An image processing and analysis systems for automatic classification of cigarette filter blockage
J.P. Stitt, Richard J. O’Connor, Lynn T. Kozlowski · 2004
Most filter cigarettes today employ ventilated filters. Heavily ventilated filters have been found to be "elastic" in that they contribute to lower tar numbers in standard smoking-machine tests while at the same time allowing smokers to get much higher doses of tar from the same cigarette when they block vents with fingers or lips. This paper describes a method for automating a stain pattern technique which permits unobtrusive measurement of behavioral vent blocking. This automation could provide a more accurate analysis of filter efficacy. The system employs image processing and analysis to generate a set of unbiased features which are subsequently categorized by a fuzzy set based classifier.