Time delay neural network for printed and cursive handwritten ch

Details Time delay neural network for printed and cursive handwritten ch Time delay neural network for printed and cursive handwritten ch

1991-04-03

1992-04-14

Brinich, Stephen

Image analysis

Histogram processing

For setting a threshold

382 15, G06K 962

Patent

active

051054680

ABSTRACT:
A time delay neural network is defined having feature detection layers which are constrained for extracting features and subsampling a sequence of feature vectors input to the particular feature detection layer. Output from the network for both digit and uppercase letters is provided by an output classification layer which is fully connected to the final feature detection layer. Each feature vector relates to coordinate information about the original character preserved in a temporal order together with additional information related to the original character at the particular coordinate point. Such additional information may include local geometric information, local pen information, and phantom stroke coordinate information relating to connecting segments between the end point of one stroke and the beginning point of another stroke.
The network is also defined to increase the number of feature elements in each feature vector from one feature detection layer to the next. That is, as the network is reducing its dependence on temporally related features, it is increasing its dependence on more features and more complex features.

REFERENCES:
patent: 4317109 (1982-02-01), Odaka et al.
patent: 4653107 (1987-03-01), Shojima et al.
patent: 4809193 (1989-02-01), Jourjine
patent: 4876731 (1989-10-01), Loris et al.
patent: 4937872 (1990-06-01), Hopfield et al.
patent: 4941122 (1990-07-01), Weideman
patent: 4965725 (1990-10-01), Rutenberg
patent: 5005206 (1991-04-01), Naillon et al.
patent: 5040230 (1991-08-01), Takatori et al.
patent: 5048100 (1991-09-01), Kuperstein
Odaka, K. et al., "Online Recognition of Handwritten Characters . . . ", The Transactions of the IECE of Japan, vol. E63, No. 2, Feb. 1980, pp. 168-169.
Tappert, C. C. et al., "The State of the Art in On-Line Handwriting Recognition", IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 12, No. 8, Aug. 1990, pp. 787-808.
Guyon, I et al., "A Time Delay Neural Network . . . ", International Neural Network Conference, vol. I, Paris, France, Jul. 9-13, 1990, pp. 42-45.
Waibel, A. et al., "Phoneme Recognition Using Time-Delay Neural Networks", IEEE Trans. on Acoustics, Speech and Signal Processing, vol. 37, No. 3, Mar. 1989, pp. 328-339.

Affiliated with

Also associated with

Rating

Time delay neural network for printed and cursive handwritten ch does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Time delay neural network for printed and cursive handwritten ch, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Time delay neural network for printed and cursive handwritten ch will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2355656