In this paper, we investigate methods for the automatic thresholding o
f X-ray images of food packets in order to determine their suitability
for the detection of contaminants (or foreign objects) that may be pr
esent within. Single and dual threshold schemes based on variance and
entropic measures of the image histogram are applied. A modified entro
pic measure is proposed which decides whether a single or dual thresho
ld is appropriate dependent on the histogram data. The performance of
each of the methods is evaluated and compared using images containing
real and computer generated foreign object samples.