WO2017079904A1

WO2017079904A1 - Currency face value identification method and device

Info

Publication number: WO2017079904A1
Application number: PCT/CN2015/094216
Authority: WO
Inventors: 周彦华
Original assignee: 深圳怡化电脑股份有限公司; 深圳市怡化时代科技有限公司; 深圳市怡化金融智能研究院
Priority date: 2015-11-10
Filing date: 2015-11-10
Publication date: 2017-05-18

Abstract

A currency face value identification method and device, the method comprising: acquiring an image of currency, the currency comprising Iranian currency; calculating a first image parameter of a first region and a second image parameter of a second region of the image; and determining the face value of the currency according to the first image parameter and the second image parameter. The present invention facilitates identifying face values of currencies of a number of countries, in particular Iranian currency.

Description

Method and device for identifying currency denomination

[0001] The present invention relates to the field of currency face value recognition technology, and in particular to a method and device for identifying currency face value.

[0002] Currently, in the field of currency processing, such as point counterfeiting, it is often necessary to perform face value recognition on currency. The currencies of different countries usually vary greatly and need to be identified using completely different technical means. There are usually many studies on the face value recognition of the US dollar, the British pound, and the Chinese yuan. However, there are currently no effective methods for identifying currencies in some countries, such as Iranian Iranian currency.

technical problem

Embodiments of the present invention provide a method and apparatus for identifying currency denominations to facilitate face value recognition of currencies in some countries, especially Iranian currency.

Problem solution

Technical solution

[0004] A first aspect of the present invention provides a method for identifying a currency face value, including:

[0005] obtaining an image of a currency, the currency including Iranian currency;

Calculating a first image parameter of the first region of the image and a second image parameter of the second region;

Determining a face value of the currency based on the first image parameter and the second image parameter.

[0008] A second aspect of the present invention provides an apparatus for identifying a currency denomination, including:

[0009] an obtaining module, configured to acquire an image of a currency, where the currency includes an Iranian currency;

[0010] a calculation module, configured to calculate a first image parameter of the first region of the image and a second image parameter of the second region;

And [0011] a determining module, configured to determine a face value of the currency according to the first image parameter and the second image parameter.

Advantageous effects of the invention

Beneficial effect [0012] As can be seen from the above, the embodiment of the present invention determines, according to the first image parameter and the second image parameter, the first image parameter of the first region of the image and the second image parameter of the second region. The face value of the currency helps to identify the face value of some countries' currencies, especially the Iranian currency.

Brief description of the drawing

DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments and the prior art description will be briefly described below. Obviously, the drawings in the following description are merely the present invention. Some of the embodiments may be obtained by those of ordinary skill in the art in view of these drawings without any inventive effort.

1 is a flowchart of a method for identifying a currency denomination according to an embodiment of the present invention;

2 is an image of a vowel value of 20,000 riels according to an embodiment of the present invention;

[0016] FIG. 3 is an image of a 50,000 riyal value provided by an embodiment of the present invention;

4 is an image of a currency value of 100,000 riels provided by an embodiment of the present invention;

[0018] FIG. 5 is an image of a 50,000 riyal value provided by an embodiment of the present invention;

[0019] FIG. 6 is an absolute value of the difference between the first gray value and the second gray value of the four currency values provided by the embodiment of the present invention, Imeanl-mean2l;

7 is a first gradation value meanl diagram of 20,000 riyals and 50,000 riels provided by an embodiment of the present invention; [0021] FIG. 8 is a first gradation value meanl of 500000 according to an embodiment of the present invention; And a second gray value me _{n n} 2 figure; [0022] FIG. 9 is a first gray value mean1 and a second gray value me _{n n} 2 diagram of 100000 according to an embodiment of the present invention; [0023] FIG. A logical structure diagram of a currency face value identification device provided by the example.

Embodiments of the invention

[0024] Embodiments of the present invention provide a method for identifying currency denominations to facilitate face value recognition of currencies in some countries, particularly Iranian currency. Embodiments of the present invention also provide a device for identifying a currency face value.

The technical solutions in the embodiments of the present invention will be clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. The embodiments are merely a part of the embodiments of the invention, and not all of the embodiments. Based on the embodiments of the present invention, all of those obtained by those of ordinary skill in the art without creative efforts The embodiments thereof should fall within the scope of protection of the present invention.

[0026] Detailed description will be respectively made below through specific embodiments.

[0027] Embodiment 1

[0028] Please refer to FIG. 1, a method for identifying a currency face value according to an embodiment of the present invention, which may include:

[0029] 110. Acquire an image of the currency, where the currency includes Iranian currency.

