Abstract: A plurality of training inputs are selected, wherein each training input corresponds to a first possible output. The quality of each of the plurality of training inputs is characterized. A first training input is selected from the training inputs, where the first training input is of higher quality than a second training input of the training inputs. The neural network is trained with the higher-quality first training input prior to training with the second training input. A neuron may be added to the neural network in accordance with the first training input, wherein the neuron is associated with the first possible output.

Abstract: An input is classified into one of a plurality of possible outputs. A top-level classifier generates an approximate identification for the input as one of the possible outputs and selects two or more neural networks corresponding to the approximate identification. The selected neural networks generate two or more identifications for the input as one or more of the possible outputs. A postprocessor classifies the input as one of the possible outputs in accordance with the two or more identifications of the selected neural networks. According to an alternative embodiment, a top-level classifier selects a subset of neurons of a neural network and the subset of neurons identifies the input as one of the possible outputs.

Abstract: A method and system including a high speed computer algorithm for rotating images stored in a computer memory, such as those captured by a CCD array. The method and system may be used with an over-the-belt optical character recognition (OCR) reader that captures a pixelized image of the surface of a parcel as it moves along a conveyor. A run-length encoded output image is obtained from a run-length encoded input image, wherein the output image is a rotated version of the input image. A predefined pixel mapping sequence for a rotation angle with a rational tangent is used to map image pixel data. Mapping image pixel data using a predefined pixel mapping sequence allows rotation without floating point computations, and allows the use of a reverse pixel mapping technique to map output runs from an input image in order to avoid the creation of holes or artifacts in the output image. Mapped output runs are scaled to preserve the aspect ratio of the rotated image.

Abstract: The present invention is a classification method and apparatus for classifying an input into one of a plurality of possible outputs. The invention generates a feature vector representative of the input. The invention then calculates a distance measure from the feature vector to the center of each neuron of a plurality of neurons, where each neuron is associated with one of the possible outputs. The invention then selects each neuron that encompasses the feature vector in accordance with the distance measure. The invention then determines a vote for each possible output, where the vote is the number of selected neurons that are associated with each possible output. If the vote for one of the possible outputs is greater than all other votes for all other possible outputs, then the invention selects that possible output as corresponding to the input.

Abstract: A classification method and apparatus for classifying an input into one of a plurality of possible outputs. Information representative of the input is compared to a neuron, where the neuron comprises a boundary defined by two or more neuron axes of different length. One of the possible outputs is then selected as corresponding to the input in accordance with that comparison. The invention is also a training method and apparatus for creating a new neuron or adjusting an existing neuron. A feature vector representative of a training input is generated, where the training input corresponds to one of a plurality of possible outputs. If no existing neuron corresponding to the training input encompasses the feature vector, then a new neuron is created, where the new neuron comprises a boundary defined by two or more neuron axes of different length.