recommendations for metric selections under specific assumptions and for specific applications.

For many applications in graphics, design, and human computer interaction, it is essential to understand where humans look in a scene. Where eye tracking devices are not a viable option, models of saliency can be used to predict fixation locations. Most saliency approaches are based on bottom-up computation that does not consider top-down image semantics and often does not match actual eye movements. To address this problem, we collected eye tracking data of 15 viewers on 1003 images and use this database as training and testing examples to learn a model of saliency based on low, middle and high-level image features. This large database of eye tracking data is publicly available with this paper.

Three-dimensional shape can be drawn using a variety of feature lines, but none of the current definitions alone seem to capture all visually-relevant lines. We introduce a new definition of feature lines based on two perceptual observations. First, human perception is sensitive to the variation of shading, and since shape perception is little affected by lighting and reflectance modification, we should focus on normal variation. Second, view-dependent lines better convey smooth surfaces. From this we define view-dependent curvature as the variation of the surface normal with respect to a viewing screen plane, and apparent ridges as the loci of points that maximize a view-dependent curvature. We present a formal definition of apparent ridges and an algorithm to render line drawings of 3D meshes. We show that our apparent ridges encompass or enhance aspects of several other feature lines.