International Journal of Computer Vision

, Volume 87, Issue 3, pp 284–303

From Images to Shape Models for Object Detection

  • Vittorio Ferrari
  • Frederic Jurie
  • Cordelia Schmid


We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and can localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the boundaries of objects, rather than just their bounding-boxes. This is achieved by a novel technique for learning a shape model of an object class given images of example instances. Furthermore, we also integrate Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately and does not need segmented examples for training (only bounding-boxes).


Object class detection Learning category models Local contour features Shape matching 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • Vittorio Ferrari
    • 1
  • Frederic Jurie
    • 2
  • Cordelia Schmid
    • 3
  1. 1.ETH ZurichZurichSwitzerland
  2. 2.University of CaenCaenFrance
  3. 3.INRIA GrenobleGrenobleFrance

Personalised recommendations