KR102214551B1 - Distance measuring method between device and face - Google Patents

Abstract

In the method of measuring the distance between the device and the face of the present invention, an application of a device equipped with a camera generates an image by recognizing the user's face, and the correlation between the distance between two points of the derived face and the distance between the face and the device After deriving the relationship, the correlation is corrected according to a weight value according to the user to derive a distance between the device and the face according to the user.

Description

Distance measuring method between device and face}

The present invention relates to a method of measuring a distance between a device held by a user and a face of the user.

As the usage of personal devices represented by smartphones increases rapidly and the usage time increases, users often experience severe eye fatigue. In order to overcome this phenomenon, it is desirable not only to reduce the use of the personal device, but also to view the display screen from a distance suitable for the eyes when using the personal device.

Accordingly, there is a need to develop a technology that enables the user to receive information about the distance between the device and the user's face. Face region detection technology is required to measure the distance between a device and a face. Face region detection detects the presence or absence of a face in an image. If there is a face in the image, the position and size of the face and the position of the eyes, nose, and mouth It is a field of technology to find.

Currently, with the rapid development of cameras, personal devices are equipped with cameras capable of recognizing faces. Therefore, it is necessary to develop a technology that more accurately measures the distance between a device and a face through a face recognition function.

An object of the present invention is to provide a method of more accurately measuring the distance between a device and a user's face through a facial recognition function provided in a smartphone.

In the method of measuring the distance between a device and a face according to an embodiment of the present invention, after an application of a device equipped with a camera recognizes a user's face and generates an image, a bitmap is applied to the generated image, and at least on the user's face Measuring the distance by calculating the number of pixels between the two points, and deriving a correlation between the device and the user's face based on the distance between the at least two points on the user's face; Analyzing, by the application of the device, a correlation between the measured distance between two points of the face and the distance between the face and the device; The application of the device sets a weight value for at least one factor among age, height, weight, gender, nationality, first name, and surname that affects the distance between two points of the face, and is corrected by the weight value. Storing the correlation; When the user inputs a factor that meets the user's condition in the application of the device, the application of the device corrects the correlation by assigning a weight value corresponding to the factor, and based on the corrected correlation Deriving a distance between the device and the face; And when correction of the correlation according to the weight value given to the user is required, the user acquires an image by photographing the user's face image with a camera provided in the device, and calculates the number of pixels through a bitmap on the face The process of deriving the distance between at least two points may be repeated at several distances, thereby generating a weight value to correct the correlation.

In this case, the step of analyzing the correlation between the distance between the two points of the measured face and the distance between the face and the device by the application of the device includes the distance between the two points of the measured face and the face and the device. It includes the process of deriving a graph for the distance between, calculating a point at which the slope value is changed in the graph, and setting a relational expression based on the point at which the slope value is changed, wherein the relational expression is as follows: Characterized in that it is represented by 1.

[Equation 1]

1) ≤ AE _{adjust_eyes_distance} AS _{adjust_slope_ref}

_{D cm = M max_distance - ((} AE adjust_eyes_distance - M max_distance) * 0.5)

2) AE _{adjust_eyes_distance>} AS _{adjust_slope_ref}

_{D cm = M max_distance - ((} AE adjust_eyes_distance - M max_distance) * 0.5 * (AS adjust_slope_ref / AE adjust_eyes_distance))

_{AS adjust_slope_ref = S slope_ref * ((} W weight -1) / 3 + 1)

AE _{adjust_eyes_distance} = E _{eyes_distance} * W _weight

{D _cm: distance between the device and the face, E _{eyes_distance:} between the eyes is obtained by a camera distance, M _{max_distance:} maximum distance of the device and the face measurable as a smart phone camera, S _{slope_ref:} point at which the slope abruptly changes, W _weight : weight}

In addition, the step of deriving the distance between at least two points on the user's face includes calculating the number of pixels included in the area between the inside of both eyes of the user in the user's face image and measuring the distance between the inside of both eyes of the user. It features.

