On the relationships between physical phenomena, distance metrics, and best bands selection in hyperspectral processing

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 4381, Issue , 2001, Pages 55-67

  Keshava, N ^a   Boettcher, P ^a  

^a MIT LINCOLN LABORATORY   (United States)

Author keywords

Allocation; Bands; Best; Detection; Hyperspectral; Metrics; Phenomenology; Resource; Separability

Indexed keywords

ALGORITHMS; AUTOMATIC TARGET RECOGNITION; DIGITAL SIGNAL PROCESSING; IMAGE SENSORS;

HYPERSPECTRAL PROCESSING;

IMAGE ANALYSIS;

EID: 0035172510     PISSN: 0277786X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1117/12.437044     Document Type: Conference Paper

References (16)

1. Generalized nonlinear inverse problems solved using the least squares criterion
2. Inverse problems: Quest for information
3. Best wavelet packet bases in a rate-distortion sense
4. Rate-distortion methods for image and video compression
5. Selecting band combinations from multispectral data
6. Analytical design of multispectral sensors
7. Practical transform coding of multispectral imagery
8. System considerations for multispectral image compression designs
9. Combining image compression and classification using vector quantization
10. Bayes risk weighted vector quantization with posterior estimation for image compression and classification
11. An adaptive detection algorithm
12. Comparative analysis of hyperspectral adaptive matched filter detectors