KR101397905B1 - Apparatus and method for media image detection, and system with the same - Google Patents

Abstract

The present invention relates to a medium image detecting apparatus and method for detecting a tilted medium image using a minimum area of a medium image, and a medium handling system using the same. In the present invention, there is provided an outline detecting section for detecting the outline of the medium image. And a minimum area detecting unit for detecting an image of the minimum area including the medium image using the detected contour. The rotation direction determination unit determines the rotation direction of the detected minimum area, and the vertex point extraction unit extracts the vertex of the medium image based on the rotation direction. The slope calculating unit calculates the slope of the medium image using the coordinates of the extracted vertexes, and the image detecting unit corrects the calculated slope to detect only the media image from which the margin image is excluded. Accordingly, since the present invention uses only the minimum area of the medium image, there is an advantage that the amount of calculation to be processed in the detection of the medium image is reduced and the processing speed is improved.

Media handling system, image detection, tilt correction, minimum area, basic area

Description

TECHNICAL FIELD [0001] The present invention relates to a medium image detecting apparatus and method, and a media handling system using the medium image detecting apparatus and method,

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

Various types of financial automation devices such as a bill recognizer, a vending machine, and a currency changer, and a medium image detection device applied to the medium handling system recognize the magnetic, image, silver, fluorescent ink, various numbers and characters printed on the medium, Whether it is fake, whether it is normal or not. The media handling system extracts only the media image by correcting the slope that occurs during the feeding of the loaded media for accurate recognition of the media.

FIG. 1 is a flow chart for explaining a banknote image detection method of a general banknote recognition apparatus step by step. FIGS. 2A to 2E are diagrams for explaining the banknote image detection method of FIG.

In Fig. 1 and Figs. 2A to 2E, the bill recognition apparatus scans an image of an incoming bill (S1). At this time, the scanned image includes a banknote image and a margin image, as shown in FIG. 2A.

The bill recognizing device is inclined from the traveling direction due to the conveying state such as vibration or noise while the bill is being conveyed to the inside, and a skew of the medium image occurs as shown in Fig. 2B.

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

The bill recognition apparatus uses an image of a neighboring pixel or corrects a pixel missing the image using an average value of neighboring pixels (S4). In Fig. 2 (d), a missing pixel corrected image is shown.

Then, the bill recognition apparatus detects the banknote image using the outermost boundary of the banknote image whose inclination is corrected as described above (S5). In FIG. 2E, a banknote image excluding marginal images is shown.

The conventional bill recognition apparatus has the following problems.

First, the conventional bill recognition apparatus corrects the inclination of the bill image by rotating the entire image. Therefore, since the entire image has to be processed, the processing speed of correcting the tilt is lowered.

Also, the processing speed for extracting banknote images from the entire image is also lowered.

On the other hand, in the case of performing matching using a part of the whole images, the conventional bill recognition apparatus rotates the entire banknote image to extract only the banknote part, and then matches with the basic area. Accordingly, the conventional bill recognition apparatus has a problem that the amount of calculation is increased and the execution speed is lowered.

It is an object of the present invention to provide a medium image detecting apparatus and method for detecting a medium image using only a minimum area of a medium image, and a medium 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 partial base area processing when a method of matching an entire image and a partial image is used.

According to an aspect of the present invention, there is provided an image processing apparatus including an outline detecting unit detecting an outline of a medium image, a minimum image detecting unit detecting an image of a minimum area including the medium image using the detected outline, A rotation direction determination unit for determining a rotation direction of the detected minimum area, a vertex extraction unit for extracting a vertex of the medium image based on the rotation direction, A slope calculating unit for calculating a slope, and an image detecting unit for correcting the calculated slope to detect only the medium image from which a margin image is excluded.

Preferably, the outline detection unit uses a Sobel mask technique.

Preferably, the minimum area detecting unit detects the minimum area using a point where the histogram value of the medium image on which the Sobel mask is performed changes to a value other than '0'.

Preferably, the rotation direction determination unit determines the direction of rotation of the medium image by comparing the widths of the left and right spaces around the highest vertex of the medium image.

The rotation direction determination unit determines that the space is rotated in a direction in which the space is wider in the left and right spaces.

Preferably, the vertex extracting unit extracts a vertex of the medium image by searching the vertices of the minimum area in a direction having a large inclination angle based on the determined rotational direction.

