Character recognition system based on a neural network
First Claim
1. A character recognition system comprising:
- input means for receiving input characters;
preprocessing means for extracting characteristics data from said input characters;
a neural network connected to said preprocessing means to recognize said input characters from said characteristics data generated by said preprocessing means and output a recognition signal wherein said neural network comprises an input layer, a middle layer and an output layer, each said layer including a plurality of neurons, each said neuron being a signal processing element, said middle layer being arranged between said input and output layers wherein each neuron in said middle layer is connected to each neuron in said input and output layers, said data processing means comprising;
first determining means for determining an activation pattern of said neurons in said input layer,second determining means for determining an activation pattern of said neurons in said output layer,for each neuron in said middle layer, neighborhood means for setting a neighborhood of neurons in said input and output layers corresponding to a neuron in said middle layer,for each neuron in said middle layer, third determining means for determining a rate of activation in said neighborhood of neurons, said rate being the total number of neurons activating in said neighborhood in said input and output layers divided by the total number of neurons in said neighborhood in said input and output layers,for each neuron in said middle layer, comparison means for comparing said rate to a threshold value,for each neuron in said middle layer, fourth determining means for determining that said neuron in said middle layer has a tendency to activate when said rate is greater than said threshold value, andfor each neuron in said middle layer, increasing means for increasing the value of weights applied to all neurons in said input layer which are connected to said neuron in said middle layer and weights applied to all neurons in said output layer which are connected to said neuron in said middle layer, in order to increase the likelihood of activation of said neuron in said middle layer and thereby generate an activation pattern in said middle layer corresponding to said recognition signal, wherein said increasing is determined by the tendency to activate of said neuron in said middle layer; and
post-processing means for storing said recognition signal; and
display means for receiving said recognition signal from said post-processing means and displaying said recognition signal.
0 Assignments
0 Petitions
Accused Products
Abstract
A character recognition system based on a neural network determines activation patterns in an input layer and output layer, increases weights of synapses in a middle layer so that neurons activate with more than a certain rate among those corresponding to neurons in the input layer and the output layer and repeats the same process for each neuron in the middle layer. The input layer and output layer possess a plurality of neurons which activate and output certain data according to a specific result and the middle layer is between the input layer and output layer. The middle layer also possesses a plurality of neurons which are connected to each neuron in the input layer and output layer.
-
Citations
1 Claim
-
1. A character recognition system comprising:
-
input means for receiving input characters; preprocessing means for extracting characteristics data from said input characters; a neural network connected to said preprocessing means to recognize said input characters from said characteristics data generated by said preprocessing means and output a recognition signal wherein said neural network comprises an input layer, a middle layer and an output layer, each said layer including a plurality of neurons, each said neuron being a signal processing element, said middle layer being arranged between said input and output layers wherein each neuron in said middle layer is connected to each neuron in said input and output layers, said data processing means comprising; first determining means for determining an activation pattern of said neurons in said input layer, second determining means for determining an activation pattern of said neurons in said output layer, for each neuron in said middle layer, neighborhood means for setting a neighborhood of neurons in said input and output layers corresponding to a neuron in said middle layer, for each neuron in said middle layer, third determining means for determining a rate of activation in said neighborhood of neurons, said rate being the total number of neurons activating in said neighborhood in said input and output layers divided by the total number of neurons in said neighborhood in said input and output layers, for each neuron in said middle layer, comparison means for comparing said rate to a threshold value, for each neuron in said middle layer, fourth determining means for determining that said neuron in said middle layer has a tendency to activate when said rate is greater than said threshold value, and for each neuron in said middle layer, increasing means for increasing the value of weights applied to all neurons in said input layer which are connected to said neuron in said middle layer and weights applied to all neurons in said output layer which are connected to said neuron in said middle layer, in order to increase the likelihood of activation of said neuron in said middle layer and thereby generate an activation pattern in said middle layer corresponding to said recognition signal, wherein said increasing is determined by the tendency to activate of said neuron in said middle layer; and post-processing means for storing said recognition signal; and display means for receiving said recognition signal from said post-processing means and displaying said recognition signal.
-
Specification