Evolving a spatio-spectral network on reconfigurable computers for multispectral feature identification

Feature identification attempts to find algorithms that can consistently separate a feature of interest from the background in the presence of noise and uncertain conditions. This paper describes the development of a high-throughput, reconfigurable computer based, feature identification system known as POOKA. POOKA is based on a novel spatio-spectral network, which can be optimized with an evolutionary algorithm on a problem-by-problem basis. The reconfigurable computer provides speed up in two places: 1) in the training environment to accelerate the computationally intensive search for new feature identification algorithms, and 2) in the application of trained networks to accelerate content based search in large multi-spectral image databases. The network is applied to several broad area features relevant to scene classification. The results are compared to those found with traditional remote sensing techniques as well as an advanced software system known as GENIE. The hardware efficiency and performance gains compared to software are also reported.

[1]  Melanie Mitchell,et al.  Evolving Cellular Automata with Genetic Algorithms: A Review of Recent Work , 2000 .

[2]  Ronaldo Fumio Hashimoto,et al.  Surface Texture Classification from Morphological Transformations , 2000, ISMM.

[3]  Paul D. Gader,et al.  Morphological shared-weight neural network for pattern classification and automatic target detection , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[4]  Peter Sussner,et al.  An introduction to morphological neural networks , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[5]  I. D. Macleod,et al.  The visibility of gratings: spatial frequency channels or bar-detecting units? , 1974, Vision research.

[6]  Robert A. Schowengerdt,et al.  A review and analysis of backpropagation neural networks for classification of remotely-sensed multi-spectral imagery , 1995 .

[7]  Clay S. Gloster,et al.  Implementation of a probabilistic neural network for multi-spectral image classification on an FPGA based custom computing machine , 1998, Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209).

[8]  Anil K. Jain.  Fundamentals of Digital Image Processing , 2018, Control of Color Imaging Systems.

[9]  Stephen S. Wilson.  Morphological Networks , 1989, Other Conferences.

[10]  P.-F. YANG,et al.  Min-max classifiers: Learnability, design and application , 1995, Pattern Recognit..

[11]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[12]  Wolfgang Banzhaf,et al.  Genetic Programming: An Introduction , 1997 .

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

[14]  Peter Sussner,et al.  Morphological perceptron learning , 1998, Proceedings of the 1998 IEEE International Symposium on Intelligent Control (ISIC) held jointly with IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA) Intell.

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

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

[17]  Neal R. Harvey,et al.  Image Feature Extraction: Genie vs Conventional Supervised Classification Techniques , 2001 .

[18]  Stephen Marshall,et al.  Parallel genetic algorithms in the optimization of morphological filters: a general design tool , 1997, J. Electronic Imaging.

[19]  Thomas S. Huang,et al.  A generalization of median filtering using linear combinations of order statistics , 1983 .

[20]  Risto Miikkulainen,et al.  Forming Neural Networks Through Efficient and Adaptive Coevolution , 1997, Evolutionary Computation.