[0030] In some embodiments of the invention, the step of obtaining an image of the currency comprises:

[0031] scanning a currency image, storing image data;

[0032] extracting frontal image data, denoising and background, and intercepting data of the effective image portion.

[0033] wherein the data of the effective image portion is an image of the currency to be acquired by the embodiment of the present invention.

[0034] In the interception, the data of the effective image portion may be exactly an image of a complete currency.

[0035] 120. Calculate a first image parameter of the first region of the image and a second image parameter of the second region.

[0036] In some embodiments of the invention, the image parameters may be grayscale values or blackpoint values.

[0037] Step 120 will be described in detail below with grayscale values as an example.

[0038] In some embodiments of the invention, the first image parameter is a first gray value and the second image parameter is a second gray value.

[0039] Step 120 is specifically: calculating a first gray value of the first region of the image and a second gray value of the second region.

[0040] In some embodiments of the present invention, the first gray value is an average gray value of the first region; [0041] the second gray value is an average gray of the second region Degree value.

[0042] In some embodiments of the invention, grayscale values in the first region and the second region may be measured by sensors. The average gray value is a ratio of a sum of gray value values of all pixel points in a region to a number of pixel points.

[0043] Step 120 will be described in detail below by taking a numerical value of a black dot as an example.

[0044] In some implementations of the invention, the first image parameter is a first black dot value, and the second image parameter is a second black dot value.

[0045] Step 120 is specifically: calculating a first black dot value of the first region of the image and a second black dot value of the second region.

[0046] In some embodiments of the present invention, the calculating the first black dot value of the first region of the image and the second black dot value of the second region include: [0047] performing binarization processing on the first region and the second region of the image;

[0048] acquiring a first black dot value of the first region of the image and a second black dot value of the second region after the binarization process.

[0049] In some embodiments of the present invention, after performing binarization processing, a binarization threshold is set, wherein the selection of the binarization threshold has multiple methods, and the embodiment of the present invention may adopt a maximum inter-class variance method. (otsu), histogram method, Kittler method.

[0050] 130. Determine a face value of the currency according to the first image parameter and the second image parameter.

[0051] In some embodiments of the invention, the image parameters may be grayscale values or blackpoint values.

[0052] The step 130 will be described in detail below by taking the gray value as an example.

[0053] In some embodiments of the invention, the first image parameter is a first gray value and the second image parameter is a second gray value.

[0054] In some embodiments of the invention, when the first image parameter is a first gray value, the second image parameter is a second gray value.

[0055] When the first image parameter is the first gray value and the second image parameter is the second gray value, step 130 is specifically: according to the first gray value and the second gray value Determine the face value of the currency.

[0056] In some embodiments of the present invention, determining the face value of the currency according to the first gray value and the second gray value includes:

[0057] an absolute value of a difference between the first gray value and the second gray value is smaller than a first threshold set in advance, and the first gray value is greater than a second threshold set in advance, Determining that the face value of the currency is 20,000 riels;

[0058] an absolute value of a difference between the first gray value and the second gray value is smaller than a first threshold set in advance, and the first gray value is smaller than a second threshold set in advance, Determining that the face value of the currency is 50,000 rials;

[0059] an absolute value of a difference between the first gray value and the second gray value is greater than a first threshold set in advance, and the first gray value is smaller than the second gray value , determining that the face value of the currency is 500,000 riyals;

[0060] an absolute value of a difference between the first gray value and the second gray value is greater than a first threshold set in advance, and the first gray value is greater than the second gray value , determining that the face value of the currency is 100,000 Yar.

[0061] Step 130 will be described in detail below by taking a numerical value of a black dot as an example.

[0062] In some embodiments of the present invention, the first image parameter is a first black dot value, and the second image parameter is a second black dot value.

[0063] When the first image parameter is a first black dot value and the second image parameter is a second black dot value 吋, step 130 is specifically:

[0064] determining a face value of the currency according to the first black dot value and the second black dot value of the first region.

[0065] The face value of the currency can be determined by comparing the values of the black dots of the binarized region.

