Abstract: A handwriting verification device includes: a normalizing section for normalizing an inputted handwriting which has been subjected to sampling at regular intervals; a registered handwriting dictionary in which registered handwriting is accommodated; a correspondence making section for making the inputted handwriting, which has been normalized in accordance with the sampling points in the sampling, correspond to the registered handwriting, so that a portion of the inputted handwriting and a portion of the registered hand writing, which coincide with each other, can be made to correspond to each other; a segment making section for making the inputted handwriting and the registered handwriting to be a segment by allotting an interval between at least two continuous sampling points as a segment in accordance with the result of making correspondence; a characteristic extracting section for extracting the characteristics of the inputted handwriting and the registered handwriting for each segment; and a handwriting

Abstract: A neural network includes a plurality of input nodes for receiving the respective elements of the input vector. A copy of all of the elements of the input vector is sent to the next level of nodes in the neural network denoted as intermediate nodes. The intermediate nodes each encode a separate template pattern. They compare the actual input pattern with the template and generate a signal indicative of the difference between the input pattern and the template pattern. Each of the templates encoded in the intermediate nodes has a class associated with it. The difference calculated by the intermediate nodes is passed to an output node for each of the intermediate nodes at a given class. The output node then selects the minimum difference amongst the values sent from the intermediate nodes. This lowest difference for the class represented by the output node is then forwarded to a selector.

Abstract: A neural network includes a plurality of input nodes for receiving the respective elements of the input vector. A copy of all of the elements of the input vector is sent to the next level of nodes in the neural network denoted as intermediate nodes. The intermediate nodes each encode a separate template pattern. They compare the actual input pattern with the template and generate a signal indicative of the difference between the input pattern and the template pattern. Each of the templates encoded in the intermediate nodes has a class associated with it. The difference calculated by the intermediate nodes is passed to an output node for each of the intermediate nodes at a given class. The output node then selects the minimum difference amongst the values sent from the intermediate nodes. This lowest difference for the class represented by the output node is then forwarded to a selector.

Abstract: A neural network includes a plurality of input nodes for receiving the respective elements of the input vector. A copy of all of the elements of the input vector is sent to the next level of nodes in the neural network denoted as intermediate nodes. The intermediate nodes each encode a separate template pattern. They compare the actual input pattern with the template and generate a signal indicative of the difference between the input pattern and the template pattern. Each of the templates encoded in the intermediate nodes has a class associated with it. The difference calculated by the intermediate nodes is passed to an output node for each of the intermediate nodes at a given class. The output node then selects the minimum difference amongst the values sent from the intermediate nodes. This lowest difference for the class represented by the output node is then forwarded to a selector.

Abstract: A self-organizing pattern classification neural network system includes means for receiving incoming pattern of signals that were processed by feature extractors that extract feature vectors from the incoming signal. These feature vectors correspond to information regarding certain features of the incoming signal. The extracted feature vectors then each pass to separate self-organizing neural network classifiers. The classifiers compare the feature vectors to templates corresponding to respective classes and output the results of their comparisons. The output from the classifier for each class enter a discriminator. The discriminator generates a classification response indicating the best class for the input signal. The classification response includes information indicative of whether the classification is possible and also includes the identified best class.