Edinburgh Research Explorer

Object localisation using the Generative Template of Features

Research output: Contribution to journalArticle

Related Edinburgh Organisations

Open Access permissions

Open

Documents

http://www.sciencedirect.com/science/article/pii/S1077314209000356
Original languageEnglish
Pages (from-to)824-838
Number of pages15
JournalComputer Vision and Image Understanding
Volume113
Issue number7
DOIs
Publication statusPublished - Jul 2009

Abstract

We introduce the Generative Template of Features (GTF), a parts-based model for visual object category detection. The GTF consists of a number of parts, and for each part there is a corresponding spatial location distribution and a distribution over ‘visual words’ (clusters of invariant features). The performance of the GTF is evaluated for object localisation, and it is shown that such a relatively simple model can give state-of-the-art performance. We also demonstrate how a Hough-transform-like method for object localisation can be derived from the GTF model.

    Research areas

  • Object localisation, Visual words, Generative Template of Features, Object recognition

Download statistics

No data available

ID: 7894431