Platform for evolving genetic automata for text segmentation

@inproceedings{Garris1992PlatformFE,
  title={Platform for evolving genetic automata for text segmentation},
  author={M. Garris},
  booktitle={Defense, Security, and Sensing},
  year={1992}
}
  • M. Garris
  • Published in
    Defense, Security, and…
    1992
  • Computer Science, Engineering
Developers of large-scale document processing and image recognition systems are in need of a dynamically robust character segmentation component. Without this essential module, potential turn-key products will remain in the laboratory indefinitely. An experiment of evolving a biologically based neural image processing system which has the ability to isolate characters within an unstructured text image is presented. In this study, organisms are simulated using a genetic algorithm with the goal… Expand

References

SHOWING 1-10 OF 10 REFERENCES
Segmenting text images with massively parallel machines
TLDR
In this paper, the segmentation of pages of text into lines of text and lines ofText into characters on a parallel machine are examined and statistically adaptive rules based on dynamic adaptive sampling are used for line segmentation. Expand
An application of neural net chips: handwritten digit recognition
TLDR
A general-purpose, fully interconnected neural-net chip was used to perform computationally intensive tasks for handwritten digit recognition, and a feature map was created by template-matching stored primitive patterns on the chip with regions on the skeletonized image. Expand
Self-organizing neural network character recognition on a massively parallel computer
TLDR
Two neural-network-based methods are combined to develop font-independent character recognition on a distributed array processor using least-squares optimized Gabor filtering and an ART-1-based learning algorithm which produces self-organizing sets of neural network weights used for character recognition. Expand
Methods for enhancing neural network handwritten character recognition
TLDR
An efficient method for increasing the generalization capacity of neural character recognition is presented and a method of using the activation strength for reclassification is described which reduced substitutional errors to 2.2%. Expand
Recognizing Hand-Printed Letters and Digits
TLDR
It is suggested that a large and representative training sample may be the single, most important factor in achieving high recognition accuracy, and doubts about the relevance to backpropagation of learning models that estimate the likelihood of high generalization from estimates of capacity are raised. Expand
Learning and Evolution in Neural Networks
TLDR
Simulation on populations of neural networks that both evolve at the population level and learn at the individual level finds both individuals that have high fitness and individuals that, although they do not have high Fitness at birth, end up with high fitness because they learn to predict. Expand
Vehicles, Experiments in Synthetic Psychology
These imaginative thought experiments are the inventions of one of the world's eminent brain researchers. They are "vehicles," a series of hypothetical, self-operating machines that exhibitExpand
and R
  • A. Wilkinson, "Massively Parallel Implementation of Character Recognition Systems," SPIE Machine Vision Applications in Character Recognition and Industrial Inspection, to be published, San Jose,
  • 1992
Adaptive Elastic Models for Character Recognition," Advances in Neural Information Processing Systems, R
  • Lippmann, Vol. IV, to be published, Denver,
  • 1991
Self-Organizing Neural Network Character Recognition on a Massively Parallel Computer," International Joint Conference on Neural Networks, Vol
  • II, pp. 325-329, San Diego,
  • 1988