KR101387858B1 - Apparatus for media recognition and method for media access direction estimating with the same - Google Patents

Abstract

The present invention relates to a media recognition apparatus for estimating a retraction direction of a medium by using segmentation brightness information of a media image, and a method of estimating a media retraction direction using the same. The present invention includes an image sensor for scanning a media image, and a brightness average calculator for equally dividing the scanned image into a predetermined number to calculate brightness averages for each divided region. In addition, an input direction estimation unit for comparing the calculated brightness averages for each region in a predetermined order by a pre-programmed input direction estimation algorithm and estimating the direction of entry of the medium according to the result is provided. According to the present invention, there is an advantage in that the inflow direction of the medium can be estimated quickly according to a simple comparison result of the brightness average.

Media Recognition, Direction of Entry Estimation, Brightness, DSP

Description

A medium recognition device and a method for estimating a medium retraction direction using the same {APPARATUS FOR MEDIA RECOGNITION AND METHOD FOR MEDIA ACCESS DIRECTION ESTIMATING WITH THE SAME}

1 is a flow chart illustrating a bill insertion direction estimation method in a conventional bill recognition apparatus.

Figure 2 is a block diagram of a bill recognition device according to an embodiment of the present invention.

3A and 3B are bill images and a brightness average table for explaining the bill entry direction estimation method shown in FIG.

FIG. 4 is a flowchart for explaining a bill input direction estimation method using the bill recognition apparatus shown in FIG. 2.

5A to 5H are exemplary diagrams of an output unit for outputting and showing a pulling direction result value processed by the pulling direction estimation method of the present invention.

Description of the Related Art [0002]

100: bill recognition device 105: bill insertion slot

110: LED 115: image sensor

120: transfer module 130: tilt correction

140: incoming direction processing unit 142: banknote image extraction unit

144: bill size estimation unit 146: brightness average calculation unit

148: incoming direction estimation unit 150: control unit

160: storage unit 170: output unit

The present invention relates to a media recognition device, and more particularly, to a media recognition device for estimating the direction of the media using the brightness average for each region of the media image, and a method for estimating the media input direction using the same.

The term " medium " used in this specification refers to, for example, banknotes, checks, tickets, certificates, etc., and may be various in thickness as compared with width or length.

The media recognition device is applied to various types of automatic teller machines and media handling devices such as banknote recognizers, vending machines, money exchangers, etc. and recognizes magnetic, images, silver, fluorescent ink, various numbers and letters printed on the media to recognize the types and forgeries of media. It is determined whether it is normal or not. For this purpose, the medium recognition device must first estimate the direction in which the medium is drawn.

1 is a step-by-step method for estimating a bill insertion direction performed by a conventional bill recognition apparatus.

In a tenth step S10 of FIG. 1, the banknote recognizing apparatus scans an image of a banknote using an image sensor. At this time, the scanned image is generally formed larger than the bill size in order to prevent only a part of the bill image is scanned by the shaking or vibration that may occur in the transfer operation. Accordingly, the scanned image includes a bill image and a margin image of the surroundings.

In the eleventh step S11, the banknote recognizing apparatus determines whether the banknotes are aligned, and if there is a tilt, corrects the inclination by the angle, and extracts only the banknote image excluding peripheral margins in the twelfth step S12.

Subsequently, boundary line feature values are extracted to extract boundary line feature values (S14). The boundary feature values refer to a boundary line direction, a disadvantage, a branch point, a line value, and the like, divided by a predetermined number. The boundary feature values thus extracted are compared with the values stored in the database (S15) to estimate the pulling direction of the bill (S16).

However, the bill recognition apparatus as described above scans an image to extract the feature values, converts the image into a filtered black-and-white image, and generates a binary code corresponding to the digital image by digital filtering. Determine the outline. In addition, the feature values are extracted through complex processing such as quantization and binary conversion of vector tablets and coordinates.

As described above, the conventional banknote recognizing apparatus has a problem that the algorithm for extracting feature values necessary for estimating the bill retracting direction is complicated and the processing steps are large and the execution speed is slow.

