CN108022362B - Method and device for detecting defect of paper money - Google Patents
Method and device for detecting defect of paper money Download PDFInfo
- Publication number
- CN108022362B CN108022362B CN201610945652.1A CN201610945652A CN108022362B CN 108022362 B CN108022362 B CN 108022362B CN 201610945652 A CN201610945652 A CN 201610945652A CN 108022362 B CN108022362 B CN 108022362B
- Authority
- CN
- China
- Prior art keywords
- detected
- paper money
- points
- channel
- abnormal data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/16—Testing the dimensions
- G07D7/164—Thickness
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The embodiment of the invention discloses a method and a device for detecting paper currency defects. The method comprises the following steps: extracting thickness data of all channels of the paper money to be detected; respectively searching abnormal data points of which the values are smaller than a first thickness threshold value in the thickness data of each channel, and recording the position information of the abnormal data points; and determining the continuous points of the abnormal data points according to the position information, comparing the continuous points with a first point threshold or a second point threshold, and determining the defect condition of the paper money to be detected according to the comparison result. Through the technical scheme, the defect detection of the paper money is realized by using the thickness data of the paper money to be detected, and the defect recognition rate of the paper money can be improved.
Description
Technical Field
The embodiment of the invention relates to a paper money processing technology, in particular to a method and a device for detecting paper money defects.
Background
Banknotes that are circulated for a long time in the market are difficult to avoid having a defect, which is not favorable for identifying the banknotes in the process of checking the banknotes, so that the defect detection of the banknotes is necessary.
In the prior art, the defect of the paper currency is basically detected by analyzing a reflectivity image of a certain wave band of the paper currency. For example, after acquiring the infrared reflectance image of the bill, the area of the infrared reflectance image of the bill is analyzed and compared with the area of a normal bill, thereby determining whether the bill is defective. Or carrying out edge detection on the infrared reflectivity image of the paper currency, and comparing the detected edge with the edge of the normal paper currency so as to determine whether the paper currency is defective or not. However, the above technical solution has limited recognition of defective banknotes, which may cause some false recognition, for example, a banknote with a folded corner is mistaken for a defective banknote.
Disclosure of Invention
The embodiment of the invention provides a method and a device for detecting a paper currency defect, which are used for detecting the paper currency defect by using thickness data of paper currency and improving the recognition rate of the paper currency defect.
In a first aspect, an embodiment of the present invention provides a method for detecting a defect of a banknote, including the following steps:
extracting thickness data of all channels of the paper money to be detected;
respectively searching abnormal data points of which the values are smaller than a first thickness threshold value in the thickness data of each channel, and recording the position information of the abnormal data points;
and determining the continuous points of the abnormal data points according to the position information, comparing the continuous points with a first point threshold or a second point threshold, and determining the defect condition of the paper money to be detected according to the comparison result.
The continuous counting comprises longitudinal continuous counting and transverse continuous counting, wherein the longitudinal direction is the short side direction of the paper money to be detected, and the transverse direction is the long side direction of the paper money to be detected.
Further, the location information includes a row number and a channel number of the abnormal data point; the longitudinal continuous points are the points of the abnormal data points in a single channel; the number of the transverse continuous points is the number of the abnormal data points of the channel corresponding to the channel number and the adjacent channel of the channel number which are continuously appeared between one or two line numbers before and after the line number.
Optionally, determining the number of consecutive abnormal data points according to the position information, comparing the number of consecutive data points with a first number threshold or a second number threshold, and determining the defect condition of the banknote to be detected according to the comparison result includes:
a. determining whether longitudinal continuous points exist in the paper money to be detected according to the position information of the abnormal data points in the single channel;
b. if the longitudinal continuous points exist in the paper money to be detected and are greater than or equal to the first point threshold value, determining that longitudinal defects exist in the paper money to be detected; and/or the presence of a gas in the gas,
c. if the longitudinal continuous counting number does not exist in the paper money to be detected or the longitudinal continuous counting number is smaller than the first counting threshold value, determining whether the transverse continuous counting number exists in the paper money to be detected according to the position information of the abnormal data point in the single channel;
d. and if the transverse continuous points exist in the paper money to be detected and the transverse continuous points are greater than or equal to the second point threshold value, determining that transverse defects exist in the paper money to be detected.
And repeating the steps a-d until defect detection is completed on the paper money area to be detected corresponding to each single channel.
Optionally, after extracting the thickness data of all the channels of the banknote to be detected, and before respectively searching for an abnormal data point with a value smaller than a first thickness threshold in the thickness data of each channel, and recording the position information of the abnormal data point, the method further includes:
determining a mean value of the thickness data of each channel;
and if the average value is smaller than a second thickness threshold value, determining that the paper money to be detected has serious defects, wherein the serious defects mean that the defect area accounts for at least one third of the area of the paper money to be detected.
In a second aspect, an embodiment of the present invention further provides a device for detecting a defective banknote, where the device includes:
the thickness data extraction module is used for extracting the thickness data of all channels of the paper money to be detected;
the abnormal data point searching module is used for respectively searching abnormal data points of which the values are smaller than a first thickness threshold value in the thickness data of each channel and recording the position information of the abnormal data points;
and the first defect detection module is used for determining the continuous points of the abnormal data points according to the position information, comparing the continuous points with a first point threshold value or a second point threshold value, and determining the defect condition of the paper money to be detected according to the comparison result.
