KR101789166B1 - Method and Apparatus for jaundice diagnosis based on an image, Assisting Apparatus for jaundice diagnosis based on an image - Google Patents

Abstract

An image-based jaundice diagnostic method and apparatus are disclosed. According to an embodiment of the present invention, there is provided a method of diagnosing an image-based jaundice comprising the steps of: receiving an image for diagnosis of jaundice in which a user's specific body part and a reference object are photographed together at a place where the user is currently located; Generating color distortion information indicating a degree of color distortion of the reference object included in the jaundice diagnostic image; Generating a correction image for jaundice diagnosis by correcting color distortion of the jaundice diagnostic image based on the color distortion information; And diagnosing a jaundice symptom for the user using the jaundice diagnostic correction image.

Description

TECHNICAL FIELD The present invention relates to an image-based jaundice diagnosis method and apparatus, and an image-based jaundice diagnosis assistant apparatus,

The present invention relates to jaundice diagnosis, and more particularly, to a method and apparatus for image-based jaundice diagnosis.

Jaundice is caused by excessive accumulation of yellow bile bile (bilirubin), which is produced during the decomposition process of special proteins containing iron, such as hemoglobin (hemoglobin), in the body, It is said to be colored yellow on mucous membrane.

There are some problems with conventional diagnostic methods for diagnosing jaundice based on a scientific view or a serological test. There is a problem that subjective diagnosis can not be made when diagnosing jaundice through visual examination, which is a physical examination that diagnoses jaundice with the naked eye. Therefore, in order to confirm jaundice, blood should be taken from the patient to measure the blood bilirubin level, and the suspect of jaundice should visit the medical institution equipped with the device to measure it, and the time can be delayed until the blood test result is obtained .

Also, patients with jaundice should visit the hospital periodically to check for signs of illness during the treatment period. There was a problem in that accessibility to healthcare services was deteriorated if the patient lived far from the medical institution or the patient's condition was not able to visit the medical institution periodically.

Korean Patent Laid-Open No. 10-2014-0108649 (entitled " Video Game Monitoring Retinal Disease, Disclosure Date: Sep. 14, 2014)

It is an object of the present invention to provide an image-based jaundice diagnostic method and apparatus for diagnosing jaundice of a user remotely.

According to another aspect of the present invention, there is provided a method for diagnosing jaundice comprising: receiving a jaundice diagnostic image of a user's specific body part and a reference object taken together; Generating color distortion information indicating a degree of color distortion of the reference object included in the jaundice diagnostic image; Generating a correction image for jaundice diagnosis by correcting color distortion of the jaundice diagnostic image based on the color distortion information; And diagnosing a jaundice symptom for the user using the jaundice diagnostic correction image.

Preferably, the step of diagnosing a jaundice symptom for the user includes transmitting the jaundice diagnosis request including the jaundice diagnosis correction image to the diagnosis server for requesting jaundice diagnosis for the user; And receiving a jaundice diagnosis result, which is a diagnosis result of the jaundice diagnosis request, from the diagnosis server.

Preferably, the jaundice diagnosis result is determined based on an image analysis result of the jaundiced diagnostic correction image, wherein at least one of medical history information on the user and medical treatment information on a person having jaundice symptoms is selected ≪ / RTI >

Preferably, the jaundice diagnosis result includes at least one of jaundice symptoms of the user based on a correlation between the user's disease and the image analysis result estimated based on at least one of history information on the user and treatment information on the other person May also include health risk information indicating whether or not this is a health hazard.

Preferably, when the reference object is a white object, the step of generating the color distortion information may include a step of obtaining the first color temperature of the reference object in the reference image photographed by the reference object under the reference light source stored in advance, Wherein the color temperature difference information is a difference value between the first color temperature of the reference object and the second color temperature of the reference object, and the color temperature difference information is a difference value between the second color temperature of the reference object and the reference color temperature of the reference object, It is possible to generate the correction image for jaundice diagnosis by correcting the color temperature of the jaundice diagnosis image to be the same as the color temperature.

Advantageously, the particular body part of the user may comprise at least one of the user's face and eye.

Preferably, the jaundice diagnosis method according to an embodiment of the present invention further includes outputting a user interface for capturing the jaundice diagnosis image, wherein the receiving of the jaundice diagnosis image is performed in real time It is possible to receive the photographed image based on the provided photographing guideline.

Preferably, the jaundice diagnostic image may be an image in which the reference object is worn or attached to a specific body part of the user.

Preferably, the reference object is a lenticular lens, the lenticular body may be composed of a single area having a white color, or a plurality of areas each having a different color.

Preferably, the color distortion information includes at least one of an illuminance of the environment in which the jaundice diagnosis image is photographed, a photography related setting value of the user device that has photographed the jaundice diagnostic image, and a lens aberration of the lens mounted on the user device Can be generated on the basis of more.

Preferably, when the reference image of the reference object is a YCbCr format and the jaundice diagnosis image is an RGB format under a previously stored reference light source, the step of generating the color distortion information may convert the jaundice diagnosis image into a YCbCr format Generating a transform image for diagnosing jaundice; And generating the color distortion information by calculating a first luminance distribution function that is a cumulative probability density function of luminance values (Y) of all the pixels belonging to the conversion image for jaundice diagnosis, Wherein the juxtaposition conversion image corresponding to the first luminance distribution function has a second luminance distribution function that is a cumulative probability density function for a luminance value (Y) of all the pixels belonging to the reference image, A diagnostic calibration image can be generated.

