Structuring Image Templates for Identification of Foreign Object in Food in Shielding Packages Based On Wavelet Transforms

X-ray Imaging has been adopted for identification of Foreign Objects in food products, especially those in metallic packages that are electromagnetic shielding. As template matching is a viable approach to Foreign Object detection in X-ray images, a method of structuring image templates based on wavelet transforms is introduced in this paper for a specific application of detecting and identifying 3 possible kinds of common Foreign Objects of bones, stones and metal wire in a food product of salted duck gizzard, a local Chinese snack food, in vacuumed packages of Aluminum-Polyethylene (AL-PE). First, X-ray images of packaged food containing foreign objects were acquired. Then the images were enhanced by reducing their noises by wavelet transforms by Wavelets of bior3.7, db1, and syms4, respectively and bior3.7 was finally adopted. Later the enhanced images were segmented to binary images using Bimodal method, an Iterative method, and OTSU method, respectively, with OTSU method having the best accuracy. In the end, the size of image templates was determined and 5 groups of templates are built. To test the performance of these templates, a matching was carried out based on extracted invariant moments of wavelet transforms of the templates and images. Results showed that the templates structured are suitable for the purpose of identification of foreign objects in food.