The continuous counting comprises longitudinal continuous counting and transverse continuous counting, wherein the longitudinal direction is the short side direction of the paper money to be detected, and the transverse direction is the long side direction of the paper money to be detected.
Further, the location information includes a row number and a channel number of the abnormal data point; the longitudinal continuous points are the points of the abnormal data points in a single channel; the number of the transverse continuous points is the number of the abnormal data points of the channel corresponding to the channel number and the adjacent channel of the channel number which are continuously appeared between one or two line numbers before and after the line number.
Optionally, the first defect detection module is specifically configured to:
a. determining whether longitudinal continuous points exist in the paper money to be detected according to the position information of the abnormal data points in the single channel;
b. if the longitudinal continuous points exist in the paper money to be detected and are greater than or equal to the first point threshold value, determining that longitudinal defects exist in the paper money to be detected; and/or the presence of a gas in the gas,
c. if the longitudinal continuous counting number does not exist in the paper money to be detected or the longitudinal continuous counting number is smaller than the first counting threshold value, determining whether the transverse continuous counting number exists in the paper money to be detected according to the position information of the abnormal data point in the single channel;
d. and if the transverse continuous points exist in the paper money to be detected and the transverse continuous points are greater than or equal to the second point threshold value, determining that transverse defects exist in the paper money to be detected.
And repeating the steps a-d until defect detection is completed on the paper money area to be detected corresponding to each single channel.
Optionally, on the basis of the above apparatus, the apparatus further includes:
the thickness mean value determining module is used for determining the mean value of the thickness data of each channel after the thickness data of all channels of the paper money to be detected are extracted, and before abnormal data points with the value smaller than a first thickness threshold value in the thickness data of each channel are respectively searched and the position information of the abnormal data points is recorded;
and the second defect detection module is used for determining that the paper money to be detected has serious defects if the average value is smaller than a second thickness threshold, wherein the serious defects mean that the defect area at least accounts for one third of the area of the paper money to be detected.
According to the embodiment of the invention, the thickness data of the paper money to be detected is acquired, the thickness data of each channel is compared with the first thickness threshold, the abnormal data point and the position information thereof are determined according to the comparison result, then the continuous number of the abnormal points of the data is determined according to the position information and is compared with the first number threshold or the second number threshold, and the defect condition of the paper money to be detected is determined according to the comparison result, so that the defect detection of the paper money is realized by using the thickness data of the paper money to be detected, and the defect identification rate of the paper money can be improved.
Drawings
FIG. 1 is a flow chart of a method for detecting a defective banknote in accordance with one embodiment of the present invention;
fig. 2a is a schematic diagram of a thickness sensor collecting original thickness data of a banknote during a banknote feeding process according to a first embodiment of the present invention;
FIG. 2b is a schematic diagram of raw thickness data of a banknote collected by a thickness sensor according to a first embodiment of the present invention;
FIG. 3 is a flowchart of a method for detecting a defective banknote according to a second embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a banknote defect detection apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a banknote defect detection apparatus according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for detecting a defective banknote according to an embodiment of the present invention, which may be performed by a defective banknote detecting apparatus, which may be implemented by software and/or hardware, and which may be integrated into any financial device capable of performing banknote recognition, such as a banknote validator, a banknote counter or a sorter. The method specifically comprises the following steps:
and S110, extracting thickness data of all channels of the paper money to be detected.
Specifically, the original thickness data of all channels of the paper money to be detected, which are acquired by the thickness sensor, are acquired. Because the original thickness data includes the thickness data of the paper money acquired by the thickness sensor when the paper money to be detected passes through and the thickness data of the background acquired by the thickness sensor when no paper money passes through, the original thickness data of all the channels needs to be denoised to obtain the thickness data of the paper money to be detected of all the channels.
Referring to fig. 2a, a row of sensor units 202 arranged side by side in the thickness sensor 201 is provided, and one sensor unit 202 corresponds to one channel 203, so the thickness sensor 201 shown in fig. 2a and including 10 sensor units 202 can be referred to as a 10-channel thickness sensor, and all channels are numbered as 1, 2, …, 9 and 10 in sequence according to the numbering direction 204. The banknote 205 to be detected passes through the thickness sensors 201 along the banknote entering direction 206 in the figure, each sensor unit 202 collects a relatively independent one-dimensional raw thickness data, and then 10 raw thickness signals can be collected by the 10-channel thickness sensor. The bill 205 to be detected may be a normal bill, or an abnormal bill adhered with an adhesive tape, having a folded corner, or having a defect. Fig. 2b is a schematic diagram of 10 original thickness data of normal paper money collected by the thickness sensor 201, and it can be seen that each numbered sensor unit corresponds to a line, the line is the original thickness data detected by the sensor unit, and a connecting line perpendicular to a position coordinate line of the paper money between two adjacent lines is not the thickness data, but is only a connecting line for data display, and has no practical significance.
