12 April 2004 Efficient method for extracting object recognition metric from correlation filter output
Author Affiliations +
Abstract
Correlation filters can be very effective for object recognition. However, these filters may become too computationally expensive when applied to large images, or large numbers of images, because they require Fourier transforms between the spatial and frequency domains. This paper makes the simplifying assumption of single object recognition and presents an algorithm designed to reduce complexity of computation and/or storage. The algorithm derives a frequency domain match metric as opposed to the standard approach of using the spatial correlation plane. The performance of the efficient algorithm is compared to that of the standard correlation filter algorithm, for both accuracy and computational requirements.
© (2004) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bhagavatula V. K. Vijaya Kumar, Jason Thornton, "Efficient method for extracting object recognition metric from correlation filter output", Proc. SPIE 5437, Optical Pattern Recognition XV, (12 April 2004); doi: 10.1117/12.543538; https://doi.org/10.1117/12.543538
PROCEEDINGS
11 PAGES


SHARE
Back to Top