KR20090062115A - Apparatus and method for media image detection, and system with the same - Google Patents

Abstract

A media image detecting apparatus and method and a media handling system using the same are provided, which improve the processing speed by reducing the computational complexity to process. A media image detecting apparatus comprises the contour detection part(15), the minimum area detection unit(16), the rotational direction determining unit(17), the vertex extracting unit(18), the slope output unit(19), and the image detection part(20). The contour detection part detects the contour line of the media image. The minimum area detection unit detects the image of the minimum area in which the media image is included by using the detected contour line. The rotational direction determining unit determines the rotational direction of the detected minimum area.

Description

Apparatus and method for detecting a media image, and a media handling system using the same {APPARATUS AND METHOD FOR MEDIA IMAGE DETECTION, AND SYSTEM WITH THE SAME}

The present invention relates to a media image detection apparatus, and more particularly, to a media image detection apparatus and method for detecting a media image using only a minimum area of the media image, and a media handling system using the same.

As used herein, the term "medium" refers to a bill, a check, a ticket, a certificate, or the like, and may be variously thinner than a width or a length.

The media image detection device applied to various types of financial automatic devices such as banknote recognizers, vending machines, money exchange machines, and media handling systems recognizes magnetic, images, silver, fluorescent ink, various numbers and letters printed on the media. It will determine whether it is forged or not. The media handling system extracts only the media image by correcting the inclination that occurs during conveyance of the media to be correctly recognized for the media.

1 is a flowchart illustrating a method of detecting a banknote image of a general banknote recognizing apparatus, and an exemplary view for explaining the banknote image detecting method of FIG. 1 is illustrated in FIGS. 2A to 2E.

1 and 2a to 2e, the bill recognition device scans the image of the bill is inserted (S1). In this case, the scanned image includes a bill image and a margin image as shown in FIG. 2A.

While the banknote recognition device transfers the bills therein, the banknote recognition device is inclined from the moving direction due to a conveying state such as vibration or noise, and skew of the media image occurs as shown in FIG. 2B.

Then, the bill recognition device estimates the tilt of the bill image (S2), and corrects the tilt by rotating the entire image by the estimated tilt (S3). In FIG. 2C, the entire banknote image rotated based on the estimated slope is shown. The rotated whole bill image includes a pixel partially missing an image during the rotation process.

The banknote recognizing apparatus corrects a pixel missing the image by using an image of a side pixel or using an average value of surrounding pixels (S4). 2D shows an image in which missing pixels are corrected.

Subsequently, the banknote recognizing apparatus detects the banknote image using the outermost boundary of the banknote image whose slope is corrected as described above (S5). 2E shows a banknote image without a margin image.

This conventional banknote recognition device has the following problems.

First, the conventional banknote recognition device corrects the tilt of the banknote image by rotating the entire image. Therefore, since the entire image must be processed, the processing speed for correcting the tilt is reduced.

In addition, the processing speed for extracting the bill image from the entire image is also lowered.

On the other hand, when performing a matching method using a part of the entire image, the conventional banknote recognition device rotates the entire banknote image to extract only the bill portion and match the base area. Accordingly, the conventional banknote recognition device has a problem that the amount of calculation is increased, the performance speed is lowered.

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and an object of the present invention is to provide a media image detecting apparatus and method for detecting a media image using only a minimum area of the media image, and a media handling system using the same.

Another object of the present invention is to reduce the amount of computation by matching the entire media image after performing the processing of the partial basic region when utilizing the method of matching the whole image and the partial image.

According to a feature of the present invention for achieving the object as described above, the present invention is a contour detection unit for detecting the contour of the media image, the minimum to detect the image of the minimum area containing the media image using the detected contour An area detection unit, a rotation direction determination unit that determines a rotation direction of the detected minimum area, a vertex extraction unit that extracts a vertex of the media image based on the rotation direction, and a coordinate of the extracted vertex And a tilt detector for calculating a tilt, and an image detector for detecting only the media image from which a blank image is excluded by correcting the calculated tilt.

It is preferable that the contour detection unit uses a Sobel mask technique.

The minimum area detector may detect the minimum area by using a point where the histogram value of the medium image on which the Sobel mask is performed is changed to a value other than '0'.

The rotation direction determiner may determine the rotation direction of the media image by comparing the widths of the left and right spaces around the uppermost vertex of the media image.