In addition, since the boundary line feature of the image is used, the vibration of the banknote transfer process, the noise of the circuit elements, the output change of the light emitting diode (Light Emitting Diode) that irradiates light on the banknote, and the sensitivity change of the image sensor are used. weak.

In addition, a large storage capacity is consumed because a database for storing the feature value of the bill is required.

Accordingly, the present invention has been made to solve the above-mentioned conventional problems, and an object of the present invention is to provide a medium recognition device and a medium retraction direction estimation method using the same, which minimizes the time required to estimate the retraction direction of the medium. .

Another object of the present invention is to provide a medium recognizing apparatus for improving accuracy in estimating a medium retracting direction and a method for estimating a medium retracting direction using the same.

According to a feature of the present invention for achieving the above object, the present invention divides the image scanned by the image sensor unit and the image sensor unit for scanning an image of the medium drawn from the outside into a predetermined number of areas. And a brightness average calculator configured to calculate a brightness average for the divided region-specific images, and includes a pull direction estimator for estimating a pull direction of the medium with reference to the calculated brightness average.

And a tilt correction unit for selectively correcting when the incoming medium has an inclination, and a media image extraction unit for extracting only a media image in a state where the inclination of the medium is in alignment with the media size for estimating a medium size from the extracted media image. It is preferable to further include an estimating unit.

The media size estimating unit estimates the vertical length of the extracted media image to determine the media type. In this case, the medium size estimating unit determines the priesthood and the old right according to the type of the medium.

The inflow direction estimating unit preferably uses an inflow direction estimation algorithm for estimating the inflow direction according to the front / rear and upright / inverted states of the medium by comparing the brightness averages of the images for each region.

In this case, the estimation algorithm sequentially continues the sum of the brightness averages of two adjacent regions among the divided regions and the brightness average of the image for each region to determine the front / back side and the upright / inverted state of the medium. It is preferable to estimate by comparison.

On the other hand, the brightness average calculation unit is characterized by dividing the area provided with the brightness average differently in two or more.

The apparatus may further include a storage unit configured to store a reference brightness average for each area according to the direction of entry for each medium, and the introduction direction estimating unit may compare the brightness average for each area of the inserted medium with the reference brightness average. The direction of entry of the medium is estimated.

According to another aspect of the invention there is provided a method for scanning an image on an incoming medium; Dividing an image of the scanned medium into a predetermined number of areas; Calculating a brightness average of the divided region-specific images; And estimating a retraction direction of the medium with reference to the calculated brightness average.

And optionally correcting the incoming medium when it is inclined; Extracting only the media image while the media is inclined; And estimating the size of the medium from the extracted media image.

In this case, the size estimating step estimates the vertical length of the extracted media image to determine the type of the media.

In addition, the size estimating step determines the priesthood and old authority according to the type of the medium.

In the estimating direction, the estimating direction is estimated according to the front / rear and upright / inverted states of the medium by comparing the sum of the brightness averages of the two regions adjacent to the divided region with the brightness averages for the respective images. It is preferable to use a pulling direction estimation algorithm.

The induction direction estimation algorithm is a sum of the brightness averages of two adjacent regions among the brightness averages of the image for each region to determine the front / back side and the upright / inverted state of the medium, and the image of each region. It is preferable to compare and estimate the brightness averages sequentially.

The region dividing step may be divided into two or more regions based on regions where the brightness averages are differently provided.

In the pulling direction estimating step, it is preferable to estimate the drawing direction of the medium by comparing a reference brightness average for each region previously stored with the brightness average for each region of the inserted medium.

According to the present invention having the above-described configuration, the incoming direction of the bill is simply estimated by scanning the input media image using a pre-programmed entry direction estimation algorithm according to the brightness average characteristic for each area divided into a predetermined number. . Accordingly, the present invention has the advantage of improving the processing speed delayed by a complicated algorithm, minimizing the effects of noise, LED output changes and image sensor sensitivity changes of the circuit elements.

Hereinafter, with reference to the accompanying drawings a preferred embodiment of the banknote recognition device according to the present invention as described above will be described in detail.

