KR20180049301A - Method for extracing the subligual vein and image apparatus for performing the method - Google Patents

Abstract

The present invention relates to a method for extracting a sublingual vein region and an image apparatus for performing the same. The method for extracting a sublingual vein region includes the steps of: obtaining a color image and an infrared image for the lower end of a tongue in a state in which the end of the tongue of a user is attached to upper teeth; and providing an image for one or more sublingual veins selected from a clinician after extracting the sublingual vein flowing in the lower end of the tongue by using a central line for distinguishing one or more blood vessels included in the obtained color and infrared images. Accordingly, the present invention can more clearly obtain the vein under the tongue.

Description

TECHNICAL FIELD [0001] The present invention relates to a method for extracting a sublingual vein region and a video apparatus for performing the method. [0002]

The following description relates to a technique for extracting a sublingual vein region, and more particularly, to a method for extracting a color image and an infrared image with respect to the lower tongue portion and extracting a sublingual vein region included in each image.

Subligual vein is located on the lower surface of the tongue and means one straight vein on one side without bending or vein spasm. Then, the sublingual vein judges the health condition of the user through five criteria about the thickness (TK), length (LE), color (CL), shape (SP) and mass (ND).

At this time, the sublingual vein can acquire a color image in which the color information of the tongue is expressed relatively accurately. However, because the position of the sublingual vein is located below the tongue, it is difficult to distinguish the sublingual vein from the shadow due to the possibility of shadowing in the process of acquiring the color image.

Therefore, in order to extract the sublingual vein, a method of extracting a more accurate sublingual vein is needed to complement the shadow generated in the color image.

The present invention can provide a method for extracting a sublingual vein region and an image device for acquiring a color image and an infrared image with respect to the lower end of the tongue to more clearly derive the vein under the tongue according to the characteristics of an image.

The present invention provides a method for extracting two subglottic veins from a color image and an infrared image using a final center line for discriminating one or more blood vessels and a method for extracting subglottic vein regions and providing an image device for a clinician diagnosing blood vessels have.

A method of extracting a sublingual vein region according to an embodiment of the present invention includes the steps of obtaining a color image and an infrared image of a lower end portion of the tongue in a state where a user attaches an end of the tongue to the upper teeth; Deleting a skin region excluding the tongue region from the acquired color image and infrared image; Removing all regions except the blood vessels in the tongue region based on the color image and the infrared image in which the skin region is deleted; Dividing the color image and the infrared image using an initial centerline for distinguishing one or more blood vessels included in the color image and the infrared image; Binarizing each of the divided color image and the infrared image, and determining a final centerline of the binarized color image and the infrared image; Applying the determined final centerline to a color image and an infrared image to extract a sublingual vein flowing at a lower end of the tongue; And selecting one or more sublingual veins of the extracted sublingual vein from the user and providing an image including the selected sublingival vein.

The step of deleting the skin region according to an exemplary embodiment may include a step of deleting a skin region in the color image using a filtering method including at least one of colorimetric information (CIE a Thresholding), luminance information (Cb Thresholding), and chrominance information Can be deleted.

The step of deleting the skin region according to an embodiment may include the steps of i) applying the filter method used for the color image to the infrared image equally, or ii) applying the skin region deleted from the color image to the infrared image, The skin area excluding the tongue area in the infrared image can be deleted.

According to an exemplary embodiment, using the median filtering, all regions except the blood vessels included in the color image and the infrared image in which the skin region is deleted may be removed with noise.

According to an exemplary embodiment, the dividing may include: determining an initial centerline for separating the at least one blood vessel using the center point of the pixels constituting the at least one blood vessel; And dividing each of the color image and the infrared image according to the position of the blood vessel into the left area and the right area based on the determined initial center line.

According to an exemplary embodiment, the final centerline of the tongue area of each image can be determined using the center of gravity of the blood vessel included in each of the divided regions of the binarized color image and the infrared image.

