Image Quality Assessment for the Visually Impaired

Tatiana Koshkina , Eric Dinet (1) , Hubert Konik (1)

1 LHC - Laboratoire Hubert Curien

In recent years, image enhancement methods have been developed to assist visually impaired people in the everyday life. These methods are promising but they currently suffer from the problem of their correct adjustment according to the specificities of each patient. To address such a problem, an objective quality metric could be used to quantify if enhancement schemes do not introduce artifacts that could be perceived as troublesome by visually deficient persons. As all existing metrics were designed to assess the image quality for observers with normal or corrected to normal vision, they are not appropriate in the context of low vision. Then an alternate framework is presented in this paper. This framework combines three distinct quality attributes that were identified as important features for the visually impaired in image quality assessment and it has been developed to adapt to the different types of visual pathologies.

Mots clés: visual aid; quality metric; image enhancement; low vision

Tatiana Koshkina, Eric Dinet, Hubert Konik. Image Quality Assessment for the Visually Impaired. HCI International 2013, Jul 2013, Las Vegas, United States. pp.275-284, ⟨10.1007/978-3-642-39191-0_31⟩. ⟨ujm-00844865⟩