# US 10,319,170 B2 · Folded bill identification method and device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,319,170 B2
- Document ID: US10319170B2
- Status: Granted
- Kind: B2
- Application number: 15/544,379
- Filed: 2015-07-13
- Published: 2018-09-20
- Granted: 2019-06-11
- Earliest claimed: 2015-02-04
- Assignees: GRG Banking Equipment Co., Ltd.
- Applicants: GRG Banking Equipment Co., Ltd.
- Inventors: Guanglu Liu; Jian Chen; Zhuming Xiao; Weirui Zheng
- Web page: https://patentgrep.com/patent/US10319170B2

## CPC

- G07D 7/183: Detecting folds or doubles
- G01N 21/3563: for analysing solids; Preparation of samples therefor
- G06F 18/2433: Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
- G07D 7/12: Visible light, infrared or ultraviolet radiation
- G07D 7/121: Apparatus characterised by sensor details
- G07D 7/20: Testing patterns thereon (G07D7/004, G07D7/005 take precedence)
- G07D 7/2008: {using pre-processing, e.g. de-blurring, averaging, normalisation or rotation}
- G07D 7/2041: {Matching statistical distributions, e.g. of particle sizes orientations}
- G07D 2207/00: Paper-money testing devices
- G07D: HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## 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.

## Claims

### Claim 1

A method for recognizing a folded bill, performed by a folded bill recognizing device, comprising:
obtaining
an infrared transmission image Ts and an infrared reflection image Fs of a to-be-recognized bill;
performing high-pass filtering on the infrared transmission image Ts to obtain a high-pass infrared transmission filtering image gTs;
performing low-pass filtering on the infrared transmission image Ts to obtain a low-pass infrared transmission filtering image dTs;
performing high-pass filtering on the infrared reflection image Fs, to obtain a high-pass infrared reflection filtering image gFs, wherein the high-pass filtering on the infrared reflection image Fs and the low-pass filtering on the infrared transmission image Ts are performed synchronously according to a geometric coordinate mapping relationship;
performing low-pass filtering on the infrared reflection image Fs, to obtain a low-pass infrared reflection filtering image dFs, wherein the low-pass filtering on the infrared reflection image Fs and the high-pass filtering on the infrared transmission image Ts are performed synchronously according to the geometric coordinate mapping relationship;
performing a differential operation on the high-pass infrared reflection filtering image gFs and the low-pass infrared transmission filtering image dTs to obtain a differential image cFTs;
performing a first characteristic extraction on the high-pass infrared transmission filtering image gTs by calculating an average gray value gT_Gs of the gTs as a characteristic value;
performing a second characteristic extraction on the low-pass infrared reflection filtering image dFs by calculating an average gray value dF_Gs of the dFs as a characteristic value;
performing a third characteristic extraction on the differential image cFTs by calculating an average gray value cFT_Gs of the cFTs as a characteristic value;
substituting the characteristic value gT_Gs, the characteristic value dF_Gs and the characteristic value cFT_Gs respectively into three models y1,y2,y3 for distinguishing folded bills and non-folded bills,
y1=f1(gT_G);
y2=f2(dF_G)
y3=f3(cFT_G)
to obtain
p1=f1(gT_Gs);
p2=f2(dF_Gs)
p3=f3(cFT_Gs);
wherein p1, p2 and p3 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 p1>T1, p2>T2, p3>T3 are all true, the to-be-recognized bill is recognized as a folded bill; in a case that p1>T1, p2>T2, p3>T3 are not all true, the to-be-recognized bill is recognized as a non-folded bill, where T1, T2 and T3 are three confidence level thresholds.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the substituting further comprises:
assigning different weighted values α,β,γ to p1, p2 and p3, wherein α+β+γ=1,α≥0,β≥0,γ≥0; and
determining a threshold Ts, 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
.

### Claim 3 (depends on 1)

The method according to claim 1, further comprising obtaining the three models y1,y2,y3 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:
y1=f1(gT_G);
y2=f2(dF_G)
y3=f3(cFT_G);
wherein y1,y2,y3 are the three models for distinguishing folded bills and non-folded bills respectively.

### Claim 4 (depends on 3)

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_Gs of the high-pass infrared transmission filtering image gTs, the characteristic value of the average gray value dF_Gs of the low-pass infrared reflection filtering image dFs and the characteristic value of the average gray value cFT_Gs of the differential filtering image cFTs of the to-be-recognized bill.