From fig. 2b, it can be seen that the raw thickness data includes thickness data 207 of the banknote collected by the thickness sensor when the banknote to be detected passes in the middle and thickness data 208 of the background collected by the thickness sensor when no banknote passes on both sides. Therefore, the thickness data 207 of the paper money to be detected in the original thickness data is extracted by performing denoising processing on the acquired original thickness data of all the channels, that is, the thickness data of all the channels of the paper money to be detected is extracted.
S120, respectively searching abnormal data points of which the values are smaller than a first thickness threshold value in the thickness data of each channel, and recording the position information of the abnormal data points.
The first thickness threshold is an empirical thickness value used for judging whether an abnormal data point exists in the thickness data of the paper money to be detected, and is generally an empirical thickness value obtained by performing a large number of mean statistics on the thickness data of defective paper money and the thickness data of normal paper money, for example, the first thickness threshold can be empirically valued to be a value not less than 30% of the mean value of the thickness data of normal paper money. The abnormal data points refer to thickness data points at which the thickness value at the position is smaller than the average thickness data value of the normal banknote at the same position or the average thickness data value of the normal banknote is smaller than a first thickness threshold value. The position information is the position of the abnormal data point in the thickness data of all the channels of the paper money to be detected, such as the information of the abnormal data point in the fourth channel of the thickness data and the specific row in the channel.
Specifically, a single-channel thickness data is extracted from the thickness data of all channels of the banknote to be detected, which is obtained in step S110, the thickness value of each thickness data point of the single channel is compared with the first thickness threshold, and the position information of all thickness data points of which the thickness values are smaller than the first thickness threshold in the comparison result is recorded, that is, the search and the record of the single-channel abnormal data point are completed. And according to the process, searching and recording the abnormal data points of each single-channel thickness data until all the channels finish searching and recording the abnormal data points.
S130, determining the continuous points of the abnormal data points according to the position information, comparing the continuous points with a first point threshold value or a second point threshold value, and determining the defect condition of the paper money to be detected according to the comparison result.
Wherein, the continuous points refer to the points of the thickness data points which are adjacent in sequence. Illustratively, the continuous counting includes a longitudinal continuous counting and a transverse continuous counting, the longitudinal direction is a short side direction of the bill to be detected, and the transverse direction is a long side direction of the bill to be detected. The location information includes the row number and channel number of the outlier data point. The number of longitudinally consecutive points is the number of consecutive occurrences of an abnormal data point within a single channel. The number of the transverse continuous points is the number of the abnormal data points which are continuously appeared between one or two line numbers before and after the line number of the channel corresponding to the channel number where the abnormal data point is located and the adjacent channel thereof.
The first point threshold is an empirical value for determining whether or not an abnormal data point constitutes a longitudinal defect, and is generally determined by performing a large number of experimental statistics on the number of thickness data points corresponding to a longitudinal defect and the defect in a defective banknote, and may be empirically set to 3 data points, for example. The second point threshold value corresponds to the first point threshold value, but is an empirical value for determining whether or not the abnormal data point constitutes a lateral defect, and is generally determined by performing a large number of experimental statistics on the number of thickness data points corresponding to the lateral defect in the defective banknote, and may be set to 5 data points empirically, for example. The first point threshold value and the second point threshold value are related to the mechanical structure of the thickness sensor, and specifically, the determination of the first point threshold value and the second point threshold value depends on the sampling frequency of the thickness sensor. For example, the sampling rate of the general-purpose 10-channel thickness sensor in fig. 2a in the short side direction of the banknote to be detected is 90 data points, and the first point threshold is set to 3 data points. However, if the sampling rate of the thickness sensor in the short side direction of the banknote to be detected is changed to 180 data points, the first point threshold value is set to 6 data points, and then empirical adjustment is performed according to a large number of experimental statistical results, for example, the first point threshold value is empirically adjusted to 5 data points or 7 data points.
Specifically, if it is determined in step S120 that there is no abnormal data point in the thickness data of all the channels of the banknote to be detected, there is no defect in the banknote to be detected. Otherwise, according to the position information of the abnormal data points recorded in step S120, the number of consecutive abnormal data points is determined, that is, the number of consecutive abnormal data points is determined to be the longitudinal consecutive number or the transverse consecutive number, and then the longitudinal consecutive number is compared with the first number threshold, or the transverse consecutive number is compared with the second number threshold, and the defect condition of the banknote to be detected, that is, whether the banknote to be detected is defective, the defect degree in the case of defective banknote, and whether the banknote to be detected is defective longitudinally or transversely, is determined according to the comparison result.
Optionally, on the basis of the above technical solution, after step S110 and before step S120, the method for detecting a banknote defect according to the embodiment of the present invention further includes: determining a mean value of the thickness data of each channel; and if the average value is smaller than a second thickness threshold value, determining that the paper money to be detected has serious defects, wherein the serious defects mean that the defect area accounts for at least one third of the area of the paper money to be detected.
The second thickness threshold is an empirical thickness value used for judging whether the paper money to be detected has serious defects, and is generally an empirical thickness value obtained by performing a large number of mean statistics on thickness data of the paper money with the serious defects and thickness data of normal paper money, for example, the second thickness threshold may be empirically set to a value not less than 50% of the mean value of the thickness data of the normal paper money. A severe defect is one in which the area of the defect is at least one third of the area of the note to be tested. For example, if the number of consecutive points is 30 or more, based on the general 10-channel thickness sensor in fig. 2a, it is considered that there is a serious defect in the bill.
