RMB sequence number identification method
An identification method and serial number technology, applied in the field of RMB identification, can solve the problems of not supporting RMB, insufficient recognition rate, and low real-time performance, etc., and achieve the effect of enhancing robustness and high identification accuracy
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Publication Date
- 2014-03-26
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention relates to the technical field of RMB identification, in particular to a method for identifying serial numbers of RMB banknotes. Background technique
[0002] The automatic recognition of the serial number of RMB banknotes is of great significance to national currency management, bank financial security and RMB banknote collection. First of all, in order to correctly plan and coordinate the monetary policy, it is necessary to have a good grasp of banknote information, such as the amount of RMB that has been issued and recovered, and the use of banknote serial numbers. Secondly, banknote serial number identification can be used to identify banknotes with specific serial numbers, providing conditions for financial institutions to carry out special treatment on specific currencies (robbery, counterfeit currency, etc.). Thirdly, the popularity of RMB collection in recent years has also made banknotes with auspicious numbers or anniversary da...
Examples
Embodiment
[0048] Such as figure 1As shown, the RMB serial number recognition method in this embodiment includes the following steps. First, preprocessing the banknote image, including processing such as improving severe exposure, extracting banknote images, and registering banknote images. Combining the top hat transformation on the basis of grayscale to improve the binarization effect of the banknote image; extracting the rectangular area where the banknote image is located to remove irrelevant background information; using the homography matrix to register the image to correct the tilt and eliminate the perspective effect ; First judge the reverse situation according to the left and right distribution of the binary image pixels of the banknote, and then judge the front and back of the banknote according to the color tone of the lower left area of the banknote. The preprocessing algorithm can be well adapted to the subsequent serial number positioning, segmentation and recognition, a...