According to another aspect of the present invention, there is provided a method for diagnosing jaundice comprising: receiving a reference image of a reference object at a location where a user is currently located; Generating color distortion information indicating a degree of color distortion of the reference object included in the reference image; Receiving an image for diagnosis of jaundice in which a specific body part of the user is photographed under the same condition as the condition for photographing the reference image; Generating a correction image for jaundice diagnosis by correcting color distortion of the jaundice diagnostic image based on the color distortion information; And diagnosing a jaundice symptom for the user using the jaundice diagnostic correction image.

According to another aspect of the present invention, there is provided a jaundice diagnosis apparatus comprising: a receiving unit for receiving a jaundice diagnosis image taken together with a specific body part of a user and a reference object; A distortion information generating unit for generating color distortion information indicating a degree of color distortion of the reference object included in the jaundice diagnosis image; An image correcting unit for correcting color distortion of the jaguar diagnostic image based on the color distortion information to generate a corrected image for jaundice diagnosis; And a diagnosis unit for diagnosing a jaundice symptom for the user using the jaundice diagnostic correction image.

Preferably, the diagnosis unit includes a transmission unit that transmits the jaundice diagnosis request including the correction image for jaundice diagnosis and requests the jaundice diagnosis to the user to the diagnosis server; And a result processor for performing the diagnosis using the jaundice diagnosis result when the jaundice diagnosis result as a diagnosis result for the jaundice diagnosis request is received from the diagnosis server through the receiver.

Preferably, the jaundice diagnosis result is determined based on an image analysis result of the jaundiced diagnostic correction image, wherein at least one of medical history information on the user and medical treatment information on a person having jaundice symptoms is selected ≪ / RTI >

Preferably, the jaundice diagnosis result includes at least one of jaundice symptoms of the user based on a correlation between the user's disease and the image analysis result estimated based on at least one of history information on the user and treatment information on the other person May also include health risk information indicating whether or not this is a health hazard.

Preferably, when the reference object is a white object, the distortion information generation unit generates the distortion color information of the reference object based on the first color temperature of the reference object in the reference image photographed by the reference object under the reference light source stored in advance, Wherein the color temperature difference information is a difference value between a first color temperature of the jaundiced image and a second color temperature of the object, and the image correction unit corrects the color temperature of the jaundat diagnosis image so that the color temperature of the reference object of the jaundice diagnosis image becomes equal to the first color temperature, The correction image for jaundice diagnosis can be generated by correcting the color temperature.

Advantageously, the particular body part of the user may comprise at least one of the user's face and eye.

Preferably, the jaundice diagnosing apparatus according to an embodiment of the present invention further includes a user interface managing unit for outputting a user interface for photographing the jaundice diagnosis image, wherein the receiving unit includes a photographing guide It is possible to receive the photographed image based on the line.

Preferably, the jaundice diagnostic image may be an image in which the reference object is worn or attached to a specific body part of the user.

Preferably, the reference object is a lenticular lens, the lenticular body may be composed of a single area having a white color, or a plurality of areas each having a different color.

Preferably, the color distortion information includes at least one of an illuminance of the environment in which the jaundice diagnosis image is photographed, a photography related setting value of the user device that has photographed the jaundice diagnostic image, and a lens aberration of the lens mounted on the user device Can be generated on the basis of more.

Preferably, when the reference image obtained by photographing the reference object is a YCbCr format and the jaundice diagnosis image is an RGB format under a pre-stored reference light source, the distortion information generator converts the jaundice diagnosis image into a YCbCr format, And generates the color distortion information by calculating a first luminance distribution function that is a cumulative probability density function of the luminance value (Y) of all the pixels belonging to the conversion image for jaundice diagnosis, and the image correction unit The diagnostic image for jaundice diagnosis can be generated by correcting the conversion image for jaundice diagnosis corresponding to the distribution function to have a second luminance distribution function which is a cumulative probability density function for the luminance value (Y) of all the pixels belonging to the reference image have.

According to another aspect of the present invention, there is provided a jaundice diagnosis apparatus comprising: a receiver for receiving a reference image of a reference object at a location where a user is currently located; A distortion information generating unit for generating color distortion information indicating a degree of color distortion of the reference object included in the reference image; When the image for jaundice diagnosis in which the specific body part of the user is photographed is received under the same condition as the condition for photographing the reference image through the receiver, the color distortion of the jaundiced image for diagnosis is corrected based on the color distortion information, An image correction unit for generating an image; And a diagnosis unit for diagnosing a jaundice symptom for the user using the jaundice diagnostic correction image.

