A Character Recognition Method for Multinational Banknote Serial Number Based on Image Fingerprint

Abstract

The invention discloses a multi-country banknote serial number character recognition method based on image fingerprints, which belongs to the technical field of banknote pattern recognition. Based on the template set and sample set of multi-country banknote serial number character pictures, the perceptual hash algorithm is used to generate training sample data, and the classification model based on SVM classifier is constructed, and the training sample data is used to train the classification model, and the trained classification model is used Identify the serial number character picture of the banknote to be processed. The method of the invention converts a single feature in the banknote serial number character recognition process into multiple features, and adopts a method based on an SVM classifier for recognition, which has a small demand for samples, fast training speed, fast recognition speed, and good performance Anti-interference ability 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 method for recognizing characters of multi-national banknote serial numbers based on image fingerprints. Background technique [0002] At present, financial equipment that supports multi-national currency processing has become a development trend. Currency recognition technology based on digital image processing has also been widely used. With the wide application of optical character recognition technology in human production and life, banknote serial number character recognition has become As an important means of preventing economic crimes in the economic field, automatic optical character recognition technology has attracted more and more attention from researchers. How to improve the accuracy and efficiency of character recognition is the most worthy of attention in this field. [0003] The work to be carried out in the traditional recognition method o...

AI Technical Summary

Problems solved by technology

[0003] The traditional recognition method of serial characters requires cumbersome work, and if the characters are not handled properly, it may directly lead to a large deviation in the recognition results

In terms of feature extraction, some character recognition methods extract specific features of pictures by scanning images, such as concavo-convexity, connected domains, intersections of horizontal and vertical lines, etc., which are fast and have high resolution, but the disadvantage is that the anti-noise ability is low, so picture character recognition Accuracy is not very stable

The recognition method based on convolutional neural network has a high accuracy rate, but this method has slow training speed, high requirements for computer hardware, and relatively strict requirements for the number of training samples, which makes it difficult to achieve in daily life development. The cost is also relatively high, and the time spent is unbearable in general projects, and once there is a problem with the training model, or the prediction of new samples is wrong, the training model is difficult to modify, and only retraining is time-consuming and laborious

Images