SYSTEM AND METHOD FOR DETECTING POTENTIAL FRAUD ON THE PART OF A CASHIER, AS WELL AS A METHOD OF FORMING A SAMPLING OF IMAGES OF GOODS FOR TRAINING AN ARTIFICIAL NEURAL NETWORK Russian patent published in 2019 - IPC G06K9/66 G06T1/40 

FIELD: computer equipment.

SUBSTANCE: invention relates to computer engineering using artificial neural networks. Technical result is achieved by obtaining data on the read item from the goods database and obtaining video data from the image capturing device, wherein when the commodity is sent by the commodity teller to the bar code reading device, reading of the barcode is performed, based on the readout signal, data on the read item from the goods database are obtained, at the moment of receiving the reading signal, an image of the displayed article is received from the image capturing device, the obtained image of the displayed article is stored to the read goods data in the goods database, then repeating the above steps for each commodity brought to bar code reading device.

EFFECT: high accuracy of detecting potential fraud on the part of the cashier.

35 cl, 3 dwg