Real-time hand tracking based on non-invariant features

A. L C Barczak, F. Dadgostar, C. H. Messom

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

9 Citations (Scopus)


In this paper we discuss the importance of the choice of features in digital image object recognition. The features can be classified as invariants or non-invariants. Invariant features are robust against one or more modifications such as rotations, translations, scaling and different light (illumination) conditions. Noninvariant features are usually very sensitive to any of these modifiers. On the other hand, non-invariant features can be used even in the event of translation, scaling and rotation, but the feature choice is in some cases more important than the training method. If the feature space is adequate then the training process can be straightforward and good classifiers can be obtained. In the last few years good algorithms have been developed relying on non-invariant features. In this article, we show how non-invariant features can cope with changes even though this requires additional computation at the detection phase. We also show preliminary results for a hand detector based on a set of cooperative Haar-like feature detectors. The results show the good potential of the method as well as the challenges to achieve real-time detection.

Original languageEnglish
Title of host publicationIMTC'05 - Proceedings of the IEEE Instrumentation and Measurement Technology Conference
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Print)0780388798, 9780780388796
Publication statusPublished - 2005
Externally publishedYes
EventIEEE International Instrumentation and Measurement Technology Conference 2005 - Ottawa, Canada
Duration: 16 May 200519 May 2005
Conference number: 22nd (Proceedings)


ConferenceIEEE International Instrumentation and Measurement Technology Conference 2005
Abbreviated titleI2MTC 2005
Internet address


  • Hand tracking
  • Non-invariant features
  • Parallel classifier

Cite this