KR101337022B1 - Financial apparatus, medium sensing apparatus and method - Google Patents

Abstract

The present invention relates to a financial machine. The financial machine according to an aspect of the present invention includes: a medium entrance unit through which a medium including a letter group which is comprised of letters of different types and sizes is able to be deposited and withdrawn; a sensing unit for obtaining the image of the medium; and a control unit which determines a letter by obtaining an individual letter image from a letter group image after obtaining the letter group image from the obtained medium image. [Reference numerals] (10) Medium input/output unit;(20) Sensing unit;(30) Storage unit;(40) Control unit;(50) Memory unit;(60) Display unit

Description

Financial apparatus, medium sensing apparatus and method for detecting media {Financial apparatus, medium sensing apparatus and method}

The present specification relates to a financial device, a media sensing device and a media sensing method.

Generally, a financial instrument is a device that processes a financial business desired by a customer. The financial instrument can deposit and withdraw the medium or automatically transfer the medium. For example, the financial device may deposit or withdraw banknotes and checks.

The financial device may include a media sensing device for sensing the media. The media sensing device may include a sensing unit and a controller to determine the information detected by the sensing unit.

In the conventional sensing unit, an optical character reader or a magnetic ink character reader is used. However, in the optical character reader, when the quality of the scanned image is good, the character reading accuracy is good, but when the quality of the scanned image is poor, the character reading accuracy is low.

An object of the present invention is to provide a financial device, a media sensing device, and a media sensing method capable of accurately reading a character from an acquired media image.

According to an aspect, a financial device includes a media entry / exit unit in which a medium including a character group consisting of characters having different types and sizes can be inserted or withdrawn; A sensing unit for acquiring an image of the medium; And a controller configured to determine a character based on the image acquired by the sensor, wherein the controller acquires a character image from the character group image to obtain a character after obtaining the character group image from the image of the obtained medium. It is characterized by determining.

According to another aspect, an apparatus for sensing a medium may include an optical character recognizer for obtaining an image of a medium including a character group consisting of characters having different types and sizes; And a controller for acquiring a character group image from the image acquired by the optical character recognizer, and obtaining a separate character image from the obtained character group image to determine a character from each character image.

According to another aspect of the present disclosure, a method for detecting a medium may include obtaining an image of a medium including a character group consisting of characters having different types and sizes by a sensing unit; Obtaining, by the controller, one or more character group images from the obtained image of the medium; Acquiring by the controller an individual character image from the one or more character group images; And determining, by the controller, a character from the individual character image.

According to the proposed invention, a medium containing characters of different sizes or types can be detected quickly and accurately using an optical image.

1 is a block diagram schematically illustrating a financial device according to an embodiment of the present invention.
2 illustrates an example of a medium according to an embodiment of the present invention.
3 and 4 are diagrams for explaining a series of processes for obtaining character information.
5 is a flowchart illustrating a medium sensing method according to an embodiment of the present invention.

Hereinafter, some embodiments of the present invention will be described in detail with reference to exemplary drawings. It should be noted that, in adding reference numerals to the constituent elements of the drawings, the same constituent elements are denoted by the same reference symbols as possible even if they are shown in different drawings. In the following description of the embodiments of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the difference that the embodiments of the present invention are not conclusive.

In describing the components of the embodiment of the present invention, terms such as first, second, A, B, (a), and (b) may be used. These terms are intended to distinguish the constituent elements from other constituent elements, and the terms do not limit the nature, order or order of the constituent elements. When a component is described as being "connected", "coupled", or "connected" to another component, the component may be directly connected or connected to the other component, Quot; may be "connected," "coupled," or "connected. &Quot;

A financial device according to an embodiment of the present invention may be a financial device that obtains various media such as banknotes, securities (including checks), giro, coins, gift certificates, etc. and processes and / or withdraws such as deposits, Such as processing such as issuance of paper money, release of paper money, release of gift certificate, and the like. Examples of such financial instruments include an automated teller machine (ATM) such as a cash dispenser (CD), a cash recycling machine, and the like. However, the financial instrument is not limited to the above-described example, and may be various devices for automating the financial business such as FIS (Financial Information System).

Hereinafter, an embodiment of the present invention will be described on the assumption that the financial instrument is a financial automatic instrument. However, this assumption is only for convenience of explanation, and the technical idea of the present invention is not limited to the financial automation equipment.

1 is a block diagram schematically illustrating a financial device according to an embodiment of the present invention.

Referring to FIG. 1, the financial device 1 according to an embodiment of the present disclosure may include a media input / output unit 10 for introducing or extracting a medium, and a media sensing device for sensing the medium.

