This paper presents a database containing 'ground truth' segmentations produced by humans for images of a wide variety of natural scenes. We define an error measure which quantifies the consistency between segmentations of differing granularities and find that different human segmentations of the same image are highly consistent. Use of this dataset is demonstrated in two applications: (1) evaluating the performance of segmentation algorithms and (2) measuring probability distributions associated with Gestalt grouping factors as well as statistics of image region properties.

The goal of this work is to accurately detect and localize boundaries in natural scenes using local image measurements. We formulate features that respond to characteristic changes in brightness, color, and texture associated with natural boundaries. In order to combine the information from these features in an optimal way, we train a classifier using human labeled images as ground truth. The output of this classifier provides the posterior probability of a boundary at each image location and orientation. We present precision-recall curves showing that the resulting detector significantly outperforms existing approaches. Our two main results are 1) that cue combination can be performed adequately with a simple linear model and 2) that a proper, explicit treatment of texture is required to detect boundaries in natural images.

Using a multitechnique approach, two temperature domains have been identified in agarose gelation. Below 35°C, fast gelation results in strong, homogeneous and weakly turbid networks. The correlation length, evaluated from the wavelength dependence of the turbidity, is close to values of pore size reported in the literature. Above 35°C, gelation is much slower and is associated with the formation of large‐scale heterogeneities that can be monitored by a marked change in the wavelength dependence of turbidity and visualised by transmission electron microscopy. Curing agarose gels at temperatures above 35°C, and then cooling them to 20°C, produces much weaker gels than those formed directly at 20°C. Dramatic reductions in the elastic modulus and failure strain and stress are found in this case as a result of demixing during cure. An interpretation, based on the kinetic competition between osmotic forces (in favor of phase separation) and elastic forces (that prevent it) is proposed. © 2001 John Wiley & Sons, Inc. Biopolymers 59: 131–144, 2001

Figure-ground organization refers to the visual perception that a contour separating two regions belongs to one of the regions. Recent studies have found neural correlates of figure-ground assignment in V2 as early as 10-25 ms after response onset, providing strong support for the role of local bottom-up processing. How much information about figure-ground assignment is available from locally computed cues? Using a large collection of natural images, in which neighboring regions were assigned a figure-ground relation by human observers, we quantified the extent to which figural regions locally tend to be smaller, more convex, and lie below ground regions. Our results suggest that these Gestalt cues are ecologically valid, and we quantify their relative power. We have also developed a simple bottom-up computational model of figure-ground assignment that takes image contours as input. Using parameters fit to natural image statistics, the model is capable of matching human-level performance when scene context limited.

No abstract