Perception Model for People with Visual Impairments

Scientists from many different disciplines (including physiology, psychology, and engineering) have worked on modelling visual perception. However this field has been less extensively studied in the context of computer science, as most existing perception models work only for very specific domains such as menu searching or icon searching tasks. We are developing a perception model that works for any application. It takes a list of mouse events, a sequence of bitmap images of an interface and locations of different objects in the interface as input, and produces a sequence of eye-movements as output. We have identified a set of features to differentiate among different screen objects and using those features, our model has reproduced the results of previous experiments on visual perception in the context of HCI. It can also simulate the effects of different visual impairments on interaction. In this paper we discuss the design, implementation and two pilot studies to demonstrate the model.