In addition, the device application is characterized by performing a process of correcting the relational expression when the user is different, and in the process of correcting the relational expression, the user holds a device having a camera in front with both hands and the user holds the camera. While viewing from the maximum distance, the position of the camera is changed to be closer to the face, calculating the point at which the distance between two points of the face and the slope value of the distance between the face and the device are changed, and setting this as a reference point. It features.

In this case, the process of correcting the relational expression by the user is a correction process in which the user directly measures the distance between the device and the face, calculates the distance between the two points of the face accordingly, and changes the W _weight value of the relational expression. It is characterized in that the relational expression is reset by performing

According to an embodiment of the present invention, when using a device equipped with a display such as a smartphone, TV, PC, or tablet, the distance from the user's face can be accurately measured, so that the user adjusts the distance to the display to reduce vision loss. Can be prevented.

In addition, the device may convert the displayed image or the quality of the image according to the distance between the display and the user to prevent deterioration of the user's eyesight.

According to an exemplary embodiment of the present invention, the quality of a displayed image or image is converted by using a method of measuring the distance between the device and the user, and the quality of sound accompanying the image can be converted to a quality optimized for the user and provided. .

1 is an overall flowchart of a method for measuring a distance between a device and a face according to an embodiment of the present invention
2 is a graph showing the relationship between the distance between the inside of both eyes and the distance between the face and the device in a method for measuring the distance between a device and a face according to an embodiment of the present invention

Hereinafter, the present embodiment will be described in detail with reference to the accompanying drawings, but it is not limited or limited by the present embodiment. In describing the present invention, detailed descriptions by known functions or configurations may be omitted to clarify the subject matter of the present invention.

1 is an overall flowchart of a method for measuring a distance between a device and a face according to an embodiment of the present invention. In the present invention, a camera built into a personal device (smart phone, PC, TV, tablet) is used to measure the distance between the device and the face, and it is assumed that the camera includes a face recognition function. The camera may acquire location information of at least two points (eye, nose, and mouth) of the face using a face recognition function, and may calculate the distance between the two points through a function of the camera itself or an application.

In the embodiment, to measure the distance between the device and the face, an application of a device equipped with a camera recognizes the user's face and generates an image, then applies a bitmap to the generated image, and at least two points on the user's face The distance is measured by calculating the number of pixels therebetween, and a step (S10) of deriving a correlation for the distance between the device and the user's face based on the distance between at least two points on the user's face may be performed.

In step S10, the user may be selected as a user whose distance between the eyes, nose, and mouth of the face is within a standard deviation of the average value. When the user's face is photographed according to the distance between the user's face and the device through a camera provided in the device, and a bitmap is used on the captured image, the distance between at least two points of the face may be calculated. In the embodiment, a method of recognizing the positions of both eyes with a camera provided in a smartphone and deriving the distance between the inside of both eyes will be described as an example.

Next, the application of the device derives a graph according to the correlation between the measured distance between the two points of the face and the distance between the face and the device, and calculates a point at which the slope value is changed in the graph ( S20) can be performed. Based on the distance between the inside of both eyes derived in step S10, and converting this into an algorithm included in an application provided in the smartphone, a graph showing the correlation as shown in FIG. 2 can be derived.

2 is a graph showing a relationship between the distance between the inside of both eyes and the distance between the face and the device in the method for measuring the distance between the device and the face derived as described above. Referring to FIG. 2, the horizontal axis represents the number of pixels between the inside of both eyes, and the vertical axis represents the distance between the face and the device. In the embodiment, the distance between the inside of both eyes may be derived by calculating the number of pixels between the inside of both eyes by constructing a bitmap on the image captured in step S10.

This graph shows the tendency that the distance between the face and the device decreases as the distance between the inside of both eyes increases, which means that the user's face enlarges from the image acquired through the camera as the smartphone approaches the user's face. Therefore, it means that the distance inside both eyes has also increased. As described above, the embodiment uses a specific pattern that appears due to two factors that change when the smartphone is closer or farther away from the face: 1) the distance inside both eyes and 2) the distance between the face and the device.

