TY - GEN
T1 - Edge detection for hyperspectral images using the Bhattacharyya distance
AU - Youn, Sungwook
AU - Lee, Chulhee
PY - 2013
Y1 - 2013
N2 - In this paper, we proposed a new edge detection algorithm for hyper spectral images using the Bhattacharyya distance. First, the principal component analysis is applied to hyper spectral images and then dominant eigenimages are selected. To compute the Bhattacharyya distance, four block pairs of each pixel are extracted: up-down, left-right, diagonal-left down and diagonal-right-down. From each pair of blocks, we compute the Bhattacharyya distance, which was used as edge information. Experiments show promising results compared to the conventional Sobel filter.
AB - In this paper, we proposed a new edge detection algorithm for hyper spectral images using the Bhattacharyya distance. First, the principal component analysis is applied to hyper spectral images and then dominant eigenimages are selected. To compute the Bhattacharyya distance, four block pairs of each pixel are extracted: up-down, left-right, diagonal-left down and diagonal-right-down. From each pair of blocks, we compute the Bhattacharyya distance, which was used as edge information. Experiments show promising results compared to the conventional Sobel filter.
UR - http://www.scopus.com/inward/record.url?scp=84900845206&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84900845206&partnerID=8YFLogxK
U2 - 10.1109/ICPADS.2013.127
DO - 10.1109/ICPADS.2013.127
M3 - Conference contribution
AN - SCOPUS:84900845206
SN - 9781479920815
T3 - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS
SP - 716
EP - 719
BT - Proceedings - 2013 19th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2013
PB - IEEE Computer Society
T2 - 2013 19th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2013
Y2 - 15 December 2013 through 18 December 2013
ER -