Object/anti-object neural network segmentation

Details Object/anti-object neural network segmentation Object/anti-object neural network segmentation

1992-03-09

1993-09-14

Boudreau, Leo H.

Image analysis

Histogram processing

For setting a threshold

382 32, 382 14, G06K 900

Patent

active

052456722

ABSTRACT:
The system of the present invention applies self-organizing and/or supervd learning network methods to the problem of segmentation. The segmenter receives a visual field, implemented as a sliding window and distinguishes occurrences of complete characters from occurrences of parts of neighboring characters. Images of isolated whole characters are true objects and the opposite of true objects are anti-objects, centered on the space between two characters. The window is moved across a line of text producing a sequence of images and the segmentation system distinguishes true objects from anti-objects. Frames classified as anti-objects demarcate character boundaries, and frames classified as true objects represent detected character images. The system of the present invention may be a feedforward adaption using a symmetric triggering network. Inputs to the network are applied directly to the separate associative memories of the network. The associative memories produce a best match pattern output for each part of the input data. The associative memories provide two or more subnetworks which define data subsets, such as objects or anti-objects, according to previously learned examples. Multi-layer perceptron architecture may also be used in the system of the present invention rather than the symmetrically triggered feedforward adaptation with tradeoffs in training time but advantages in speed.

REFERENCES:
patent: 3295106 (1966-12-01), Horn
patent: 4510617 (1985-04-01), Mori
patent: 4790024 (1988-12-01), Peppers
patent: 4809344 (1989-02-01), Peppers
patent: 4817169 (1989-03-01), Peppers
patent: 4827529 (1989-05-01), Peppers
patent: 5014327 (1991-05-01), Potter
patent: 5020117 (1991-05-01), Ooi

Affiliated with

Also associated with

Rating

Object/anti-object neural network segmentation does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Object/anti-object neural network segmentation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Object/anti-object neural network segmentation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2034373