Image Feature Extraction: Genie vs Conventional Supervised Classification Techniques

We have developed an automated feature de- tection/classification system, called Genie (GENetic Im- agery Exploitation), which has been designed to generate image processing pipelines for a variety of feature detec- tion/classification tasks. Genie is a hybrid evolutionary al- gorithm that addresses the general problem of finding fea- tures of interest in multi-spectral remotely-sensed images. We describe our system in detail together with experiments involving comparisons of Genie with several conventional su- pervised classification techniques, for a number of classifi- cation tasks using multi-spectral remotely-sensed imagery.

[1]  John A. Richards,et al.  Remote Sensing Digital Image Analysis , 1986 .

[2]  Peter J. Angeline,et al.  Algorithm Discovery using the Genetic Programming Paradigm: Extracting Low-Contrast Curvilinear Features from SAR Images of Arctic Ice , 1996 .

[3]  Riccardo Poli,et al.  Genetic Programming with User-Driven Selection : Experiments on the Evolution of Algorithms for Image Enhancement , 1997 .

[4]  R. Rex Kay,et al.  Multispectral Thermal Imager mission overview , 1999, Optics & Photonics.

[5]  Neal R. Harvey,et al.  GENIE: a hybrid genetic algorithm for feature classification in multispectral images , 2000, SPIE Optics + Photonics.

[6]  A. Mazer,et al.  Image processing software for imaging spectrometry data analysis , 1988 .

[7]  Manuela M. Veloso,et al.  A Contolled Experiment: Evolution for Learning Difficult Image Classification , 1995, EPIA.

[8]  Fred A. Kruse,et al.  The Spectral Image Processing System (SIPS) - Interactive visualization and analysis of imaging spectrometer data , 1993 .

[9]  Neal R. Harvey,et al.  Parallel evolution of image processing tools for multispectral imagery , 2000, SPIE Optics + Photonics.

[10]  Melanie Mitchell,et al.  Investigation of image feature extraction by a genetic algorithm , 1999, Optics + Photonics.

[11]  NEAL R. HARVEY,et al.  GA Optimisation of Multidimensional Grey-Scale Soft Morphological Filters with Applications in Archive Film Restoration , 2000, ISMM.

[12]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[13]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[14]  Bernard F. Buxton,et al.  Evolving edge detectors with genetic programming , 1996 .

[15]  P. Argos,et al.  Potential of genetic algorithms in protein folding and protein engineering simulations. , 1992, Protein engineering.

[16]  Meemong Lee,et al.  Image Processing Software For Imaging Spectrometry , 1987, Optics & Photonics.

[17]  Neal R. Harvey,et al.  Finding Golf Courses: The Ultra High Tech Approach , 2000, EvoWorkshops.

[18]  Neal R. Harvey,et al.  Evolving retrieval algorithms with a genetic programming scheme , 1999, Optics & Photonics.

[19]  Neal R. Harvey,et al.  MTI dense-cloud mask algorithm compared to a cloud mask evolved by a genetic algorithm and to the MODIS cloud mask , 2000, SPIE Optics + Photonics.

[20]  Azriel Rosenfeld,et al.  Experiments with texture classification using averages of local pattern matches , 1981, IEEE Transactions on Systems, Man, and Cybernetics.