GENIE: a hybrid genetic algorithm for feature classification in multispectral images
Simon Perkins,James Theiler,Steven P. Brumby,Neal R. Harvey,Reid B. Porter,John J. Szymanski,Jeffrey J. Bloch +6 more
- Vol. 4120, pp 52-62
Reads0
Chats0
TLDR
Genie as mentioned in this paper is a hybrid learning system that combines a GA and a more conventional classifier to output a final classification. But the GA alone is not sufficient to correctly classify a pixel.Abstract:
We consider the problem of pixel-by-pixel classification of a multi- spectral image using supervised learning. Conventional spuervised classification techniques such as maximum likelihood classification and less conventional ones s uch as neural networks, typically base such classifications solely on the spectral components of each pixel. It is easy to see why: the color of a pixel provides a nice, bounded, fixed dimensional space in which these classifiers work well. It is often the case however, that spectral information alone is not sufficient to correctly classify a pixel. Maybe spatial neighborhood information is required as well. Or maybe the raw spectral components do not themselves make for easy classification, but some arithmetic combination of them would. In either of these cases we have the problem of selecting suitable spatial, spectral or spatio-spectral features that allow the classifier to do its job well. The number of all possible such features is extremely large. How can we select a suitable subset? We have developed GENIE, a hybrid learning system that combines a genetic algorithm that searches a space of image processing operations for a set that can produce suitable feature planes, and a more conventional classifier which uses those feature planes to output a final classification. In this paper we show that the use of a hybrid GA provides significant advantages over using either a GA alone or more conventional classification methods alone. We present results using high-resolution IKONOS data, looking for regions of burned forest and for roads.read more
Citations
More filters
Journal ArticleDOI
Medical Image Segmentation Using Genetic Algorithms
TL;DR: An attempt has been made to review the major applications of GAs to the domain of medical image segmentation and shows that the genetic algorithmic framework prove to be effective in coming out of local optima.
Journal ArticleDOI
Comparison of GENIE and conventional supervised classifiers for multispectral image feature extraction
Neal R. Harvey,James Theiler,Steven P. Brumby,Simon Perkins,John J. Szymanski,Jeffrey J. Bloch,Reid B. Porter,M. Galassi,Aaron Cody Young +8 more
TL;DR: The authors describe their system in detail together with experiments involving comparisons of GENIE with several conventional supervised classification techniques, for a number of classification tasks using multispectral remotely sensed imagery.
Journal ArticleDOI
The Deep Lens Survey Transient Search. I. Short Timescale and Astrometric Variability
Andrew C. Becker,Andrew C. Becker,Andrew C. Becker,David Wittman,David Wittman,P. Boeshaar,P. Boeshaar,Alejandro Clocchiatti,Ian P. Dell'Antonio,Dale A. Frail,Jules P. Halpern,Vera Margoniner,Vera Margoniner,Dara Norman,J. A. Tyson,J. A. Tyson,Robert A. Schommer +16 more
TL;DR: The Deep Lens Survey (DLS) transient search as discussed by the authors was the first survey to classify and report all types of photometric and astrometric variability detected, including solar system objects, variable stars, supernovae, and short timescale phenomena.
Proceedings ArticleDOI
Segmentation of medical images using a genetic algorithm
Payel Ghosh,Melanie Mitchell +1 more
TL;DR: A genetic algorithm for automating the segmentation of the prostate on two-dimensional slices of pelvic computed tomography (CT) images is presented and preliminary tests show promise by converging on the prostate region.
Journal ArticleDOI
Multicomponent Image Segmentation Using a Genetic Algorithm and Artificial Neural Network
TL;DR: A new multicomponent image segmentation method is developed using a nonparametric unsupervised artificial neural network called Kohonen's self-organizing map (SOM) and hybrid genetic algorithm (HGA) that is used to detect the main features that are present in the image.
References
More filters
Book
Neural networks for pattern recognition
TL;DR: This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Proceedings Article
Experiments with a new boosting algorithm
Yoav Freund,Robert E. Schapire +1 more
TL;DR: This paper describes experiments carried out to assess how well AdaBoost with and without pseudo-loss, performs on real learning problems and compared boosting to Breiman's "bagging" method when used to aggregate various classifiers.
Book
Genetic Programming: An Introduction
TL;DR: The authors discuss GP software tools, including Discipulus, the GP software developed by the authors, and Appendix D mentions events most closely related to the field of genetic programming.
Proceedings Article
Homologous crossover in genetic programming
TL;DR: A new crossover operator for linear genomes that encourages the emergence of positional homology in the population is introduced and preliminary experimental results suggest that this approach is a promising direction for redesign of the mechanism of crossover.
Book ChapterDOI
Finding Golf Courses: The Ultra High Tech Approach
Neal R. Harvey,Simon Perkins,Steven P. Brumby,James Theiler,Reid B. Porter,A. Cody Young,Anil K. Varghese,John J. Szymanski,Jeffrey J. Bloch +8 more
TL;DR: Genie as mentioned in this paper is a hybrid evolutionary algorithm-based system that tackles the general problem of finding features of interest in multi-spectral remotely-sensed images, including, but not limited to, golf courses.