According to another aspect of the present invention, there is provided a jaundice diagnostic apparatus comprising: a jaundice diagnostic apparatus for receiving a reference eye image of an eyeball of a user at a first location of a user, A receiving unit for receiving a jaundice diagnostic image of the user's eye taken at a place; A distortion information generation unit for generating color distortion information indicating a degree of color distortion in the jaundice diagnostic image by comparing the iris color in the reference eye image with the iris color in the jaundice diagnostic image; An image correcting unit for correcting color distortion of the jaguar diagnostic image based on the color distortion information to generate a corrected image for jaundice diagnosis; And a diagnosis unit for diagnosing a jaundice symptom for the user using the jaundice diagnostic correction image.

According to another aspect of the present invention, there is provided an image-based jaundice diagnosis apparatus comprising: a receiver for receiving a jaundice diagnosis image of a user's specific body part and a reference object taken together; A distortion information generating unit for generating color distortion information indicating a degree of color distortion of the reference object included in the jaundice diagnosis image; An image correcting unit for correcting color distortion of the jaguar diagnostic image based on the color distortion information to generate a corrected image for jaundice diagnosis; And a transmission unit for transmitting the correction image for jaundice diagnosis to a device of a doctor.

According to another aspect of the present invention, there is provided an image-based jaundice diagnosis assistant device comprising: a receiver for receiving a jaundiced diagnostic correction image having color distortion corrected as an image taken together with a specific body part of a user and a reference object; ; A retrieval unit for retrieving history information about the user from a patient history DB including history information on a plurality of jaundice patients; And an output unit for outputting the retrieved history information on the user and the jaundice diagnostic correction image.

Preferably, the image-based jaundice diagnosis assistant device according to an embodiment of the present invention performs image analysis on the jaundiced diagnostic correction image to determine whether the user has jaundice symptoms and the image analysis result indicating the depth of jaundice And the output unit may further output the image analysis result.

According to an embodiment of the present invention, it is possible to remotely diagnose jaundice of a user, thereby reducing time and economic waste caused when a user without jaundice symptoms visits the hospital, There is no need for medical treatment, which reduces doctor's working hours.

Further, according to another embodiment of the present invention, a diagnosis result of jaundice symptoms automatically calculated based on an image for diagnosis of jaundice, history information of a user, and medical information on a person having jaundice symptoms is provided by a doctor as auxiliary data , Jaundice diagnosis and prescription can be done, the physician's medical burden is reduced.

According to another embodiment of the present invention, the user can be diagnosed with jaundice symptoms at any time, thereby enabling an early diagnosis of disease.

1 is a flowchart illustrating an image-based jaundice diagnostic method according to an embodiment of the present invention.
2 is a view illustrating an image for diagnosing jaundice according to an embodiment of the present invention.
3 is a diagram illustrating a user interface according to an embodiment of the present invention.
4 is a flowchart illustrating an image-based jaundice diagnosis method according to another embodiment of the present invention.
5 is a view for explaining an image-based jaundice diagnosis apparatus according to an embodiment of the present invention.
6 is a diagram for explaining a method of generating a correction image for jaundice diagnosis using a luminance distribution function according to an embodiment of the present invention.
7 is a view for explaining an image-based jaundice diagnosis assistant apparatus according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all changes, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals are used for like elements in describing each drawing.

The terms first, second, A, B, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a flowchart illustrating an image-based jaundice diagnostic method according to an embodiment of the present invention.

In step 110, the jaundice diagnostic device receives the jaundice diagnostic image that is taken together with the user's specific body part and the reference object.

At this time, the image for diagnosing jaundice may be an image photographed at a place where the user is currently located, and the specific body part of the user may be a face of the user, an eyeball, or the body part such as a wrist for identifying the user's skin.

In addition, the reference object is a white object such as a white paper, a white post-it, a white cloth, a white flak stick model, a white hat, a white band, and a white eyeglass as a reference object for correcting colors of the user's face skin and eyes. Or may be a color band, a color chart, or the like composed of a plurality of colors.

In addition, the image for diagnosing jaundice may be obtained by a method in which a user takes a reference object by taking it in the hand, or by placing it at a position near a user's body part and then taking a picture, or by taking a picture ≪ / RTI >

For example, the reference object may be composed of a single region having white or an eye composed of a plurality of regions each having a different color, which will be described later with reference to Fig.

The reason for generating the image for diagnosing jaundice by photographing the user's specific body part and reference object together is that the color of the user's body part may be distorted depending on the environment of the user's body part It is because.

For example, when a user with a hyperactive symptom is taken to the hospital's office and the user's eye is photographed under a fluorescent lamp, and the user subsequently takes a picture of the user's eye with the incandescent lamp turned on at his home, The user's eyeball becomes yellow more in the image taken by the incandescent lamp, even if it does not change. Therefore, there is a need to correct such color distortion, so that a jaundice image for diagnosis is taken together with the reference object.

In another embodiment, a user interface for photographing a jaundice diagnosis image provided by the jaundice diagnostic apparatus when the user takes an image for jaundice diagnosis may be used, which will be described later with reference to Fig.

In step 120, the jaundice diagnostic apparatus generates color distortion information indicating the degree of color distortion of the reference object included in the jaundice diagnostic image.

At this time, the color distortion information includes the illumination of the environment in which the jaundice diagnostic image is captured, the shooting related setting values (aperture value, shutter speed, ISO, etc.) of the user device that has captured the jaundice diagnostic image, And the like.

