Paper note recognition method and device and equipment
A banknote identification and banknote technology are applied in the field of banknote identification methods and devices and equipment, and can solve problems such as banknote identification that cannot meet the requirements of high efficiency.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0055] Figure 1a It is a flow chart of a banknote identification method provided by Embodiment 1 of the present invention. The method of this embodiment can be executed by a banknote identification device, which can be implemented by means of hardware and / or software, and can generally be integrated into banknote verification machine, ATM machine. The method of this embodiment specifically includes:
[0056] S101. From the grayscale image of the standard size of the banknote to be recognized, acquire a pair of local patterns matching at least one pair of feature positions.
[0057] In this embodiment, the standard size grayscale image specifically refers to scaling the forward grayscale image of the banknote to be recognized according to the standard size to obtain the forward grayscale image of the banknote to be recognized with the same size as the standard size. Wherein, the positive grayscale image of the banknote to be recognized specifically refers to the positive gray...
Embodiment 2
[0081] figure 2 It is a flow chart of a banknote identification method provided by Embodiment 2 of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiments. In this embodiment, in the standard-sized grayscale image of the banknote to be identified, a local pattern pair matching at least one characteristic position pair is obtained, and the optimization is: to obtain the to-be-identified banknote A grayscale image of banknotes; adjusting the grayscale image to a standard size grayscale image according to a set standard size; in the standard size grayscale image, obtaining a pair of partial patterns matching at least one pair of feature positions.
[0082] The gray level comparison rule is optimized as: gray level mean value comparison, gray level mean square deviation comparison or gray level difference maximum value comparison.
[0083] Optimize the grayscale comparison rule to grayscale mean comparison;
[0084] Correspondingly, a...
Embodiment 3
[0115] image 3 It is a flow chart of a banknote identification method provided by Embodiment 3 of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiments. In this embodiment, before obtaining a local pattern pair matching at least one characteristic position pair in the standard-sized grayscale image of the banknote to be recognized, the optimization includes: obtaining The standard banknote set corresponding to the target currency, and obtain the standard size grayscale image sets of the target currency in different orientations and different currency values; in the target standard size grayscale image set corresponding to the target orientation and target currency value, respectively in In each target standard size grayscale image, obtain a partial pattern pair matching at least one feature position pair; according to the grayscale comparison rule, compare the first pattern and the second pattern included in the local pattern pair...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


