From images to shape models for object detection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2008

From images to shape models for object detection

Vittorio Ferrari
  • Function : Author
  • PersonId : 852592
Frédéric Jurie
Cordelia Schmid
  • Function : Author
  • PersonId : 831154


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 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 made possible by a novel technique for learning a shape model of an object class given {\em 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, while needing no segmented examples for training (only bounding-boxes)
Fichier principal
Vignette du fichier
RR-6600.pdf (2.3 Mo) Télécharger le fichier
Vignette du fichier
icon.jpg (5.83 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

inria-00308388 , version 1 (30-07-2008)


  • HAL Id : inria-00308388 , version 1


Vittorio Ferrari, Frédéric Jurie, Cordelia Schmid. From images to shape models for object detection. [Research Report] RR-6600, INRIA. 2008. ⟨inria-00308388⟩
249 View
985 Download


Gmail Facebook X LinkedIn More