An evolutionary programming approach to the simulation of visual attention
- 13 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 851-858
- https://doi.org/10.1109/cec.2001.934279
Abstract
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 (Michalewicz 1996) 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.Keywords
This publication has 18 references indexed in Scilit:
- Evolving feature-extraction algorithms: adapting genetic programming for image analysis in geoscience and remote sensingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Automatic identification of perceptually important regions in an imagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Evolution — The Best Possible Search Algorithm?BT Technology Journal, 2000
- Genetic programming for automatic target classification and recognition in synthetic aperture radar imageryPublished by Springer Nature ,1998
- Locating Salient Object FeaturesPublished by British Machine Vision Association and Society for Pattern Recognition ,1998
- Digital color imagingIEEE Transactions on Image Processing, 1997
- Data and Model-Driven Selection Using Color RegionsInternational Journal of Computer Vision, 1997
- Automatic generation of salient features for the recognition of partially occluded partsRobotica, 1987
- Fractal-Based Description of Natural ScenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984
- An evolutionary approach to the concept of randomnessThe Computer Journal, 1973