Classifying system having a single neural network architecture f

Details Classifying system having a single neural network architecture f Classifying system having a single neural network architecture f

1995-08-08

1999-01-12

Boudreau, Leo H.

Image analysis

Learning systems

Neural networks

382161, 706 26, G06K 980

Patent

active

058599258

ABSTRACT:
A classification system is provided for combining multiple input representations by a single neural network architecture. In such a classification system having a single neural network architecture, classification channels corresponding to various input representations may be integrated through their own and shared hidden layers of the network to produce highly accurate classification. The classification system is particularly applicable to character classifying applications which use stroke and character image features as the main classification criteria, along with scalar features such as stroke count and aspect ratio features as secondary classification. The classification channels corresponding to the scalar features may be cross wired to the classification channels corresponding to the main input representations for further improving the accuracy of the classification output. Because a single neural network architecture is used, only one, standard training technique is needed for this classification system, special data handling is minimized, and the training time can be reduced, while highly accurate classification is achieved.

REFERENCES:
patent: 5239594 (1993-08-01), Yoda
patent: 5337370 (1994-08-01), Gilles et al.
patent: 5418864 (1995-05-01), Murdock et al.
Anthony Ralston, Edwin D. Reilly, Jr., Encyclopedia of Computer Science and Engnpeering, Van Norstrand Rewhold Company, 1983, pp. 124-125.
Frank Ayres, Jr., Theory and Problems of Matrices, Schaum Publishing Co., 1962, p. 67.
J. E. Tierney; N. Revell ; Printed Cyrillic Character Recognition System; 1994; Neural Networks, 1994 International Conference; vol. 6; pp. 3856-3861.

Affiliated with

Also associated with

Rating

Classifying system having a single neural network architecture f does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Classifying system having a single neural network architecture f, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Classifying system having a single neural network architecture f will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1523265