Method and device for classifying sheet media

Abstract

The invention relates to the processing technology of image information, in particular to a method and a device for classifying sheet media quickly according to the image information. The method comprises the following steps of: acquiring the image information of the sheet media to be identified; performing normalization processing on the acquired image information according to a preset standard image dimension so as to obtain the image information to be identified; performing feature extraction on the image information to be identified to form a feature vector; and sending the feature vector into a classifier which is trained by standard sheet media to obtain a classification result, wherein the normalization processing comprises the following steps of: identifying whether the dimension of the acquired image information is smaller than that of the preset standard image, if so, directly returning an unknown type of the sheet media; and otherwise, calculating the geometric center of the acquired image information; and intercepting the image information with the same dimension as that of the preset standard image by taking the geometric center as the center to form the image information to be identified. By the method, the discrimination degree of the feature vectors in different classifications can be improved effectively and the generalization capability of the classifier can be enhanced.

Description

technical field [0001] The invention relates to an image information processing technology, in particular to a method and a device for rapidly classifying sheet media based on image information. Background technique [0002] In the financial field, in order to automatically process a large number of bills, such as a large number of mixed banknotes in the circulation process, banks need to sort out these large numbers of mixed banknotes, that is, banknote sorting operations. In order to automatically classify banknotes of different currencies and denominations, the current solution obtains the image information of each banknote to be processed, and then analyzes and compares the image information to achieve classification. [0003] The existing classification techniques mainly fall into the following two categories: [0004] One is to match the features of the extracted thin-sheet medium (hereinafter referred to as the object to be identified) with the standard feature data ...

AI Technical Summary

Problems solved by technology

[0014] The above method requires that the extracted features have a good degree of discrimination, but it is unrealistic to ensure that the degree of discrimination of the extracted features has a stable and good degree of discrimination.

Moreover, no matter which of the above technical solutions has a strong dependence on the standard feature data, when the size of the image changes to a certain extent, the position of the selected feature will also change, which will affect the recognition effect.

Images