Object recognition benefits from fast new algorithms

JANUARY 14, 2009--General object recognition is a specific application of pattern analysis in which the target object may be present in different orientations. Objects can also be present at different distances, producing scale differences and images with less detail. Finally, if the location is unknown, a classification algorithm must be applied to all possibilities in the test input.

Certain types of classifiers can achieve this with the fast methods currently available, which make them preferable for use in general object recognition applications. One category of classifiers is the distortion-invariant filter (DIF). These filters can be implemented efficiently using fast Fourier transforms (FFTs) to locate shifted and multiple objects. A single DIF can handle all aspect-view and a number of scale distortions.

DIFs use combinations of training-set images that are representative of the expected distortions in the test set. Many different filters have been developed to address the various distortion problems. Now, Rohit Patnaik and David Casasent of Carnegie Mellon University have demonstrated a new approach that combines DIFs and the kernel technique to address the need for fast online filter shifts and improved filter performance. For more information, go to: http://spie.org/x31555.xml