Foreign Objects Recognizing in shielding-packaged Food by Invariant Moment Matching

摘要

At present, X-ray imaging systems are employed to detect foreign objects in shielded packaged food products. An innovated method is researched in the paper to classify and to locate foreign objects based on matching by invariant moments. Feature vectors constructed by feature invariant moments extracted from template wavelet coefficient matrix were used for recognition and location of foreign objects in X-ray images. Matching between the normalized invariant moment vectors of target image and template images shows that this matching approach by invariant moments is precise and rapid in recognizing foreign objects in X-ray images of shielding-packaged food products.