Open Access. Powered by Scholars. Published by Universities.®

Electrical and Computer Engineering Commons™

Open Access. Powered by Scholars. Published by Universities.®

Florida Institute of Technology

1996

Articles 1 - 11 of 11

Full-Text Articles in Electrical and Computer Engineering

Novel High-Speed Architecture For Machine Vision Applications, Bassam S. Farroha, Raghvendra G. Deshmukh Oct 1996

Novel High-Speed Architecture For Machine Vision Applications, Bassam S. Farroha, Raghvendra G. Deshmukh

Electrical Engineering and Computer Science Faculty Publications

This paper focuses on producing a state-of-the-art technique for designing an image recognition system for machine vision applications. The motivation behind the new system design is to provide a unique methodology, using strategic design techniques, to implement a system that addresses real-world image recognition applications. The introduction of application-specific, massively parallel array of processors, where low-level processing is accomplished on reconfigurable hardware structures, highlights the scheme. The system was built and simulated on a VLSI chip and results were verified using Electric Rules Check and Harris Timing Analysis examination tools. The system is composed of there functional layers and a …

Go to article

Real-Time Optically Processed Face Recognition System Based On Arbitrary Moiré Contours, Rafael A. Andrade, Bernard R. Gilbert, Donald W. Dawson, Chris L. Hart, Samuel Peter Kozaitis, Joel H. Blatt Sep 1996

Real-Time Optically Processed Face Recognition System Based On Arbitrary Moiré Contours, Rafael A. Andrade, Bernard R. Gilbert, Donald W. Dawson, Chris L. Hart, Samuel Peter Kozaitis, Joel H. Blatt

Electrical Engineering and Computer Science Faculty Publications

We demonstrate a hybrid electronic-optical real-time system that performs 3-D face recognition. We constructed custom reference gratings that formed a desired moire pattern when mixed with images of structurally illuminated faces. The moiré patterns could be in any form such as, equal depth contours, error maps, or any arbitrary pattern. We demonstrate video methods to generate such error maps in real time, thus developing a real-time automated face recognition system based on the optical processing of arbitrary moiré contours. We chose the moiré pattern to be in the form of a Fresnel zone plate, which is displayed on a liquid …

Go to article

Multiresolution Wavelet Processing For Binary Phase-Only Filters, Samuel Peter Kozaitis Jul 1996

Multiresolution Wavelet Processing For Binary Phase-Only Filters, Samuel Peter Kozaitis

Electrical Engineering and Computer Science Faculty Publications

We used the discrete wavelet transform to approximate an image at a lower resolution in preparation for object recognition using correlation techniques. We cross- correlated the low-resolution image with a similarly processed image containing an object of interest. Then, we synthesized the cross-correlation result to the resolution of original image. Using this approach, we avoided cross- correlating an image multiple times and passing information between levels of an image representation such as an image pyramid. We satisfactorily identified objects at 1/4 resolution using the wavelet representation and binary phase-only filters. We chose wavelets based on their impulse response and found …

Go to article

Real-Time Optically Processed Face-Recognition System Based On Arbitrary Moire Contours, Rafael A. Andrade, Bernard R. Gilbert, Donald W. Dawson, Chris L. Hart, Samuel Peter Kozaitis, Joel H. Blatt Jul 1996

Real-Time Optically Processed Face-Recognition System Based On Arbitrary Moire Contours, Rafael A. Andrade, Bernard R. Gilbert, Donald W. Dawson, Chris L. Hart, Samuel Peter Kozaitis, Joel H. Blatt

Electrical Engineering and Computer Science Faculty Publications

A real-time diffraction based optical processed 3-D shape recognition system has been built and demonstrated. The system uses an Ar-ion laser interferometer to project variable spatial frequency structural illumination on 3 dimensional targets which are viewed by a camera. The video data is mixed with a computer generated mask (converted to RS-170 video) and the resulting output video signal is sent to a liquid crystal television (modified to function as a spatial light modulator) which is illuminated by a He-Ne laser. The video mixing process, based on a commercial Chroma-Key circuit, generates an arbitrary moire pattern which is a function …

Go to article

Similarity-Based Learning For Pattern Classification, Laurene V. Fausett Mar 1996

Similarity-Based Learning For Pattern Classification, Laurene V. Fausett

Electrical Engineering and Computer Science Faculty Publications

Several standard neural networks, including counterpropagation networks, predictive ART networks, and radial basis function networks, are based on a combination of clustering (unsupervised learning) and mapping (supervised learning). A comparison of the characteristics of these networks for pattern classification problems is presented.