Specifically, each piece of single-channel thickness data is extracted from the thickness data of all the channels of the banknote to be detected acquired in step S110, and the mean value of the single-channel thickness data is calculated. And then comparing the average value with a second thickness threshold value, and if the average value is smaller than the second thickness threshold value, determining that serious defects exist in the paper money area to be detected corresponding to the single channel. And (4) according to the process, detecting the severe defect of the paper money region to be detected corresponding to each single channel. If it is determined that the severe defect exists in the region of the paper money to be detected corresponding to at least one single channel in the process, the severe defect exists in the paper money to be detected, and the defect detection of the paper money to be detected is finished. Otherwise, if it is determined that no serious defect exists in the banknote to be detected corresponding to all the single channels in the process, the banknote to be detected does not have a serious defect, and the step S120 and the subsequent steps are continuously executed. The method has the advantages that when the paper money to be detected has serious defects, the existence of the serious defects can be judged only by carrying out mean value calculation on the thickness data of each single channel, the abnormal data points do not need to be searched one by one, then the existence of longitudinal continuous points and/or transverse continuous points is judged, the defect condition of the paper money to be detected is judged on the basis of the abnormal data points, and the data operation amount and the data processing time can be reduced.
It should be understood that the scheme for detecting serious defects is only a simpler and faster defect detection method, which is generally performed before the above technical scheme, and when the scheme for detecting serious defects determines that no serious defects exist in the paper money to be detected, the steps S120 to S130 are continued to detect other defect conditions. Of course, the technical solutions of step S110 to step S130 may be directly executed without executing the solution of detecting a serious defect to detect the defect condition of the bill to be detected.
According to the technical scheme, the thickness data of the paper money to be detected is acquired, the thickness data of each single channel is compared with the first thickness threshold, the abnormal data points and the position information of the abnormal data points are determined according to the comparison result, then the continuous number of the abnormal data points is determined according to the position information, the abnormal data points are compared with the first number threshold or the second number threshold, the defect condition of the paper money to be detected is determined according to the comparison result, the defect detection of the paper money is achieved by using the thickness data of the paper money to be detected, and the defect identification rate of the paper money can be improved.
Example two
Fig. 3 is a flowchart of a method for detecting a defective banknote according to a second embodiment of the present invention, and the present embodiment optimizes step S130 to step S330 to step S380 based on the above embodiment. Wherein, the same steps as those in the above embodiments are denoted by the same reference numerals, and explanations of the same or corresponding terms as those in the above embodiments are omitted. A method for detecting a banknote defect according to a second embodiment of the present invention is described below with reference to fig. 3, where the method of this embodiment includes:
and S110, extracting thickness data of all channels of the paper money to be detected.
S120, respectively searching abnormal data points of which the values are smaller than a first thickness threshold value in the thickness data of each channel, and recording the position information of the abnormal data points.
S330, determining whether longitudinal continuous points exist in the paper money to be detected according to the position information of the abnormal data points in the single channel.
Specifically, in step S120, specific position information of an abnormal data point in each single-channel thickness data has been recorded, for example, the abnormal data point is located in the several rows of the several channels, and then, according to this position information in the single channel, it is searched whether the row numbers of the abnormal data points located in the same channel number in the banknote to be detected are consecutive. If the row numbers of the abnormal data points in the same channel number are continuous, counting the continuous number of the abnormal data points, wherein the number is the longitudinal continuous number in the channel number, namely determining whether the longitudinal continuous number exists in the paper money to be detected according to the position information of the abnormal data points in the single channel. Otherwise, no longitudinal continuous counting number exists in the paper money to be detected.
For example, the row numbers for the thickness data points within each channel of the general 10-channel thickness sensor shown in FIG. 2a are from 1 to 90. If the row numbers of the abnormal data points in the channel with the channel number of 1 are respectively 80, 81, 85, 86, 87 and 88, then the abnormal data points with the row numbers of 80 and 81 can be determined as a longitudinal continuous point, and the longitudinal continuous point has 2 total abnormal data points, and the longitudinal continuous point is 2 and can be called as a first longitudinal continuous point; meanwhile, the abnormal data points having the line numbers 85, 86, 87, and 88 are another longitudinally consecutive point, which has a total of 4 abnormal data points, and the longitudinally consecutive point number is 4, which may be referred to as a second longitudinally consecutive point number. That is, there are a total of 2 longitudinally consecutive points within a channel with channel number 1: the number of first longitudinal continuation points is 2 and the number of second longitudinal continuation points is 4.
S340, if the longitudinal continuous points exist in the paper money to be detected and are more than or equal to the first point threshold value, determining that longitudinal defects exist in the paper money to be detected.
The defect refers to a missing part in the paper money, and the defect can be a mild defect with the defect area accounting for less than one fifth of the area of the paper money to be detected or a severe defect. For example, with reference to the general 10-channel thickness sensor in fig. 2a, if the number of consecutive abnormal data points is within 18, it can be considered that there is a slight defect in the banknote.