In a preferred embodiment of the present invention will be described by taking an example of estimating the bill accepting direction using the brightness average of 10,000 won bill. However, it should be noted that this can be applied to various media recognition devices that recognize not only different types of bills such as 1,000-won or 5,000-won bills, but also media that can be distinguished by the brightness averages of certain areas such as checks, gift certificates, and tickets. do.

2 is a block diagram of a bill recognition device according to a preferred embodiment of the present invention.

As shown in these figures, the banknote recognition device 100 of the present invention receives the banknote through the banknote injection port 105. The banknote input port 105 generates a signal when sensing the input of the banknote.

In the banknote recognizing apparatus 100 according to the present invention, when the signal is detected, a light emitting diode (LED) for irradiating light to the banknote transferred in a predetermined direction (for example, a lateral direction) by a transfer module (hereinafter referred to as 'LED'). 110, and an image sensor 115 for scanning the image of the bill reflected by the irradiated light is provided. In this case, the image sensor 115 scans an area larger than the bill specification in case the bill is not drawn in a straight state due to the vibration of the transfer module 120. Accordingly, the scanned image includes an image of the bill and a margin image. The image sensor 115 may use a charge-coupled device or a contact image sensor.

When the banknote scanned by the image sensor 115 is not aligned horizontally and there is a skew, a tilt correction unit 130 is provided to correct the tilt. This is because the inclination may occur when the conveyed banknote is inclined by the vibration of the transfer module 120. When the banknote is transferred in a horizontal state and no inclination occurs, it is obvious that the inclination correcting unit 130 does not perform the inclination correction operation.

The bill recognition device 100 is provided with a retraction direction processing unit 140 for estimating the retraction direction of the bill by using the size information of the input bill and the brightness average information of the predetermined portion. The pulling direction processor 140 includes a banknote image extracting unit 142, a banknote size estimating unit 144, a brightness average calculating unit 146, and a pulling direction estimating unit 148.

The banknote image extracting unit 142 extracts only the banknote image by removing the margin image from the scanned image of the banknote which is tilted or transferred in a horizontal state.

The banknote size estimating unit 144 estimates the size of the banknote from the extracted banknote image. The banknote size estimating unit 144 is for judging the winding type of the current banknote according to the estimated banknote size. In the present embodiment, a description is made using the 10,000 won bill, and the bill size estimating unit 144 is used to determine the new and old books in which the recent standard has been changed among the 10,000 won bill by estimating the vertical length of the bill. In addition, it is obvious that various media that can be distinguished by size can be determined.

The brightness average calculation unit 146 equally divides the bill image into a predetermined number (for example, eight equal parts) to estimate a drawing direction of the bill, and includes four areas (a, b, Calculate the brightness mean for c, d). Since the number of the divided areas and the brightness average calculation area is determined according to the brightness average property of the 10,000 won bill, it is obvious that the number of the divided areas and the brightness average calculation area is changed according to the characteristics of the medium.

For example, FIG. 3A shows an exemplary diagram in which the priesthood 10,000 won bill is divided into eight equal parts as described above. As shown, the brightness average calculator 146 calculates brightness averages for four areas (a, b, c, and d) located in the left and right areas. The reason for calculating the brightness average for the area (a, b, c, d) is that the brightness average of the area for each input medium can be distinguished differently.

3B shows a brightness average table in which brightness averages for the illustrated regions a, b, c, and d for the priesthood full circle are stored. As shown in the drawing, the brightness average values for the predetermined area for each medium to be input are preferably tabulated and arranged.

 In addition, the pulling direction estimating unit 148 sequentially compares the calculated brightness averages for each region by the pulling direction estimation algorithm and estimates the pulling direction of the banknote according to the result. The retrieval direction estimation algorithm is configured to pre-set the comparison order by using the characteristics of the image brightness average for each area according to the paper rolls of the bill, and to pre-programmed to estimate the retraction direction of the bill according to the comparison result is stored later It is stored in the unit 160.