Here, the user device includes all devices having a photographing function capable of photographing a user's image, such as a user's smartphone, a mobile phone, a notebook computer, a desktop computer, and a communication function capable of transmitting an image for jaundice diagnosis to the outside, User device or a device mounted on a user device.

At this time, the color distortion information may be information based on the color temperature.

More specifically, the jaundice diagnosis apparatus includes a first color temperature, which is a color temperature of a reference object in a reference image in which a reference object (or a reference body and a specific body part of the user) is photographed under a reference light source stored in advance, Which is a difference value between the first color temperature and the second color temperature which is the color temperature of the object, as color distortion information.

Here, the reference light source may be a virtual light source based on a specific color temperature (5600K or 3200K), or may be an actual light source of a hospital office that the user has previously desired.

For example, if the reference object is white A4 paper, since the first color temperature value which is the color temperature for the white A4 paper in the reference image in which white A4 paper is photographed under a light source based on a specific color temperature is already known, Which is a difference value between a first color temperature value and a second color temperature which is a color temperature of a reference object included in an image for jaundice diagnosis, is generated to generate color distortion information. In this case, the jaundice diagnosis apparatus may store only the first color temperature value for the white A4 paper in advance, instead of storing the reference image in advance.

Also, when a user with jaundice symptoms visits a hospital, the reference light source is a light source installed in the clinic of the hospital in the case of a reference image generated by photographing a reference object in a clinic of the hospital or photographing a reference object and a user together , The color temperature of the reference object in the reference image becomes the first color temperature.

In another embodiment, the color distortion information may be information based on luminance (Y).

For example, when the reference image is in the YCbCr format and the image for jaundice diagnosis is in the RGB format, the jaundice diagnosis apparatus converts the image for jaundice diagnosis in the RGB format into the YCbCr format to generate a converted image for jaundice diagnosis, The first luminance distribution function, which is a cumulative probability density function for the luminance value (Y) of the pixel, can be calculated and generated as color distortion information.

In step 130, the jaundice diagnostic apparatus corrects the color distortion of the jaundice diagnosis image based on the color distortion information, thereby generating a correction image for jaundice diagnosis.

If the color distortion information is the color temperature difference information, the jaundice diagnosis apparatus corrects the color temperature of the jaundice diagnosis image so that the color temperature of the basic object of the jaundice diagnosis image becomes equal to the first color temperature based on the color temperature difference information, .

If the color distortion information is a first luminance distribution function, the jaundice diagnostic apparatus calculates a second luminance distribution function, which is a cumulative probability density function for the luminance value (Y) of all the pixels belonging to the reference image in the YCbCr format, The correction image for jaundice diagnosis is generated by correcting the jaundice diagnosis image corresponding to the distribution function to have the second luminance distribution function

This will be described with reference to FIG.

6 is a view for explaining a method of generating a correction image for jaundice diagnosis using a luminance distribution function according to an embodiment of the present invention.

6, a red graph represents a first luminance distribution function corresponding to a jugular diagnostic image requiring correction, a blue graph represents a second luminance distribution function corresponding to a reference image, a horizontal axis represents a luminance value, and a vertical axis represents a luminance value Cumulative probability density value.

6, in the process of correcting the first luminance distribution function to match the second luminance distribution function, the luminance value of the pixel in the first luminance distribution function (red graph) is converted into the second luminance distribution function having the same cumulative probability density value To the luminance value of the pixel in the pixel (blue graph).

For example, when the luminance value of the pixel x1 in the first luminance distribution function (red graph) is to be corrected, the pixel x2 having the cumulative probability density value equal to 0.3, which is the cumulative probability density value of the pixel x1, Function (blue graph), and converts the luminance value of the pixel x1 into the luminance value of the pixel x2.

In step 140, the jaundice diagnostic device diagnoses jaundice symptoms for the user using the correction image for jaundice diagnosis.

Preferably, when diagnosing a jaundice symptom for a user, the jaundice diagnosis apparatus transmits a jaundice diagnosis request including a correction image for jaundice diagnosis and requesting a jaundice diagnosis to the user to a diagnosis server (e.g., a server provided in the hospital) , Diagnosis may be performed by receiving a diagnosis result of jaundice, which is a diagnosis result for a jaundice diagnosis request, from the diagnosis server.

In another embodiment, the jaundice diagnostic device may perform a jaundice diagnosis by directly analyzing the jaundiced diagnostic image without transmitting it to the diagnostic server.

On the other hand, the diagnosis server can determine the jaundice diagnosis result based on the image analysis result on the correction image for jaundice diagnosis.

In yet another embodiment, the diagnostic server may determine the jaundice diagnostic result based not only on the image analysis results, but also on medical history information about the user, medical information on others with jaundice symptoms, and the like.

At this time, the diagnosis server estimates the disease of the user based on at least one of the medical history information on the user and the medical treatment information on the other person, and based on the correlation between the estimated user's disease and the image analysis result, It may also produce a diagnosis of jaundice, which includes health risk information indicating whether it is at risk for health. For example, the health risk of jaundice symptoms when the user is suffering from A disease may be higher than the health risk of jaundice symptoms when the patient is suffering from B disease. Therefore, even a user suffering from the same degree of jaundice may be judged to have a high health risk if he or she is suffering from the disease A, and the health risk is not high when the patient is suffering from the disease B.