Preferably, the rotation direction determiner is determined to be rotated in a direction in which a space is widely located in the left and right spaces.

Preferably, the vertex extracting unit extracts a vertex of the media image by searching from the vertices of the minimum area in a direction in which the inclination angle is large based on the determined rotation direction.

The vertex extracting unit may search for and extract a vertex of the media image from the vertices of the minimum region in the determined rotation direction.

The slope calculator may estimate a horizontal / vertical length of the media image by using vertex coordinates of the extracted media image, and calculates a slope of the media image by Equation 1.

‥‥‥수학식 1

‥‥‥ Equation 1

The image detector preferably detects only a media image excluding a margin image.

Preferably, the image detector maps the upper left vertex coordinates of the minimum region image in the reverse direction.

According to another feature of the invention, the present invention is a media image detection device; And a control unit for controlling the storing and withdrawal of the medium using the media image recognized by the media image detecting apparatus.

It is preferable that the said medium is a banknote.

According to another feature of the invention, the present invention comprises the steps of detecting the contour of the media image, detecting the image of the minimum region containing the media image using the detected contour, rotation of the detected minimum region Determining a direction, calculating a slope of the media image using coordinates of vertices extracted based on the rotation direction, and detecting only the media image excluding a margin image by correcting the calculated slope. It is configured to include.

Preferably, the contour detection step uses a Sobel mask technique.

The detecting of the minimum region may include creating a histogram of the media image on which the Sobel mask has been performed, and detecting the minimum region using the histogram value.

In the detecting of the minimum region, the minimum region may be detected according to a coordinate of a point where the histogram value changes to a value other than '0'.

In the determining of the rotation direction, it is preferable to determine the rotation direction of the media image by comparing the widths of the left and right spaces around the uppermost vertex of the media image.

In the rotation direction determination step, it is preferable to determine that the area is rotated in a wide direction by comparing the width of the left and right space.

The vertex coordinates are preferably extracted from the vertices of the minimum region in a direction in which the inclination angle is large based on the determined rotation direction.

Preferably, the vertex coordinates are extracted by searching for vertices of the media image in the determined rotation direction from the vertices of the minimum region.

In the step of calculating the slope, the horizontal / vertical length of the media image is estimated using vertex coordinates of the extracted media image, and the slope of the media image is calculated by substituting the estimated horizontal / vertical length into Equation 1. It is preferable.

‥‥‥수학식 1

‥‥‥ Equation 1

In the image detection step, it is preferable to detect only the media image whose slope is corrected by rotating the minimum region image based on the calculated slope.

In the image detecting step, it is preferable to perform reverse mapping around the upper left vertex coordinate of the minimum region image.

The present invention preferably further includes the step of storing and discharging the medium using the extracted media image.

According to still another aspect of the present invention, the present invention provides a method for scanning an image of a medium, extracting a preset base region image from the scanned media image, correcting a tilt of the extracted base region image, and And correcting the inclination of the entire media image by matching the inclination corrected base region image with the entire media image.

As described above, the present invention detects the media image using only the minimum area of the media image. Accordingly, the present invention has the following effects.

First, the present invention improves the processing speed by reducing the amount of calculation to be processed in the image detection operation.

In addition, the present invention may extract the media image by matching the entire image after extracting the image of the basic region which is a part of the entire image.

Accordingly, the present invention can process the operation of detecting the media image from a large amount of media in real time.

Hereinafter, an apparatus and method for detecting a media image according to a preferred embodiment of the present invention, and a media handling system using the same will be described in detail with reference to the accompanying drawings.

3 is a block diagram of a media image detection apparatus according to a preferred embodiment of the present invention.

In the present embodiment, it will be described using a financial automatic machine that performs the input / discharge of the bill. However, the present invention can be applied to a media handling system that handles various types of media such as checks, certificates, tickets, as well as bills.

As shown in Figure 3, the banknote recognition device 10 of the present invention receives the banknote through the inlet (11). The inlet 11 generates a signal when sensing the input of the bill.

When the bill detection signal is generated from the inlet (11), the light emitting diode (Light Emitting diode, hereinafter referred to as "LED") 13 for irradiating light to the bill conveyed by the transfer module 12, and the irradiation An image sensor 14 for scanning the image of the banknote reflected by the light is provided. In this case, the image sensor 14 scans an area larger than the bill standard in case the bill is not drawn in a straight state due to the vibration of the transfer module 12. Thus, the scanned image includes an image of the banknote and a margin image. The image sensor 14 preferably uses a charge-coupled device or a contact image sensor.

