Abstract: A coin discriminating apparatus includes a coin passage member, a first transporting belt disposed above the coin passage member, thereby transporting it, a first light source, a first light detector, a second transporting belt for supporting the lower surface of the coin, a coin passage forming member disposed above the second transporting belt, a second light source, a second light detector, a first pattern data memory for storing the pattern data of the lower surface of the coin, a second pattern data memory for storing the pattern data of the upper surface of the coin, a reference pattern data memory for storing reference pattern data of coins of each denomination, a discriminator for comparing the pattern data of the lower surface of the coin with the reference pattern data of coins of each denomination and comparing the pattern data of the upper surface of the coin with the reference pattern data of coins of each denomination, thereby discriminating whether or not the coin is acceptable and the denomina
Abstract: The coin-type determining device, for determining the presence or absence of inclined notches formed on the circumferential surface of the coin transferred through a coin transfer path, comprises: a plurality of notch detecting devices provided separately from each other with respect to an axis of the coin; a determining device for determining the presence or absence of inclined notches based on the difference between the notch detection results by the notch detecting devices.
Abstract: A money identifying method and a device which can identify money with high precision and quickly by optimally binarizing a surface image of the money. The center coordinates and radius of subject coin C are extracted by coin shape extraction section 106 from the surface image of the subject coin C obtained by area sensor 103, and an effective threshold calculation range is extracted by threshold calculation range extraction section 107 from the extracted center coordinates and radius of the coin. And, a density histogram is created by histogram generation section 108 on the basis of the threshold calculation range, an optimum binary threshold value is calculated from the density histogram by binary threshold calculation section 109 according to a discriminating analysis, and the optimum binary threshold value is used to binarize an image for identifying the subject coin C.
Abstract: A funds processing system receives, dispenses, and sorts currency and substantially immediately furnishes an associated accounting system with data, including the value of the currency processed, in a single transaction. The system determines the denomination of the received currency, sorts the received currency, generates electrical signals representing the amount of received currency in each denomination in each batch of currency received, has a memory for receiving data representing the amount of each denomination of currency received. The system also contains a controller for transferring data from the memory to the associated cash accounting system so that deposits and withdrawals executed at the funds processing system are entered in the accounting system substantially immediately after the execution of the deposits and withdrawals. The system dispenses currency based upon the amount of received currency and the amount deposited into the accounting system.
May 13, 1996
Date of Patent:
November 9, 1999
Douglas U. Mennie, William J. Jones, Mark C. Munro
Abstract: 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.