Detection of pecan weevil larvae in pecan nutmeat using multispectral imaging system

Scope and method of study. The food industry has zero tolerance for pecan weevils, Curculio caryae or their larvae. It is inevitable that some pecan weevil larvae will be interspersed with pecan nutmeat during processing. Therefore it is required to separate the weevil larvae from the nutmeat. This project utilizes multispectral imaging techniques to detect and identify pecan weevil larvae in pecan nutmeat. Diffuse reflectance measurements were obtained for both pecan weevil larvae and pecan nutmeat using a spectrometer sensitive to visible and near infrared light. Principle component analysis (PCA) and derivative analysis was performed to identify the spectral wavelengths that best differentiated pecan nutmeat from pecan weevil larvae. Four spectral wavelengths were successfully identified using these procedures. Multispectral images of pecan weevil larvae interspersed with pecan nutmeat using the selected band pass interference filters were obtained. The images were taken with a NIR enhanced camera, AVT Dolphin F 145-B from Allied Vision Technologies, Newburyport, MA. The images were then processed using various morphological image processing algorithms, filtering, masking and thresholding techniques. This method was compared to a novel active contour based image segmentation algorithm. (Abstract shortened by UMI.)...