Fifth International Conference on Image Processing and Its Applications 1995
DOI: 10.1049/cp:19950653
|View full text |Cite
|
Sign up to set email alerts
|

Wavelet transforms on vector spaces as a method of multispectral image characterisation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 0 publications
0
2
0
Order By: Relevance
“…We consider the imagery in multi-dimensional vector space [7]. That is, at each pixel location we have a 3-dimensional vector for 3-bands of the videography imagery.…”
Section: Multiresolution Classification Schemementioning
confidence: 99%
See 1 more Smart Citation
“…We consider the imagery in multi-dimensional vector space [7]. That is, at each pixel location we have a 3-dimensional vector for 3-bands of the videography imagery.…”
Section: Multiresolution Classification Schemementioning
confidence: 99%
“…In lowlow, low-high, high-low and high-high subspaces, we first compute the mean absolute distance, assuming we get M types after thresholding, that is: ml m= 1,2,.. .M (7) o, (m) where dLLp is the distance in low-low subband of band p , .Cup(i,j) is the coefficient at location (i,j) in low-low subband of band p , pu,,(m) and ou,,(m) are the mean and standard deviation in low-low subband of band p for type m. Then the distance in the low-low subspace is defined as: p=l Similarly, we can compute dLH, dHL and dHH. Since most of the useful information is in low-low subspace, we can not just add these four distance together to be the total distance.…”
Section: A Unsupervised Classificationmentioning
confidence: 99%