초록 ▼

A bill-recognition apparatus includes a neural network having a learning capability and performs high-efficiency pattern recognition of seven kinds of U.S. dollar bills. Pattern image data optically inputted through a sensor is compressed using plurality of column masks, and then a plurality of valu

A bill-recognition apparatus includes a neural network having a learning capability and performs high-efficiency pattern recognition of seven kinds of U.S. dollar bills. Pattern image data optically inputted through a sensor is compressed using plurality of column masks, and then a plurality of values representative of images (slab values) are determined. The image data is divided into a large number of strip-shaped segments, and some of theses segments are masked with column areas of masks. The values representative of images compressed through column masks are not influenced by a slight inclination of the pattern image during the reading operation. These values representative of images are inputted to a separation processing unit (neural network). From these values, the separation processing unit calculates separation values corresponding to respective decision patterns associated with pattern images, using weights which have been adjusted to optimum values for respective decision patterns. A correct pattern image is determined from the maximum value of the separation values. The above arrangement allows for a reduction in scale of the neural network and control system. Furthermore, bill recognition may also be achieved by separation processing using a plurality of small-scaled neural networks connected in cascade, or replacing weight functions in the same neural network and performing separation processing a plurality of times for the same slab values (cascade processing). In this way, it is possible to reduce the scale of the neural network and the control system.

대표청구항 ▼

[ What is claimed is:] [1.] A pattern recognition apparatus comprising:an image sensor for optically detecting a pattern image of an object to be recognized;a pre-processing unit for converting pattern image data detected by said image sensor into a plurality of representative values of the pattern

[ What is claimed is:] [1.] A pattern recognition apparatus comprising:an image sensor for optically detecting a pattern image of an object to be recognized;a pre-processing unit for converting pattern image data detected by said image sensor into a plurality of representative values of the pattern image, using a plurality of area masks each having a plurality of rectangular segments wherein random rectangular segments are closed;a memory unit for storing weights which have been adjusted to optimum representative values for decision images to be recognized;a separation processing unit for receiving in parallel said plurality of representative values of the pattern image, and then calculating separation values corresponding to respective decision images within the pattern image using the weights stored in said memory unit; anda decision unit for detecting the maximum or minimum value of said separation values and then outputting a decision corresponding to the maximum or minimum value as the pattern image of the object.