[0066] In some embodiments of the present invention, when the first image parameter is a first black dot value, the second image parameter is a second black dot value 吋, and the currency is Iranian currency 吋, The step 130 includes: [0067] an absolute value of a difference between the first black dot value and the second black dot value is less than a preset third threshold, and the first black dot value Less than a preset fourth threshold 吋, determining that the face value of the currency is 20,000 riels;

[0068] The absolute value of the difference between the first black dot value and the second black dot value is smaller than a preset third threshold, and the first black dot value is greater than a preset fourth value Threshold 吋, determining that the face value of the currency is 50,000 riels;

[0069] The absolute value of the difference between the first black dot value and the second black dot value is greater than a preset third threshold, and the first black dot value is smaller than the second black Point a value 吋 to determine the face value of the currency is 100,000 riyals;

[0070] The absolute value of the difference between the first black dot value and the second black dot value is greater than a preset third threshold, and the first black dot value is greater than the second black Click on the value 吋 to determine the face value of the currency is 500000 riyals.

[0071] In some embodiments of the present invention, when the currency is Iranian currency, the coordinates of the first region in the image are [0.231L-0.615L], [0.189W-0.267W];

[0072] the second region is a coordinate in the image of [0.231L-0.615L], [0.767W-0.844W]; wherein the L is the length of the image, W is the width of the image.

[0074] The recognition performance of the first region and the second region at the above position is stable, and the recognition effect is good.

[0075] In some embodiments of the invention, when the currency is Iranian currency, the first region is in the image The coordinates in [0.231L-0.269L], [0.208W-0.248W];

[0076] the second region is a coordinate in the image of [0.231L-0.269L], [0.786W-0.824W]; wherein the L is the length of the image, W is the width of the image.

[0078] By reducing the area of the area, the amount of calculation can be reduced, and the calculation efficiency can be improved.

[0079] In some embodiments of the present invention, the specific positions of the first region and the second region may be represented by position coordinates related to the length L and the width W of the image, and position coordinates associated with pixels of the image may also be used. To indicate the specific location of the first area and the second area.

[0080] In some embodiments of the invention, step 110 further includes the following steps:

[0081] According to the image, the degree of fouling of the currency is detected, and when the degree of fouling of the currency does not exceed a certain range, step 120 is performed.

[0082] By the stain detection, it is possible to prevent the step 120 from being unrecognizable to the currency.

[0083] In some embodiments of the invention, when the degree of fouling of the currency exceeds a certain range, the currency is returned to the user.

[0084] In some embodiments of the invention, the fouling detection may employ the currently commonly used fouling detection techniques.

[0085] It can be understood that the foregoing solution of the embodiment of the present invention can be implemented, for example, in an ATM machine, a money counter, or the like.

[0086] In order to facilitate a better understanding of the technical solutions provided by the embodiments of the present invention, the principle of the embodiments of the present invention will be described below by way of an example.

[0087] First, in the horizontal direction 200DPI, vertical 15DPI, the front image size is Χ[1-1300], Υ[1-450], the first area position is Χ[300-800], Υ[85-120], The position of the two regions is Χ[300-800], Υ[345-380], and the position coordinates of X and 该 are represented by pixels.

[0088] Please refer to FIG. 2 to FIG. 9. FIG. 2 is an image with a value of 20,000 riels, FIG. 3 is an image with a value of 50,000 riels, and FIG. 4 is an image with a ri in value of 100,000 riels. Image with a value of 500,000 rials

[0089] As can be seen from FIG. 2, both the first region 10 and the second region 11 are relatively bright, and the first gray value mean1 of the first region 10 and the second gray value mean2 of the second region 11 are not much different. Therefore, the values of meanl and mean2 are larger.

, and relatively close.

[0090] As can be seen from FIG. 3, both the first region 20 and the second region 21 are relatively dark, and the first grayscale of the first region 20 The value mean1 and the second gray value mean2 of the second region 21 are not much different, so the values of meanl and mean2 are small.

, and relatively close.

[0091] As can be seen from FIG. 4, the first region 30 is brighter, the second region 31 is darker, and the first gray value mean1 of the first region 30 and the second gray value mean2 of the second region 11 are significantly different. Therefore meanl is greater than mean2.

[0092] As can be seen from FIG. 5, the first region 40 is darker, the second region 41 is brighter, and the first grayscale value mean1 of the first region 40 and the second grayscale value mean2 of the second region 41 are significantly different. Therefore meanl is smaller than mean2.

[0093] In Figure 6, there are four currency values of Imeanl-mean2l. It can be seen from 6 that the first region of the 50000 riyal and the 20000 riyal and the second region of the Imeanl-mean2l are relatively small, about 10;

[0094] Imeanl-mean2l of the first region and the second region of 100,000 riyals and 500,000 rials is relatively large, about 35 or more;

[0095] Setting the first threshold T 1 according to this feature can divide the banknote into 50,000 riyals and 20,000 riels.

Another category of 100,000 riyals and 500,000 rials.