The sublingual vein according to an exemplary embodiment may be arranged in different areas in the divided regions in the color image and the infrared image according to the final center line. In accordance with the area and geometry information according to the shape arranged at the lower end of the tongue, Vascular abnormalities can be predicted.

An image acquiring unit for acquiring a color image and an infrared image with respect to a lower end portion of the tongue in a state where a user attaches an end of the tongue to the upper teeth; A skin area deleting unit for deleting a skin area excluding the tongue area in the obtained color image and infrared image; A region removing unit for removing all regions except the blood vessels in the tongue region based on the color image and the infrared ray image in which the skin region is deleted; An image dividing unit dividing the color image and the infrared image using an initial center line for distinguishing one or more blood vessels included in the color image and the infrared image; A final centerline determining unit for binarizing the divided color image and the infrared image, respectively, and determining a final centerline for the binarized color image and the infrared image; A sublingual vein extracting unit for applying the determined final center line to a color image and an infrared image to extract a sublingual vein flowing at a lower end of the tongue; And And a sublingival vein supply unit for selecting one or more sublingual veins of the extracted sublingual vein from the user and providing an image including the selected sublingival vein.

The skin region deletion unit may delete a skin region excluding the tongue region in the color image using a filtering method including at least one of color space information, luminance information, and color difference information.

The skin region deletion unit according to an embodiment may be configured such that i) the filter method used for the color image is applied to the infrared image equally, or ii) the skin region deleted from the color image is applied to the infrared image, The skin area excluding the tongue area can be deleted.

The region removing unit according to an embodiment can remove all areas except the blood vessels included in each of the color image and the infrared image in which the skin area is deleted by noise using median filtering.

The image dividing unit may include an initial centerline determining unit for determining an initial centerline for identifying the at least one blood vessel using the center point of the pixels constituting the at least one blood vessel; And a region dividing unit dividing each of the color image and the infrared image according to the position of the blood vessel into the left area and the right area based on the determined initial center line.

The final centerline determining unit may determine a final centerline of the tongue region of each image using the center of gravity of the blood vessel included in each of the divided regions in the binarized color image and the infrared image.

The sublingual vein according to an exemplary embodiment may be arranged in different areas in the divided regions in the color image and the infrared image according to the final center line. In accordance with the area and geometry information according to the shape arranged at the lower end of the tongue, Vascular abnormalities can be predicted.

The sublingual vein region extraction method and imaging apparatus according to an embodiment of the present invention can obtain a vein under the tongue according to the characteristics of the image more clearly by complementing the subterranean vein boundary through the infrared image based on the acquired color image .

The sublingual vein region extraction method and imaging apparatus according to an embodiment of the present invention divides each of the two blood vessels included in the color image and the infrared image to determine whether the diagnosis error is maximized Can be reduced.

1 is a conceptual diagram for acquiring an image including a sublingual vein using a camera according to an embodiment.
FIG. 2 is a view for explaining a detailed operation performed by an imaging device for extracting a sublingual vein according to an embodiment.
FIG. 3 is a diagram illustrating a process of extracting a sublingual vein region from each of a color image and an infrared image according to an embodiment.
4 is a view for explaining a flow of deriving a sublingual vein from a color image and an infrared image according to an embodiment
5 is a flowchart illustrating a method of extracting a sublingual vein region according to an embodiment.
FIG. 6 is a view showing data for determining a blood vessel problem for a clinician's selected left sublingual vein or right sublingual vein according to an embodiment.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a conceptual diagram for acquiring an image including a sublingual vein using a camera according to an embodiment.

Referring to FIG. 1, the imaging device 101 may use a camera (not shown) to capture a sublingual vein. Here, the camera may be used to acquire an image of a sublingual vein located at the lower end of the tongue, that is, a camera disposed with the camera oriented from below to the upside. Here, the camera may correspond to at least one of a color camera capable of acquiring a color image 103 for a sublingual vein or an infrared camera capable of acquiring an infrared image 104 for a sublingival vein.

