Abstract
The purpose of this study is to detect jamming in sealing aluminum packages for food material. Two types of package are examined; one is an unpigmented silver package and the other is orange colored. The detection algorithm developed in this study consists of the following methods: capturing image data of the package seal area; 24 bit decomposition of RGB components (8 bits each channel), delineation of the seal area, FFT processing, image denoising by a mask operation, IFFT processing and binary conversion by a brightness threshold. The optimum brightness threshold is calculated by discriminant analysis. The combined optimum brightness thresholds for the detection of jamming in the unpigmented silver packages are an overall brightness threshold of 15 and a red component of 8. The discrimination ratio for jamming packages is 100% using the above thresholds. For orange colored packages, the optimum brightness thresholds for detecting jamming are an overall brightness threshold of 28 and a blue component of 8, which provides a discrimination ratio of 100%. It was shown that it is possible to reliably detect jamming in sealing food package using the detection systems developed in this study.
