Location: Stored Product Insect Research Unit
Title: Imaging and Automated Detection of Sitophilus Oryzae L. (Coleoptera: Curculionidae) Pupae in Hard Red Winter Wheat Authors
Submitted to: Meeting Abstract
Publication Type: Other
Publication Acceptance Date: May 26, 2005
Publication Date: May 26, 2005
Citation: Toews, M.D., Pearson, T.C., Arthur, F.H., Campbell, J.F. 2005. Imaging and automated detection of Sitophilus oryzae l. (Coleoptera: curculionidae) pupae in hard red winter wheat. Meeting Abstract, 2005 Industry Alliance Meeting, Fayetteville, AR. Technical Abstract: Computed tomography, a modern imaging technique commonly used for diagnosing human health ailments, utilizes multiple x-rays and sophisticated software to create a cross sectional representation of a subject. We investigated using this technique to image Hard Red Winter wheat samples infested with pupae of the rice weevil, and then developed a software program to rapidly recognize and quantify infested kernels in a given sample. Samples were imaged in 7.6 cm (dia) plastic tubes filled with one kg of wheat and densities of 0, 50, or 100 infested kernels. Spaces among wheat kernels were filled with corn oil to increase the contrast with kernels containing insects. Automated image processing was conducted separately on each 100 g portion of the prepared samples in a custom C language program. The average detection rate in the 5 infested kernels/100 g samples was 94.4 ± 7.3% (mean ± SD) while the average detection accuracy in the 10 infested kernels/100 g sample was 87.3 ± 7.9%. Detection accuracy in the 10 infested kernels/100g samples was slightly lower than the 5 infested kernels/100g samples due to some infested kernels overlapping with each other or air bubbles in the oil. In the control replicates, an average of 1.2 ± 0.9 (n = 10) bubbles was incorrectly classed as infested kernels. In light of these positive results, future studies should be conducted utilizing additional grains, insect species, and life stages.