Preferably, the vertex extracting unit searches for and extracts a vertex of the medium image in the determined direction of rotation from each vertex of the minimum area.

Preferably, the slope calculating unit estimates the horizontal / vertical length of the medium image using the vertex coordinates of the extracted medium image, and calculates the slope of the medium image according to Equation (1).

‥‥‥수학식 1

1

Preferably, the image detecting unit detects only the medium image excluding the margin image.

Preferably, the image detecting unit performs a reverse mapping on the upper left vertex coordinates of the minimum area image.

According to another aspect of the present invention, there is provided a media image detection apparatus comprising: a media image detection apparatus; And a control unit for controlling the receipt and receipt of the medium by using the medium image recognized by the medium image detection apparatus.

It is preferable that the medium is a banknote.

According to still another aspect of the present invention, there is provided a method of reproducing a medium image, comprising the steps of: detecting a contour of a medium image; detecting an image of the minimum area including the medium image using the detected contour; Calculating a slope of the medium image using the coordinates of the vertex extracted based on the rotation direction, and correcting the calculated slope to detect only the medium image from which the margin image is excluded .

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

The minimum area detection step may include generating a histogram of the medium image on which the Sobel mask is performed, and detecting the minimum area using the histogram value.

Preferably, the minimum area detecting step detects the minimum area according to coordinates of a point where the histogram value changes to a value other than '0'.

Preferably, the rotating direction determining step determines the rotating direction of the medium image by comparing the widths of the left and right spaces around the highest vertex of the medium image.

The rotation direction determination step may compare the widths of the left and right spaces and determine that the width of the left and right spaces is rotated in a wider direction.

Preferably, the vertex coordinates are searched in a direction having a large inclination angle based on the determined rotation direction from each vertex of the minimum area and extracted.

Preferably, the vertex coordinates are searched for vertices of the media image in the determined direction of rotation from the respective vertices of the minimum area.

The slope calculating step estimates the horizontal / vertical length of the medium image using the vertex coordinates of the extracted medium image, and substitutes the estimated horizontal / vertical length into the equation 1 to calculate the slope of the medium image .

‥‥‥수학식 1

1

Preferably, the image detecting step detects only the medium image whose slope is corrected by rotating the minimum area image based on the calculated slope.

Preferably, the image detection step maps backward about the coordinates of the upper left vertex of the minimum area image.

It is preferable that the present invention further includes a step of performing a storing and receiving operation of the medium by using the extracted medium image.

According to another aspect of the present invention, there is provided an image processing method including the steps of scanning an image of a medium, extracting a predetermined basic area image from the scanned medium image, correcting a slope of the extracted basic area image, And correcting the slope of the entire media image by matching the slope-corrected base area image with the entire media image.

As described above, the present invention detects a medium image using only a minimum area of the medium 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 performed in the image detecting operation.

In addition, the present invention can extract a medium image by extracting an image of a basic region, which is a part of the entire image, and then matching the entire image.

Thus, the present invention can handle the operation of detecting a medium image from a large amount of media in real time.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a media image detecting apparatus and method 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 detecting apparatus according to a preferred embodiment of the present invention.

In this embodiment, description will be made using a financial automatic machine that performs input / discharge of bills. However, the present invention can be applied not only to bills but also to media handling systems that handle various types of media such as checks, certificates, and tickets.

As shown in FIG. 3, the bill recognition apparatus 10 of the present invention receives bills through the input port 11. The input port 11 generates a signal when it detects an input of a bill.

A light emitting diode (hereinafter referred to as "LED") 13 that emits light to a bill conveyed by the conveying module 12 when the bill sensing signal is generated from the input port 11, And an image sensor 14 for scanning an image of the bill reflected by the light. At this time, the image sensor 14 scans an area larger than the paper currency standard in case the paper currency is not drawn in a straight state due to the vibration of the conveyance module 12. Accordingly, the scanned image includes an image of the bill and a margin image. The image sensor 14 preferably uses a charge-coupled device or a contact image sensor.

And an outline detecting unit 15 for detecting the outline of the bill image in the scanned image. The outline detection unit 15 may use various outline detection methods such as a prewith mask, a Robert mask, a laplacian mask, and a canny mask, but in the present embodiment, It is explained that the Sobel mask method having excellent detection accuracy is used. The contour detection unit 15 uses 'Gx' / 'Gy' to retrieve horizontal / vertical components of the scanned image to create a histogram in the X-axis / Y-axis direction. Tables 1a and 1b are 'Gx' / 'Gy' tables of the Sobel mask for retrieving the horizontal / vertical components of the scanned image.