Go to article

Neural Network Architecture For Solving The Algebraic Matrix Riccati Equation, Fredric M. Ham, Emmanuel G. Collins Mar 1996

Neural Network Architecture For Solving The Algebraic Matrix Riccati Equation, Fredric M. Ham, Emmanuel G. Collins

Electrical Engineering and Computer Science Faculty Publications

This paper presents a neurocomputing approach for solving the algebraic matrix Riccati equation. This approach is able to utilize a good initial condition to reduce the computation time in comparison to standard methods for solving the Riccati equation. The repeated solutions of closely related Riccati equations appears in homotopy algorithms to solve certain problems in fixed-architecture control. Hence, the new approach has the potential to significantly speed-up these algorithms. It also has potential applications in adaptive control. The structured neural network architecture is trained using error backpropagation based on a steepest-descent learning rule. An example is given which illustrates the …

Go to article

Determination Of Adaptively Adjusted Coefficients For Hopfield Neural Networks Utilizing The Energy Function, Chiyeon Park, Donald W. Fausett Mar 1996

Determination Of Adaptively Adjusted Coefficients For Hopfield Neural Networks Utilizing The Energy Function, Chiyeon Park, Donald W. Fausett

Electrical Engineering and Computer Science Faculty Publications

With its potential for parallel computation and general applicability, the Hopfield neural network has been investigated and improved by many researchers in order to extend its usefulness to various combinatorial problems. In spite of its success in several applications within different energy function formulations, determination of the energy coefficients has been based primarily on trial and error methods since no practical and systematic way of finding good values has been available preciously, although some theoretical analyses have been presented. In this paper, we present a methodical procedure which adaptively determines the energy coefficients leading to a valid solution as the …

Go to article

Partial Least-Squares Regression Neural Network (Plsnet) With Supervised Adaptive Modular Learning, Fredric M. Ham, Ivica Kostanic Mar 1996

Partial Least-Squares Regression Neural Network (Plsnet) With Supervised Adaptive Modular Learning, Fredric M. Ham, Ivica Kostanic

Electrical Engineering and Computer Science Faculty Publications

We present in this paper an adaptive linear neural network architecture called PLSNET. This network is based on partial least-squares (PLS) regression. The architecture is a modular network with stages that are associated with the desired number of PLS factors that are to be retained. PLSNET actually consists of two separate but coupled architectures, PLSNET-C for PLS calibration, and PLSNET-P for prediction (or estimation). We show that PLSNET-C can be trained by supervised learning with three standard Hebbian learning rules that extracts the PLS weight loading vectors, the regression coefficients, and the loading vectors for the univariate output component case …

Go to article

Comparison Of Function Approximation With Sigmoid And Radial Basis Function Networks, Gary Russell, Laurene V. Fausett Mar 1996

Comparison Of Function Approximation With Sigmoid And Radial Basis Function Networks, Gary Russell, Laurene V. Fausett

Electrical Engineering and Computer Science Faculty Publications

Theoretical and computational results have demonstrated that several types of neural networks have the universal approximation property, i.e., the ability to represent any continuous function to an arbitrary degree of accuracy, given enough hidden units. However, practical considerations, such as the relative advantages of different networks for function approximation using a small to moderate number of hidden units, are not as well understood. This paper presents preliminary results of investigations into the comparison of networks using sigmoidal activation functions and networks using radial basis functions. In particular, we consider the ability of several such networks to learn mappings from the …

Go to article

Application Of Neural Networks To Channel Assignment For Cellular Cdma Networks With Multiple Services And Mobile Base Stations, William S. Hortos Mar 1996

Application Of Neural Networks To Channel Assignment For Cellular Cdma Networks With Multiple Services And Mobile Base Stations, William S. Hortos

Electrical Engineering and Computer Science Faculty Publications

The use of artificial neural networks to the channel assignment problem for cellular code- division multiple access (CDMA) telecommunications systems is considered. CDMA takes advantage of voice activity and spatial isolation because its capacity is only interference limited, unlike time-division multiple access (TDMA) and frequency-division multiple access (FDMA) where capacities are bandwidth limited. Any reduction in interference in CDMA translates linearly into increased capacity. FDMA and TDMA use a frequency reuse pattern as a method to increase capacity, while CDMA reuses the same frequency for all cells and gains a reuse efficiency by means of orthogonal codes. The latter method …

Go to article

Discrete Riccati Equation Solutions: Distributed Algorithms, Demetrios G. Lainiotis, Konstantinos N. Kostas Plataniotis, Paraskevas Papaparaskeva Jan 1996

Discrete Riccati Equation Solutions: Distributed Algorithms, Demetrios G. Lainiotis, Konstantinos N. Kostas Plataniotis, Paraskevas Papaparaskeva

Electrical Engineering and Computer Science Faculty Publications

In this paper new distributed algorithms for the solution of the discrete Riccati equation are introduced. The algorithms are used to provide robust and computational efficient solutions to the discrete Riccati equation. The proposed distributed algorithms are theoretically interesting and computationally attractive.

Go to article