The analysis of natural linear structures, termed "lineaments in satellite
images, provides important information to the geologist, In the satellite i
maging process, important features of the observed tridimensional scene, in
cluding geological lineaments, are mapped into the resulting 2-D image as s
harp radiation variations or ed,ne elements (edgels), Edgels are detected b
y a first-order differentiation operator and are linked together with those
in the vicinity on a basis of orientation continuity.
Lineaments are mapped into remotely sensed satellite images as long and con
tinuous quasilinear features and can be described as a connected sequence o
f edgels whose direction may change gradually along the sequence. Parts of
the same lineament can be occluded by geomorphological features and must be
linked together, a major drawback with local and small neighborhood detect
ors.
We propose a cellular neural network (CNN) architecture to offer a large di
rectional neighborhood to the lineament detection algorithm. The CNN uses a
large circular neighborhood coupled with a directional-induced gradient fi
eld to link together edgels with similar and continuous orientation. Missin
g edgels are restored if a surrounding lineament is detected.