Contour detection unit 15 for detecting the contour of the banknote image in the scanned image is provided. The contour detector 15 may use various contour detection methods, such as a Preit Mask, a Robert Mask, a Laplacian Mask, and a Kenny Mask. It is described by using a sobel mask method with excellent detection accuracy. The contour detector 15 uses 'Gx' / 'Gy' to search the horizontal / vertical components of the scanned image in order to create a histogram in the X-axis / Y-axis direction. Tables 1a and 1b are 'Gx' / 'Gy' tables of Sobel masks that retrieve the horizontal / vertical components of the scanned image.

The contour detector 15 adds the image of 'Gx' and the image of 'Gy' into one image. The image performing 'Gx' / 'Gy' has a value between '0' and 255 'according to the brightness. Accordingly, the contour detector 15 processes all values less than '128', which is half of the maximum value of '255', as '0', that is, black, and creates an image displayed only with values greater than or equal to '128'. The outline of the banknote image is detected in the generated image.

The banknote image scanned by the image sensor 14 may not be horizontally aligned and skew may occur. The inclination is generated according to a transfer state such as vibration or noise of the transfer module 12 for transferring the bill. When the banknote is transported in a horizontal state and no inclination occurs, it is preferable to extract the image after correcting the inclination.

The minimum area detector 16 is provided to detect the minimum area including the media image in the image generated by the contour detector 15. The minimum area detector 16 creates a histogram in the X-axis / Y-axis direction on the image created by the contour detector 15. The histogram becomes larger as the flow of banknote images increases. Accordingly, the minimum area detector 16 detects a point that meets the outline of the banknote image according to the change of the histogram values, and detects the minimum region including the banknote image.

Rotational direction determination unit 17 for determining the rotational direction of the bill image is provided. The rotation direction determination unit 17 calculates the width of the left and right triangle areas around the highest vertex among the points where the detected minimum area meets the outline of the banknote image. In addition, the rotation direction determiner 17 determines the direction in which the wide area is located as the rotation direction by comparing the calculated areas of the left and right triangle areas.

A vertex extracting unit 18 for extracting vertices of the media image is provided. The vertex extracting unit 18 extracts vertices of the banknote image by searching for points that meet the contour along a direction having a large angle from the vertices of the minimum area toward the vertices of the media image.

In addition, a tilt calculator 19 for calculating a tilt of the media image is rotated. The tilt calculator 19 estimates the horizontal / vertical length of the media image by using vertex coordinates of the media image. The slope is calculated by substituting the estimated horizontal / vertical length into Equation 1.

An image detector 20 is provided to extract only the media image from which the margin image is excluded by correcting the calculated slope. The image detector 20 rotates the banknote image by the calculated slope about one of the vertex coordinates of the minimum region image, for example, the upper left vertex coordinate. To this end, the image detection unit 20 detects only the banknote image from which the blank image is removed by reversely mapping the coordinates of the new image from the original banknote image. Since the reverse mapping method retrieves data from the original image based on the coordinates of the new image, empty coordinates do not occur in the new image. You can also import duplicate data from the original image, but you don't have to create a new image and correct the image again. Accordingly, the image detector 20 detects only the media image whose slope of the estimated media image size is corrected.

In addition, the control unit 21 for controlling the entire bill recognition device 10 to detect the bill image is provided. The control unit 21 is preferably a central processing unit (Central Processing Unit) of the automated teller machine including the banknote recognition device (10).

In addition, it is preferable that the display unit 22 for displaying the operation process of the banknote recognition device and the media image in which the rotation direction, inclination, center point, and inclination of the media image are corrected are provided.

Next, the bill image detection method of the bill recognition apparatus according to a preferred embodiment of the present invention will be described in detail with reference to FIG.

4 is a flowchart illustrating a bill image detection method of a bill recognition device according to a preferred embodiment of the present invention.

In this embodiment, it will be described using a thousand won bill.

When the banknote is inserted into the inlet 11 and the transfer by the transfer module 12 is started, the LED 13 irradiates light to the banknote under the control of the control unit 21 in the tenth step S10 of FIG. The image sensor 14 scans an image of the banknote reflected by the irradiated light. 5A to 5C show exemplary views of the scanned image. As shown in Figures 5a to 5c, the scanned image includes a bill image and a margin image. In addition, the bill may be skewed while the banknote is drawn in an oblique state according to a transfer state such as vibration of the transfer module 12.