The contour detecting unit 15 combines the image of 'Gx' and the image of 'Gy' into one image. The image of 'Gx' / 'Gy' has a value between 0 and 255 according to the brightness. Accordingly, the outline detecting unit 15 processes all values less than 128, which is half of the maximum value 255, as 0, i.e., black, and creates an image represented by only values of 128 or more. The outline of the bill image is detected in the thus created image.

A bill image scanned by the image sensor 14 may not be horizontally aligned but skew may occur. The inclination is generated in accordance with a conveyance state such as vibration or noise of the conveyance module 12 conveying the bill. When the banknote is conveyed in a horizontal state and no tilt is generated, it is preferable that the image is extracted after correcting the tilt.

And a minimum area detecting unit 16 for detecting a minimum area including the medium image on the image created by the outline detecting unit 15. [ The minimum area detection unit 16 creates a histogram in the X-axis / Y-axis direction on the image created by the contour detection unit 15. The histogram has a larger value as the flow of banknote images increases. The minimum area detection unit 16 detects a point where the contour of the bill image is detected according to the change of the histogram values, and detects a minimum area including the bill image.

And a rotation direction determination unit 17 for determining the rotation direction of the bill images. The rotation direction determination unit 17 calculates the widths of the right and left triangular areas around the highest vertex among the points where the detected minimum area and the contour of the banknote image meet. Then, the rotation direction determination unit 17 compares the calculated widths of the left and right triangular areas, and determines the direction in which the wide area is located as the rotation direction.

And a vertex extracting unit 18 for extracting a vertex of the medium image. The vertex extracting unit 18 extracts the vertexes of the banknote images by searching for points that meet the contour along a direction having a larger angle in the right and left directions toward the vertex of the medium image from the respective vertexes of the minimum area.

The slope calculating unit 19 calculates the slope of the medium image. The slope calculating unit 19 estimates the horizontal / vertical length of the medium image using the vertex coordinates of the medium image. Then, the slope is calculated by substituting the estimated horizontal / vertical length into the equation (1).

And an image detecting unit 20 for correcting the calculated inclination and extracting only a medium image from which margin images are excluded. The image detecting unit 20 rotates the bill image by the calculated slope about one of the vertex coordinates of the minimum area image, for example, the upper left vertex coordinate. To this end, the image detecting unit 20 detects only a banknote image in which a blank image is removed by mapping the coordinates of the new image backward from the original banknote image. Since the reverse mapping method fetches data from the original image based on the coordinates of the new image, blank coordinates do not occur in the new image. You can also import duplicate data from the original image, but you do not need to create a new image and then correct the image again. Accordingly, the image detecting unit 20 detects only the medium image whose slope of the estimated medium image size is corrected.

In addition, a control unit 21 for controlling the entire bill recognition apparatus 10 to detect the bill image is provided. The control unit 21 is preferably a central processing unit of the financial automatic machine including the bill recognition apparatus 10. [

In addition, it is preferable that a display unit 22 for displaying the media image in which the operation process of the bill recognition apparatus and the rotation direction, tilt, center point, and tilt of the medium image are corrected is provided.

Next, a bill image detection method of a 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 apparatus according to a preferred embodiment of the present invention.

In this embodiment, a description will be made using a bill of 10,000 won.

When the banknote is charged into the charging port 11 and conveyance by the conveying module 12 is started, the LED 13 illuminates the banknote under the control of the controller 21 in the tenth step S10 of FIG. 4 And the image sensor 14 scans the image of the bill reflected by the irradiated light. Figures 5A-5C illustrate examples of scanned images. As shown in FIGS. 5A to 5C, the scanned image includes a bill image and a margin image. A skew may be generated as the bill is drawn in an oblique state according to a conveying state such as vibration of the conveying module 12. [

If the slope is not generated, the amount of damage to the banknote is estimated, or the next operation is performed in accordance with the order of the winding type determination and the incoming direction estimation.

On the other hand, if a tilt occurs, the contour detection unit 15 detects the contour of the banknote image using the Sobel mask method in step 12 (S12). Will be described with reference to the image shown in Fig. 5B. Figure 6a shows the vertical components of the media image detected by 'Gx' in Table 1a. 6B shows the horizontal component of the medium image detected by 'Gy' in Table 1b.

