We present a method for the simultaneous detection and segmentation of objects from static images. We employ lowlevel contour features that enable us to learn the coarse object shape using a simple training phase requiring no manual segmentation. Based on the observation that most interesting objects (e.g., people) have regular and closed boundaries, we exploit relations between these features to extract mid-level cues, such as continuity and closure. For segmentation, we employ a Markov Random Field that combines these cues with information learned from training. The algorithm is evaluated for extracting person silhouettes from surveillance images, and quantitative results are presented.