Supercharge Your Innovation With Domain-Expert AI Agents!

Medium classification method and apparatus thereof

A classification method and technology of a classification device, which are applied to devices for accepting coins, inspection of the authenticity of banknotes, instruments, etc., can solve the problems of time-consuming classification, unfavorable to improve the efficiency of serial number recognition, etc., and achieve rapid and stable classification and reduction mode. Types, effects on circulation and regulation

Inactive Publication Date: 2016-12-07
SHENZHEN YIHUA COMP +2
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiments of the present invention is to provide a method for classifying media, aiming to solve the problems of the existing media classifying methods, which take a long time to classify and are not conducive to improving the efficiency of serial number recognition

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Medium classification method and apparatus thereof
  • Medium classification method and apparatus thereof
  • Medium classification method and apparatus thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] figure 1 It is a flowchart of the implementation of the medium classification method provided by the embodiment of the present invention, and is described in detail as follows:

[0031] In step S101, acquire banknote images;

[0032] In step S102, in the banknote image, cut out the digital image of the serial number;

[0033] In step S103, the digital image is processed using a skeleton thinning algorithm and a pre-established black pixel point value table;

[0034] Black pixels are: pixels whose color is black.

[0035] In step S104, digital recognition is carried out to the processed digital image;

[0036] In step S105, when the result of digital recognition is digital defacement, the serial number of the banknote image is classified as a defaced serial number.

[0037] When no number is identified or two numbers are recognized, the result of digital recognition is digital defacement, and the serial number of the banknote image is classified as a defaced serial n...

Embodiment 2

[0050] The embodiment of the present invention describes the implementation process of establishing a black pixel point value table, which is described in detail as follows:

[0051] Before processing the digital image using the skeleton thinning algorithm and the pre-established black pixel point value table, the medium classification method further includes:

[0052] Assign different values ​​to the 8 areas around a black pixel to establish a black pixel value table.

[0053] According to the 8 fields of black pixels, there are two cases of black pixels and white pixels in any area of ​​the 8 fields, so the number of combinations is 2 to the 8th power, and all cases can be mapped to a 0-255 in the index table.

[0054] Refer to Table 1. Table 1 is a better sample table of the black pixel point value table when the black pixel point is 0. The details are as follows:

[0055] Table 1

[0056] 1

2

4

8

0

16

32

64

128

[0057...

Embodiment 3

[0061] Figure 6 It is a flowchart of the implementation of step S103 of the medium classification method provided by the embodiment of the present invention, and is described in detail as follows:

[0062] In step S601, in the digital image, locate black pixels;

[0063] In step S602, use the pre-established black pixel point value table to extract the values ​​of 8 areas around the positioned black pixel point;

[0064] In step S603, according to the values ​​of the 8 areas around the black pixel point, using the skeleton thinning algorithm, it is judged whether the black pixel point is a boundary point and the connected component does not increase after the black pixel point is removed;

[0065] In step S604, when the black pixel point is a boundary point and the connected component does not increase after the black pixel point is removed, the black pixel point is deleted.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention is suitable for the stained crown size classification field and provides a medium classification method and an apparatus thereof. The medium classification method comprises the following steps of acquiring a paper currency image; in the paper currency image, cutting and taking out a digital image of a crown size; using a skeleton thinning algorithm and a pre-established black pixel point value table to process the digital image; carrying out digital identification on the processed digital image; and when a result of the digital identification is that digits are stained, classifying the crown size of the paper currency image as the stained crown size. By using an existing medium classification method, classification consuming time is long, which is not good for increasing crown size identification efficiency. By using the method and the apparatus of the invention, the above problem is solved. The method and the apparatus of the invention have the following advantages that on a first aspect, classification complexity is reduced; on a second aspect, an image identification characteristic after preprocessing is obvious, which is good for subsequent processing; and on a third aspect, the paper currency image with the stained crown size can be rapidly and stably classified, which is good for paper currency circulation and supervision.

Description

technical field [0001] The invention belongs to the field of classification of defaced serial numbers, and in particular relates to a medium classification method and device. Background technique [0002] The code on the RMB banknotes is also called the crown number. The "crown" is two or three English letters printed on the banknotes to mark the printing batch. It is arranged and printed by the banknote printing factory according to certain rules; the "number" is It is the serial number of Arabic numerals printed behind the crown, which is used to mark the sequence of each banknote in the batch with the same crown. By querying the serial number, the entire circulation process of each banknote from issuance to recycling can be traced. [0003] However, the existing media classification method takes a long time to classify, which is not conducive to improving the efficiency of serial number recognition. The reason is that the existing media classification method lacks image...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G07D7/187G07D7/20G07D11/00
CPCG07D7/187G07D7/20G07D11/50
Inventor 傅博扬
Owner SHENZHEN YIHUA COMP
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com