[0096] For the first category, it can be seen from FIG. 7 that the average value of the first region of the 20,000 riyals is large.

110 or so; the first region of the 50000 riyal has a small grayscale average of about 20; by setting the second threshold T2, the two currency values can be divided.

[0097] In the second category, it can be seen from FIG. 8 and FIG. 9 that the meanl of 500,000 riels is much smaller than mean2, and the meanl of 100,000 riyals is much larger than mean2, whereby the two currencies can be distinguished. The specific judgment is as follows:

[0098] (1) lmeanl-mean2l<Tl, compare the size of meanl and T2, if:

[0099] a.meanl>T2, determine the face value of the banknote is 20,000 rials;

[0100] b. meanl < T2, determine the face value of the banknotes is 50,000 rials;

[0101] (2) lmeanl-mean2l>Tl, compare the size of meanl and mean2, if:

[0102] c meanl<mean2, determining that the banknote has a face value of 500,000 riels;

[0103] d. meanl>mean2, determining that the banknote has a face value of 100,000 riyals.

[0104] T1 is optional and suitable for about 25, and T2 is suitable for [60-70].

[0105] It can be seen that, in some feasible implementation manners of the present invention, the first image parameter of the first region of the image and the second image parameter of the second region are calculated according to the first image parameter and The second image parameter determines a face value of the currency, which helps to identify the face value of the currency of some countries, in particular It is Iranian currency. The algorithm can be designed according to the characteristics of the Iranian currency. It has strong pertinence and obvious and stable identification features. The algorithm has good simple effect and can identify the four large denominations of the current market. It can flexibly change Tl and Τ2 according to the needs. The recognition result is optimized.

[0106] Embodiment 2

[0107] In order to better implement the above-described aspects of the embodiments of the present invention, related apparatuses for cooperating to implement the above aspects are also provided below.

[0108] Referring to FIG. 10, an embodiment of the present invention provides a device for identifying a currency denomination, which may include:

[0109] The obtaining module 11 is configured to obtain an image of a currency, where the currency includes an Iranian currency;

[0110] a calculation module 12, configured to calculate a first image parameter of the first region of the image and a second image of the second region

[0111] The determining module 13 is configured to determine a face value of the currency according to the first image parameter and the second image parameter.

[0112] In an embodiment of the invention, the first image parameter is a first gray value, and the second image parameter is a second gray value.

[0113] When the first image parameter is the first gray value, the second image parameter is the second gray value 吋, [0114] the obtaining module 11 is specifically configured to acquire an image of the currency, where the currency includes Iranian currency;

[0115] The calculating module 12 is specifically configured to calculate a first gray value of the first region of the image and a second gray value of the second region;

[0116] The determining module 13 is specifically configured to determine a face value of the currency according to the first gray value and the second gray value.

[0117] In some embodiments of the invention, it helps to identify the face value of the currency of some countries, especially the Iranian currency. The algorithm can be designed according to the characteristics of the Iranian currency. It has strong pertinence and obvious and stable identification features. The algorithm has good simple effect and can identify the four large denominations of the current market. It can flexibly change Tl and Τ2 according to the needs. The recognition result is optimized.

[0118] the first gray value is an average gray value of the first region;

[0119] The second gray value is an average gray value of the second region.

[0120] when the currency is an Iranian currency, the determining module is specifically configured to: the absolute value of the difference between the first gray value and the second gray value is less than a preset first threshold, And the first gray value is greater than the pre Setting a second threshold 吋, determining that the face value of the currency is 20,000 riels; the absolute value of the difference between the first gradation value and the second gradation value is less than a preset first threshold, And the first gray value is smaller than a preset second threshold 吋, determining that the face value of the currency is 50,000 riels; the absolute difference between the first gradation value and the second gradation value The value is greater than a preset first threshold, and the first gray value is less than the second gray value 吋, determining that the face value of the currency is 500000 riels; at the first gray value and the The absolute value of the difference of the second gray value is greater than a first threshold set in advance, and the first gray value is greater than the second gray value, and the face value of the currency is determined to be 100,000 riels.

[0121] In an embodiment of the invention, the first image parameter is a first black dot value, and the second image parameter is a second black dot value.

[0122] The determining module 13 is specifically configured to determine a face value of the currency according to the first black dot value and the second black dot value of the first region.

[0123] It can be understood that the functions of the various functional modules of the device in the embodiments of the present invention may be specifically implemented according to the method in the foregoing method embodiments, and the specific implementation process may refer to the related description in the foregoing method embodiments, and details are not described herein again. .

