KR20230046023A - Method and device of measuring hand grip strength using image-based finger angle estimation, recording medium for performing the method - Google Patents

Abstract

The present invention relates to a device for measuring grasping power using image-based finger angle estimation, which comprises: a hand image tracking unit for detecting a hand image of an examinee for each predetermined frame; an initial angle calculation unit for calculating a finger bending angle based on the radius of an elastic body and the length of a finger of the examinee when the examinee holds the elastic body of a spherical shape; a palm area deriving unit for deriving an area of the palm of the examinee; and a grasping power measuring unit for measuring grasping power of the examinee based on a finger bending angle change and the area of the palm when the examinee applies force to the elastic body. Accordingly, grasping power can be measured by deriving an angle for each finger using data obtained by recognizing the hand of a person using an easily available elastic body (e.g., a rubber ball), a computer, and a webcam.

Description

Apparatus and method for measuring grip strength using image-based finger angle estimation, and recording medium for performing the same

The present invention relates to an apparatus and method for measuring grip strength using image-based finger angle estimation, and a recording medium for performing the same, and more particularly, to determine grip strength by calculating the angle of a finger using data recognizing an examiner's hand holding an elastic body. It is about the technique of measuring.

Sarcopenia refers to a condition in which the muscles of the body are abnormally reduced or weakened, resulting in poor physical activity. More than 20% of the elderly population in Korea is confirmed to have sarcopenia, and recently, sarcopenia has been internationally recognized as a disease and a 'disease code' has been assigned.

In order to effectively treat sarcopenia and minimize side effects of sarcopenia, early diagnosis of sarcopenia and effective treatment based thereon are very important. A representative value used for diagnosing sarcopenia is grip strength.

Currently, human grip strength is measured as an objective numerical value through a grip dynamometer, and the corresponding data is used in various fields. Typically, it is used for medical purposes such as civil servant selection tests or sarcopenia diagnosis. The grip dynamometer used at this time is quite expensive, and it is difficult for individuals to measure and use the grip strength.

KR 10-2235532 B1 KR 10-1055259 B1

Therefore, the technical problem of the present invention has been focused on this point, and an object of the present invention is to provide a grip strength measuring device using image-based finger angle estimation.

Another object of the present invention is to provide a method for measuring grip strength using image-based finger angle estimation.

Another object of the present invention is to provide a recording medium on which a computer program for performing the grip strength measuring method using the image-based finger angle estimation is recorded.

An apparatus for measuring grip strength using image-based finger angle estimation according to an embodiment for realizing the above object of the present invention includes a hand image tracking unit that detects an image of a hand of a examiner at each predetermined frame; an initial angle calculating unit that calculates a finger bending angle based on the radius of the elastic body and the length of the examiner's finger when the examiner holds a spherical elastic body; a palm area derivation unit for deriving the area of the examiner's palm; and a grip strength measuring unit that measures the examiner's grip strength based on the area of the palm and the change in angle of finger bending when the examiner applies force to the elastic body.

In an embodiment of the present invention, the initial angle calculation unit may measure the lengths of fingers other than the thumb of the inspector and use them to calculate the finger bending angle.

In an embodiment of the present invention, the grip force measuring unit may repeatedly measure the grip force when the examiner applies force to the elastic body a predetermined number of times.

In an embodiment of the present invention, the grip strength measurement unit may measure the grip strength by averaging the bending angles of all fingers.

In an embodiment of the present invention, the grip strength measuring unit may derive a result by arranging the repeatedly measured grip strength measurements of the inspector in descending order and averaging the grip strength measurements up to a preset upper rank.

In an embodiment of the present invention, the grip strength measuring unit may assign a weight to an angle at a proximal interphalangeal joint (PIP) joint among finger joints.

In an embodiment of the present invention, the grip strength measuring unit may measure the grip strength based on an angle of bending of each individual finger.

In an embodiment of the present invention, the grip strength measuring device using the image-based finger angle estimation may measure different grip strength ranges by using two or more elastic bodies having different pressures.

In an embodiment of the present invention, the hand image tracking unit may track a change in hand shape centering on the examiner's hand.

In an embodiment of the present invention, the palm area derivation unit may derive the palm area by measuring the width of the examiner's palm and the length from the wrist to the tip of the middle finger.

