Our study aims at the characterization of H I gas cloud images for classifi
cation purposes using their brightness temperature distribution. The morpho
logy and velocity structure of the gas cloud is not taken into account in t
his first study. The analysis is based on spatial contiguity at a chosen ra
dial velocity value. It is assumed that the form brightness temperature dis
tribution of each cloud is dependent on the physical process that created i
t. We wish to identify the existing relations between different clouds as a
first step toward understanding the evolutionary and physical processes th
at form them. Our study starts with an exploratory analysis based on princi
pal components analysis and on cluster analysis. Because the inherent signa
l in each image is noise, the characterization is then studied by using a m
ethod of density estimation by deconvolution. The clustering of the images
is done by considering single linkage and complete linkage criteria of clus
ter aggregation.