G. Agam et I. Dinstein, GEOMETRIC SEPARATION OF PARTIALLY OVERLAPPING NONRIGID OBJECTS APPLIED TO AUTOMATIC CHROMOSOME CLASSIFICATION, IEEE transactions on pattern analysis and machine intelligence, 19(11), 1997, pp. 1212-1222
A common task in cytogenetic tests is the classification of human chro
mosomes. Successful separation between touching and overlapping chromo
somes in a metaphase image is vital for correct classification. Curren
t systems for automatic chromosome classification are mostly interacti
ve and require human intervention for correct separation between touch
ing and overlapping chromosomes. Since chromosomes are nonrigid object
s, special separation methods are required to segregate them. Common m
ethods for separation between touching chromosomes tend to fail where
ambiguity or incomplete information are involved, and so are unable to
segregate overlapping chromosomes. The proposed approach treats the s
eparation problem as an identification problem, and, in this way, mana
ges to segregate overlapping chromosomes. This approach encompasses lo
w-level knowledge about the objects and uses only extracted informatio
n, therefore, it is fast and does not depend on the existence of a sep
arating path. The method described in this paper can be adopted for ot
her applications, where separation between touching and overlapping no
nrigid objects is required.