In addition, the LED 110, the image sensor 115, the transfer module 120, the tilt correction unit 130, the banknote image extraction unit 142, the banknote size estimating unit 144 to estimate the pulling direction of the banknote ), A brightness average calculator 146, a retraction direction estimator 148, and a controller 150 for controlling the storage 160. The controller 150 preferably controls the entire bill recognition apparatus so as to perform recognition of the bill, judging the kind of paper money, whether a forgery is present, normal banknotes, and a processing operation according thereto after estimating the input direction of the bill. To this end, the controller 150 may be configured by changing and applying various types of control units such as a microprocessor, a central control unit, or a digital signal processor according to operating characteristics. Can be.

The storage unit 160 stores the pulling direction estimation algorithm for estimating the pulling direction of the banknote by the banknote size data, various data for each banknote including the brightness average for each region divided into a predetermined number, or data thereof. The storage unit 160 may use a main memory device for storing various programs and data for driving the automated teller machine including the banknote recognition device or other media handling device.

In addition, the bill recognition device 100 may further include an output unit 170 for outputting the result of the input direction determination result and processing of the input bill. The output unit 170 generally uses a liquid crystal display (LCD).

In the preferred embodiment of the present invention, the banknote recognizing apparatus 100 has been described as an example of estimating the retracting direction of the input 10,000 won bill, it is apparent that it is possible to determine a variety of different media and sizes other than this.

Hereinafter, a method of estimating a bill insertion direction using a bill recognition apparatus according to a preferred embodiment of the present invention will be described in detail with reference to an operation method.

Next, with reference to Figures 4 to 5 will be described a bill entry direction estimation method using a bill recognition apparatus according to a preferred embodiment of the present invention.

FIG. 4 is a flowchart for explaining a method of estimating a bill insertion direction using the bill recognition device shown in FIG. 2.

In the following description, the preferred embodiment of the present invention will be described taking the input direction of the 10,000 won media as an example.

First, when a banknote is input through the banknote injection hole 105, the transfer by the transfer module 120 is started. In step 100 of FIG. 4, under the control of the controller 150, the LED 105 irradiates light onto the incoming banknote, and the image sensor 115 scans the banknote image reflected by the irradiated light. do. In this case, the scanned image includes an image of a banknote and a margin image.

In step 105, the tilt correction unit 130 corrects the tilt when a banknote is inclined while being inserted in an oblique state according to a transport state such as vibration of the transport module 120. If the slope does not occur, the operation proceeds to the next operation.

Accordingly, the banknote image extracting unit 142 extracts only the banknote image excluding the margin image from the image of the tilted state (S110).

Subsequently, in step 115, the banknote size estimating unit 144 estimates the size of the extracted banknote image and compares the estimated vertical length of the banknote with the size data of the banknote stored in the storage unit 160. For example, the size of a new voucher issued recently (Jan. 2007) is 148 * 68mm in width * and 161 * 76mm in the size of the license. Accordingly, in this embodiment, the length of the extracted bills is compared with a length less than 72 mm to distinguish the priesthood and the bills.

In addition, it is apparent that the bill size estimating unit 144 can determine each kind of media (for example: thousand won, five thousand won, and ten thousand won) and the type of standardized media using the length of the bill. This is possible because the size of each medium is standardized and its size can be distinguished differently.

As a result of the inspection, if the vertical length of the banknote is less than 72mm, the banknote size estimating unit 144 judges the banknote as a new priesthood bill (S120), and if the vertical length of the banknote is larger than 72mm, the banknote size estimation unit ( 144) it is determined that the bill as a krwon 10,000 won (S170).

When the bill notes are determined as described above, then the incoming direction of the bills is estimated. For this purpose, the brightness average calculation unit 146 determines the number of banknote images by a predetermined number, for example, 4 * 2 in width * length as shown in FIG. 3A. Then, the image is divided equally into eight regions, and the brightness averages of the images of the regions (a), (b), (c), and (d) are calculated (S125). The reason why the brightness averages of the areas (a), (b), (c), and (d) are calculated as described above is that the brightness average calculation values of the areas are easy to distinguish the pulling direction.

Subsequently, the pulling direction estimating unit 148 calculates the brightness average sum of two adjacent areas, that is, the regions (a) and (b) and the regions (c) and (d) according to the pulling direction estimation algorithm.