Looking at the correlation graph of FIG. 2, it can be seen that there is a point at which the inclination changes when the measured values are connected, which is the number of pixels representing the distance between both eyes as the device gradually moves away from the face. It indicates that there is a tendency to decrease. Therefore, in order to accurately calculate the distance between the device and the face, different relational expressions need to be set based on the point at which the inclination is changed, and the point at which the inclination is changed in FIG. 2 is a value corresponding to a point of 120 on the horizontal axis. It can be seen that

As described above, the application of the device may specify a point at which the slope value of the distance between the face and the device changes according to the distance between the two points of the face by referring to the data of the graph as described above. However, since the point at which the slope value of the distance between the face and the device is changed appears somewhat different depending on the user, it is necessary to grasp it in order to accurately derive the distance between the device and the face.

Therefore, the step (S30) of setting a weight value for a plurality of factors affecting the distance between two points of the face by the application of the device and storing the correlation corrected by the weight value (S30) may be performed. have. Here, the plurality of factors affecting the distance between two points of the face may include at least one of the user's age, height, weight, gender, nationality, first name, and last name. In the embodiment, it is assumed that when the user's age is the same, points at which the slope value of the distance between the face and the device changes according to the distance between two points of the face has a similar pattern, and the same weight value is assigned.

Here, the correlation between the measured distance between two points of the face and the distance between the face and the device may be expressed as an equation, for example, may be expressed as Equation 1 below.

[Equation 1]

1) ≤ AE _{adjust_eyes_distance} AS _{adjust_slope_ref}

_{D cm = M max_distance - ((} AE adjust_eyes_distance - M max_distance) * 0.5)

2) AE _{adjust_eyes_distance>} AS _{adjust_slope_ref}

_{D cm = M max_distance - ((} AE adjust_eyes_distance - M max_distance) * 0.5 * (AS adjust_slope_ref / AE adjust_eyes_distance))

{D _cm: distance between the device and the face, E _{eyes_distance:} between the eyes is obtained by a camera distance, M _{max_distance:} maximum distance of the device and the face measurable as a smart phone camera, S _{slope_ref:} point at which the slope abruptly changes, W _weight : weight}

Adjustment of slope change point according to weight

_{AS adjust_slope_ref = S slope_ref * ((} W weight -1) / 3 + 1)

Adjustment of distance between eyes according to weight

AE _{adjust_eyes_distance} = E _{eyes_distance} * W _weight

The mathematical expression distance inside both eyes on the basis of the _weight value W may be less than the _weight W value, or derived in large two kinds of equations. The correlation can be corrected by changing the W _weight value in the above equation. For example, the W _weight value can be significantly corrected as the actual eye space narrows, such as 1.0 for adult males, 1.12 for 14-year-old girls, and 1.4 for 4-year-old girls.

Based on Equation 1 above, a correlation between the measured distance between two points on the face and the distance between the face and the device can be visually confirmed.

In order to convert the graph disclosed in FIG. 2 into an equation, various methods can be applied, and the same can be applied to the point of using the change in the pattern that appears due to the distance inside both eyes and the distance between the face and the device.

And, when the user inputs a factor meeting the user's condition in the application of the device, the application of the device corrects the correlation by assigning a weight value corresponding to the factor, and the corrected correlation Based on the derivation of the distance between the device and the face (S40) may be performed.

The application of the device sets a reference value for the correlation between the measured distance between two points of the face and the distance between the face and the device through a process corresponding to S10 to S30, and affects the distance between the two points of the face. The process of pre-saving weight values for a plurality of factors that affects is preceded.

When a user uses the application for the first time, when the user inputs a factor value corresponding to the user, the application can correct the correlation to suit the current user by applying a weight value corresponding to the input factor in the initially set correlation. have.

That is, since this embodiment is based on distance information inside both eyes, each individual actually has a different face shape, and an error may occur in the resolution of the device camera used by the individual. A correction process is needed to apply the equation for a smartphone application.