If the inclination does not occur, the amount of damage to the banknote is estimated, or the flow proceeds to the next operation according to the order such as discrimination of the kind and the estimation of the pulling direction.

On the other hand, when the tilt occurs, the contour detection unit 15 detects the contour of the banknote image in the twelfth step (S12) using a sobel mask method. It demonstrates using the image shown in FIG. 5B. FIG. 6A shows the vertical component of the media image detected by 'Gx' in Table 1A. 6B shows horizontal components of the media image detected by 'Gy' in Table 1B.

The contour detector 15 adds the vertical component and the horizontal component into one image as shown in FIG. 6C. The image of performing the Sobel mask operation using the 'Gx' and 'Gy' has a value between '0 and 255' according to the brightness. Accordingly, the contour detector 15 processes all values less than '128' which is half of the maximum value '255' into '0', that is, black, and creates an image in which only values greater than or equal to '128' are displayed. In FIG. 6D, an image displaying only values of '128' or more is illustrated by the contour detector 15. The outline of the banknote image is detected through the generated image.

In a fourteenth step S14, the minimum area detector 16 creates a histogram in the X-axis and Y-axis directions on the image created by the contour detector 15. 7A illustrates a histogram made from the banknote image. The histogram becomes larger as the flow of banknote images increases.

In the sixteenth step S16, the minimum area detector 16 detects a point that meets an outline of the banknote image according to the change of the histogram values, and detects the minimum region including the banknote image. FIG. 7B illustrates an example of a method of detecting a minimum region using a histogram. As shown in FIG. 7B, the minimum area detector 16 has a point between '2' and '3' on the Y-axis whose histogram value is changed to a value other than '0', '6' and '7'. Perform a search in the horizontal direction between points. Then, the search is performed in the vertical direction between the '2' and '3' points on the X axis and the '8' and '9' points on the X-axis whose histogram values are changed to values other than '0'. Accordingly, the minimum area detector 16 detects the minimum area including the outline of the banknote image.

In an eighteenth step S18, the rotation direction determiner 17 extracts points that meet the outline of the banknote image, that is, virtual vertices, from the respective vertices of the detected minimum region. 8A to 8C are exemplary views illustrating a method of extracting a virtual vertex. In FIG. 8A, coordinates E (x2) of the virtual vertices are obtained using vertex coordinates of the minimum region, for example, A (x1, y1) and B (x7, y7), C (x5, y5), and D (x3, y3). , y2), F (x8, y8), G (x6, y6), H (x4, y4) are detected. At this time, y1 = y2 = y3, x1 = x8 = x7, y7 = y6 = y5, x3 = x4 = x5.

Subsequently, in the twentieth step S20, the rotation direction determiner 17 determines the width of the left and right triangle-shaped blank images, that is, areas 1 and 2, of the topmost vertex of the banknote image, that is, the point E. Compare. As a result of comparison, when the area of the first area is narrower than the second area as shown in FIG. 8A, the rotation direction determination unit 17 determines that the banknote image is rotated in the right direction. On the other hand, if the width of the area 2 is narrower than the area 1 as shown in Figure 8b, the rotation direction determination unit 17 determines that the banknote image is rotated in the left direction.

In the twenty-second step S22, the inclination calculation unit 19 is configured such that the inclination angle of the vertex of the banknote image is larger in the direction based on the determined rotation direction from the vertices A, B, C, and D of the minimum region. Search and extract the vertices of the bill image.

9A to 9C are exemplary views for explaining a method of estimating a vertex. In FIG. 9A in which the banknote image shown in FIG. 8B is enlarged, the minimum region image is divided into a banknote region pixel and a margin region pixel. At this time, if the vertex is searched from the left side to the right side of the banknote image, that is, the first inclination angle is gentle, the point detected by the minimum area detection unit 16 in the sixteenth step S16 instead of the second point. Recognize 1 (x2, y2) as a vertex

In order to solve such a problem, the slope calculation unit 19 searches for a vertex using the third angle in which the inclination angle is steeper than the first angle. For example, in the image rotated to the left as shown in FIG. 9B, the tilt calculator 19 uses a relatively steep angle of inclination to indicate the direction indicated by the arrow, that is, the direction in which the image is rotated to the left. Navigate to extract the coordinates of the vertices. In addition, in the image rotated to the right as shown in FIG. 9C, the tilt calculator 19 searches for the right direction in the same direction as the arrow, that is, the direction in which the image is rotated, by using a relatively steep angle. Extract the coordinates of the vertices.

