A Multi-Country Banknote Currency Recognition Method Based on Image Fingerprint

Abstract

The invention discloses an image fingerprint-based recognition method for multi-national banknotes and belongs to the technical field of banknote pattern recognition. Based on the template set and sample set of the multi-national banknote background image, the perceptual hash algorithm is used to generate training sample data, and the classification model based on the SVM classifier is constructed, and the training sample data is used to train the classification model, and the trained classification model is used for processing Banknote images are used to predict and identify currency types. The method of the invention converts a single feature in the banknote identification process into multiple features, and adopts a method based on an SVM classifier for identification, which requires a small amount of samples, fast training speed, fast recognition speed, and has good anti-interference ability , which can improve the error tolerance rate of prediction.

Description

technical field [0001] The invention relates to the technical field of banknote pattern recognition, in particular to a multi-national banknote currency identification method based on image fingerprints. Background technique [0002] At present, financial equipment that supports multi-national currency processing has become a development trend, and currency recognition technology based on digital image processing has also been widely used. [0003] In such financial instruments that support multi-national currency processing, when dealing with currencies of different countries, it is often necessary to manually set the current currency category to be processed, and the degree of automation is low; the current currency recognition technology based on digital image processing usually uses recognition The calculation of the algorithm is complex and the time complexity is high, especially when the currency types increase, the currency recognition time will increase exponentially...

AI Technical Summary

Problems solved by technology

Some traditional currency identification is judged by the projection of the serial number, the first letter of the serial number or the number of digits of the serial number. The results show a large deviation

In terms of feature extraction, the traditional method is to extract multiple local features of the image as the basis for classification. This method has high requirements for image processing. If there is noise in the image or the processing is not in place, it will have a great impact on the recognition result. impact, weak anti-interference ability

The template matching algorithm used in traditional pattern recognition, by matching a large number of templates, also needs to consider the size and direction of the templates, and the recognition efficiency is relatively low

Images