Folded bill identification method and device

Patent metadata

Field	Value
Publication number	US-10319170-B2
Application number	US-201515544379-A
Country	US
Kind code	B2
Filing date	Jul 13, 2015
Priority date	Feb 4, 2015
Publication date	Jun 11, 2019
Grant date	Jun 11, 2019

Abstract

A folded bill recognizing method and a folded bill recognizing device are provided. The folded bill recognizing device includes: a bill input port configured to receive a to-be-recognized bill or a sample bill; a signal collecting module configured to collect a CIS image of the bill, to obtain an infrared transmission image T and an infrared reflection image F; a signal recognizing module configured to recognize whether the to-be-recognized bill has a fold; and a receiving/rejecting module configured to perform a receiving or rejecting operation on the to-be-recognized bill. The device can effectively recognize a folded bill.

First claim

The invention claimed is:

1. A method for recognizing a folded bill, performed by a folded bill recognizing device, comprising:
obtaining
an infrared transmission image T s and an infrared reflection image F s of a to-be-recognized bill;
performing high-pass filtering on the infrared transmission image T s to obtain a high-pass infrared transmission filtering image gT s ;
performing low-pass filtering on the infrared transmission image T s to obtain a low-pass infrared transmission filtering image dT s ;
performing high-pass filtering on the infrared reflection image F s , to obtain a high-pass infrared reflection filtering image gF s , wherein the high-pass filtering on the infrared reflection image F s and the low-pass filtering on the infrared transmission image T s are performed synchronously according to a geometric coordinate mapping relationship;
performing low-pass filtering on the infrared reflection image F s , to obtain a low-pass infrared reflection filtering image dF s , wherein the low-pass filtering on the infrared reflection image F s and the high-pass filtering on the infrared transmission image T s are performed synchronously according to the geometric coordinate mapping relationship;
performing a differential operation on the high-pass infrared reflection filtering image gF s and the low-pass infrared transmission filtering image dT s to obtain a differential image cFT s ;
performing a first characteristic extraction on the high-pass infrared transmission filtering image gT s by calculating an average gray value gT_G s of the gT s as a characteristic value;
performing a second characteristic extraction on the low-pass infrared reflection filtering image dF s by calculating an average gray value dF_G s of the dF s as a characteristic value;
performing a third characteristic extraction on the differential image cFT s by calculating an average gray value cFT_G s of the cFT s as a characteristic value;
substituting the characteristic value gT_G s , the characteristic value dF_G s and the characteristic value cFT_G s respectively into three models y 1 ,y 2 ,y 3 for distinguishing folded bills and non-folded bills,
y 1 =f 1 ( gT _ G );
y 2 =f 2 ( dF _ G )
y 3 =f 3 ( cFT _ G )
to obtain
p 1 =f 1 ( gT _ G s );
p 2 =f 2 ( dF _ G s )
p 3 =f 3 ( cFT _ G s );

wherein p 1 , p 2 and p 3 are confidence levels for determining the to-be-recognized bill as a folded bill; f1, f2 and f3 indicate learnt multi-characteristic classifying probability distribution models; in a case that p 1 >T 1 , p 2 >T 2 , p 3 >T 3 are all true, the to-be-recognized bill is recognized as a folded bill; in a case that p 1 >T 1 , p 2 >T 2 , p 3 >T 3 are not all true, the to-be-recognized bill is recognized as a non-folded bill, where T 1 , T 2 and T 3 are three confidence level thresholds.

2. The method according to claim 1 , wherein the substituting further comprises:
assigning different weighted values α,β,γ to p 1 , p 2 and p 3 , wherein α+β+γ=1,α≥0,β≥0,γ≥0; and
determining a threshold T s , wherein
the bill classifying decision model is:

p
s

=

α
*

p
1

+

β
*

p
2

+

γ
*

p
3

,

{

>

T
s

folded
⁢

⁢
bill

≤

T
s

non
⁢

-

⁢
folded
⁢

⁢
bill

.

3. The method according to claim 1 , further comprising obtaining the three models y 1 ,y 2 ,y 3 for distinguishing folded bills and non-folded bills, the obtaining comprising:
collecting a certain number of samples of folded bills and non-folded bills;
obtaining, for each of the samples, a characteristic value of an average gray value gT_G of a high-pass infrared transmission filtering image gT, a characteristic value of an average gray value dF_G of a low-pass infrared reflection filtering image dF and a characteristic value of an average gray value cFT_G of a differential filtering image cFT;
counting the characteristic value of the gT_G, the characteristic value of the dF_G and the characteristic value of the cFT_G respectively, to obtain a probability distribution graph of the gT_G, a probability distribution graph of the dF_G and a probability distribution graph of the cFT_G corresponding to the folded bills as the following formulas:
y 1 =f 1 ( gT _ G );
y 2 =f 2 ( dF _ G )
y 3 =f 3 ( cFT _ G );

wherein y 1 ,y 2 ,y 3 are the three models for distinguishing folded bills and non-folded bills respectively.

4. The method according to claim 3 , wherein a method for obtaining, for each of the samples, the characteristic value of the average gray value gT_G of the high-pass infrared transmission filtering image gT, the characteristic value of the average gray value dF_G of the low-pass infrared reflection filtering image dF and the characteristic value of the average gray value cFT_G of the differential filtering image cFT is the same as the method for obtaining the characteristic value of the average gray value gT_G s of the high-pass infrared transmission filtering image gT s , the characteristic value of the average gray value dF_G s of the low-pass infrared reflection filtering image dF s and the characteristic value of the average gray value cFT_G s of the differential filtering image cFT s of the to-be-recognized bill.

5. The method according to claim 3 , wherein a method for obtaining the three models y 1 ,y 2 ,y 3 for distinguishing folded bills and non-folded bills comprises:
collecting a certain number of samples of folded bills and non-folded bills;
obtaini

Assignees

• Grg Banking Equipment Co Ltd

Inventors

• Liu Guanglu
• Chen Jian
• Xiao Zhuming
• Zheng Weirui

Classifications

• G07D2207/00

  Paper-money testing devices · CPC title

• G07D7/2041

  Matching statistical distributions, e.g. of particle sizes orientations · CPC title

• G07D7/2008

  using pre-processing, e.g. de-blurring, averaging, normalisation or rotation · CPC title

• G07D7/12

  Visible light, infrared or ultraviolet radiation · CPC title

• G01N21/3563

  for analysing solids; Preparation of samples therefor · CPC title