| | |
Summary: Proceedings of the Sixteenth International Conference on Pattern Recognition, 2002.
Fusion of Global and Local Information for Object Detection
Ashutosh Garg
, Shivani Agarwal
¡ , Thomas S. Huang
Beckman Institute,
¡ Department of Computer Science
University of Illinois, Urbana, IL 61801¢ ashutosh,sagarwal,t-huang1£ @uiuc.edu
Abstract
This paper presents a framework for fusing together
global and local information in images to form a powerful
object detection system. We begin by describing two detec-
tion algorithms. The first algorithm uses independent com-
ponent analysis (ICA) to derive an image representation
that captures global information in the input data. The sec-
ond algorithm uses a part-based representation that relies
on local properties of the data. The strengths of the two de-
tection algorithms are then combined to form a more pow-
erful detector. The approach is evaluated on a database of
|
