초록 ▼

Pattern recognition, for instance optical character recognition, is achieved by training a neural network, scanning an image, segmenting the image to detect a pattern, preprocessing the detected pattern, and applying the preprocessed detected pattern to the trained neural network. The preprocessing

Pattern recognition, for instance optical character recognition, is achieved by training a neural network, scanning an image, segmenting the image to detect a pattern, preprocessing the detected pattern, and applying the preprocessed detected pattern to the trained neural network. The preprocessing includes determining a centroid of the pattern and centrally positioning the centroid in a frame containing the pattern. The training of the neural network includes randomly displacing template patterns within frames before applying the template patterns to the neural network.

대표청구항 ▼

A computer-implemented process of training a neural network, said process comprising: a) providing a plurality of templates, each template corresponding to a distinct image; and b) for each of the plurality of templates: defining a frame around the template; determining a centroid of the template; p

A computer-implemented process of training a neural network, said process comprising: a) providing a plurality of templates, each template corresponding to a distinct image; and b) for each of the plurality of templates: defining a frame around the template; determining a centroid of the template; positioning the template within the frame such that the centroid is centrally located with respect to the frame; randomly displacing the template horizontally and vertically within the frame; and training the neural network by applying the randomly displaced template to the neural network.