Eardrum color content analysis in video-otoscopy images for the diagnosis support of pediatric otitis

摘要

This paper proposes a preliminary study towards the implementation of a pediatric otorhynolaryngology diagnosis support system for the visual diagnosis of the ear drum, based on the automatic evaluation by digital image processing techniques of otoscopic digital color images of the eardrum and the medium ear. The final goal of the research is the development of a complete and coherent algorithm that starts with the acquisition of an otoscopic image and ends with the computation of some statistical measures associated to the eardrum structure and characteristics, yielding effective diagnosis support information for pediatric otology. This paper investigates the influence of color on the detection performance of the presence of otitis condition.