The contour detecting unit 15 combines the vertical component and the horizontal component into one image as shown in FIG. 6C. The image obtained by performing the Sobel mask operation using 'Gx' and 'Gy' has a value between 0 and 255 according to the brightness. Therefore, the contour detecting unit 15 processes all values less than 128, which is half of the maximum value 255, to 0, i.e., black, and creates an image in which only values of 128 or more are displayed. FIG. 6D illustrates an image for displaying only the values of '128' or more by the contour detection unit 15. The outline of the bill image is detected through the thus created image.

In step S14, the minimum area detection unit 16 creates a histogram in the X-axis and Y-axis directions on the image created by the contour detection unit 15. [ FIG. 7A illustrates a histogram created from the image of the banknote. The histogram has a larger value as the flow of banknote images increases.

In step S16, the minimum area detection unit 16 detects a point where the contour of the bill image is detected according to the change of the histogram values, and detects a minimum area including the bill image. FIG. 7B shows an exemplary diagram for explaining a method of detecting a minimum area using a histogram. 7B, the minimum area detecting unit 16 detects the minimum area between the '2' point and the '3' point on the Y axis where the histogram value changes to a value other than '0' And performs a search in the horizontal direction between the points. The search is performed in the vertical direction between the '2' point and the '3' point on the X axis where the histogram value changes to a value other than '0', and between the '8' point and the '9' point. Accordingly, the minimum area detection unit 16 detects the minimum area including the contour of the bill image.

In step S18, the rotation direction determination unit 17 extracts points, i.e., virtual vertices, which meet the outline of the bill image, from the respective vertices of the detected minimum area. 8A to 8C are diagrams illustrating an example of a method for extracting a virtual vertex. In FIG. 8A, the coordinates E (x2, y3) of the virtual vertex are calculated using the vertex coordinates of the minimum area, for example, A (x1, y1) and B (x7, y7), C , y2), F (x8, y8), G (x6, y6) and H (x4, y4) are detected. At this time, y1 = y2 = y3, x1 = x8 = x7, y7 = y6 = y5, x3 = x4 = x5.

Next, in step S20, the rotation direction determination unit 17 determines the width of the left and right triangular-shaped margin images, that is, the widths of the first and second areas around the top vertex of the banknote image, that is, Compare. As a result of the comparison, if the width of the first area is narrower than the width of the second area, the rotation direction determination unit 17 determines that the banknote image is rotated in the right direction as shown in FIG. 8A. On the other hand, if the area of the second area is narrower than the area of the first area as shown in FIG. 8B, the rotating direction determining unit 17 determines that the banknote image is rotated in the leftward direction.

In step S22, the inclination calculating unit 19 calculates the inclination angle of the banknote image vertex from the vertexes A, B, C, and D of the minimum area based on the determined rotation direction And extracts the vertices of the banknote images.

Figs. 9A to 9C show exemplary diagrams for explaining a method of estimating a vertex. In FIG. 9A where the banknote image shown in FIG. 8B is enlarged, the minimum area image is divided into a banknote area pixel and a blank area pixel. At this time, if the vertex is searched from the left side to the right side of the banknote image, that is, at the angle 1 at which the inclination angle is gentle, the point detected by the minimum area detecting unit 16 in the 16th step (S16) 1 (x2, y2) is recognized as a vertex.

In order to solve such a problem, the tilt calculating unit 19 searches for a vertex by using an angle of 3, which is tilted relative to the first angle. For example, in the image rotated to the left as shown in Fig. 9B, the tilt calculating section 19 calculates the tilt angle of the image in the direction indicated by the arrow using the angle at which the tilt angle is relatively fast, And extracts the coordinates of the vertices. Further, in the image rotated to the right as shown in Fig. 9C, the tilt calculating section 19 calculates the tilt angle of the image in the direction indicated by the arrow using the angle at which the tilt angle is relatively fast, that is, And extracts the coordinates of the vertices.

In step S24, the slope calculating unit 19 estimates the horizontal length and vertical length of the banknote image using the coordinates (E, F, G, H) of the extracted vertexes. Then, the slope calculating unit 19 calculates the slope of the banknote image by substituting the estimated horizontal length and vertical length into the equation (1).