Specifically, if it is determined in step S330 that the number of longitudinal continuous points exists in the single-channel thickness data, and the number of longitudinal continuous points is greater than or equal to the first point threshold value, it may be determined that a longitudinal defect exists in the banknote to be detected region corresponding to the single channel. For example, the preferred first point threshold in step S130 is 3 data points, and for the first longitudinal continuous point and the second longitudinal continuous point in the channel with channel number 1 in step S330, the first longitudinal continuous point is 2, which is smaller than the first point threshold, so that there is no longitudinal defect; and for the second longitudinal continuous point, the number is larger than the first point threshold value, so that it is determined that the banknote to be detected has a longitudinal defect at the position, that is, if the banknote to be detected 205 in fig. 2a is taken as a reference, it can be determined that the lower left corner region of the banknote to be detected has a longitudinal defect.
S350, if the longitudinal continuous counting number does not exist in the paper money to be detected, or the longitudinal continuous counting number is smaller than the first counting threshold value, determining whether the transverse continuous counting number exists in the paper money to be detected according to the position information of the abnormal data point in the single channel.
Specifically, if it is determined in step S330 that there are no longitudinal continuous points in the single-channel thickness data of the banknote to be detected, or it is determined in step S330 that there are longitudinal continuous points in the single-channel thickness data of the banknote to be detected, but it is determined in step S340 that the longitudinal continuous points are smaller than the first point threshold, it may be determined that there is no longitudinal defect in the corresponding region of the single channel in the banknote to be detected. At this time, according to the row number and the channel number of the abnormal data point recorded in step S120, the abnormal data point between one or two row numbers before and after the row number is searched in the single channel and the adjacent channel thereof, and whether the row number of the searched abnormal data point is continuous is judged, so as to determine whether the number of the horizontal continuous points exists in the paper money to be detected. That is, if no abnormal data point is found in the adjacent channel, no transverse continuous point exists in the paper money to be detected; if one or two abnormal data points are found between the line numbers before and after the line number in the adjacent channel and the line numbers are continuous, determining that the transverse continuous points exist in the paper money to be detected, counting the total number of the abnormal data points found in the single channel and the adjacent channel, wherein the total number is the transverse continuous points in the paper money to be detected.
For example, if the positions of the abnormal data points in the channel with channel number 1 are only at the line number 80 and the line number 81, it is determined that there is no longitudinal defect in the banknote to be detected according to step S330. At this time, it is searched for whether there is an abnormal data point between the row number 79 to the row number 82 or between the row number 78 to the row number 83 within the channel of the channel number 2. If no abnormal data point exists at the position, no transverse continuous points exist in the to-be-detected paper money area corresponding to the channel number 1 and the channel number 2. If the row numbers of the abnormal data points in the channel with the channel number 2 are 78 and 82 respectively, the adjacent channel of the channel number 1 has the abnormal data points, but the row numbers are discontinuous, so that the transverse continuous points do not exist in the to-be-detected banknote area corresponding to the channel number 1 and the channel number 2. If the row numbers of the abnormal data points in the channel with the channel number of 2 are respectively 79, 80, 81 and 82, the adjacent channels of the channel number 1 not only have abnormal data points, but also the row numbers of the abnormal data points in the two adjacent channels are continuous, so that the transverse continuous points exist in the region of the paper money to be detected corresponding to the channel numbers 1 and 2, the total number of the abnormal data points in the channel numbers 1 and 2 is counted to be 6, and the transverse continuous points in the paper money to be detected are determined to be 6.
And S360, if the transverse continuous points exist in the paper money to be detected and the transverse continuous points are larger than or equal to the second point threshold value, determining that the transverse defect exists in the paper money to be detected.
Specifically, if it is determined in step S350 that the number of horizontal consecutive dots exists in the banknote to be detected, the number of horizontal consecutive dots is compared with the second threshold value, and if the number of horizontal consecutive dots is greater than or equal to the second threshold value as a result of the comparison, it is determined that a horizontal defect exists in the banknote to be detected, and the horizontal defect may be a mild defect or a severe defect. And if the transverse continuous points are smaller than the second point threshold value as a comparison result, determining that the transverse defect does not exist in the paper money to be detected.
For example, if there are horizontal consecutive points in step S350, that is, the positions of the abnormal data points in channel number 1 are at line number 80 and line number 81, the line numbers in channel number 2 are 79, 80, 81, and 82, respectively, and the corresponding horizontal consecutive points are 6, which is greater than the preferred second point threshold value 5 in step S130, it is determined that there is a horizontal defect in the banknote to be detected corresponding to channel number 1.
And S370, judging whether defect detection is finished on the to-be-detected paper money area corresponding to each single channel.
Specifically, the steps S330 to S360 are to perform the detection process of the longitudinal defect or the transverse defect of the banknote to be detected for a single channel, and in the embodiment of the present invention, the banknote defect detection is performed for all channels of the banknote to be detected, so after the steps S330 to S360 are performed, it is necessary to determine whether the banknote defect detection is completed for the banknote region to be detected corresponding to each single channel. And if the detected paper money region corresponding to the single channel without defect detection exists after the judgment, jumping to the step S330, continuing to execute the step S360, and then performing detection on whether the defect detection is finished on the paper money region to be detected corresponding to each single channel, and repeating the steps until the defect detection is finished on the paper money region to be detected corresponding to each single channel.
