In search of perceptually salient groupings

Y Z Song, B Xiao, Peter Hall, Liang Wang

Research output: Contribution to journalArticlepeer-review

14 Citations (SciVal)


Finding meaningful groupings of image primitives has been a long-standing problem in computer vision. This paper studies how salient groupings can be produced using established theories in the field of visual perception alone. The major contribution is a novel definition of the Gestalt principle of Pragnanz, based upon Koffka's definition that image descriptions should be both stable and simple. Our method is global in the sense that it operates over all primitives in an image at once. It works regardless of the type of image primitives and is generally independent of image properties such as intensity, color, and texture. A novel experiment is designed to quantitatively evaluate the groupings outputs by our method, which takes human disagreement into account and is generic to outputs of any grouper. We also demonstrate the value of our method in an image segmentation application and quantitatively show that segmentations deliver promising results when benchmarked using the Berkeley Segmentation Dataset (BSDS).
Original languageEnglish
Pages (from-to)935-947
Number of pages13
JournalIEEE Transactions on Image Processing
Issue number4
Early online date17 Oct 2010
Publication statusPublished - Apr 2011


  • gestalt
  • pragnanz
  • perceptual grouping
  • image segmentation


Dive into the research topics of 'In search of perceptually salient groupings'. Together they form a unique fingerprint.

Cite this