In this case, the jaundice diagnostic device may output a message asking the user who is suffering from the A disease to visit the hospital as soon as the health risk is high.

On the other hand, the illness suffered by the user may be automatically estimated by the machine learning based on history information about the user, medical information on the other, or the like, but may be directly determined by the doctor.

In addition, the diagnosis result of jaundice may be determined automatically through image analysis and various data analysis as described above, but it may be decided by the physician as an auxiliary data of image analysis and various data analysis results. At this time, the doctor considers the history information of the user together to diagnose and prescribe the jaundice symptom, so that it can provide the patient-customized diagnosis and prescription.

Thus, according to the embodiment of FIG. 1, after the user does not want to go to the hospital in advance or only visits the hospital for the first time for the reference object and the user's specific body part, There is an advantage of being able to diagnose jaundice symptoms remotely without having to visit.

2 is a view illustrating an image for diagnosing jaundice according to an embodiment of the present invention.

Referring to FIG. 2, a user wears an eye 220 having a plurality of regions having different colors in his or her eyeball 210 and photographs an image for diagnosis of jaundice. In this case, the eye 220 may be composed of a plurality of regions having different colors, but may be a single region having white.

In the case where the reference object is the lid 220 as described above, there is an advantage that the user can easily wear it and can take an image. On the other hand, upon receiving the photographed jaundice diagnosis image as shown in FIG. 2, the jaundice diagnosis apparatus calibrates the jaundice diagnosis image based on hues corresponding to a plurality of regions included in the eye 220, do.

For example, the jaundice diagnosis apparatus calculates the RGB pixel difference value by subtracting the RGB pixel value for each of the colors under the reference light source from the RGB pixel values for each of the colors included in the jaundice diagnosis image, Value is added to the RGB pixel value of each of the pixels included in the image for diagnosing jaundice, thereby generating a correction image for jaundice diagnosis.

Next, the jaundice diagnostic device transmits a calibration image for diagnosis of jaundice to the diagnostic server.

Next, the diagnostic server extracts all or a part of the pixels corresponding to the eyeball or facial skin of the user, and selects jaudal pixels belonging to the RGB pixel value interval corresponding to the jaundice of the extracted pixel values.

Finally, the jaundice diagnostic device can diagnose whether the user has jaundice symptoms and the depth of jaundice by comparing the ratio of jaundice pixels among pixels extracted from the user's eye or facial skin to at least one threshold value.

For example, if the ratio of jaundice pixels is 50% or more, the jaundice symptoms are present. If the ratio of jaundice pixels is 80% or more, it can be diagnosed as jaundice. The user of the jaundice diagnostic device can change these thresholds as needed.

3 is a diagram illustrating a user interface according to an embodiment of the present invention.

3, a user interface 232, 234, 236 for capturing an image for diagnosis of jaundice is output to the user device 230. The user inputs his or her eye 210 to the upper left of the user device 230 And the user's eye 220 is aligned with the eye area 234 on the upper right side of the user device 230 and then clicked on the lower shooting button 236 to display the jaundice diagnosis image .

At this time, the user takes an image for diagnosis of jaundice according to the shooting guidelines provided in real time in the user interfaces 232, 234, and 236.

For example, if the user is too close to the user device, the user interface 232, 234, or 236 may display a message saying that the user's eye 210 is slightly backward, You may.

In addition, the photographing button 236 may be used to adjust the focus of the subject or the size of the eye area 232 and the eye area 234 on the user interfaces 232, 234, and 236.

4 is a flowchart illustrating an image-based jaundice diagnosis method according to another embodiment of the present invention.

In step 410, the jaundice diagnostic device receives a reference image of the reference object at the location where the user is currently located.

In step 420, the jaundice diagnostic apparatus generates color distortion information indicating the degree of color distortion of the reference object included in the reference image.

The present embodiment differs from the embodiment of FIG. 1 in that color distortion information is generated using a reference image obtained by photographing a reference object at a place where the user is currently located.

At this time, the color distortion information may be generated based on the color temperature difference information as described above, or may be generated using the luminance distribution function.

In step 430, the jaundice diagnostic device receives the jaundice diagnostic image that has taken the user's specific body part under the same condition as the condition of shooting the reference image.

At this time, the same shooting conditions mean that they are photographed at the same light source, the same surrounding environment, and the same place.

In step 440, the jaundice diagnostic apparatus generates a corrected image for jaundice diagnosis by correcting the color distortion of the jaundice diagnostic image based on the color distortion information.

At this time, since the image for diagnosis of jaundice is captured under the same condition as the reference image, it is possible to correct effectively even if the color distortion of the image for diagnosis of jaundice is corrected using the color distortion information generated by using the reference image.

In step 450, the jaundice diagnostic device diagnoses jaundice symptoms for the user using the calibration image for jaundice diagnosis.

5 is a view for explaining an image-based jaundice diagnosis apparatus according to an embodiment of the present invention.

5, the jaundice diagnosis apparatus 500 according to an embodiment of the present invention includes a receiving unit 510, a distortion information generating unit 520, an image correcting unit 530, and a diagnosis unit 540.