In an embodiment of the present invention, the apparatus for measuring grip strength using image-based finger angle estimation may further include a modeling unit that models a relationship between a change in angle of bending of a finger and an area of a palm and grip strength.

In an embodiment of the present invention, the modeling unit may model the area of the palm in a multi-dimensional manner.

A method for measuring grip strength using image-based finger angle estimation according to an embodiment for realizing another object of the present invention described above includes detecting an image of an examiner's hand for each predetermined frame; calculating a finger bending angle based on a radius of the elastic body and a length of the examiner's finger when the examiner holds a spherical elastic body; Deriving the area of the examiner's palm; and and measuring the examiner's grip strength based on the area of the palm and the change in the bending angle of the fingers when the examiner applies force to the elastic body.

In an embodiment of the present invention, the step of measuring the grip strength of the inspector may include repeatedly measuring the grip strength when the inspector applies force to the elastic body a predetermined number of times; arranging the repeatedly measured grip strength measurements of the inspector in descending order; and deriving a result by averaging grip strength measurement values up to a preset higher rank.

In an exemplary embodiment of the present invention, the measuring of the examiner's grip strength may include measuring the grip strength based on individual finger bend angles or measuring the grip strength based on individual finger bend angles.

In an embodiment of the present invention, the grip strength measuring method using the image-based finger angle estimation may further include modeling a relationship between a change in a finger bend angle and a palm area and grip strength.

A computer program for performing the grip strength measurement method using the image-based finger angle estimation is recorded in a computer-readable storage medium according to an embodiment for realizing another object of the present invention.

According to the apparatus and method for measuring grip strength using such image-based finger angle estimation, a relatively easily obtainable elastic body (eg, rubber ball), a computer, a web cam, etc. are used, and the image data obtained by recognizing the examiner's hand is used as finger The grip force can be measured by calculating the angular change of each bending. Therefore, it is possible to effectively measure the grip strength without expensive equipment and use it usefully in the medical field such as sarcopenia diagnosis.

1 is a block diagram of an apparatus for measuring grip strength using image-based finger angle estimation according to an embodiment of the present invention.
2 is an exemplary diagram of conditions for measuring grip strength in the present invention.
3 is a view for explaining derivation of an angle of finger bending when force is applied to the finger.
4 is a view for explaining derivation of an angle of bending of a finger when force is not applied to the finger.
5 is a view showing a state in which a tester applies force to a rubber ball held in his hand.
6 is a graph showing a relationship between an angle change amount, a palm area, and an actual grip strength.
7 is a flowchart of a method for measuring grip strength using image-based finger angle estimation according to an embodiment of the present invention.
FIG. 8 is a flowchart of an example of the step of measuring the grip strength of the inspector of FIG. 7 .

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The detailed description of the present invention which follows refers to the accompanying drawings which illustrate, by way of illustration, specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable one skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention are different from each other but are not necessarily mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be implemented in one embodiment in another embodiment without departing from the spirit and scope of the invention. Additionally, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the detailed description set forth below is not to be taken in a limiting sense, and the scope of the present invention, if properly described, is limited only by the appended claims, along with all equivalents as claimed by those claims. Like reference numbers in the drawings indicate the same or similar function throughout the various aspects.

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

1 is a block diagram of an apparatus for measuring grip strength using image-based finger angle estimation according to an embodiment of the present invention.

An apparatus for measuring grip strength (10, hereinafter) using image-based finger angle estimation according to the present invention measures a person's hand using a relatively easily available elastic body (eg, a rubber ball) and an imaging device such as a computer or web cam. The grip strength is measured by deriving an angle for each finger with the recognized data.

Referring to FIG. 1 , an apparatus 10 according to the present invention includes a hand image tracking unit 110 , an initial angle calculation unit 130 , a palm area derivation unit 150 and a grip strength measurement unit 170 . In addition, the device 10 may further include a modeling unit.

In the apparatus 10 of the present invention, software (application) for measuring grip strength using image-based finger angle estimation may be installed and executed, and the hand image tracking unit 110 and the initial angle calculation unit 130 may be installed. , Configurations of the palm area deriving unit 150 and the grip strength measurement unit 170 may be controlled by software for performing grip strength measurement using the image-based finger angle estimation executed in the device 10 .

The device 10 may be a separate terminal or a part of a module of the terminal. In addition, the hand image tracking unit 110, the initial angle calculation unit 130, the palm area derivation unit 150, and the grip strength measurement unit 170 may be formed as an integrated module or composed of one or more modules. can lose However, on the contrary, each component may be composed of a separate module.

