### Abstract

This paper investigates the effect of spectral screening on processing hyperspectral data through Independent Component Analysis (ICA). ICA is a multivariate data analysis method producing components that are statistically independent. In the context of the linear mixture model, the endmember abundances can be viewed as independent components, the endmembers forming the columns of the mixing matrix. In essence, the ICA processing can be seen as an alternative solution to endmember unmixing. In the context of feature extraction, each feature will be represented by an independent component, thus leading to maximum separability among features.Spectral screening is defined as the reduction of the image cube to a subset of representative pixel vectors with the goal of achieving a considerable speedup in further processing. At the base of spectral screening are the measure used to assess the similarity between two pixel vectors and a threshold value. Two pixel vectors are similar if the value yielded by the similarity measure is smaller than the threshold and dissimilar otherwise. The spectral screened subset has to be formed such that any two vectors in the subset are dissimilar and for any vector in the original image cube there is a similar vector in the subset. The method we present uses spectral angle as distance measure. A necessary condition for the success of spectral screening is that the result of processing the reduced subset can be extended to the entire data. Intuitively, a larger subset would lead to increased accuracy. However, the overhead introduced by the spectral screening is directly proportional to the subset size. Our investigation has focused on finding the "ideal" threshold value that maximizes both the accuracy and the speedup. The practical effectiveness of the methods was tested on HYDICE data. The results indicate that considerable speedup is obtained without a considerable loss of accuracy. The presented method leads to a significant increase in computational efficiency allowing faster processing of hyperspectral images.

Original language | English |
---|---|

Pages (from-to) | 241-252 |

Number of pages | 12 |

Journal | Proceedings of SPIE - The International Society for Optical Engineering |

Volume | 5093 |

DOIs | |

State | Published - 1 Dec 2003 |

Event | Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery IX - Orlando, FL, United States Duration: 21 Apr 2003 → 24 Apr 2003 |

### Fingerprint

### Keywords

- Feature separability
- Hyperspectral imagery processing
- Independent component analysis
- Spectral angle
- Spectral screening

### Cite this

}

**Investigation of Spectral Screening Techniques for Independent Component Analysis Based Hyperspectral Image Processing.** / Robila, Stefan.

Research output: Contribution to journal › Conference article › Research › peer-review

TY - JOUR

T1 - Investigation of Spectral Screening Techniques for Independent Component Analysis Based Hyperspectral Image Processing

AU - Robila, Stefan

PY - 2003/12/1

Y1 - 2003/12/1

N2 - This paper investigates the effect of spectral screening on processing hyperspectral data through Independent Component Analysis (ICA). ICA is a multivariate data analysis method producing components that are statistically independent. In the context of the linear mixture model, the endmember abundances can be viewed as independent components, the endmembers forming the columns of the mixing matrix. In essence, the ICA processing can be seen as an alternative solution to endmember unmixing. In the context of feature extraction, each feature will be represented by an independent component, thus leading to maximum separability among features.Spectral screening is defined as the reduction of the image cube to a subset of representative pixel vectors with the goal of achieving a considerable speedup in further processing. At the base of spectral screening are the measure used to assess the similarity between two pixel vectors and a threshold value. Two pixel vectors are similar if the value yielded by the similarity measure is smaller than the threshold and dissimilar otherwise. The spectral screened subset has to be formed such that any two vectors in the subset are dissimilar and for any vector in the original image cube there is a similar vector in the subset. The method we present uses spectral angle as distance measure. A necessary condition for the success of spectral screening is that the result of processing the reduced subset can be extended to the entire data. Intuitively, a larger subset would lead to increased accuracy. However, the overhead introduced by the spectral screening is directly proportional to the subset size. Our investigation has focused on finding the "ideal" threshold value that maximizes both the accuracy and the speedup. The practical effectiveness of the methods was tested on HYDICE data. The results indicate that considerable speedup is obtained without a considerable loss of accuracy. The presented method leads to a significant increase in computational efficiency allowing faster processing of hyperspectral images.

AB - This paper investigates the effect of spectral screening on processing hyperspectral data through Independent Component Analysis (ICA). ICA is a multivariate data analysis method producing components that are statistically independent. In the context of the linear mixture model, the endmember abundances can be viewed as independent components, the endmembers forming the columns of the mixing matrix. In essence, the ICA processing can be seen as an alternative solution to endmember unmixing. In the context of feature extraction, each feature will be represented by an independent component, thus leading to maximum separability among features.Spectral screening is defined as the reduction of the image cube to a subset of representative pixel vectors with the goal of achieving a considerable speedup in further processing. At the base of spectral screening are the measure used to assess the similarity between two pixel vectors and a threshold value. Two pixel vectors are similar if the value yielded by the similarity measure is smaller than the threshold and dissimilar otherwise. The spectral screened subset has to be formed such that any two vectors in the subset are dissimilar and for any vector in the original image cube there is a similar vector in the subset. The method we present uses spectral angle as distance measure. A necessary condition for the success of spectral screening is that the result of processing the reduced subset can be extended to the entire data. Intuitively, a larger subset would lead to increased accuracy. However, the overhead introduced by the spectral screening is directly proportional to the subset size. Our investigation has focused on finding the "ideal" threshold value that maximizes both the accuracy and the speedup. The practical effectiveness of the methods was tested on HYDICE data. The results indicate that considerable speedup is obtained without a considerable loss of accuracy. The presented method leads to a significant increase in computational efficiency allowing faster processing of hyperspectral images.

KW - Feature separability

KW - Hyperspectral imagery processing

KW - Independent component analysis

KW - Spectral angle

KW - Spectral screening

UR - http://www.scopus.com/inward/record.url?scp=1642475068&partnerID=8YFLogxK

U2 - 10.1117/12.487091

DO - 10.1117/12.487091

M3 - Conference article

VL - 5093

SP - 241

EP - 252

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

ER -