Recognizing objects from their incomplete representation: A survey

The recognition of single objects is an old research field with many techniques and robust results. The probabilistic recognition of incomplete objects, however, remains an active field with challenging issues associated to shadows, illumination and others. With object incompleteness we mean missing parts of a known object and not low-resolution images of that object. The employment of various single machine-learning methodologies for accurate classification of the incomplete objects did not always provide a robust answer to the challenging problem. Thus in this paper we present a survey on research methodologies associated with the recognition of objects with incompleteness.