Efficient Search And Verification for Function Based Classification From Real Range Images

Guy Froimovich, Ehud Rivlin, Ilan Shimshoni, and Octavian Soldea.
Efficient Search and Verification for Function Based Classification from Real Range Images.
CVIU, 105:200-217, 2007

Online Version

A pdf version is available for download.

Abstract

In this work we propose a probabilistic model for generic object classification from raw range images. Our approach supports a validation process in wich classes are verified using a functional class graph in which functional parts and their realization hypotheses are explored. The validation tree is efficiently searched. Some functional requirements are validated in a final procedure for more efficient separation of objects from non-objects. The search employs a knowledge repository mechanism that monotonically adds knowledge during the search and speeds up the classification process. Finally, we describe our implementation and present results of experiments on a database that comprises about 150 real raw range images of object instances from 10 classes.

Keywords

Co-authors

Bibtex Entry

@article{FroimovichRSS07a,
  title = {Efficient Search and Verification for Function Based Classification from Real Range Images},
  author = {Guy Froimovich and Ehud Rivlin and Ilan Shimshoni and Octavian Soldea},
  year = {2007},
  journal = {CVIU},
  volume = {105},
  pages = {200-217},
  keywords = {Function based reasoning; Recognition; Classification; Computer vision; Raw range images; 3D segmentation},
  abstract = {In this work we propose a probabilistic model for generic object classification from raw range images. Our approach supports a validation process in wich classes are verified using a functional class graph in which functional parts and their realization hypotheses are explored. The validation tree is efficiently searched. Some functional requirements are validated in a final procedure for more efficient separation of objects from non-objects. The search employs a knowledge repository mechanism that monotonically adds knowledge during the search and speeds up the classification process. Finally, we describe our implementation and present results of experiments on a database that comprises about 150 real raw range images of object instances from 10 classes.}
}