Here, the color camera is an apparatus for acquiring an image of a subject through a photographing lens, and can acquire information including three primary color outputs of red (R), green (G), and blue (B) . And, the infrared camera can be used to grasp the laceration of the surface under the tongue, and the infrared image 104 may include an image with no infrared light source or ii) an image with infrared light source depending on the situation, The present invention is not limited thereto, and various infrared images can be obtained.

At this time, in order to take a picture of the sublingual vein, the user can lift the tip of the tongue and make an operation so that the tip of the tongue comes into contact with the back of the upper and lower teeth. In addition, the user can apply force as if pushing the tooth forward with the tongue in a fixed state with the tongue end attached to the upper teeth so that the sublingual vein can protrude well. This can be done to make the veins on the lower surface of the tongue look more dull. As described above, according to the present invention, it is possible to acquire the image of the tongue lower side more accurately and easily by suggesting the photographing posture of the user in order to acquire the image of the lower tongue.

Then, the imaging device can extract each blood vessel, that is, the sublingual vein, from the color image 103 and the infrared image 104 including the surface under the tongue of the user through the camera. In the present invention, the color image 103 and the infrared image 104 are divided into a left area and a right area, and the divided areas are divided into a left area and a right area. 2 vessels per image can be extracted by extracting blood vessels from the area.

The present invention provides a clinician with a total of four sublingual veins extracted from the color image 103 and the infrared image 104 and the clinician has at least two sublingual vessels for diagnosing vascular problems among the four sublingival veins provided You can choose veins. Further, the present invention provides a clinician to diagnose a problem of a blood vessel more accurately by providing a selected sublingual vein image by a clinician.

FIG. 2 is a view for explaining a detailed operation performed by an imaging device for extracting a sublingual vein according to an embodiment.

2, the imaging device 201 includes an image acquiring unit 202, a skin area deleting unit 203, a region eliminating unit 204, an image dividing unit 205, a final center line determining unit 206, An extraction unit 207 and a sublingual vein supply unit 208. [

Specifically, the image acquisition unit 202 may acquire an image of a lower portion of a user's tongue using a camera mounted on the imaging device or interlocked with the imaging device. At this time, the image acquiring unit 202 may acquire a color image and an infrared image in order to improve the accuracy of the sublingual vein flowing at the lower end of the tongue.

In other words, because the color of the sublingual vein is relatively well distinguished from the color of the lower portion of the tongue due to the inherent color of the tongue and the intrinsic color of the blood vessel, the present invention provides color information on the tongue and blood vessels Can be acquired more accurately. However, the color image is likely to cause an image shadow due to the position of the tongue, and the division of blood vessels may be unclear due to the shadow. Therefore, in order to solve this problem, the present invention can extract the sublingual vein more accurately for the blood vessel by additionally acquiring the infrared image for dividing the boundary using the image.

The skin region deleting unit 203 deletes the skin region excluding the tongue region in the color image using a filter method including at least one of CIE a Thresholding, Cb Thresholding, and Cr Thresholding Can be deleted. In addition, the skin region deleting unit 203 may apply the filter scheme used for the color image to the infrared image in the same way, or ii) apply the skin region deleted from the color image to the infrared image, The skin area excluding the tongue area can be deleted.

Here, the skin region deletion unit 203 removes the noise (skin region) included in the infrared image more accurately by applying the infrared method or the filter method applied to delete the skin region included in the color image in the same manner can do. In other words, the infrared image contains information about the lacerations of the tongue area, which makes it difficult to distinguish between the tongue area and the skin area. Accordingly, the present invention can compensate for the disadvantages of the above-described infrared region by applying the filter method and the deleted skin region applied to the color image in which the tongue region and the skin region are clearly distinct from each other to the infrared region.

The region removing unit 204 may remove all regions except the blood vessels included in the color image and the infrared image in which the skin region is deleted by noise using median filtering. In other words, the region removing unit 204 may remove an area other than the blood vessels constituting the tongue area, that is, the 'tongue', thereby filtering the image so that only the blood vessel exists in the image.

