Learning to detect natural image boundaries using local brightness, color, and texture cues

TLDR

The study aims to accurately detect and localize natural scene boundaries using local image measurements. The authors extract brightness, color, and texture features, train a classifier on human‑labeled images, and output posterior probabilities for boundary presence at each location and orientation. The detector outperforms existing methods, showing that a simple linear cue combination suffices and that explicit texture modeling is essential for accurate boundary detection.

Abstract

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.