The receiving unit 510 receives the jaundice image for diagnosis, in which the user's specific body part and the reference object are photographed together at the place where the user is currently located.

The distortion information generating unit 520 generates color distortion information indicating the degree of color distortion of the reference object included in the jaundice diagnostic image.

The image correcting unit 530 corrects the color distortion of the image for jaundice diagnosis based on the color distortion information to generate a corrected image for jaundice diagnosis.

The diagnostic unit 540 diagnoses jaundice symptoms for the user using the jaundice diagnostic correction image.

At this time, the diagnosis unit 540 may include a transmission unit (not shown) and a result processing unit (not shown).

The transmitting unit includes a calibration image for jaundice diagnosis and sends a jaundice diagnosis request to the diagnosis server (not shown) requesting jaundice diagnosis for the user.

In another embodiment, instead of sending a jaundice diagnostic request to the diagnostic server, the sending unit may send the jaundice diagnostic correction image directly to the physician's device.

At this time, the device of the doctor includes all the devices having a communication function capable of receiving a calibration image for jaundice diagnosis, such as a doctor's smartphone, a mobile phone, a notebook, and a desktop computer, and a display function capable of outputting a calibration image for jaundice diagnosis.

The result processor receives the jaundice diagnosis result, which is the diagnosis result of the jaundice diagnosis request, from the diagnosis server (not shown) through the receiver 510, and performs jaundice diagnosis for the user using the jaundice diagnosis result. Preferably, the jaundice diagnostic apparatus 500 according to an exemplary embodiment of the present invention may further include a user interface management unit (not shown) for outputting a user interface for capturing an image for diagnosis of jaundice.

The jaundice diagnostic apparatus 500 according to another embodiment of the present invention can operate as follows.

The receiving unit 510 receives the reference image of the reference object at the location where the user is currently located.

The distortion information generation unit 520 generates color distortion information indicating the degree of color distortion of the reference object included in the reference image.

The image correcting unit 530 receives the jaundiced image for which the user's specific body part is photographed under the same condition as the condition for photographing the reference image through the receiving unit 510, To generate a calibration image for jaundice diagnosis.

The diagnostic unit 540 diagnoses jaundice symptoms for the user using the jaundice diagnostic correction image.

The jaundice diagnostic apparatus 500 according to another embodiment of the present invention may operate as follows.

The receiving unit 510 receives the reference eye image obtained by photographing the user's eyeball in the first place where the photographing condition is known, and receives the jaundiced image for the user's eyeball in the second place other than the first place.

Here, the first place may be a hospital office, and the second place may be a place other than a hospital office such as a user's home.

The distortion information generation unit 520 generates color distortion information indicating the degree of color distortion in the jaundice diagnostic image by comparing the iris color in the reference eye image with the iris color in the jaundice diagnostic image.

The reason for generating the color distortion information by comparing the iris colors is that the iris color does not change even if the user has jaundice symptoms, so that if the iris colors in the reference eye image and the jaundice diagnosis image are different, And the degree of color distortion can be known.

The image correcting unit 530 corrects the color distortion of the image for jaundice diagnosis based on the color distortion information to generate a corrected image for jaundice diagnosis.

The diagnostic unit 540 diagnoses jaundice symptoms for the user using the jaundice diagnostic correction image.

At this time, the diagnosis unit 540 can diagnose the jaundice symptom based on whether the color of the user's eye (sclera) included in the correction image for jaundice diagnosis corresponds to jaundice.

7 is a view for explaining an image-based jaundice diagnosis assistant apparatus according to an embodiment of the present invention.

Referring to FIG. 7, a jaundice diagnosis assistant apparatus 700 according to an embodiment of the present invention includes a receiving unit 710, a searching unit 720, and an outputting unit 730.

At this time, the jaundice diagnosis assisting device 700 may be a device mounted on the doctor's device or a doctor's device.

The receiving unit 710 receives the jumping diagnostic image for jaguar diagnosis in which the color distortion is corrected as an image taken together with the specific body part of the user and the reference object.

At this time, the receiving unit 710 can receive the jaundice diagnostic correction image from the diagnostic server or the user device.

In another embodiment, the receiver 710 may include a calibration image for jaundice diagnosis and may receive a jaundice diagnostic request to request a jaundice diagnosis for the user.

The retrieving unit 720 retrieves history information about the user from the patient history DB including history information on a plurality of jaundice patients.

At this time, the searching unit 710 can identify the user using the identification information (e.g., the phone number of the smart phone) of the user device that transmitted the jaundice diagnostic correction image, and retrieve the history information about the identified user.

In another embodiment, when the receiving unit 710 receives a jaundice diagnostic request, the jaundice diagnostic request may include user identification information for identifying the user, and the retrieving unit 710 may include a user identification History information about the user can be retrieved based on the information.

The output unit 730 outputs history information about the searched user and a jaundice diagnostic correction image.

According to the present embodiment, since the doctor does not need to directly retrieve the history information about the user, the history information for the user corresponding to the jaundice diagnosis correction image is provided together with the jaundice diagnosis correction image, thereby improving convenience in the examination.

