Simple Gabor feature space for invariant object recognition

Ville Kyrki*, Joni Kristian Kamarainen, Heikki Kälviäinen

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

189 Citations (Scopus)


Invariant object recognition is one of the most challenging problems in computer vision. The authors propose a simple Gabor feature space, which has been successfully applied to applications, e.g., in invariant face detection to extract facial features in demanding environments. In the proposed feature space, illumination, rotation, scale, and translation invariant recognition of objects can be realized within a reasonable amount of computation. In this study, fundamental properties of Gabor features, construction of the simple feature space, and invariant search operations in the feature space are discussed in more detail.

Original languageEnglish
Pages (from-to)311-318
Number of pages8
JournalPattern Recognition Letters
Issue number3
Publication statusPublished - Feb 2004
MoE publication typeA1 Journal article-refereed


  • Feature extraction
  • Gabor filter
  • Invariant object recognition


Dive into the research topics of 'Simple Gabor feature space for invariant object recognition'. Together they form a unique fingerprint.

Cite this