Hyperspectral image analysis using genetic programming

Genetic programming is used to evolve mineral identification functions for hyperspectral images. The input image set comprises 168 images from different wavelengths ranging from 428 nm (visible blue) to 2507 nm (invisible shortwave in the infrared), taken over Cuprite, Nevada, with the AVIRIS hyperspectral sensor. A composite mineral image indicating the overall reflectance percentage of three minerals (alunite, kaolnite, bud-dingtonite) is used as a reference or "solution" image. The training set is manually selected from this composite image. The task of the GP system is to evolve mineral identifiers, where each identifier is trained to identify one of the three mineral specimens. A number of different GP experiments were undertaken, which parameterized features such as thresh-olded mineral reflectance intensity and target GP language. The results are promising, especially for minerals with higher reflectance thresholds (more intense concentrations).

[1]  Brian J. Ross,et al.  Using genetic programming to synthesize monotonic stochastic processes , 2007 .

[2]  Jason M. Daida,et al.  Classification of spectral imagery using genetic programming , 2000 .

[3]  Roger N. Clark,et al.  Mapping minerals, amorphous materials, environmental materials, vegetation, water, ice and snow, and other materials: The USGS tricorder algorithm , 1995 .

[4]  David E. Larch.  Genetic algorithms for terrain categorization of Landsat images , 1994, Other Conferences.

[5]  Brian J. Ross,et al.  Evolutionary Learning and Stochastic Process Algebra , 2007 .

[6]  Brian J. Ross.  A Process Algebra for Stochastic Music Composition , 1995, ICMC.

[7]  Brian J. Ross,et al.  Procedural 3D texture synthesis using genetic programming , 2004, Comput. Graph..

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

[9]  K. Staenz,et al.  Retrieval of surface reflectance from hyperspectral Data using a look-up table approach , 1997 .

[10]  Brian J. Ross,et al.  Parsing Probabilistic Context Free Languages with Multi-Objective Genetic Algorithms , 2004 .

[11]  Brian J. Ross,et al.  Searching for Search Algorithms: Experiments in Meta-search , 2002 .

[12]  Yang Hong,et al.  A back - propagation neural network for mineralogical mapping from AVIRIS data , 1997 .

[13]  B. Ross.  Evolving Protein Motifs Using a Stochastic Regular Language with Codon-Level Probabilities , 2002 .

[14]  Brian J. Ross,et al.  The Inductive Inference of Cyclic Synchronized Interleaving , 1994, ECAI.

[15]  Jessica A. Faust,et al.  Imaging Spectroscopy and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) , 1998 .

[16]  Da Ma,et al.  ABUNDANCE EXTRACTIONS FROM AVIRIS IMAGE USING A SELF-ORGANIZING NEURAL NETWORK , 2000 .

[17]  Cameron Wellock,et al.  An Examination of Lamarckian Genetic Algorithms , 2001 .

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

[19]  James C. Bezdek,et al.  Applications and Science of Neural Networks, Fuzzy Systems and Evolutionary Computation IV , 1998 .

[20]  Robert O. Green,et al.  AVIRIS data and neural networks applied to an urban ecosystem , 1992 .

[21]  Daniel L. Civco,et al.  Artificial Neural Networks for Land-Cover Classification and Mapping , 1993, Int. J. Geogr. Inf. Sci..

[22]  Brian J. Ross,et al.  An Algebraic Semantics of Prolog Program Termination , 1991, ICLP.

[23]  P. Dreyer.  Classification of land cover using optimized neural nets on SPOT data , 1993 .

[24]  Daniel Howard,et al.  A staged genetic programming strategy for image analysis , 1999 .

[25]  Brian J. Ross,et al.  Evolutionary Image Synthesis Using a Model of Aesthetics , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[26]  Brian J. Ross,et al.  Evolving dynamic Bayesian networks with Multi-objective genetic algorithms , 2007, Applied Intelligence.

[27]  Neal R. Harvey,et al.  GENETIC PROGRAMMING APPROACH TO EXTRACTING FEATURES FROM REMOTELY SENSED IMAGERY , 2001 .

[28]  Erzsébet Merényi,et al.  Classification of the LCVF AVIRIS test site with a Kohonen artificial neural network , 1993 .

[29]  Brian J. Ross,et al.  A π-calculus Semantics of Logical Variables and Unification , 1992, NAPAW.

[30]  Ronald G. Resmini,et al.  Mineral mapping with HYperspectral Digital Imagery Collection Experiment (HYDICE) sensor data at Cuprite, Nevada, U.S.A. , 1997 .

[31]  Giles M. Foody,et al.  An evaluation of some factors affecting the accuracy of classification by an artificial neural network , 1997 .

[32]  Brian J. Ross,et al.  The evaluation of a stochastic regular motif language for protein sequences , 2001 .

[33]  David J. Montana,et al.  Strongly Typed Genetic Programming , 1995, Evolutionary Computation.

[34]  Robert A. Neville,et al.  Hyperspectral imagery for mineral exploration: comparison of data from two airborne sensors , 1998, Optics & Photonics.

[35]  J. K. Kinnear,et al.  Advances in Genetic Programming , 1994 .

[36]  Brian J. Ross,et al.  Pairwise Sequence Comparison and the Genetic Programming of Iterative Concurrent Programs , 1998 .

[37]  Brian J. Ross,et al.  The Partial Evaluation of Imperative Programs Using Prolog , 1989, International Workshop on Meta-Programming in Logic.

[38]  Brian J. Ross,et al.  Edge detection of petrographic images using genetic programming , 2000 .

[39]  Brian J. Ross,et al.  Using Algebraic Semantics for Proving Prolog termination and Transformation , 1991, ALPUK.

[40]  Brian J. Ross.  A Semantic Approach to Prolog Program Analysis , 1991, ICLP Workshop on Construction of Logic Programs.

[41]  Brian J. Ross.  The Effects of Randomly Sampled Training Data on Program Evolution , 2000, GECCO.

[42]  Brian J. Ross.  Semantics-based Partial Evaluation of Prolog Programs , 1991, LOPSTR.

[43]  William F. Punch,et al.  Lil-gp 1.01 User's Manual , 1995 .

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