TY - RPRT
T1 - Texture alteration detection in bitemporal images of lesions with psoriasis
AU - Maletti, Gabriela Mariel
AU - Ersbøll, Bjarne Kjær
PY - 2003
Y1 - 2003
N2 - The objective of this work is to explore the feasibility of quantifying textural change between pairs of segmented patterns without registering them. The Multi-variate Alteration Detection (M.A.D.) Transform is applied to a texture model constructed with the data of segmented psoriasis lesions images. The texture model is Haralick's co-occurrence matrix, which is computed and normalized for each single band with the equalized data of a given lesion. The contribution of each single color band to the textural change is analyzed.
AB - The objective of this work is to explore the feasibility of quantifying textural change between pairs of segmented patterns without registering them. The Multi-variate Alteration Detection (M.A.D.) Transform is applied to a texture model constructed with the data of segmented psoriasis lesions images. The texture model is Haralick's co-occurrence matrix, which is computed and normalized for each single band with the equalized data of a given lesion. The contribution of each single color band to the textural change is analyzed.
KW - texture model
KW - co-occurrence matrix
KW - |psoriasis
KW - Multivariate Alteration Detection
KW - dermatological images
KW - M.A.D. Transform
M3 - Report
BT - Texture alteration detection in bitemporal images of lesions with psoriasis
ER -