The image divider 205 may divide the color image and the infrared image using an initial center line for distinguishing one or more blood vessels included in the color image and the infrared image. In other words, the image dividing unit 205 can determine an initial center line for dividing the image using the center point of the pixels constituting the blood vessel with respect to the blood vessel existing in the image. For example, each image may include only two blood vessels centered on the larynx. The image segmentation unit 205 can determine an initial centerline for distinguishing a blood vessel positioned on the left side and a blood vessel positioned on the right side through the center value of pixels constituting each of the two blood vessels.

Then, the image divider 205 divides each of the color image and the infrared image according to the position of the blood vessel into the left area and the right area based on the determined initial center line.

The final centerline determining unit 206 may binarize the divided color image and the infrared image, respectively, and determine a final centerline for the binarized color image and the infrared image. Here, the final centerline determination unit 206 can determine the final centerline of the tongue area of each image using the center of gravity of the blood vessel included in each of the divided regions in the binarized color image and the infrared image.

The sublingual vein extracting unit 207 can extract the sublingual vein flowing at the lower end of the tongue by applying the determined final center line to the color image and the infrared image.

The sublingual vena cava 208 may select one or more of the extracted sublingual veins from the user and provide an image containing the selected sublingival vein.

FIG. 3 is a diagram illustrating a process of extracting a sublingual vein region from each of a color image and an infrared image according to an embodiment.

Referring to FIG. 3, the imaging apparatus can derive the center points of the pixels constituting one or more blood vessels included in the color image and the infrared image in which the interface is reduced. Specifically, the imaging device can acquire a color image including an arterial blood vessel, that is, a sublingual vein flowing at the lower end of the tongue, and an infrared image through a color camera and an infrared camera. In general, the sublingual vein flows through the lingual frenulun located between the lower part of the tongue and the bottom of the mouth, and the flowing blood vessels can be referred to as the sublingual vein. And these blood vessels can flow in different forms from the underside of the tongue. That is, blood vessels flowing on the lower surface of the tongue are different in shape from person to person, and area and geometric information may be different depending on whether the person has a vascular disease.

Therefore, the imaging device acquires a color image and an infrared image including two blood vessels, extracts a sublingual vein according to two blood vessels from the acquired image, Can be determined.

For this purpose, the imaging device can distinguish two blood vessels included in the color image and the infrared image, respectively. In detail, the present invention can determine an initial center line in a whole image using center points of pixels constituting a sublingual vein included in a color image and an infrared image to which ROI clustering and flattening are applied.

Here, the imaging apparatus can determine an initial centerline along the center point of the pixels constituting the blood vessel included in the color image through Equation (1) below.

Then, the imaging apparatus can determine an initial centerline along the center of the pixels constituting the blood vessel included in the infrared image through Equation (2) below.

For example, the imaging device may derive the center points of the pixels of two blood vessels included in the color image and the infrared image, respectively, and determine the initial center line in the image based on the center points of two pixels corresponding to the two blood vessels.

Then, the image device can divide each of the color image and the infrared image into a left area and a right area based on the determined initial center line. That is, the image device can divide each image into two regions so as to include respective blood vessels located on the right and left sides of the larynx.

The image device can binarize the divided color image and the infrared image, respectively, and determine the final center line by using the center of gravity of the blood vessel included in each of the divided regions of the binarized color image and the infrared image. Here, the center of gravity may be derived for each of the color image and the infrared image.

That is, the center of gravity corresponding to the blood vessels (mclx, mcly), (mcrx, mcry) according to the blood vessels located at the left and right is derived from the color image, mirly), (mirrx, mirry) can be derived.

Then, the image device can determine the final center line for each of the binarized color image and the infrared image using the center of gravity respectively derived from the color image and the infrared image. That is, the imaging device primarily determines the sublingival vein, that is, the center line to the blood vessel, using the pixels constituting the image, and then secondarily determines the weight center of the sublingual vein included in the image, that is, By determining the center line along the center, the left and right sides of the image can be adjusted to be symmetrical.

The final centerline along the center of gravity of the left and right blood vessels can be determined through Equation (3) below, and the final centerline along the center of gravity of the left and right blood vessels can be determined through the following Equation (4) have.