And S380, finishing the defect detection of the paper money to be detected, and carrying out the defect detection of the next paper money to be detected.
Specifically, when it is determined in step S370 that the defect detection is completed for each banknote to be detected region corresponding to a single channel, which indicates that the defect detection for the banknote to be detected is completed, the defect detection for the banknote to be detected is ended, and the defect detection for the next banknote to be detected is performed.
It should be noted that whether step S350 and step S360 are executed or not is not limited herein, for example, step S350 and step S360 may not be executed, and only the banknote to be detected corresponding to a single channel is detected, whether a longitudinal defect exists or not is detected, and the detection of a transverse defect is not performed. Of course, the steps S350 and S360 may also be executed sequentially after the step 330, at this time, the longitudinal defect is detected first, and when there is no longitudinal defect in the banknote region to be detected corresponding to the single channel, whether there is a transverse defect in the banknote region to be detected corresponding to the single channel and the adjacent channel is further detected.
According to the technical scheme of the embodiment, abnormal data points and position information of the abnormal data points are determined by obtaining thickness data of paper money to be detected, comparing the thickness data of a single channel with a first thickness threshold value, then determining longitudinal continuous points in the single channel according to the position information, comparing the longitudinal continuous points with a first point threshold value to detect longitudinal defects in the paper money to be detected, when no longitudinal defects exist in the paper money to be detected, determining transverse continuous points in adjacent channels according to the position information, comparing the transverse continuous points with a second point threshold value to detect transverse defects in the paper money to be detected, and forming a cycle operation by the processes until defect detection is completed on a paper money region to be detected corresponding to each single channel, namely defect detection is completed on the whole paper money to be detected, so that the paper money defect detection is realized by using the thickness data of the paper money to be detected, the recognition rate of the defect of the paper money can be improved.
EXAMPLE III
Fig. 4 is a schematic structural diagram of a banknote defect detection apparatus according to a third embodiment of the present invention, and the same or corresponding terms as those in any of the above embodiments in this embodiment are not repeated herein. The apparatus may include:
and the thickness data extraction module 410 is used for extracting the thickness data of all channels of the paper money to be detected.
The abnormal data point searching module 440 is configured to search for an abnormal data point, of which a value is smaller than a first thickness threshold, in the thickness data of each of the channels extracted by the thickness data extracting module 410, and record position information of the abnormal data point.
The first defect detection module 450 is configured to determine the number of consecutive points of the abnormal data points according to the position information recorded by the abnormal data point search module 440, compare the number of consecutive points with a first point threshold or a second point threshold, and determine the defect condition of the banknote to be detected according to the comparison result.
The continuous counting comprises longitudinal continuous counting and transverse continuous counting, wherein the longitudinal direction is the short side direction of the paper money to be detected, and the transverse direction is the long side direction of the paper money to be detected. The position information comprises a row number and a channel number of the abnormal data point; the longitudinal continuous points are the points of the abnormal data points in a single channel; the number of the transverse continuous points is the number of the abnormal data points of the channel corresponding to the channel number and the adjacent channel of the channel number which are continuously appeared between one or two line numbers before and after the line number.
By the paper currency defect detection device, the paper currency defect detection is realized by using the thickness data of the paper currency to be detected, and the recognition rate of the paper currency defect is improved.
The device for detecting the defect of the paper currency, provided by the embodiment of the invention, can execute the method for detecting the defect of the paper currency, provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 5 is a schematic structural diagram of a banknote defect detection apparatus according to a fourth embodiment of the present invention, which is specifically described and optimized based on the foregoing embodiments. Wherein, the figure units same as the above embodiments are provided with the same reference numerals, and the explanation of the same or corresponding terms as any of the above embodiments is not repeated herein. The apparatus of this embodiment may include:
and the thickness data extraction module 410 is used for extracting the thickness data of all channels of the paper money to be detected.
A thickness mean determination module 420 for determining a mean of the thickness data of each of all the channels extracted by the thickness data extraction module 410;
the second defect detecting module 430 is configured to determine that a severe defect exists in the banknote to be detected if the thickness data mean value of at least one single channel exists in the thickness data mean value of each channel determined by the thickness mean value determining module 420 and is smaller than a second thickness threshold, where the severe defect is a defect whose area is at least one third of the area of the banknote to be detected.
The abnormal data point searching module 440 is configured to search, when the second defect detecting module 430 determines that there is no serious defect in the banknote to be detected, the abnormal data points whose value is smaller than the first thickness threshold value in the thickness data of each of the channels extracted by the thickness data extracting module 410, and record position information of the abnormal data points.
The first defect detection module 450 is specifically configured to:
a. determining whether longitudinal continuous points exist in the paper money to be detected according to the position information of the abnormal data points in the single channel;
b. if the longitudinal continuous points exist in the paper money to be detected and are greater than or equal to the first point threshold value, determining that longitudinal defects exist in the paper money to be detected; and/or the presence of a gas in the gas,
c. if the longitudinal continuous counting number does not exist in the paper money to be detected or the longitudinal continuous counting number is smaller than the first counting threshold value, determining whether the transverse continuous counting number exists in the paper money to be detected according to the position information of the abnormal data point in the single channel;
d. and if the transverse continuous points exist in the paper money to be detected and the transverse continuous points are greater than or equal to the second point threshold value, determining that transverse defects exist in the paper money to be detected.
