25 May 2016 Building robust neighborhoods for manifold learning-based image classification and anomaly detection
Author Affiliations +
Abstract
We exploit manifold learning algorithms to perform image classification and anomaly detection in complex scenes involving hyperspectral land cover and broadband IR maritime data. The results of standard manifold learning techniques are improved by including spatial information. This is accomplished by creating super-pixels which are robust to affine transformations inherent in natural scenes. We utilize techniques from harmonic analysis and image processing, namely, rotation, skew, flip, and shift operators to develop a more representational graph structure which defines the data-dependent manifold.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Timothy Doster, Timothy Doster, Colin C. Olson, Colin C. Olson, } "Building robust neighborhoods for manifold learning-based image classification and anomaly detection ", Proc. SPIE 9840, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXII, 984015 (25 May 2016); doi: 10.1117/12.2227224; https://doi.org/10.1117/12.2227224
PROCEEDINGS
13 PAGES


SHARE
RELATED CONTENT

Image Segmentation By Edge Tracing
Proceedings of SPIE (March 16 1983)
Real-time analysis of the grain on wooden planks
Proceedings of SPIE (March 07 2002)
Object Tracking Using Curvilinear Features
Proceedings of SPIE (December 15 1988)
Focusing on targets through exclusion
Proceedings of SPIE (July 31 1991)

Back to Top