Low-level hierarchical multiscale segmentation statistics of natural images

Emre Akbas, Narendra Ahuja

Research output: Contribution to journalArticlepeer-review


This paper is aimed at obtaining the statistics as a probabilistic model pertaining to the geometric, topological and photometric structure of natural images. The image structure is represented by its segmentation graph derived from the low-level hierarchical multiscale image segmentation. We first estimate the statistics of a number of segmentation graph properties from a large number of images. Our estimates confirm some findings reported in the past work, as well as provide some new ones. We then obtain a Markov random field based model of the segmentation graph which subsumes the observed statistics. To demonstrate the value of the model and the statistics, we show how its use as a prior impacts three applications: image classification, semantic image segmentation and object detection.

Original languageEnglish (US)
Article number6710173
Pages (from-to)1900-1906
Number of pages7
JournalIEEE transactions on pattern analysis and machine intelligence
Issue number9
StatePublished - Sep 2014


  • Markov random field
  • Natural image statistics
  • low-level hierarchical segmentation

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Low-level hierarchical multiscale segmentation statistics of natural images'. Together they form a unique fingerprint.

Cite this