The device 10 may be mobile or stationary. The apparatus 10 may be in the form of a server or engine, and may be a device, an apparatus, a terminal, a user equipment (UE), a mobile station (MS), or a wireless device. It can be called by other terms such as wireless device, handheld device, etc.

The device 10 may execute or manufacture various software based on an operating system (OS), that is, a system. The operating system is a system program for enabling software to use the hardware of the device, and is a mobile computer operating system such as Android OS, iOS, Windows mobile OS, Bada OS, Symbian OS, Blackberry OS, and Windows-based, Linux-based, Unix-based, It can include all computer operating systems such as MAC, AIX, and HP-UX.

The hand image tracking unit 110 detects an examiner's hand image for each predetermined frame. The hand image tracking unit 110 may be, for example, an image capturing device such as a camera or a web cam.

The hand image tracking unit 110 may track a change in hand shape centering on the examiner's hand.

Referring to FIG. 2, as an example of a condition for measuring grip strength in the present invention, it is performed in a place with sufficient light, such as right under a fluorescent lamp, and a certain distance from the hand image tracking unit 110 such as a web cam (for example, , 40 cm), the grip strength can be measured with the examiner's wrist fixed.

In one embodiment, a real-time image taken by a web cam can be processed using a function provided by OpenCV. In real-time video, you can provide images for each frame so that Mediapipe can detect hands, and then perform each function when a specific input is given.

In addition, frames for 3 seconds after the wrist is fixed for a certain period of time (eg, 3 seconds) may be stored, and 60 or more frames may be stored. However, these numbers are only examples and conditions can be changed as needed.

The initial angle calculating unit 130 calculates a finger bending angle based on the radius of the elastic body and the length of the examiner's finger when the examiner holds a spherical elastic body.

For example, a rubber ball may be used as the elastic body, and grip strength in different ranges may be measured using rubber balls having various sizes, elasticity, or pressure.

The initial angle calculating unit 130 may measure the lengths of the examiner's fingers, excluding the thumb, and use them to calculate the finger bending angle.

In one embodiment, an open source Mediapipe module provided by Google can be used to track finger movements from hand images. Mediapipe provides a deep learning model that recognizes various video objects, and among them, the Hands solution that recognizes hands can be used.

The Hands solution trains only the palm excluding the fingers, and then performs regression analysis based on the recognized palm to detect five fingers. Hand landmarks are displayed in the entire detected palm area.

Therefore, since Mediapipe optimized the model by reducing the complexity of the learning data, the detection accuracy is high and the tracking speed for the finger joint is fast even in real-time video.

Referring to FIG. 3, using the Mediapipe Model, the landmark of the hand is brought.

Using this, we can get the x, y, and z points from each point. Here, in order to derive the angle of the first interphalangeal joint for each finger, the angle is derived as shown in Equation 1 below through the vector dot product.

[Equation 1]

Referring to FIG. 4, assuming that the rubber ball is a perfect sphere, the angle calculation formula when the rubber ball is held (when no force is applied) can be derived as shown in Equation 2 below using the principle of an inscribed quadrangle .

[Equation 2]

Here, r represents the radius of the rubber ball, and l represents the length of the finger.

The palm area derivation unit 150 derives the area of the examiner's palm. For example, the palm area deriving unit 150 may derive the palm area by measuring the width of the examiner's palm and the length from the wrist to the tip of the middle finger.

In another embodiment, the palm area deriving unit 150 may measure in advance before deriving an image and input the initial value.

The grip strength measuring unit 170 measures the examiner's grip strength based on the area of the palm and the change in the bending angle of the fingers when the examiner applies force to the elastic body.

Referring to FIG. 5 , the angle when force is applied to the rubber ball can be calculated for each knuckle by Equation 1 based on the 3D location tracking result of the finger joint.

In one embodiment, the tester may apply force to the rubber ball according to the signal and store an average of four knuckle angles measured for a predetermined time (eg, 3 seconds) while maintaining the force. Thereafter, a grip strength measurement value may be derived through the stored angle.

For accurate measurement, the grip force measurement unit 170 may repeatedly measure the grip force when the examiner applies force to the elastic body a predetermined number of times (eg, 5 times).