The apparatus for sensing a medium may include a sensing unit 20 for sensing an incoming medium or a medium to be extracted, and a controller 40 for determining a state of a medium based on information detected by the sensing unit 20. Can be.

In addition, the financial device 1 includes a storage unit 30 in which a medium is stored, a memory unit 50 in which information for use in reading the medium is stored, and a display unit 60 for displaying a processing state of the medium. ) May be included.

The detector 20 may include at least an optical character reader. The optical character reader may include a light emitting portion and a light receiving portion, and may acquire an image transmitted through the medium or the reflected image information of the medium.

2 is a diagram illustrating an example of a medium according to an embodiment of the present invention.

Referring to FIG. 2, among the acquired image mediums M, the information obtained by the sensor 20 is character field information. By obtaining such character field information, the amount or state of the medium can be determined. The text field information may include one or more text group images G1.

At this time, in the present specification, the letter refers to a visual sign system irrespective of language such as Korean, alphabet, Chinese, Roman, and numbers.

3 and 4 are diagrams for explaining a series of processes for acquiring text information, and FIG. 5 is a flowchart illustrating a medium sensing method according to an embodiment of the present invention.

Hereinafter, an example of detecting a medium when the medium is inserted will be described.

2 to 5, the medium is fed through the medium entry / exit unit (S1). The input medium is moved to the sensing unit 20, and an image of the input medium is obtained by the sensing unit 20 (S2).

Then, the controller 40 first obtains the character group image from the obtained image of the medium (S3). Referring to FIG. 2, in the image of the medium M, the control unit 40 acquires, by way of example, one character group image (G1: primary character group image).

In general, the position on which the character M should be printed on the medium M is already determined. In addition, four pieces of coordinate information of the character group image to be obtained for each medium are stored in the memory unit 50 in advance. That is, four coordinate information is stored to acquire one character group image.

Since the size may vary depending on the type of the media, the position where the text is printed may vary according to the size of the media. Thus, the memory unit 50 may store coordinate information for each size of the medium. As another example, the memory unit 50 may store a length value for determining the size of an image to be acquired along with two coordinate information.

Therefore, when the image of the medium M is recognized, the coordinates of the four vertices of the recognized image are determined, and the primary character group image is obtained using the coordinate information of the character group image corresponding to the determined four vertex coordinates. do.

The primary character group image may be obtained by cutting an area defined by coordinates for acquiring a character group image in the image of the medium.

The obtained primary character group image includes a plurality of characters. Hereinafter, a case in which the types of the plurality of characters are different and the sizes of the plurality of characters are different will be described. In addition, the types of letters will be described with an example of alphabets and numbers.

The obtained character group image G1 includes a character 111 and background information 112 other than the character. In this case, the background color of the character group image G1 may be a color of the medium, and the color of the character may be black.

Next, the controller 40 corrects the obtained primary character group image to obtain a secondary character group image (S4).

The controller 40 inverts the color of the primary character group image G1 obtained in step S3 to obtain the inverted first group image G11. In the first group image G11, the color of the text is white, for example, and the background color is black.

Next, the controller 40 performs a segmentation process of removing unnecessary background (information) from the first group image G11.

First, the first group image G11 is divided into a plurality of pixels, and a gray value of each pixel is added in the horizontal direction. That is, the sum of gray values is obtained for each row. Next, the gray sum of each row is compared to find the point where the difference in gray values is greatest between two adjacent rows, and the image is cropped (crop the top and bottom margins of the image).

Then, similarly, the gray value of each pixel is added in the vertical direction. That is, the sum of gray values is obtained for each column. Then, we find the points with the greatest difference in gray values between two adjacent columns. Then, two points located at the outermost sides of the found points are searched to obtain an image of the second group image G21 which is finally processed (cutting the left and right margins of the image).

However, the position of the margin cut in FIG. 3 is for ease of explanation, and the actual cut portion may vary for each medium. The reason is that the point where the difference in the cray value is large may vary according to the scan state, and the cut point may be the same position as the boundary of the character or a position spaced apart from the boundary of the character.

The second group image G21 is corrected so that the font of each character is the same in the second group image G21 to obtain a third group image G31.

First, the gray value of each pixel of the character is added in the vertical direction. When the sum of gray values for each character is plotted on the graph, each character has one or more maximum values and two minimum values. And the distance between the two minimum values is the horizontal size of the expected character.

After obtaining the horizontal size of each character, the gray value of the pixel is added in the horizontal direction for each character. The gray sum of each row is compared to find the point where the difference in gray values between the two adjacent rows is greatest. When the sum of gray values for each character is plotted on the graph, each character has one or more maximum values and two minimum values. And the distance between the two minimum values is the vertical size of the character expected.