### Claim 5 (depends on 3)

The method according to claim 3, wherein a method for obtaining the three models y1,y2,y3 for distinguishing folded bills and non-folded bills comprises:
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:
y1=f1(gT_G);
y2=f2(dF_G);
y3=f3(cFT_G);
wherein y1,y2,y3 are the three models for distinguishing folded bills and non-folded bills respectively.

### Claim 6 (depends on 5)

The method according to claim 5, 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_Gs of the high-pass infrared transmission filtering image gTs, the characteristic value of the average gray value dF_Gs of the low-pass infrared reflection filtering image dFs and the characteristic value of the average gray value cFT_Gs of the differential filtering image cFTs of the to-be-recognized bill.

### Claim 7 (depends on 1)

The method according to claim 1, wherein the method further comprises:
prior to performing the high-pass filtering-on the infrared transmission image Ts,
calculating a high-pass filter threshold and a low-pass filter threshold for the image signals Ts and Fs by:
calculating an average gray value of the Ts as:
avG
=
∑
i
=
1
w
*
h
⁢
⁢
pix
⁡
(
i
)
/
(
w
*
h
)
;
where pix(i) is a gray value corresponding to a pixel of Ts, w is the width of the image signal Ts, h is the height of the image signal Ts; and
calculating the high-pass filter threshold corresponding to Ts as T11=j*avG,1≤j≤(255/avG), and the low-pass filter threshold corresponding to Ts as T22=k*avG,0≤k≤1.

### Claim 8 (depends on 7)

The method according to claim 7, wherein a calculating model for calculating the average gray value gT_Gs of the gTs, a calculating model for calculating the average gray value dF_Gs of the dFs and a calculating model for calculating the average gray value cFT_Gs of the cFTs are the same as the calculating models for calculating the average gray values of the Ts.

### Claim 9

A method for recognizing a folded bill, comprising:
obtaining an infrared transmission image Ts and an infrared reflection image Fs of a to-be-recognized bill;
performing high-pass filtering on the infrared transmission image Ts to obtain a high-pass infrared transmission filtering image gTs;
performing low-pass filtering on the infrared transmission image Ts to obtain a low-pass infrared transmission filtering image dTs;
performing a first characteristic extraction on the high-pass infrared transmission filtering image gTs by calculating an average gray value gT_Gs of the gTs as a characteristic value;
performing high-pass filtering on the infrared reflection image Fs, to obtain a high-pass infrared reflection filtering image gFs, wherein the high-pass filtering on the infrared reflection image Fs and the low-pass filtering on the infrared transmission image Ts are performed synchronously according to a geometric coordinate mapping relationship;
performing low-pass filtering on the infrared reflection image Fs to obtain a low-pass infrared reflection filtering image dFs, wherein the low-pass filtering on the infrared reflection image Fs and the high-pass filtering on the infrared transmission image Ts are performed synchronously according to the geometric coordinate mapping relationship;
performing a second characteristic extraction on the low-pass infrared reflection filtering image dFs by calculating an average gray value dF_Gs of the dFs as a characteristic value;
performing a differential operation on the high-pass infrared reflection filtering image gFs and the low-pass infrared transmission filtering image dTs to obtain a differential image cFTs;
performing a third characteristic extraction on the differential image cFTs by calculating an average gray value cFT_Gs of the cFTs as a characteristic value; and
substituting the characteristic value gT_Gs, the characteristic value dF_Gs and the characteristic value cFT_Gs respectively into three models y1,y2,y3 for distinguishing rippled bills and non-rippled bills,
y1=f1(gT_G);
y2=f2(dF_G)
y3=f3(cFT_G);
to obtain
p1=f1(gT_Gs);
p2=f2(dF_Gs)
p3=f3(cFT_Gs);
wherein p1, p2 and p3 are confidence levels for determining the to-be-recognized bill as a rippled bill; f1, f2 and f3 indicate learnt multi-characteristic classifying probability distribution models; in a case that p1>T1, p2>T2, p3>T3 are all true, the to-be-recognized bill is recognized as a rippled bill; in a case that p1>T1, p2>T2, p3>T3 are not all true, the to-be-recognized bill is recognized as a non-rippled bill, where T1, T2 and T3 are three confidence level thresholds.