In a twenty-fourth step S24, the slope calculator 19 estimates the horizontal length and the vertical length of the banknote image using the extracted coordinates E, F, G, and H of the vertices. Then, the slope calculator 19 calculates the slope of the banknote image by substituting the estimated horizontal length and vertical length into Equation (1).

In operation 26, the image detector 20 rotates the banknote image about any one of the extracted vertices E, F, G, and H to correct the calculated tilt. For example, when the banknote image is rotated to the left, the image detector 20 rotates to the right about the point O (x8, y8) of FIG. 9B. On the other hand, when the banknote image is rotated to the right, the image detector 20 rotates to the left around the point O '(x2, y2) of FIG. 9C. As such, the method of rotating the image to correct the tilt may use the equation of a straight line passing through the coordinates or use the least square method. In the present embodiment, the image detector 20 performs reverse mapping to bring the data corresponding to the new image coordinates from the data of the original image in order to display the banknote image with the inclination corrected. At this time, since the vertex coordinates (E, F, G, H) of the banknote image is recognized, the image detector 20 rotates the banknote image using only the banknote image coordinates, thus perfecting the margin image and the banknote image. To separate. Accordingly, the image detector 20 may detect the banknote image from which the blank image is excluded.

10A to 10C are exemplary views illustrating an image detection process. In the case of correcting the inclination of the banknote image as shown in FIG. 10A, the control unit 21 indicates, as shown in FIG. 10B, that the rotation direction: right, tilt: 14.736495, rotation center point: x = 61, y = 48. The estimated result may be controlled to be displayed on the screen of the display unit 22. In addition, the display unit 22 may display a banknote image whose slope is corrected through the tilt correction process on the screen as illustrated in FIG. 10C.

 Through the above-described process, the present invention corrects and detects the inclination of the banknote image using the minimum area detected from the histogram of the banknote image, thereby reducing the amount of calculation to be processed and improving the processing speed.

Although the above embodiments have been described using bills, the present invention can be applied not only to bills, but also to a media image detection apparatus for scanning and recognizing images of various media such as checks, tickets, and certificates, and a media handling system using the same.

In the above embodiment, the inclination was corrected using the entire banknote image. 11A and 11B show examples of utilizing the present invention. As shown in FIG. 11A, the present invention extracts only a basic region, for example, a basic region, '10000', which is a part of a preset banknote image, and corrects the tilt using a tilt correction method as described in the above embodiment. . In addition, the entire banknote image having the corrected slope may be detected by matching the base region having the corrected slope with the entire banknote image of FIG. 11B. As such, when using a basic region which is a part of the entire image, the present invention can further improve the processing speed to process the image detection operation of multiple bills in real time.

As described above, the present invention has been described with reference to the embodiments shown in the drawings, which are merely exemplary, and a person of ordinary skill in the art without departing from the spirit and scope of the present invention. It will be apparent that various modifications, changes, and equivalent other embodiments are possible. Therefore, the true technical protection scope of the present invention will be defined by the technical spirit of the appended claims.

1 is a flowchart illustrating a general method of detecting a media image.

2A to 2E are exemplary views for explaining a general method of detecting a media image.

Figure 3 is a block diagram of a media image detection apparatus according to an embodiment of the present invention.

Figure 4 is a flow chart illustrating a step-by-step method for detecting a media image in accordance with a preferred embodiment of the present invention.

5A to 5C are exemplary views of media images recognized by the media image detection apparatus.

6A to 6D are exemplary views of a media image in which a Sobel mask is performed.

7A and 7B are exemplary views for explaining a method of detecting a minimum region.

8A and 8C are exemplary views for explaining a method of estimating a rotation direction.

9A to 9C are exemplary views for explaining a vertex extraction method.

10A to 10C are exemplary views for explaining an image detection method.

11A and 11B are exemplary views for explaining the application of the present invention.