And repeating the steps a-d until defect detection is completed on the paper money area to be detected corresponding to each single channel.
The paper money defect detection device of the fourth embodiment of the invention realizes the detection of paper money defects by using the thickness data of the paper money to be detected in two steps, namely, the detection of serious defects is firstly carried out by using the thickness data mean value of each channel, and when no serious defects exist in the paper money to be detected, the defect condition of the paper money to be detected is judged by using longitudinal continuous counting and/or transverse continuous counting, so that the data processing time can be effectively shortened, and the recognition rate of the paper money defects is improved.
The device for detecting the defect of the paper currency, provided by the embodiment of the invention, can execute the method for detecting the defect of the paper currency, provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (6)
1. A method for detecting a defective banknote, comprising:
extracting thickness data of all channels of the paper money to be detected;
respectively searching abnormal data points of which the values are smaller than a first thickness threshold value in the thickness data of each channel, and recording the position information of the abnormal data points;
determining the continuous points of the abnormal data points according to the position information, comparing the continuous points with a first point threshold or a second point threshold, and determining the defect condition of the paper money to be detected according to the comparison result;
the continuous counting comprises longitudinal continuous counting and transverse continuous counting, wherein the longitudinal direction is the short side direction of the paper money to be detected, and the transverse direction is the long side direction of the paper money to be detected;
the position information comprises a line number and a channel number of the abnormal data point;
the longitudinal continuous points are the points of the abnormal data points in a single channel;
the number of the transverse continuous points is the number of the abnormal data points of the channel corresponding to the channel number and the adjacent channel of the channel number which are continuously appeared between one or two line numbers before and after the line number.
2. The method according to claim 1, wherein the determining the continuous points of the abnormal data points according to the position information and comparing the continuous points with a first point threshold or a second point threshold, and the determining the defect condition of the paper money to be detected according to the comparison result comprises:
a. determining whether longitudinal continuous points exist in the paper money to be detected according to the position information of the abnormal data points in the single channel;
b. if the longitudinal continuous points exist in the paper money to be detected and are greater than or equal to the first point threshold value, determining that longitudinal defects exist in the paper money to be detected; and/or the presence of a gas in the gas,
c. if the longitudinal continuous counting number does not exist in the paper money to be detected or the longitudinal continuous counting number is smaller than the first counting threshold value, determining whether the transverse continuous counting number exists in the paper money to be detected according to the position information of the abnormal data point in the single channel;
d. if the transverse continuous points exist in the paper money to be detected and the transverse continuous points are larger than or equal to the second point threshold value, determining that transverse defects exist in the paper money to be detected;
and repeating the steps a-d until defect detection is completed on the paper money area to be detected corresponding to each single channel.
3. The method according to claim 1, wherein after the extracting of the thickness data of all the channels of the paper money to be detected, and before the searching of the abnormal data points with the value smaller than the first thickness threshold value in the thickness data of each channel and the recording of the position information of the abnormal data points, the method further comprises:
determining a mean value of the thickness data of each channel;
and if the average value is smaller than a second thickness threshold value, determining that the paper money to be detected has serious defects, wherein the serious defects mean that the defect area accounts for at least one third of the area of the paper money to be detected.
4. A defective banknote detection apparatus, comprising:
the thickness data extraction module is used for extracting the thickness data of all channels of the paper money to be detected;
the abnormal data point searching module is used for respectively searching abnormal data points of which the values are smaller than a first thickness threshold value in the thickness data of each channel and recording the position information of the abnormal data points;
the first defect detection module is used for determining the continuous points of the abnormal data points according to the position information, comparing the continuous points with a first point threshold value or a second point threshold value, and determining the defect condition of the paper money to be detected according to the comparison result;
the continuous counting comprises longitudinal continuous counting and transverse continuous counting, wherein the longitudinal direction is the short side direction of the paper money to be detected, and the transverse direction is the long side direction of the paper money to be detected;
the position information comprises a line number and a channel number of the abnormal data point;
the longitudinal continuous points are the points of the abnormal data points in a single channel;
the number of the transverse continuous points is the number of the abnormal data points of the channel corresponding to the channel number and the adjacent channel of the channel number which are continuously appeared between one or two line numbers before and after the line number.
5. The apparatus of claim 4, wherein the first defect detection module is specifically configured to:
a. determining whether longitudinal continuous points exist in the paper money to be detected according to the position information of the abnormal data points in the single channel;
b. if the longitudinal continuous points exist in the paper money to be detected and are greater than or equal to the first point threshold value, determining that longitudinal defects exist in the paper money to be detected; and/or the presence of a gas in the gas,
c. if the longitudinal continuous counting number does not exist in the paper money to be detected or the longitudinal continuous counting number is smaller than the first counting threshold value, determining whether the transverse continuous counting number exists in the paper money to be detected according to the position information of the abnormal data point in the single channel;
d. if the transverse continuous points exist in the paper money to be detected and the transverse continuous points are larger than or equal to the second point threshold value, determining that transverse defects exist in the paper money to be detected;
and repeating the steps a-d until defect detection is completed on the paper money area to be detected corresponding to each single channel.