Then, the sum of the brightness averages of the areas (a) and (b) (hereinafter 'a + b') and the sum of the brightness averages of the areas (c) and (d) (hereinafter, 'c + d') are compared ( S130). When 'a + b' is greater than 'c + d', the retraction direction estimator 24 compares the brightness averages of the areas (a) and (b) again (S135).

As a result of the determination in step 135, when the brightness average value of the area (a) is greater than the brightness average value of the area (b), the retraction direction estimator 148 estimates the retraction direction of the input 10,000 won as the front direction of the priesthood. (S140).

When the pulling direction is determined as a priesthood front facing direction, the output unit 170 is output to the screen of FIG. 5A. That is, it is preferable that the banknote image corresponding to the retracting direction of the banknote as described above and the description describing the same are output together.

As a result of the determination in step 135, when the brightness average value of the area (a) is smaller than the brightness average value of the area (b), the retraction direction estimating unit 148 shifts the input direction of the 10,000 won circle into the inverted direction of the priesthood back. It is estimated (S145).

If it is determined that the retraction direction is the inverted direction of the priesthood back, the output unit 170 is output to the screen of Figure 5b. That is, it is preferable that the banknote image corresponding to the retracting direction of the banknote as described above and the description describing the same are output together.

On the contrary, when the comparison result of 'a + b' and 'c + d' is smaller than 'c + d' in operation 130, the retraction direction estimator 24 is (c) and (d In step S150, brightness averages of the areas are compared.

As a result of the determination of step 150, when the brightness calculation value of the area (c) is greater than the brightness calculation value of the area (d), the retraction direction estimating unit 148 determines the direction of the backside of the priesthood (S155).

When it is determined that the retracting direction is the direction for establishing the back side of the priesthood, it is output to the output unit 170 on the screen of FIG. 5C. That is, it is preferable that the banknote image corresponding to the retracting direction of the banknote as described above and the description describing the same are output together.

On the other hand, if the brightness average value of the area (c) is less than the brightness average value of the area (d) as the determination result of step 150, the retraction direction estimator 148 determines that the priesthood is in the inverted direction (S160). When the retracting direction is determined as the priesthood front inverted direction, the output unit 170 is output to the screen of FIG. 5D. That is, it is preferable that the banknote image corresponding to the retracting direction of the banknote as described above and the description describing the same are output together.

On the other hand, in step 115, the banknote size estimating unit 144 estimates the size of the extracted banknote image and determines that the input banknote is an old bill of 10,000 won when the estimated length of the banknote is 72 mm or more (S170).

When the bill notes are determined as described above, the billing direction of the bill is subsequently estimated. For this purpose, the brightness average calculation unit 146 measures a predetermined number of banknote images, for example, 4 * 2 in width * length as shown in FIG. 4A. Then, the image is divided equally into eight regions and the brightness averages of the images of the regions (a), (b), (c), and (d) are calculated (S175).

Subsequently, the pulling direction estimating unit 148 calculates the brightness average sum of two adjacent areas, that is, the areas (a) and (b) and the areas (c) and (d) according to the pulling direction estimation algorithm.

Then, the sum of the brightness averages of 'a + b' and 'c + d' is compared (S180). When the 'a + b' is greater than the 'c + d' sum, the inflow direction estimator 148 compares the brightness averages of the areas (a) and (b) again (S185).

As a result of the determination in operation 185, when the brightness average value of the region (a) is greater than the brightness average value of the region (b), the retraction direction estimator 148 determines that the inverted direction of the old winding is reversed (S190).

If it is determined that the retracting direction is the inverted direction of the old winding, the screen of FIG. 5E is output to the output unit 170. That is, it is preferable that the banknote image corresponding to the incoming direction of the banknote and the description for describing the banknote are output together as shown.

On the other hand, when the brightness average value of region (a) is smaller than the brightness average value of region (b) as a result of the determination in step 185, the retraction direction estimator 148 determines that it is the upright direction of the old winding (S195).

When it is determined that the retraction direction is the old winding front upright direction, it is output to the output unit 170 on the screen of FIG. 5F. That is, it is preferable that the banknote image corresponding to the retracting direction of the banknote as described above and the description describing the same are output together.

On the other hand, when the comparison result of 'a + b' and 'c + d' is smaller than 'c + d' in operation 180, the retraction direction estimator 24 is (c) and (d The brightness average of the area is compared (S200).