`` Explanation of symbols for main parts of drawings ''

11: Banknote input 12: Transfer module

13: LED 14: Image Sensor

15: contour detection unit 16: minimum area detection unit

17: rotation direction determination unit 18: vertex extraction unit

19: slope calculation unit 20: image detection unit

21 control unit 22 display unit

Claims (25)

An outline detection unit for detecting an outline of the media image; A minimum region detector for detecting an image of the minimum region including the media image by using the detected contour line; A rotation direction determination unit to determine a rotation direction of the detected minimum region; A vertex extracting unit extracting vertices of the media image based on the rotation direction; A slope calculator for calculating a slope of the media image using the extracted coordinates of the vertices, and And an image detector for detecting only the media image from which a margin image is excluded by correcting the calculated tilt. The method of claim 1, wherein the contour detection unit, A media image detection apparatus using a Sobel mask technique. The method of claim 2, wherein the minimum area detection unit, And detecting the minimum area by using a point at which a histogram value of the medium image on which the Sobel mask is performed is changed to a value other than '0'. The method of claim 1, wherein the rotation direction determination unit, And a rotation direction of the media image is determined by comparing the widths of the left and right spaces around the uppermost vertex of the media image. The method of claim 4, wherein the rotation direction determination unit, And determining that the space is rotated in a direction in which the space is wide among the left and right spaces. The method of claim 1, wherein the vertex extracting unit, And extracting a vertex of the media image by searching in a direction having a large inclination angle based on the determined rotation direction from the vertices of the minimum region. The method of claim 1, wherein the vertex extracting unit, And extracting a vertex of the media image from the vertices of the minimum area in the determined rotation direction. The method of claim 1, wherein the slope calculation unit, And estimating a horizontal / vertical length of the media image by using vertex coordinates of the extracted media image, and calculating a slope of the media image by Equation 1.

‥‥‥ Equation 1 The method of claim 1, wherein the image detection unit, A media image detection apparatus, characterized in that for detecting only the media image excluding the margin image. The method of claim 9, wherein the image detection unit, And backward mapping the upper left vertex coordinates of the minimum region image. A media image detection device comprising any one of claims 1 to 10; And a control unit for controlling the storage and withdrawal of the medium using the media image recognized by the media image detection apparatus. The method of claim 11, wherein the medium, A media handling system, characterized in that the bill. Detecting an outline of the media image, Detecting an image of the smallest region including the media image by using the detected contour line; Determining a rotation direction of the detected minimum region; Calculating a slope of the media image using coordinates of vertices extracted based on the rotation direction, and And detecting only the media image from which a blank image is excluded by correcting the calculated slope. The method of claim 13, wherein the detecting of the outline comprises: A method of detecting a media image, characterized by using the Sobel mask technique. The method of claim 14, wherein the detecting of the minimum area comprises: Creating a histogram of the media image on which the Sobel mask is performed; And detecting the minimum region by using the histogram value. The method of claim 15, wherein the detecting the minimum area, And detecting the minimum area according to a coordinate of a point where the histogram value changes to a value other than '0'. The method of claim 13, wherein the determining of the rotation direction comprises: And determining the rotation direction of the media image by comparing the widths of the left and right spaces around the uppermost vertex of the media image. The method of claim 17, wherein the determining of the rotation direction comprises: And comparing the widths of the left and right spaces and determining that the widths are rotated in a wide direction. The method of claim 13, wherein the vertex coordinates, And extracting from the vertices of the minimum region in a direction in which the inclination angle is large based on the determined rotation direction. The method of claim 13, wherein the vertex coordinates, And extracting a vertex of the media image from the vertices of the minimum region in the determined rotation direction. The method of claim 13, wherein the slope calculation step, Estimating the horizontal / vertical length of the media image by using vertex coordinates of the extracted media image, and calculating the slope of the media image by substituting the estimated horizontal / vertical length into Equation 1 Detection method.

‥‥‥ Equation 1 The method of claim 13, wherein the image detection step, And detecting only a media image of which a tilt is corrected by rotating the minimum region image based on the calculated tilt. The method of claim 22, wherein the image detection step, And backward mapping the upper left vertex coordinates of the minimum region image. The method of claim 13, And storing and dispensing the medium by using the extracted medium image. Scanning an image of the medium, Extracting a preset base area image from the scanned media images; Correcting the inclination of the extracted basic region image, and And correcting the inclination of the entire media image by matching the inclination corrected base region image with the entire media image.

Images