An evolutionary programming approach to the simulation of visual attention

Most higher animals in the world have an ability to sense danger by spotting anomalies in their environment and surviving by taking appropriate evasive action. Those organisms that have the benefit of vision are able to direct attention rapidly towards the unusual without any prior knowledge of the environment. Existing models of visual attention have provided plausible explanations for many of the standard percepts and illusions and yet all have defied implementations that have led to generic applications. This paper describes an evolutionary programming approach to derive a measure of visual attention that may be used to identify regions of interest in many categories of images. A population of individuals, or pixel neighbourhoods, is evolved that performs best at discriminating between salient and non-salient image features. A number of results are provided.