[0124] It can be seen that, in some feasible implementation manners of the present invention, the first image parameter of the first region of the image and the second image parameter of the second region are calculated according to the first image parameter and The second image parameter determines the face value of the currency, which helps to identify the face value of the currency of some countries, especially the Iranian currency. The algorithm can be designed according to the characteristics of the Iranian currency. It has strong pertinence and obvious and stable identification features. The algorithm has good simple effect and can identify the four large denominations of the current market. It can flexibly change Tl and Τ2 according to the needs. The recognition result is optimized.

[0125] In the above embodiments, the descriptions of the various embodiments have different emphasis, and the parts that are not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0126] In summary, the method and apparatus for identifying currency face value according to an embodiment of the present invention, by calculating a first image parameter of a first region of the image and a second image parameter of the second region, according to the first image parameter and The second image parameter determines the face value of the currency, which helps to identify the face value of the currency of some countries, especially the Iranian currency.

[0127] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as one. The series of combinations of actions, but those skilled in the art will appreciate that the present invention is not limited by the order of the acts described, as some steps may be performed in other sequences or in the same manner in accordance with the present invention. In addition, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0128] Those skilled in the art can understand that all or part of the steps of the foregoing embodiments may be completed by a program to instruct related hardware, and the program may be stored in a computer readable storage medium, the storage medium. Can include: ROM, RAM. Disk or CD.

[0129] The method and device for identifying the currency denomination provided by the embodiment of the present invention are described in detail. The principles and embodiments of the present invention are described in the following. The description of the above embodiment is only for helping. The method of the present invention and its core idea are understood; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific embodiments and application scopes. It should not be construed as limiting the invention.

Claims

Claim

A method for identifying a currency denomination, which is characterized by comprising:

Obtaining an image of the currency, including the Iranian currency;

Calculating a first image parameter of the first region of the image and a second image parameter of the second region determining a face value of the currency based on the first image parameter and the second image parameter. The method according to claim 1, wherein the first image parameter is a first gray value and the second image parameter is a second gray value.

The method of claim 2, wherein

The first gray value is an average gray value of the first region;

The second gray value is an average gray value of the second region.

The method according to claim 2, wherein when the currency is an Iranian currency, the determining the face value of the currency according to the first image parameter and the second image parameter comprises:

Determining that the absolute value of the difference between the first gray value and the second gray value is less than a preset first threshold, and the first gray value is greater than a preset second threshold The face value of the currency is 20,000 rials;

Determining that the absolute value of the difference between the first gray value and the second gray value is less than a preset first threshold, and the first gray value is less than a preset second threshold The face value of the currency is 50,000 rials;

The absolute value of the difference between the first gray value and the second gray value is greater than a preset first threshold, and the first gray value is smaller than the second gray value, determining The face value of the currency is 500,000 rials;

The absolute value of the difference between the first gray value and the second gray value is greater than a preset first threshold, and the first gray value is greater than the second gray value, determining The face value of the currency is 100,000 riyals.

The method according to claim 1, wherein the first image parameter is a first black dot value, and the second image parameter is a second black dot value. A device for identifying currency denominations, comprising:

An acquisition module, configured to obtain an image of a currency, the currency including an Iranian currency;

a calculation module, configured to calculate a first image parameter of the first region of the image and a second image parameter of the second region;

And a determining module, configured to determine a face value of the currency according to the first image parameter and the second image parameter.

The device according to claim 6, wherein

The first image parameter is a first gray value, and the second image parameter is a second gray value. The device according to claim 7, wherein

The first gray value is an average gray value of the first region;

The second gray value is an average gray value of the second region.

The device according to claim 7, wherein

When the currency is an Iranian currency, the determining module is specifically configured to: the absolute value of the difference between the first gray value and the second gray value is less than a preset first threshold, and The first gradation value is greater than a preset second threshold 吋, determining that the face value of the currency is 2000 riels; the absolute value of the difference between the first gradation value and the second gradation value is less than Determining a first threshold, and the first gray value is less than a second threshold set in advance, determining that the face value of the currency is 50,000 riels; at the first gray value and the second gray The absolute value of the difference value of the degree value is greater than a preset first threshold value, and the first gray value is smaller than the second gray value 吋, determining that the face value of the currency is 500,000 riels; Determining the absolute value of the difference between a gray value and the second gray value is greater than a preset first threshold, and the first gray value is greater than the second gray value, determining a face value of the currency It is 100,000 riyals.

The device according to claim 6, wherein the first image parameter is a first black dot value, and the second image parameter is a second black dot value.