Basically, a general correction value is determined according to factors such as age, but if the value is not accurate or it is determined that correction is necessary, an additional correction process may be performed.

Therefore, if it is necessary to correct the correlation according to the weight value assigned to the user, the user acquires an image by photographing the user's face image with a camera provided in the device, and calculates the number of pixels through a bitmap. By repeatedly performing the process of deriving the distance between at least two points on the face of, generating a weight value for correcting the correlation (S50) may be performed.

The step S50 may be a step performed to set a reference point for a distance between two points in the image obtained by the device.

In the process of correcting the relational expression, the position of the camera is changed so that the position of the camera is closer to the face while the user holds the device equipped with the camera in the front with both hands and the user is looking at the camera at the maximum distance. A process of calculating a point at which the slope value of the distance between the face and the device changes and setting it as a reference point may be performed.

In addition, the process of correcting the relational expression by the user includes a correction process in which the user directly measures the distance between the device and the face, calculates the distance between two points of the face, and changes the W _weight value of the relational expression. To reset the relational expression.

For example, assuming that the distance between the device and the face is 30 cm, a process for setting a reference point for the distance between both eyes in the bitmap of the image obtained through the camera may be performed. The user may directly measure the first distance between the device and the face to separate the device from the user's face, and perform a correction process by operating an algorithm of a smartphone application. In the smartphone application, a correction process of resetting the W _weight of Equation 1 that has been previously set may be performed by deriving the distance between the user's both eyes according to the actual measured distance, and deriving a correlation according thereto.

As Equation 1 included in the algorithm of the smart phone application is changed as described above, the distance between the user's device and the face of the actual smart phone can be more accurately measured.

As an example of the above correction process, the user creates a table corresponding to the weight according to the distance between eyes through a test. Then, when the application performs the correction step, two dots appear, and the user adjusts the position of the device so that the two dots are located inside both eyes. When the position adjustment of the device is completed, the weight value can be obtained by comparing it with a table created in advance, and the correlation can be corrected through this.

Alternatively, the user can perform the correction process while looking at the display screen while holding the smartphone with both hands. When the user gradually approaches the smartphone toward the face, the smartphone application can determine the point at which the slope of the graph changes from the correlation value while deriving a correlation based on the derived distance between the eyes. The distance between the device and the face can be more accurately measured by correcting the error to fit the user using the point at which the inclination is changed as described above.

Since the method of measuring the distance between the device and the face of the embodiment may have different reference points for each person, standard data information can be constructed by performing the process of accumulating personal information in a database in the process of setting the reference point for each person. .

In other words, when setting the reference point, if information including age, height, weight, gender, nationality, first name, and last name is entered into the application and a server that accumulates this information is built, the data is accumulated every time a user uses the application. Therefore, it can be used as big data.

For example, standard information can be derived by accumulating information on the correlation between age and distance between eyes, the correlation between height and eyes, and between sex and eyes. It is possible to comprehensively derive the correlation of the distance between the eyes and the distance between the eyes caused by the genetic influence, so when a user inputs personal information, the distance information between the device and the face close to the actual value can be provided. have. That is, when the user inputs part of the personal information (body information) into the smartphone application, an optimized reference value may be derived from the accumulated information and a correction process may be automatically performed to suit the user.

When the method of measuring the distance between the device and the face of the embodiment is used, the application of the smartphone provides the user with the distance between the current display screen of the smartphone and the face to the user, thereby inducing the user to view the smartphone screen at an appropriate distance. can do. In addition, when it is determined that the user is viewing the smartphone at a distance closer than the distance derived for a specific time, a pop-up message may be generated to trigger an action of moving the smartphone to a distance.

In addition, the embodiment may perform a process of changing the quality of the displayed image according to the derived distance after the distance between the user's face and the smartphone is derived, and thus may include a configuration that prevents vision loss. have.