Preferably, the image-based jaundice diagnosis assistant apparatus 700 according to an exemplary embodiment of the present invention performs image analysis on the corrected image for jaundice diagnosis to determine whether the user has jaundice symptoms and an image analysis result indicating the depth of jaundice (Not shown). In this case, the output unit outputs the image analysis result as well as the history information for the user and the correction image for jaundice diagnosis. In another embodiment, the analyzer may further generate health risk information, in which case the output may assist in diagnosing the doctor's jaundice by outputting health risk information.

The present invention has been described with reference to the preferred embodiments. It will be understood by those skilled 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. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined by the appended claims rather than by the foregoing description, and all differences within the scope of equivalents thereof should be construed as being included in the present invention.

Claims (28)

Receiving a jaundice diagnostic image of a user's specific body part and a reference object taken together;
Generating color distortion information indicating a degree of color distortion of the reference object included in the jaundice diagnostic image;
Generating a correction image for jaundice diagnosis by correcting color distortion of the jaundice diagnostic image based on the color distortion information; And
Diagnosing a jaundice symptom for the user using the jaundiced diagnostic correction image,
The reference object is an eye,
Wherein the lid is comprised of a single region having white or a plurality of regions having different hues. The method according to claim 1,
The step of diagnosing jaundice symptoms for the user
Transmitting a jaundice diagnosis request including the jaundice diagnosis correction image to the diagnosis server for requesting jaundice diagnosis for the user; And
And receiving a jaundice diagnosis result as a diagnosis result for the jaundice diagnosis request from the diagnosis server. 3. The method of claim 2,
The diagnosis of jaundice
The medical history information is determined based on at least one of medical history information on the user and medical information on another person having jaundice symptoms, Image-based diagnosis of jaundice. The method of claim 3,
The diagnosis of jaundice
Based on a correlation between the user's disease and the image analysis result estimated based on at least one of medical history information on the user and medical treatment information on the other person, whether the user's jaundice symptom is at a dangerous level to health And further comprising health risk information. The method according to claim 1,
When the reference object is a white object,
Wherein the step of generating the color distortion information comprises the steps of: obtaining a color temperature, which is a difference between a first color temperature of the reference object in the reference image photographed by the reference object and a second color temperature of the reference object included in the jaundice diagnosis image under a pre- Generates difference information,
Wherein the step of generating the correction image for jaundan diagnosis comprises the step of correcting the color temperature of the jaundice diagnosis image so that the color temperature of the reference object of the jaundice diagnosis image becomes equal to the first color temperature on the basis of the color temperature difference information, Wherein the image-based jaundice diagnostic method comprises: The method according to claim 1,
The particular body part of the user
And at least one of the user's face and the eyeball. The method according to claim 1,
Further comprising the step of outputting a user interface for photographing the jaundice diagnosis image,
The step of receiving the jaundice diagnostic image
Wherein the captured image is received based on a photographing guideline provided in real time on the user interface. The method according to claim 1,
The jaundice diagnostic image
Wherein the reference object is an image that is worn or attached to a specific body part of the user. delete The method according to claim 1,
The color distortion information
Wherein the jaundice diagnosis image is generated based on at least one of an illuminance of the environment in which the jaundice diagnosis image is taken, an image-related setting value of the user device that has photographed the jaundice diagnostic image, and a lens aberration for the lens mounted on the user device Image - based diagnosis of jaundice. The method according to claim 1,
When the reference image of the reference object is a YCbCr format and the jaundice diagnosis image is an RGB format under a pre-stored reference light source,
The step of generating color distortion information
Converting the jaundice diagnostic image into a YCbCr format to generate a converted image for jaundice diagnosis; And
And generating the color distortion information by calculating a first luminance distribution function that is a cumulative probability density function for a luminance value (Y) of all pixels belonging to the conversion image for jaundice diagnosis,
The step of generating the correction image for jaundice diagnosis
Wherein the juxtaposition diagnostic conversion image corresponding to the first luminance distribution function has a second luminance distribution function as a cumulative probability density function for the luminance value (Y) of all the pixels belonging to the reference image, Wherein the image-based jaundice diagnostic method comprises: Receiving a reference image of a reference object at a location where the user is currently located;
Generating color distortion information indicating a degree of color distortion of the reference object included in the reference image;
Receiving an image for diagnosis of jaundice in which a specific body part of the user is photographed under the same condition as the condition for photographing the reference image;
Generating a correction image for jaundice diagnosis by correcting color distortion of the jaundice diagnostic image based on the color distortion information; And
And diagnosing a jaundice symptom for the user using the jaundiced diagnostic correction image. A receiving unit for receiving a jaundice diagnostic image taken together with a specific body part of a user and a reference object;
A distortion information generating unit for generating color distortion information indicating a degree of color distortion of the reference object included in the jaundice diagnosis image;
An image correcting unit for correcting color distortion of the jaguar diagnostic image based on the color distortion information to generate a corrected image for jaundice diagnosis; And
And diagnosing a jaundice symptom for the user by using the jaundice diagnostic correction image,
The reference object is an eye,
Wherein the eyelid is comprised of a single region having white or a plurality of regions each having a different color. 14. The method of claim 13,
