The Robotics Institute

Carnegie Mellon Robotics Institute

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

This paper presents a technique for using training data to design image filters for appearance-based object recognition. Rather than scanning the image with a single set of filters and using the results to test for the existence of objects, we use many sets of filters and take linear combinations of their outputs. The combining coefficients are optimized in a training phase to encourage discriminability between the filter responses for distinct parts of the object and clutter. Our experiments on three popular filter types show that by using this approach to combine sets of filters whose design parameters vary over a wide range, we can achieve detection performance competitive with that of any individual filter set. This in turn can ease the task of fine-tuning the settings for both the filters and the mechanisms that analyze their outputs.

Keywords

image filter, object recognition, discriminant

Notes

Associated Center(s) / Consortia: Vision and Autonomous Systems Center

Associated Project(s): 2D Recognition

Text Reference

Owen Carmichael, "Discriminant Filters for Object Recognition," tech. report CMU-RI-TR-02-09, Robotics Institute, Carnegie Mellon University, March, 2002

BibTeX Reference

@techreport{Carmichael_2002_3954,
   author = "Owen Carmichael",
   title = "Discriminant Filters for Object Recognition",
   booktitle = "",
   institution = "Robotics Institute",
   month = "March",
   year = "2002",
   number= "CMU-RI-TR-02-09",
   address= "Pittsburgh, PA",
}

The Robotics Institute

Menu