Soft Xray Inspection of Wheat Kernels Infested by Sitophilus Oryzae

The potential of a soft Xray method (15 kV and 65 .A) to detect internal seed infestations by the rice weevil(Sitophilus oryzae) in Canada Western Red Spring wheat was determined in this study. The infested kernels were identifiedby the presence of egg plugs and were scanned with a realtime fluoroscope every 5 to 7 d until the adults emerged from thekernels. A total of 57 features using histogram groups, textural features, and histogram and shape moments were extractedfrom the Xray images of the wheat kernels. Parametric and nonparametric classifiers, and a 4layer back propagationneural network classifier were used to identify uninfested and infested wheat kernels using histogram and textural featuresindependently, and using all 57 features together. There was no significant difference between the classifiers for theidentification of uninfested and infested wheat kernels. More than 95% of uninfested kernels and kernels infested by larvalstages were correctly identified by all the classifiers. Wheat kernels infested by pupaeadults and insectdamaged kernelswere identified with more than 99% accuracy by the classifiers.