The diagnosis unit
A transmission unit for transmitting the jaundice diagnosis request including the jaundice diagnosis correction image to the diagnosis server for requesting jaundice diagnosis for the user; And
And a result processor for performing the diagnosis using the jaundice diagnosis result when a diagnosis result of the jaundice diagnosis result for the jaundice diagnosis request is received from the diagnosis server through the receiver, . 15. The method of claim 14,
The diagnosis of jaundice
The medical history information is determined based on at least one of medical history information on the user and medical information on another person having jaundice symptoms, Image-based jaundice diagnostic device. 16. The method of claim 15,
The diagnosis of jaundice
Based on a correlation between the user's disease and the image analysis result estimated based on at least one of medical history information on the user and medical treatment information on the other person, whether the user's jaundice symptom is at a dangerous level to health And further comprising health risk information. 14. The method of claim 13,
When the reference object is a white object,
The distortion information generation unit generates color temperature difference information, which is a difference value between a first color temperature of the reference object in the reference image photographed by the reference object and a second color temperature of the reference object included in the jaundice diagnosis image under a previously stored reference light source and,
Wherein the image correcting unit corrects the color temperature of the jaundice diagnosis image so that the color temperature of the reference object of the jaundice diagnosis image becomes equal to the first color temperature based on the color temperature difference information, Image-based jaundice diagnostic device. 14. The method of claim 13,
The particular body part of the user
And at least one of the user's face and the eyeball. 14. The method of claim 13,
Further comprising a user interface management unit for outputting a user interface for shooting the jaundice diagnosis image,
The receiving unit
Wherein the image-based jaundice diagnosis apparatus receives the photographed image based on a photographing guideline provided in real time on the user interface. 14. The method of claim 13,
The jaundice diagnostic image
Wherein the reference object is an image that is worn or attached to a specific body part of the user. delete 14. The method of claim 13,
The color distortion information
Wherein the jaundice diagnosis image is generated based on at least one of an illuminance of the environment in which the jaundice diagnosis image is taken, an image-related setting value of the user device that has photographed the jaundice diagnostic image, and a lens aberration for the lens mounted on the user device Image based jaundice diagnostic device. 14. The method of claim 13,
When the reference image of the reference object is a YCbCr format and the jaundice diagnosis image is an RGB format under a pre-stored reference light source,
The distortion information generation unit
A first luminance distribution function, which is a cumulative probability density function for the luminance value (Y) of all the pixels belonging to the conversion image for jaundice diagnosis, is calculated by converting the jaundice diagnosis image into a YCbCr format, Generates distortion information,
The image correction unit
Wherein the juxtaposition diagnostic conversion image corresponding to the first luminance distribution function has a second luminance distribution function as a cumulative probability density function for the luminance value (Y) of all the pixels belonging to the reference image, Wherein said image-based jaundice diagnostic apparatus comprises: A receiver for receiving a reference image of a reference object at a location where the user is currently located;
A distortion information generating unit for generating color distortion information indicating a degree of color distortion of the reference object included in the reference image;
When the image for jaundice diagnosis in which the specific body part of the user is photographed is received under the same condition as the condition for photographing the reference image through the receiver, the color distortion of the jaundiced image for diagnosis is corrected based on the color distortion information, An image correction unit for generating an image; And
And a diagnosis unit for diagnosing a jaundice symptom of the user using the jaundiced diagnostic correction image. A receiving unit receiving a reference eye image of a user's eyeball in a first location where a photographing condition is known and receiving an image of the user's eye in a second location other than the first location;
A distortion information generation unit for generating color distortion information indicating a degree of color distortion in the jaundice diagnostic image by comparing the iris color in the reference eye image with the iris color in the jaundice diagnostic image;
An image correcting unit for correcting color distortion of the jaguar diagnostic image based on the color distortion information to generate a corrected image for jaundice diagnosis; And
And a diagnosis unit for diagnosing a jaundice symptom of the user using the jaundiced diagnostic correction image. A receiving unit for receiving a jaundice diagnostic image taken together with a specific body part of a user and a reference object;
A distortion information generating unit for generating color distortion information indicating a degree of color distortion of the reference object included in the jaundice diagnosis image;
An image correcting unit for correcting color distortion of the jaguar diagnostic image based on the color distortion information to generate a corrected image for jaundice diagnosis; And
And a transfer unit for transferring the jaundice diagnostic correction image to the device of the doctor,
The reference object is an eye,
Wherein the eyelid is comprised of a single region having white or a plurality of regions each having a different color. A receiving unit for receiving a jugular diagnostic correction image having color distortion corrected as an image of a user's specific body part and a reference object taken together;
A retrieval unit for retrieving history information about the user from a patient history DB including history information on a plurality of jaundice patients; And
And an output unit for outputting the retrieved history information on the user and the jaundice diagnostic correction image,
The reference object is an eye,
Wherein the lid is comprised of a single region having white or a plurality of regions having different colors. 28. The method of claim 27,
Further comprising an analyzer for performing an image analysis on the jaundice diagnostic correction image to generate image analysis results indicating whether the user has jaundice symptoms and the depth of jaundice,
Wherein the output unit further outputs the image analysis result.

Images