In addition, in the embodiment, after the distance between the user's face and the smartphone is derived, a process of changing the quality of the displayed image according to the derived distance is performed, and the accompanying sound is converted to be optimized for the user. It may include a configuration that can prevent.

In the above, the present invention has been described with reference to its preferred embodiments, but these are only examples and do not limit the present invention, and those of ordinary skill in the field to which the present invention pertains will not depart from the essential characteristics of the present invention. It will be appreciated that various modifications and applications not illustrated above are possible. For example, each component specifically shown in the embodiment of the present invention can be modified and implemented. And differences related to these modifications and applications should be construed as being included in the scope of the present invention defined in the appended claims.

Claims (5)

After the application of the device equipped with the camera recognizes the user's face and generates an image, it applies a bitmap to the generated image, calculates the number of pixels between at least two points on the user's face, measures the distance, and Deriving a correlation with respect to the distance between the device and the user's face based on the distance between at least two points on the face;
Analyzing, by the application of the device, a correlation between the measured distance between two points of the face and the distance between the face and the device;
The application of the device sets a weight value for at least one factor among age, height, weight, gender, nationality, first name, and surname that affects the distance between two points of the face, and is corrected by the weight value. Storing the correlation;
When the user inputs a factor that meets the user's condition in the application of the device, the application of the device corrects the correlation by assigning a weight value corresponding to the factor, and based on the corrected correlation Deriving a distance between the device and the face; And
When correction of the correlation according to the weight value given to the user is necessary, the user acquires an image by photographing the user's face image with a camera provided in the device, and calculates the number of pixels through a bitmap to at least on the user's face. Generating a weight value to correct the correlation by repeating the process of deriving the distance between the two points at several distances,
The step of analyzing the correlation between the distance between the two points of the measured face and the distance between the face and the device, by the application of the device, includes the distance between the two points of the measured face and the distance between the face and the device. A method of measuring a distance between a device and a face, comprising: deriving a graph for, calculating a point at which a slope value changes abruptly in the graph, and setting a relational expression based on a point at which the slope value changes. The method of claim 1,
The relational expression is a method for measuring a distance between a device and a face, characterized in that it is expressed by Equation 1 below.
[Equation 1]
1) ≤ AE _{adjust_eyes_distance} AS _{adjust_slope_ref
D cm = M max_distance - ((} AE adjust_eyes_distance - M max_distance) * 0.5)
2) AE _{adjust_eyes_distance>} AS _{adjust_slope_ref
D cm = M max_distance - ((} AE adjust_eyes_distance - M max_distance) * 0.5 * (AS adjust_slope_ref / AE adjust_eyes_distance))
_{AS adjust_slope_ref = S slope_ref * ((} W weight -1) / 3 + 1)
AE _{adjust_eyes_distance} = E _{eyes_distance} * W _weight
{D _cm: distance between the device and the face, E _{eyes_distance:} between the eyes is obtained by a camera distance, M _{max_distance:} maximum distance of the device and the face measurable as a smart phone camera, S _{slope_ref:} point at which the slope abruptly changes, W _weight : weight} The method of claim 1,
In the step of deriving the distance between at least two points on the user's face, the distance between the inside of both eyes of the user is measured by calculating the number of pixels included in the area between the inside of both eyes of the user in the user's face image. How to measure the distance between the device and the face. The method of claim 2,
The device application is characterized by performing a process of correcting the relational expression when the user is different,
In the process of correcting the relational expression, the position of the camera is changed so that the position of the camera is closer to the face while the user holds the device equipped with the camera in the front with both hands and the user is looking at the camera at the maximum distance. A method of measuring a distance between a device and a face, comprising calculating a point at which a slope value of a distance between a face and a device is changed and setting it as a reference point. The method of claim 4,
In the process of correcting the relational expression by the user, the user directly measures the distance between the device and the face, calculates the distance between two points of the face accordingly, and performs a correction process of changing the W _weight value of the relational expression. A method of measuring a distance between a device and a face, wherein the relational expression is reset.

Images