As a result of the determination in step 200, when the brightness average value of the area (c) is greater than the brightness average value of the area (d), the retracting direction estimating unit 148 determines that the area is inverted in the forward direction (S205).

When the pulling direction is determined as the old winding front inverted direction, the output unit 170 outputs the screen of FIG. 5G. That is, it is preferable that the banknote image corresponding to the retracting direction of the banknote as described above and the description describing the same are output together.

On the contrary, if the brightness average value of the area (c) is smaller than the brightness average value of the area (d), the retraction direction estimating unit 148 determines that the rear surface is in the upright direction (S210).

When it is determined that the retraction direction is the old winding back side up direction, it is output to the output unit 170 on the screen of FIG. 5H.

In the above example, the present invention has been described using a thousand won bill, but the present invention can be applied to a media recognition device and method for scanning and recognizing images of various media such as checks, tickets, certificates, as well as bills such as thousand won bills and five thousand won bills. .

To this end, the order of inference estimation algorithm is applied by changing the comparison order and its calculation method according to the characteristics of the medium to be recognized, that is, the brightness average characteristic of the image for each region divided into a predetermined number.

While the present invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, It will be apparent that various modifications, alterations, and other equivalent embodiments are possible. Accordingly, the true scope of the present invention should be determined by the technical idea of the appended claims.

In the media recognition device according to the present invention as described in detail above, the following effects can be expected.

That is, firstly, the present invention is performed by a simple operation of comparing the brightness average for each segment of the bill image, and thus, the processing speed is faster than that of the conventional technology of comparing various feature points and feature values with a database.

In addition, the present invention is driven by an algorithm using brightness averages of bill images regardless of changes in LED output, sensitivity of the image sensor, vibration of the transfer module, or noise generated in other circuit elements, thereby improving accuracy and accuracy of bill recognition. It has the advantage of being.

In addition, the present invention stores only estimation algorithms excluding various feature points and feature values in the storage unit, thereby reducing the consumed storage capacity and reducing the manufacturing cost.

Accordingly, the present invention improves the satisfaction by quickly and accurately estimating the direction in which the medium is drawn.

Claims (16)

An image sensor unit scanning an image of a medium drawn from the outside; A brightness average calculation unit for dividing the image scanned by the image sensor unit into a predetermined number of regions and calculating brightness averages for the divided regions of each image; And And a retraction direction estimator for estimating a retracting direction of the medium by sequentially comparing the sum of the brightness averages of two adjacent areas among the calculated brightness averages for the divided region-specific images and the brightness averages for the respective areas. Media recognition device. The method according to claim 1, A tilt correction unit for selectively correcting the incoming medium when there is a tilt; A media image extraction unit for extracting only a media image in a state where the inclination of the media is aligned; and And a media size estimator for estimating a media size from the extracted media image. 3. The method of claim 2, The medium size estimating unit, And a media recognition device for estimating a media type by estimating a vertical length of the extracted media image. 3. The method of claim 2, The medium size estimating unit, Media recognition device for judging the priesthood and the old right according to the type of the medium. The method according to claim 1 or 2, The drawing direction estimating unit, And a lead-input estimation algorithm for estimating a pull-in direction according to the front / back side and the upright / vertical state of the medium by comparing brightness averages of the images for each region. delete The method according to claim 1, The brightness average calculation unit, And a media recognition device for dividing an area provided with different brightness averages into two or more. The method according to claim 1, The apparatus may further include a storage unit configured to store a reference brightness average for each region according to the direction of entry for each medium. And the retraction direction estimating unit estimates the retraction direction of the medium by comparing the brightness average of each region of the retracted medium with the reference brightness average. Scanning an image for an incoming medium; Dividing an image of the scanned medium into a predetermined number of areas; Calculating a brightness average of the divided region-specific images; And And estimating a direction of introduction of the medium by sequentially comparing the sum of the brightness averages of two adjacent regions among the calculated brightness averages of the divided region images and the brightness averages of the respective regions. A method of estimating the direction of media inlet using delete delete delete delete delete delete delete

Images