Unsupervised learning of high-order structural semantics from images

Jizhou Gao, Yin Hu, Jinze Liu, Ruigang Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

24 Scopus citations


Structural semantics are fundamental to understanding both natural and man-made objects from languages to buildings. They are manifested as repeated structures or patterns and are often captured in images. Finding repeated patterns in images, therefore, has important applications in scene understanding, 3D reconstruction, and image retrieval as well as image compression. Previous approaches in visual-pattern mining limited themselves by looking for frequently co-occurring features within a small neighborhood in an image. However, semantics of a visual pattern are typically defined by specific spatial relationships between features regardless of the spatial proximity. In this paper, semantics are represented as visual elements and geometric relationships between them. A novel unsupervised learning algorithm finds pair-wise associations of visual elements that have consistent geometric relationships suffi-ciently often. The algorithms are efficient - maximal matchings are determined without combinatorial search. High-order structural semantics are extracted by mining patterns that are composed of pairwise spatially consistent associations of visual elements. We demonstrate the effectiveness of our approach for discovering repeated visual patterns on a variety of image collections.

Original languageEnglish
Title of host publication2009 IEEE 12th International Conference on Computer Vision, ICCV 2009
Number of pages8
StatePublished - 2009
Event12th International Conference on Computer Vision, ICCV 2009 - Kyoto, Japan
Duration: Sep 29 2009Oct 2 2009

Publication series

NameProceedings of the IEEE International Conference on Computer Vision


Conference12th International Conference on Computer Vision, ICCV 2009

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Unsupervised learning of high-order structural semantics from images'. Together they form a unique fingerprint.

Cite this