Abstract: A system and method of image processing using neural networks to control image processing elements. Neural network parameters are defined by genotypes consisting of network vectors. Genotypes may be selectively mutated and cross-bred to provide a mechanism for modifying the behavior of the neural networks, or phenotypes. Genetic modeling processes are used to perform such mutation and cross-over. User feedback concerning output images, is used to select particular genotypes for further mutation and exploration. Preconditioning is employed to extract structural information from source images prior to network processing. Genetic morphing and subnet fusion are also available, to provide additional variations on image processing operations.

Abstract: A system and method for processing moving images employ an interactive particle system comprising virtual image processing elements, or paintbrushes, in order to avoid problems of noise amplification and sensitivity to temporal discontinuities in source images. Attributes and parameters of paintbrushes may be specified by the user, and may vary dependent on the content of the source image. Paintbrushes may interact and may respond to virtual forces of various types. The system and method provide mechanisms by which the user may specify force parameters, by which source images can become forces, and by which force attributes may diffuse throughout the display field.