In step 26, the image detector 20 rotates the banknote image around any one of the extracted vertices E, F, G, and H to correct the calculated slope. For example, when the bill image is rotated to the left, the image detecting unit 20 rotates to the right about the point O (x8, y8) in Fig. 9B. On the other hand, when the bill image is rotated to the right, the image detecting unit 20 rotates to the left about the point O '(x2, y2) in FIG. 9C. Thus, the method of rotating the image to correct for the tilt may use a linear equation that passes through the coordinates, or may use the least squares method. In this embodiment, the image detecting unit 20 maps the data corresponding to the new image coordinates back to fetch from the data of the original image, in order to display the banknote image with the corrected slope. At this time, because the vertex coordinates (E, F, G, H) of the banknote image are recognized, the image detecting unit 20 rotates the banknote image using only the banknote image coordinates, . Thus, the image detecting section 20 can detect the banknote image excluding the margin image.

Figs. 10A to 10C show an example of explaining the image detection process. 10A, the control unit 21 determines that the slope of the banknote image as shown in FIG. 10A is 'Rotation direction: right, slope: 14.736495, rotation center point: x = 61, y = 48' It is possible to control the display unit 22 to display the estimated result on the screen. Then, the display unit 22 may display the banknote image whose inclination is corrected through the inclination correction process, as shown in FIG. 10C.

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

Although the present invention has been described using the banknote, the present invention can be applied to a medium image detecting apparatus that scans and recognizes images of various media such as checks, tickets, and certificates as well as bills, and a medium handling system using the apparatus.

delete

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.

BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 is a flow chart illustrating a general media image detection method.

2A to 2E are diagrams for explaining a general medium image detection method;

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

FIG. 4 is a flow chart illustrating a step of a media image detection method according to a preferred embodiment of the present invention; FIG.

Figures 5A-5C illustrate examples of media images recognized in a media image detection device.

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

FIGS. 7A and 7B are exemplary diagrams for explaining a method of detecting a minimum area. FIG.

8A and 8C are diagrams for explaining a method of estimating the direction of rotation;

9A to 9C are diagrams for explaining a method of extracting a vertex.

10A to 10C are exemplary diagrams for explaining an image detecting method.

delete

DESCRIPTION OF THE REFERENCE NUMERALS to the main parts of the drawings "

11: bill insertion slot 12: conveying module

13: LED 14: Image sensor

15: contour detection unit 16: minimum area detection unit

17: Rotation direction determination unit 18: Vertex point extraction unit

19: slope calculating section 20: image detecting section

21: control unit 22: display unit

Claims (25)

An outline detector for detecting an outline of the medium image, A minimum area detector for detecting an image of a minimum area including the medium image using a histogram value within the detected contour, A rotation direction determination unit for determining a rotation direction of the detected minimum area, A vertex extracting unit for extracting a vertex of the medium image based on the rotation direction, A slope calculating unit for calculating a slope of the medium image by using the coordinates of the extracted vertex, And an image detecting unit for correcting the calculated inclination to detect only the medium image from which the margin image is excluded. delete delete The apparatus according to claim 1, Determining a direction of rotation of the medium image by comparing widths of left and right spaces around the top vertex of the medium image, And determines that the space is rotated in a direction in which the space is located in the left and right spaces. delete The apparatus of claim 1, And extracts a vertex of the medium image by searching the vertices of the minimum area in a direction having a large inclination angle based on the determined rotation direction. The apparatus of claim 1, And searching for and extracting a vertex of the medium image in the determined rotation direction from each vertex of the minimum area. The apparatus according to claim 1, Estimating the horizontal and vertical lengths of the medium image using the vertex coordinates of the extracted medium image, and calculating the slope of the medium image based on the estimated horizontal length and vertical length. The image processing apparatus according to claim 1, And detects only the medium image excluding the margin image. 10. The image pickup apparatus according to claim 9, Wherein the backward mapping is performed with respect to the upper left vertex coordinates of the minimum area image. A media image detection apparatus comprising: a media image detection apparatus according to any one of claims 1 to 10; And a control unit for controlling the storage, receipt and delivery of the medium by using the medium image recognized by the medium image detection apparatus. delete Detecting a contour of the media image, Detecting an image of a minimum area including the medium image using the histogram value within the detected contour, Determining a rotation direction of the detected minimum area, Calculating a slope of the medium image using the coordinates of the vertex extracted based on the rotation direction, and And correcting the calculated slope to detect only the medium image from which the margin image is excluded. delete delete delete delete delete delete delete delete delete delete delete delete

Images