The horizontal size and the vertical size of each acquired character may be different. Therefore, by using bilinear interpolation, the characters are corrected so that the horizontal and vertical are constant sizes (the size of the reference characters).

In this case, the size of the reference character may be stored in the memory unit 50 or may be selected as the size of any one character (eg, the smallest character) among the characters belonging to the character group.

That is, the second character group image acquisition step in step S4 includes the steps of inverting the color of the primary character group image, a segmentation step of removing unnecessary background (information) from the inverted primary character group image; A character size equalization step of equalizing the size of the character.

In the present embodiment, an image sharpening step of sharpening an image of a character before or after the character size equalization step may be further performed.

Next, the controller 40 obtains an individual character image N1 from the obtained secondary character group image G31 (S5).

That is, the controller 40 obtains the individual character image N1 through the segmentation process as described above in the secondary character group image. At this time, the process of inverting the color of the individual character image obtained after the segmentation process may be further performed. Accordingly, the color of the text in the finally obtained individual text image is black, for example, and the background color is white. Of course, it is also possible that the inversion process is not performed after the segmentation process.

Next, the controller 40 compares the information stored in the memory unit 50 with the obtained individual character image N1 and determines individual characters (S6). In detail, the controller 40 divides the obtained individual character image N1 into a plurality of pixels. Then, the character information is determined using the predetermined template of the individual character image N1 divided into a plurality of pixels.

In the present specification, the size of the template is equal to the sum of two or more pixels, and as illustrated in FIG. 4, a plurality of templates T1 to T3 for determining individual characters may be provided, and the sizes of the plurality of templates may be provided. May be different. Such templates are pre-generated and stored in the memory unit 50 in consideration of fonts of characters printed on a medium. The type or number of templates may be different for each type of character.

For example, the form of the template for determining numbers and the form for the template for determining letters may be different. Alternatively, the form of the template for determining the number and the form for the template for determining the number may be partly the same, and the other part may be different. In addition, the number of templates for determining numbers and the number of templates for determining characters may be different.

However, since the type of the letter is not known before the letter is determined, the template for determining the number may be used first, and then the template for determining the alphabet may be used, or vice versa.

The controller 40 selects a specific template and places the selected specific template on an individual character image divided into a plurality of pixels (the pixel in which the specific template is first placed may be determined or changed). Check the gray value of the pixel being positioned.

The controller 40 may determine a character by moving a specific template from an individual character image, and after performing the determination process of the specific character using the specific template, determine the determination of the specific character using the next template. Can be. That is, in this embodiment, the process of determining one character may be performed a plurality of times.

As described above, the controller 40 primarily determines one individual character using a plurality of templates, and determines the next character after the determination of one individual character is completed.

As another example, the controller 40 may determine a character by comparing the color of each pixel with information stored in the memory unit 50 in the individual character image divided into a plurality of pixels. For example, when determining the number 0, the memory unit 50 stores a plurality of previously obtained and stored numerical information, and determines whether the number 0 matches the number 0.

The control unit 40 secondarily determines an undetermined character in step S6 (S7).

For example, some of the templates stored in the memory unit 50 are extracted to determine the undetermined characters in the same manner as the method of determining the characters primarily. As another example, an undetermined character may be secondarily determined using a second template, which is a kind template different from a plurality of templates (primary template) stored in the memory unit 50.

Next, the controller 40 extracts some characters from all the characters and determines characters in a third manner (S8). The reason for determining the characters in the third order is to accurately determine the characters that can be mistaken. Characters capable of erroneous determination may be determined by a plurality of experiments and stored in advance in the memory unit 50.

For example, the misdeterminable letter may be the number "8" and the letter "B". If the character determined in step S6 or step S7 is "8", the letter "B" may be incorrectly determined to be "8", and so in step S8, the control unit 40 determines some characters in a third manner.

In the third step of determining the text, the same template or the other template may be used as the template used in the first or second determination of the text.

According to the present exemplary embodiment, after a character is primarily determined, a character that is determined to be misdeterminable among characters is extracted, instead of all the characters that the determined character is determined correctly, and only the extracted characters are targeted. By judging whether or not an error is determined, there is an effect that the time for determining a character is shortened.

Next, the controller 40 determines whether or not all characters are recognizable among all the determined characters (S9). As a result, when all the characters are recognizable, the controller 40 performs the media processing (S10). On the other hand, if one or more characters of the determined total characters are not recognizable, a recognition error is displayed on the display unit 60 (S11).

