Elizabeth Botha

Optical symbolic substitution for morphological transformations

An optical architecture that uses symbolic substitution to perform morphological transformations is proposed. It is shown how the four basic morphological transformation operations can be posed as symbolic substitution problems. Representative examples of the application of morphological transformations to image processing are given.

Backpropagation uses prior information efficiently

The ability of neural net classifiers to deal with a priori information is investigated. For this purpose, backpropagation classifiers are trained with data from known distributions with variable a priori probabilities, and their performance on separate test sets is evaluated. It is found that backpropagation employs a priori information in a slightly suboptimal fashion, but this does not have serious consequences on the performance of the classifier. Furthermore, it is found that the inferior generalization that results when an excessive number of network parameters are used can (partially) be ascribed to this suboptimality.

Optical laboratory morphological inspection processor

Morphological transformations are applied to industrial inspection problems. A real time optical architecture to implement morphological transformations such as erosion, opening, closing, and skeletonization is described and analyzed. The first real time optical laboratory results of erosion and opening are presented for locating string in tobacco.

Optical symbolic substitution using multichannel correlators

On presente une nouvelle architecture de deux correlateurs utilises pour les operations logiques et numeriques

Multifunctional Optical Processor Based On Symbolic Substitution

We propose an optical multifunctional processor that can perform logic, numeric, pattern recognition, morphological, and inference operations. The ability to perform such diverse functions on one optical processor architecture is unique. The processor uses the technique of symbolic substitution and is based on an optical correlator architecture. Several inputs can be operated on in parallel, and different functions can be performed at one time, making it a multiple-instruction multiple-data processor.

Optical correlator production system neural net

A new neural net is described that can easily and cost-effectively accommodate multiple objects in the field of view in parallel. The use of a correlator achieves shift invariance and accommodates multiple objects in parallel. Distortion-invariant filters provide aspect-invariant distortion. Symbolic encoding, the use of generic object parts, and a production system neural net allow large class problems to be addressed. Optical laboratory data on the production system inputs are provided and emphasized. Test data assume binary inputs, although analog (probability) input neurons are possible.

Applications Of Optical Morphological Transformations

Applications of morphological transformations on an optical symbolic substitution processor are presented. Simulation results of several morphological image processing operations (edge detection, hit-or-miss transformation, and skeletonization) are presented, and examples of their use in industrial inspection are given.

Knowledge in optical symbolic pattern recognition processors

Definitions of symbolic processing, explicit and implicit declarative knowledge, and procedural knowledge are given. Architectures for optical symbolic correlation processors for pattern recognition problems are given, and the uses of explicit and implicit declarative knowledge as well as procedural knowledge are discussed.

A Symbolic Neural Net Production System: Obstacle Avoidance, Navigation, Shift-Invariance And Multiple Objects

A symbolic neural net is described. It uses a multichannel symbolic correlator to produce input neuron data to an optical neural net production system. It has use in obstacle avoidance, navigation, and scene analysis applications. The shift-invariance and ability to handle multiple objects are novel aspects of this symbolic neural net. Initial simulated data are provided and symbolic optical filter banks are discussed. The neural net production system is described. A parallel and iterative set of rules and results for our case study are presented. Its adaptive learning aspects are noted.

Optical laboratory realization of a symbolic production system

An optical symbolic neural net is described. It uses an optical symbolic correlator. This produces a new input neuron representation space that is shift-invariant and can accommodate multiple objects. No other neural net can handle multiple objects within the field of view. Initial optical laboratory data are presented. An optical neural net production system processes this new neuron data. This aspect of the system is briefly described.