Automated visual inspection of glass bottles using adapted median filtering

This work presents a digital image processing technique for the automated visual inspection of glass bottles based on a well-known method used for inspecting aluminium die castings. The idea of this method is to generate median filters adapted to the structure of the object under test. Thus, a "defect-free" reference image can be estimated from the original image of the inspection object. The reference image is compared with the original one, and defects are detected when the difference between them is considerable. The configuration of the filters is performed off-line including a priori information about real defect-free images. In the other hand, the filtering self is performed on-line. Thus, a fast on-line inspection is ensured. According to our experiments, the detection performance in glass bottles was 85% and the false alarms rate was 4%. Additionally, the processing time was only 0.3s/image.