The imaging device can extract the sublingual vein flowing at the lower end of the tongue by applying the determined final center line to the color image and the infrared image. At this time, the imaging device extracts the sublingual vein for the left vessel and the sublingual vein for the right vessel in the sublingual vein for the left vessel and the sublingual vein image for the right vessel in the color image, respectively. Finally, The image of the vein can be extracted.

The four sublingual veins extracted through this procedure can be provided as information on the left sublingual vein or the right sublingual vein at the request of the clinician. In other words, as mentioned above, the sublingual vein is not realized symmetrically. Therefore, the left and right blood vessels may have different shapes, even though the sublingual vein is extracted from the undersurface of the tongue of a person. And the sublingival veins with different shapes may contain different information about the blood vessels. For example, the left subclavian vein of the color image and the right subclavian vein of the IR image are narrow and long, whereas the right subclavian vein of the color image and the left subclavian vein of the IR image may be both wide and wide have. Finally, the four sublingual veins obtained through color imaging and infrared imaging can appear in the shape of different blood vessels.

In addition, these sublingual veins may exhibit different vascular conditions depending on the clinician's findings.

The present invention distinguishes two blood vessels obtained through an image, and extracts a sublingual vein therefrom, so that the clinician can be used to easily diagnose the blood vessel condition selectively. In other words, the present invention provides a total of four sublingual veins extracted from each of the color image and the infrared image to the user, and the user, that is, the clinician, determines the state of the user's blood vessel based on the four sublingual veins provided from the imaging device At least two sublingival veins can be selected. For example, the clinician may select the left sublingual vein of the color image and the right sublingual vein of the infrared image, respectively, of the four sublingival veins provided from the imaging device. The imaging device can then provide the clinician with an image that includes the two sublingival veins selected by the clinician, either individually or as a single image.

In addition, the present invention can perform a logical combination (or /) on each binarized color image and infrared image to extract a sublingual vein region flowing at the lower end of the tongue.

As a result, the imaging device obtains the color information on the blood vessels on the lower surface of the tongue from the color image, obtains the thermal information on the blood vessels on the lower surface of the tongue from the infrared image, and performs logical combination between the acquired color information and the thermal information , It is possible to extract a more accurate sublingival vein.

In order to distinguish between different types of blood vessels according to the type of image, the shape of the left blood vessel, and the shape of the right blood vessel, the present invention may be applied to a user And selects at least two images for diagnosing the state of the blood vessel from the user, and delivers the selected image to the user.

The present invention can be used as an index for a user's health diagnosis by extracting a sublingual vein region from a color image and an infrared image at the lower end obtained in the same environment.

4 is a flowchart illustrating a method of extracting a sublingual vein region according to an embodiment.

In step 401, the imaging device may acquire a color image of the lower portion of the tongue using a color camera. In step 402, the imaging device may acquire an infrared image of the lower portion of the tongue using an infrared camera.

In order to acquire a color image and an infrared image, the user may take an attitude as described with reference to FIG. 1 and acquire a color image and an infrared image with respect to the lower end of the tongue corresponding to the posture viewed through the camera, respectively.

Thereafter, in step 403, the imaging device may remove the skin area except the tongue area included in the color image. Here, the skin region may be a body part adjacent to the tongue, such as gums, lips, and the like. Then, the imaging apparatus can delete the skin region excluding the tongue region using colorimetric information (CIE a Thresholding), luminance (Cb Thresholding) and chrominance (Cr Thresholding).

In addition, the imaging apparatus can remove the skin region excluding the tongue region included in the infrared image. At this time, the image device can remove the skin area excluding the tongue area by applying the same colorimetric information, luminance, and color difference used in the color image. Alternatively, the imaging apparatus can delete the skin region excluding the tongue region in the infrared image by applying the skin region deleted from the color image to the infrared ray image. The reason for applying the filter method (filter method using colorimetric information / luminance / color difference) or the skin region deleted from the color image to the infrared image is the same as the filter used for deleting the skin region in the color image, This is because classification based on information / luminance / chrominance is easier than infrared image.

