Représentation et reconnaissance d'objets par champs réceptifs

Vincent Colin de Verdière 1
1 PRIMA - Perception, recognition and integration for observation of activity
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes
Abstract : This thesis belong to the field of modelisation and recognition of objects using their appearance. Each object is modeled by a collection of images and recognition is obtained by the matching between a new image and a model image. Images are modeled by measures on local features. Several local descriptor bases are theoretically and experimentally evaluated and a Gaussian derivative basis is selected for its properties which include~: high discriminability for a concise description, scalability and steerability. Invariance to orientation is obtained by setting derivative directions according to the local gradient. Invariance to scale is obtained by a new technique which locally selects a characteristic scale for describing a neighborhood. This scale correspond to a maximum over scale of a Laplacian operator. These invariances are experimentally validated. In our system, an image is decomposed in a grid of overlapping windows which is represented by a corresponding grid of local features computed on these windows. This highly redundant representation enables us to design two robust recognition techniques~: the first one is based on a simple vote and the second one based on the prediction--verification method consists in splitting the recognition process in an hypothesis generation step for a single window followed by a verification step which checks the generated hypothesis on the neighboring windows with inclusion of geometric coherence constraints.
Document type :
Theses
Complete list of metadatas

https://tel.archives-ouvertes.fr/tel-00004820
Contributor : Thèses Imag <>
Submitted on : Wednesday, February 18, 2004 - 12:00:10 PM
Last modification on : Wednesday, April 11, 2018 - 1:54:06 AM
Long-term archiving on : Wednesday, September 12, 2012 - 1:30:15 PM

Identifiers

  • HAL Id : tel-00004820, version 1

Collections

INRIA | IMAG | UGA

Citation

Vincent Colin de Verdière. Représentation et reconnaissance d'objets par champs réceptifs. Interface homme-machine [cs.HC]. Institut National Polytechnique de Grenoble - INPG, 1999. Français. ⟨tel-00004820⟩

Share

Metrics

Record views

462

Files downloads

454