Segmentation of natural scenes
Pattern Recognition
Neural networks for automatic target recognition
Neural Networks - Special issue: automatic target recognition
Texture classification and segmentation by cellular neural networks using genetic learning
Computer Vision and Image Understanding
Genetic Learning for Adaptive Image Segmentation
Genetic Learning for Adaptive Image Segmentation
Generating Image Filters for Target Recognition by Genetic Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Selection of Gabor Filters for Pixel Classification
Automatic Selection of Gabor Filters for Pixel Classification
Evolving descriptors for texture segmentation
Pattern Recognition
Learning pattern classification-a survey
IEEE Transactions on Information Theory
| Hi-index | 0.00 |
We present an approach to automatic image segmentation, in which user-selected sets of examples and counter-examples supply information about the specific segmentation problem. In our approach, image segmentation is guided by a genetic algorithm which learns the appropriate subset and spatial combination of a collection of discriminating functions, associated with image features. The genetic algorithm encodes discriminating functions into a functional template representation, which can be applied to the input image to produce a candidate segmentation. The performance of each candidate segmentation is evaluated within the genetic algorithm, by a comparison to two physics-based techniques for region growing and edge detection. Through the process of segmentation, evaluation, and recombination, the genetic algorithm optimizes functional template design efficiently. The contributions of this chapter include: genetic learning of functional template design, physics-based segmentation evaluation, novel crossover operator and fitness function, as well as a system prototype and experiments on real synthetic aperture radar (SAR) imagery of varying complexity.