Optimizing Digital Hardware Perceptrons for Multi-Spectral Image Classification

Authors:
Reid Porter;Neal Harvey;Simon Perkins;James Theiler;Steven Brumby;Jeffrey Bloch;Maya Gokhale;John Szymanski
Affiliations:
Nonproliferation and International Security Division, Los Alamos National Laboratory, New Mexico. rporter@lanl.gov;Nonproliferation and International Security Division, Los Alamos National Laboratory, New Mexico;Nonproliferation and International Security Division, Los Alamos National Laboratory, New Mexico;Nonproliferation and International Security Division, Los Alamos National Laboratory, New Mexico;Nonproliferation and International Security Division, Los Alamos National Laboratory, New Mexico;Nonproliferation and International Security Division, Los Alamos National Laboratory, New Mexico;Nonproliferation and International Security Division, Los Alamos National Laboratory, New Mexico;Nonproliferation and International Security Division, Los Alamos National Laboratory, New Mexico
Venue:
Journal of Mathematical Imaging and Vision
Year:
2003

Citing 14
Cited 3

Unsupervised texture segmentation using Gabor filters

Pattern Recognition
An overview of median and stack filtering

Circuits, Systems, and Signal Processing - Special issue: median and morphological filters
Genetic Reinforcement Learning for Neurocontrol Problems

Machine Learning - Special issue on genetic algorithms
Seeing the light: artificial evolution, real vision

SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot

SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Selection of relevant features and examples in machine learning

Artificial Intelligence - Special issue on relevance
Convolutional networks for images, speech, and time series

The handbook of brain theory and neural networks
Principles in the Evolutionary Design of Digital Circuits—Part I

Genetic Programming and Evolvable Machines
Boosting the margin: A new explanation for the effectiveness of voting methods

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Implementation of a Probabilistic Neural Network for Multi-spectral Image Classification on an FPGA based Custom Computing Machine

SBRN '98 Proceedings of the Vth Brazilian Symposium on Neural Networks
Evolving Network Architectures With Custom Computers For Multi-Spectral Feature Identification

EH '01 Proceedings of the The 3rd NASA/DoD Workshop on Evolvable Hardware
Forming neural networks through efficient and adaptive coevolution

Evolutionary Computation
An incremental approach to developing intelligent neural networkcontrollers for robots

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Evaluation of convolutional neural networks for visual recognition

IEEE Transactions on Neural Networks

A reconfigurable computing framework for multi-scale cellular image processing

Microprocessors & Microsystems
A Brief Review and Comparison of Feedforward Morphological Neural Networks with Applications to Classification

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Morphological perceptrons with competitive learning: Lattice-theoretical framework and constructive learning algorithm

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a system for solving pixel-based multi-spectral image classification problems with high throughput pipelined hardware. We introduce a new shared weight network architecture that contains both neural network and morphological network functionality. We then describe its implementation on Reconfigurable Computers. The implementation provides speed-up for our system in two ways. (1) In the optimization of our network, using Evolutionary Algorithms, for new features and data sets of interest. (2) In the application of an optimized network to large image databases, or directly at the sensor as required. We apply our system to 4 feature identification problems of practical interest, and compare its performance to two advanced software systems designed specifically for multi-spectral image classification. We achieve comparable performance in both training and testing. We estimate speed-up of two orders of magnitude compared to a Pentium III 500 MHz software implementation.