Therefore, the present invention can easily distinguish the tongue area and the skin area from the infrared image by applying the deleted skin area (lip / gums) to the infrared image based on the filter method used in the color image.

Therefore, in deleting a skin region from an infrared image, the present invention can apply i) the result of a color image, or ii) apply a filter identical to a filter method used in a color image to an infrared image.

In steps 404 and 405, the imaging device may remove any area other than the sublingual vein in the tongue area. In other words, the imaging device can remove the noise included in each of the color image and the infrared image in which the skin region is deleted by using median filtering. For example, the imaging device may perform preprocessing to fill the removed sphere with CIE a, Cr, and Cb thresholding.

In steps 406 and 407, the imaging device may reduce all areas except the sublingual vein in the tongue area included in the color image and the infrared image by reducing the boundary surface based on the color image and the infrared image from which the noise is removed have. That is, the imaging device can derive only the subglottic vein flowing at the lower end of the tongue through ROI clustering and planarization.

In steps 408 and 409, the imaging device may binarize images derived only from the sublingival vein.

In step 410, the imaging device can distinguish two blood vessels included in the color image and the infrared image, respectively. In detail, the present invention can determine an initial center line in a whole image using center points of pixels constituting a sublingual vein included in a color image and an infrared image to which ROI clustering and flattening are applied. Then, the image device can divide each of the color image and the infrared image into a left area and a right area based on the determined initial center line. That is, the image device can divide each image into two regions so as to include respective blood vessels located on the right and left sides of the larynx.

The image device can binarize the divided color image and the infrared image, respectively, and determine the final center line by using the center of gravity of the blood vessel included in each of the divided regions of the binarized color image and the infrared image. Here, the center of gravity may be derived for each of the color image and the infrared image.

In step 511, the imaging device may apply the determined final centerline to the color and infrared images to extract the sublingual vein flowing at the lower end of the tongue. At this time, the imaging device extracts the sublingual vein for the left vessel and the sublingual vein for the right vessel in the sublingual vein for the left vessel and the sublingual vein image for the right vessel in the color image, respectively. Finally, The image of the vein can be extracted.

Thereafter, the imaging device provides the user with a total of four sublingual veins extracted from the color image and the infrared image, respectively, and at least two sublingival veins can be selected by the user. And, the imaging device can be used easily for the clinician to selectively diagnose the vascular condition by providing the user with the selected sublingual vein image.

FIG. 5 is a view showing data for determining a blood vessel problem for a clinician's selected left sublingual vein or right sublingival vein according to an embodiment.

Referring to FIG. 5, the clinician can divide two blood vessels included in a color image and an infrared image, respectively, in order to minimize diagnostic errors in determining a blood vessel problem. In this case, the color image and the infrared image may include blood vessels of different shapes, even though images of the lower portion of the tongue of the same person are acquired as they include different values in representing objects. For example, the color image may include a color value for the tongue blood vessel, and the infrared image may include a light source for the tongue blood vessel.

Therefore, the present invention can make a more sophisticated judgment by measuring the area and the geometric information based on the image of the blood vessel selected by the clinician.

The methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software.

While the invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. This is possible.

Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined by the equivalents of the claims, as well as the claims.

101: Imaging device
102: tongue
103: Color video
104: Infrared image

Claims (14)

