1 February 2006 Multipixel anomaly detection in noisy multispectral images
Author Affiliations +
Optical Engineering, 45(2), 023604 (2006). doi:10.1117/1.2166639
Abstract
Basing ourselves on a novel segmentation algorithm for multispectral images, we consider how to detect multipixel anomalous objects in image cubes where spectral information is available. In particular, we have developed several morphological filters to compensate for noise that may be present in the initial cube. We show that for different types of noise (Gaussian and speckle), a modification of our morphology technique allows us to better detect targets without an enhanced false-alarm result.
Eran Ohel, Stanley R. Rotman, Dan G. Blumberg, "Multipixel anomaly detection in noisy multispectral images," Optical Engineering 45(2), 023604 (1 February 2006). http://dx.doi.org/10.1117/1.2166639
JOURNAL ARTICLE
8 PAGES


SHARE
KEYWORDS
Image segmentation

Detection and tracking algorithms

Target detection

Signal to noise ratio

Image filtering

Speckle

Optical engineering

RELATED CONTENT

Polarization vision for object detection
Proceedings of SPIE (February 25 1994)
Advances in real time spectral tracking
Proceedings of SPIE (September 30 2009)
The PAUCam readout electronics system
Proceedings of SPIE (August 09 2016)

Back to Top