9 November 2005 Feature extraction and band selection methods for hyperspectral imagery applied for identifying defects
Author Affiliations +
Proceedings Volume 5996, Optical Sensors and Sensing Systems for Natural Resources and Food Safety and Quality; 59960U (2005); doi: 10.1117/12.631068
Event: Optics East 2005, 2005, Boston, MA, United States
Abstract
An important task in hyperspectral data processing is to reduce the redundancy of the spectral and spatial information without losing any valuable details that are needed for the subsequent detection, discrimination and classification processes. Band selection and combination not only serves as the first step of hyperspectral data processing that leads to a significant decrease in computational complexity in the successive procedures, but also a research tool for determining optimal spectra requirements for different online applications. In order to uniquely characterize the materials of interest, band selection criteria for optimal band was defined. An integrated PCA and Fisher linear discriminant (FLD) method has been developed based on the criteria that used for hyperspectral feature band selection and combination. This method has been compared with other feature extraction and selection methods when applied to detect apple defects, and the performance of each method was evaluated and compared based on the detection results.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xuemei Cheng, Tao Yang, Yud-Ren Chen, Xin Chen, "Feature extraction and band selection methods for hyperspectral imagery applied for identifying defects", Proc. SPIE 5996, Optical Sensors and Sensing Systems for Natural Resources and Food Safety and Quality, 59960U (9 November 2005); doi: 10.1117/12.631068; https://doi.org/10.1117/12.631068
PROCEEDINGS
10 PAGES


SHARE
KEYWORDS
Principal component analysis

Ferroelectric LCDs

Feature extraction

Hyperspectral imaging

Defect detection

Data processing

Remote sensing

Back to Top