Success in visually searching for a small object or target in a natural scene depends on many factors, including the spatial structure of the scene and the pattern of observers' eye movements. The aim of this study was to determine to what extent local color properties of natural scenes can account for target-detection performance. A computer-controlled high-resolution color monitor was used to...

Scene images share underlying regularities on the global scale. In order to develop a representation that encodes the global properties of scene images and reflects their inherent regularities, we train a probabilistic hierarchical model to infer correlational information from scene images. The model parameters fitted to the characteristic statistics of scene images reveal an efficient represen...

We present a process for estimating spatially-varying surface reflectance of a complex scene observed under natural illumination conditions. The process uses a laser-scanned model of the scene’s geometry, a set of digital images viewing the scene’s surfaces under a variety of natural illumination conditions, and a set of corresponding measurements of the scene’s incident illumination in each ph...

Natural images are the composite consequence of multiple factors related to scene structure, illumination, and imaging. For facial images, the factors include different facial geometries, expressions, head poses, and lighting conditions. We apply multilinear algebra, the algebra of higherorder tensors, to obtain a parsimonious representation of facial image ensembles which separates these facto...

Robust pattern recognition within the Bayesian framework for scene segmentation/boundary detection is oftentimes hampered by the presence of textures within natural images. In order to improve segmentation/boundary detection on natural images, it is necessary to combine multiple features eeectively. This paper introduces two algorithms for combining both color and texture features to assist bou...

This paper describes recent work on a neural network approach to outdoor scene interpretation. The results of evaluating a range of automatic region-based segmentation techniques based on a new segmentation quality metric are presented. The optimal technique is used to segment images of natural outdoor scenes. A powerful set of features designed for outdoor scene analysis is extracted from regi...

In the segmentation of natural images, most algorithms rely on the concept of occlusion. Intuitively, if all of the pixels in a region are the same color, they are probably part of the same object, which is blocking all of the light from the objects behind it. In x-ray images, however, this assumption is violated. In this paper, we introduce SATISφ, a method for separating objects in a set of x...