According to the present invention, although the quality of the image of the acquired medium is not good, the character group image correction process and a plurality of character determination steps are performed, so that the character can be recognized accurately.

The present invention may further include the following embodiments.

In the present invention, it is also possible to obtain the individual character image by cutting the second group image without performing the character size equalization step of equalizing the character size in step S4. In this case, the size of the acquired text image may be different, and in this case, one or more of the size, shape, or number of templates may vary according to the size of the text.

In addition, the step of determining a character secondaryly or the step of determining a character secondary may be omitted.

While the present invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not limited to the disclosed embodiments. That is, within the scope of the present invention, all of the components may be selectively coupled to one or more of them. Furthermore, the terms "comprises", "comprising", or "having" described above mean that a component can be implanted unless otherwise specifically stated, But should be construed as including other elements. All terms, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Terms used generally, such as terms defined in a dictionary, should be interpreted to coincide with the contextual meaning of the related art, and shall not be interpreted in an ideal or excessively formal sense unless explicitly defined in the present invention.

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The protection scope of the present invention should be interpreted by the following claims, and all technical ideas within the equivalent scope should be interpreted as being included in the scope of the present invention.

20: detection unit 40: control unit

Claims (18)

A media entry / exit unit in which a medium including a character group composed of characters of different types and sizes can be inserted or extracted;
A sensing unit for acquiring an image of the medium; And
And a controller configured to determine a character based on the image obtained by the detector.
The control unit, after acquiring a character group image using the print position and size of the predetermined character in the image of the obtained medium, and obtains the individual character image from the character group image to determine the character. The method of claim 1,
Further comprising a memory unit for storing information for use in the determination of the medium,
The controller determines a character using the information stored in the memory unit and the individual character image. The method of claim 1,
The controller acquires a primary character group image from an image of the obtained medium,
Correcting the acquired primary character group image to obtain a secondary character group image,
A financial device that obtains an individual character group image from the obtained secondary character group image. The method of claim 1,
The controller may first determine a character of the individual character image using a primary template, and secondly determine a character of an undetermined individual character image among the individual character images using a secondary template. A financial device for finally determining the selected characters of the first and second characters determined by using a template, a secondary template or a tertiary template. The method of claim 3, wherein
Correcting the primary group image includes inverting the colors of the primary character group image, cropping the top and bottom margins and the left and right margins in the primary character group image, and sizes of characters having different sizes within the primary character group image. A financial device comprising the same. The method of claim 5, wherein
Acquiring the individual character image is a financial device to obtain an individual character image of the same size. The method of claim 5, wherein
Correcting the primary group image includes inverting the colors of the primary character group image and cropping the top and bottom and left and right margins in the primary character group image,
Acquiring the individual character image is a financial device to obtain individual character images of different sizes. The method of claim 5, wherein
The first and second character group images are divided into pixels, and the upper and lower margins are based on two points where the sum of gray values for each row, which is the sum of gray values of pixels in the horizontal direction, is the largest difference in the sum of gray values between two adjacent rows. Financial device to cut the. The method of claim 5, wherein
The primary character group image is divided into pixels, and the sum of gray values for each column, which is the sum of gray values of pixels in the vertical direction, is found to have the largest difference in the sum of gray values between two adjacent columns, and is located at the outermost sides on both sides. A financial device that cuts the left and right margins based on two points. The method of claim 1,
The controller determines a character after dividing the obtained individual character image into a plurality of pixels. 11. The method of claim 10,
The controller determines a character by using the colors of each of the plurality of pixels. The method of claim 9,
The controller determines characters by using a plurality of templates sequentially,
The template is a financial device having a size larger than one pixel. 13. The method of claim 12,
The plurality of templates are generated in consideration of the font of the character. 13. The method of claim 12,
Financial instruments with different forms or numbers of templates, depending on the type of letter. The method of claim 1,
The determination of the character is carried out a number of times,
Financial instruments that differ in the type or number of letters to be determined for each time. The method of claim 1,
The determination of the character is carried out a number of times,
Financial instruments of different types or numbers of templates used to determine letters for each time. An optical character recognizer for obtaining an image of a medium including a character group composed of characters of different types and sizes; And
A control unit for acquiring a character group image from the image acquired by the optical character recognizer using a preset printing position and size, and acquiring an individual character image from the obtained character group image to determine a character from each character image; Media sensing device. Obtaining an image of a medium including a character group consisting of characters having different types and sizes by a sensing unit;
Obtaining one or more character group images by the controller using a printing position and size of a predetermined character in the obtained image of the medium;
Acquiring by the controller an individual character image from the one or more character group images; And
Determining a character from the individual character image by the controller.

Images