A method for extracting a sublingual vein region performed by an imaging device,
Acquiring a color image and an infrared image with respect to a lower end portion of the tongue while the end of the tongue is attached to the upper teeth by a user;
Deleting a skin region excluding the tongue region from the acquired color image and infrared image;
Removing all regions except the blood vessels in the tongue region based on the color image and the infrared image in which the skin region is deleted;
Dividing the color image and the infrared image using an initial centerline for distinguishing one or more blood vessels included in the color image and the infrared image;
Binarizing each of the divided color image and the infrared image, and determining a final centerline of the binarized color image and the infrared image; And
Applying the determined final centerline to a color image and an infrared image to extract a sublingual vein flowing at a lower end of the tongue;
Selecting one or more sublingual veins of the extracted sublinginal vein from the user and providing an image including the selected sublingival vein;
The method comprising the steps of: The method according to claim 1,
Wherein deleting the skin region comprises:
A sublingual vein region extraction method for deleting a skin region excluding a tongue region in the color image using a filtering method including at least one of colorimetric information (CIE a Thresholding), luminance information (Cb Thresholding), and chrominance information . 3. The method of claim 2,
Wherein deleting the skin region comprises:
i) applying the same filter scheme used for the color image to the infrared image, or
ii) applying a skin region deleted from the color image to an infrared image to delete a skin region excluding a tongue region in the infrared image. The method according to claim 1,
Wherein the removing comprises:
A method for extracting a sublingual vein region, which removes all regions excluding blood vessels included in each of a color image and an infrared image, from which the skin region has been deleted, by using median filtering. The method according to claim 1,
Wherein the dividing step comprises:
Determining an initial centerline for identifying the one or more blood vessels using the center point of the pixels constituting the at least one blood vessel;
Dividing each of the color image and the infrared image according to the position of the blood vessel into the left area and the right area based on the determined initial center line
The method comprising the steps of: The method according to claim 1,
Wherein the determining comprises:
And determining a final center line for a tongue area of each image using the center of gravity of the blood vessel included in each of the divided regions in the binarized color image and the infrared image. The method according to claim 1,
The sub-
The color image and the infrared image according to the final center line may be arranged in different areas in the respective divided areas,
Wherein a portion of the tongue in the lower portion of the tongue is divided into a plurality of regions, An image acquiring unit for acquiring a color image and an infrared image with respect to a lower end portion of the tongue in a state where a user attaches an end of the tongue to the upper teeth;
A skin area deleting unit for deleting a skin area excluding the tongue area in the obtained color image and infrared image;
A region removing unit for removing all regions except the blood vessels in the tongue region based on the color image and the infrared ray image in which the skin region is deleted;
An image dividing unit dividing the color image and the infrared image using an initial center line for distinguishing one or more blood vessels included in the color image and the infrared image;
A final centerline determining unit for binarizing the divided color image and the infrared image, respectively, and determining a final centerline for the binarized color image and the infrared image; And
A sublingual vein extracting unit for applying the determined final center line to a color image and an infrared image to extract a sublingual vein flowing at a lower end of the tongue; And
A sublingual venous punc- ture selecting one or more sublingual veins of the extracted sublingual vein from the user and providing an image including the selected sublingival vein;
. 9. The method of claim 8,
Wherein the skin area deleting unit comprises:
Wherein the skin region excluding the tongue region in the color image is deleted using a filtering method including at least one of colorimetric information, luminance information, and color difference information. 10. The method of claim 9,
Wherein the skin area deleting unit comprises:
i) applying the same filter scheme used for the color image to the infrared image, or
ii) applying the skin region deleted from the color image to the infrared image, and deleting the skin region excluding the tongue region in the infrared image. 9. The method of claim 8,
Wherein the area removing unit comprises:
And removes all areas except the blood vessels included in each of the color image and the infrared image in which the skin area is deleted by noise using median filtering. 9. The method of claim 8,
Wherein the image dividing unit comprises:
An initial centerline determining unit for determining an initial centerline for identifying the at least one blood vessel using the center point of the pixels constituting the at least one blood vessel;
And dividing the color image and the infrared image according to the position of the blood vessel into a left area and a right area based on the determined initial center line,
. 9. The method of claim 8,
The final centerline determining unit determines,
And determining a final center line for a tongue region of each image using the center of gravity of the blood vessel included in each of the divided regions in the binarized color image and the infrared image. 9. The method of claim 8,
The sub-
The color image and the infrared image according to the final center line may be arranged in different areas in the respective divided areas,
Wherein an abnormality of the blood vessel of the user is predicted according to the area and the geometry information according to the shape disposed at the lower end of the tongue.

Images