6. The apparatus of claim 4, further comprising:
the thickness mean value determining module is used for determining the mean value of the thickness data of each channel after the thickness data of all channels of the paper money to be detected are extracted, and before abnormal data points with the value smaller than a first thickness threshold value in the thickness data of each channel are respectively searched and the position information of the abnormal data points is recorded;
and the second defect detection module is used for determining that the paper money to be detected has serious defects if the average value is smaller than a second thickness threshold, wherein the serious defects mean that the defect area at least accounts for one third of the area of the paper money to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610945652.1A CN108022362B (en) | 2016-11-02 | 2016-11-02 | Method and device for detecting defect of paper money |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610945652.1A CN108022362B (en) | 2016-11-02 | 2016-11-02 | Method and device for detecting defect of paper money |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108022362A CN108022362A (en) | 2018-05-11 |
| CN108022362B true CN108022362B (en) | 2020-03-27 |
Family
ID=62069950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610945652.1A Active CN108022362B (en) | 2016-11-02 | 2016-11-02 | Method and device for detecting defect of paper money |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108022362B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101449299A (en) * | 2006-07-21 | 2009-06-03 | 光荣株式会社 | A deformed coin detecting device |
| JP2009129390A (en) * | 2007-11-28 | 2009-06-11 | Oki Electric Ind Co Ltd | Medium discrimination device |
| CN101788280A (en) * | 2010-02-11 | 2010-07-28 | 浙江金利电子有限公司 | Device for identifying banknote thickness abnormity through ultrasonic wave and method thereof |
| CN103617671A (en) * | 2013-12-12 | 2014-03-05 | 广州广电运通金融电子股份有限公司 | Method and system for recognizing bill with abnormal thickness |
| CN105354912A (en) * | 2015-09-14 | 2016-02-24 | 深圳怡化电脑股份有限公司 | Method and device of banknote detection |
| WO2016088279A1 (en) * | 2014-12-05 | 2016-06-09 | グローリー株式会社 | Paper sheet thickness determination method and thickness determination device |
-
2016
- 2016-11-02 CN CN201610945652.1A patent/CN108022362B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101449299A (en) * | 2006-07-21 | 2009-06-03 | 光荣株式会社 | A deformed coin detecting device |
| JP2009129390A (en) * | 2007-11-28 | 2009-06-11 | Oki Electric Ind Co Ltd | Medium discrimination device |
| CN101788280A (en) * | 2010-02-11 | 2010-07-28 | 浙江金利电子有限公司 | Device for identifying banknote thickness abnormity through ultrasonic wave and method thereof |
| CN103617671A (en) * | 2013-12-12 | 2014-03-05 | 广州广电运通金融电子股份有限公司 | Method and system for recognizing bill with abnormal thickness |
| WO2016088279A1 (en) * | 2014-12-05 | 2016-06-09 | グローリー株式会社 | Paper sheet thickness determination method and thickness determination device |
| CN105354912A (en) * | 2015-09-14 | 2016-02-24 | 深圳怡化电脑股份有限公司 | Method and device of banknote detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108022362A (en) | 2018-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104408819B (en) | A kind of detection method of bank note adhesive tape | |
| EP3082113A1 (en) | Method and system for recognizing bill with abnormal thickness | |
| CN102176262B (en) | Thickness detecting method and device for slice medium | |
| CN106875540B (en) | Paper money thickness abnormity detection method and device | |
| CN103606221A (en) | Fault automatic diagnostic method of counter and device | |
| EP3046083A1 (en) | Method and apparatus for detecting magnetic signal of paper money | |
| CN107978062B (en) | Method and device for detecting adhesive tape money | |
| CN105069893A (en) | Method and apparatus for checking bank note | |
| CN108022362B (en) | Method and device for detecting defect of paper money | |
| CN108663004B (en) | Method and device for detecting abnormal thickness of paper money | |
| CN106971450B (en) | method and device for identifying abnormal thickness of paper money | |
| TWI770927B (en) | Fingerprint identification method, storage medium, and terminal | |
| CN108492443B (en) | Method, device and equipment for detecting adhesive tape on paper money and storage medium | |
| CN108010184B (en) | Method and device for detecting paper currency folding angle | |
| CN108932788B (en) | Method, device and equipment for detecting abnormal thickness grade of paper money | |
| CN108961530B (en) | Paper currency defect identification method and system | |
| CN106846606B (en) | A kind of collecting method, device and finance device | |
| CN108694770B (en) | Method and device for detecting adhesive tape money | |
| CN115239723A (en) | Plate rolling machine part detection method based on pattern recognition | |
| CN106355740A (en) | Currency detection information processing device and method | |
| CN107818627B (en) | Monitoring method for state of paper money recognition module, storage device and financial self-service device | |
| CN106780958B (en) | Method and device for detecting the crossing of a banknote in the detection range of a thickness sensor | |
| CN107170111B (en) | Control method and device for reducing waste paper money | |
| CN108960222B (en) | Image binarization method, device, equipment and storage medium | |
| CN108877028B (en) | Method, device and equipment for detecting paper money |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |