Consider the task of malformed object classification in an industrial setting, where the term ‘malformed’ encompasses objects that are afflicted with geometric deviations, corroded or broken. Recognizing whether such an object can be repaired, taken apart so that its components can be used otherwise, or dispatched for recycling, is a difficult classification task. Despite the progress of artificial intelligence for the classification of objects based on images, the classification of malformed objects still demands human involvement, because each such object is unique. Ideally, the intelligent machine should demand expert support only when it is uncertain about the class. But what if the human is also uncertain?
In this project we investigate methods for recognizing human uncertainty in an unobtrusive manner and active feature acquisition algorithms for reducing machine uncertainty. We also intend to build reference datasets where human uncertainty is controlled and measured. Our cooperation has been triggered through the networking activities of CHIM (https://forschungsnetzwerk-chim.de/