Spectral segmentation via minimum barrier distance

Constructing a reliable affinity matrix is crucial for spectral segmentation. In this paper, we define a technique to create a reliable affinity matrix for the application to spectral segmentation. We propose an affinity model based on the minimum barrier distance (MBD). First, the image is over-segmented into superpixels; then the subset of the pixels, located in the center of these superpixels, is used to compute the MBD-based affinities of the original image, with particular care taken to avoid a strong boundary, as described in the classical model. To deal with images with faint object and random or “clutter” background, we present gradient data that are integrated with the MBD data. To capture different perceptual grouping cues, the completed affinity model includes MBD, color, and spatial cues of the image. Finally, spectral segmentation is implemented at the superpixel level to provide an image segmentation result with pixel granularity. Experiments using the Berkeley image segmentation database validate the effectiveness of the proposed method. Covering, PRI, VOI, and the F-measure are used to evaluate the results relative to several state-of-the-art algorithms.