For example, the grip strength measurer 170 may measure the grip strength by averaging the angles of bending of all fingers that are repeatedly measured. Alternatively, the result may be derived by arranging the repeatedly measured grip strength measurement values of the inspector in descending order and averaging the grip strength measurement values up to preset higher ranks (eg, first and second ranks).

In another embodiment, the grip strength measuring unit 170 may assign a weight to an angle at a proximal interphalangeal joint (PIP) joint among finger joints.

The fingers include a total of three joints, the metacarpophalangeal joint (MCP), the proximal interphalangeal joint (PIP), and the distal interphalangeal joint (DIP) in the four fingers except for the thumb. Among them, since it plays the most important role in gripping objects, and the distal interphalangeal joint angle tends to be dependent on the proximal interphalangeal joint angle, more accurate grip strength can be measured by assigning weight to the proximal interphalangeal joint in the middle.

In addition, the grip strength measuring unit 170 may measure the grip strength of all fingers or may measure the grip strength based on the bending angle of each finger. Even in the case of measuring the bending angles of individual fingers, the grip force can be measured by repeatedly holding the elastic body a number of times and measuring the bending angles and averaging them.

The grip strength measuring unit 170 may measure different grip strength ranges by using two or more elastic bodies having different pressures.

The apparatus 10 may further include a modeling unit that models a relationship between a change in angle of finger bending and an area of the palm and grip strength. In this case, the area of the palm can be modeled multidimensionally.

Hereinafter, experimental results for measuring the accuracy of grip strength measurement according to the present invention will be described.

First, the order of experiments is as follows.

(1) Measure the lengths of four fingers excluding the thumb among the five fingers of the experimenter, and calculate the angle when the rubber ball is gripped using a program using Equation 2.

(2) Calculate the area of the palm by measuring the width of the palm and the length from the wrist to the tip of the middle finger.

(3) Measure the user's actual grip strength.

(4) After having the experimenter hold the rubber ball in an appropriate experimental environment, when the posture is stable, force the rubber ball for 3 seconds and repeat this 5 times.

In this experiment, actual grip strength was measured using TAKEI PHIYSICAL FITNESS TEST: GRIP-D. For accurate measurement, all measurers stood upright with their feet shoulder-width apart, held the grip strength meter in the hand on which the measurer was more comfortable, and gave strength to their hand according to the "start" signal. In this position, the measurement was repeated four times, and the average of the top two values was recorded as the actual grip strength.

The experiment was conducted with 12 adult males and females in their 20s and 30s, and each experimenter obtained four types of data: actual grip strength, angle when holding a rubber ball, angle when force was applied to the rubber ball, and palm area. measured.

Through the data obtained using Matlab, the x-axis is the angle difference, the y-axis is the hand size, and the z-axis is the actual grip strength, and the resultant graph in FIG. 6 and Equation 3 below are derived using the Multiple Linear Least-Squares Regression method did

[Equation 3]

Here, x ₁ is the amount of change in angle, x ₂ is the palm area, and y is the actual grip strength.

Using Equation 3, the grip strength was derived from the length of the experimenter's four fingers, the size of the palm, and the angle when force was applied to the rubber ball. To verify this, the result of obtaining the error rate of the actual grip strength and the grip strength measured by the program It is shown in Table 1 below.

experimenter actual grip strength Calculate grip strength Error rate (%) One 45.9 49.5 7.84 2 40.7 39.4 3.19 3 28.2 29.2 3.42

Through this, it can be confirmed that the grip strength can be approximately measured based on the computer vision-based angular change and the model based on the palm area proposed in the present invention.

Through the present invention, a program capable of measuring grip strength using a rubber ball and a camera was implemented. Although the number of samples is small by making data with 12 experimenters, the grip strength is measured with an error rate of less than 10%, and there is an advantage that anyone can easily configure the environment and measure the grip strength.

7 is a flowchart of a method for measuring grip strength using image-based finger angle estimation according to an embodiment of the present invention.

The method for measuring grip strength using image-based finger angle estimation according to the present embodiment may be performed in substantially the same configuration as the device 10 of FIG. 1 . Accordingly, components identical to those of the apparatus 10 of FIG. 1 are given the same reference numerals, and repeated descriptions are omitted.

In addition, the grip strength measurement method using image-based finger angle estimation according to the present embodiment may be executed by software (application) for performing grip strength measurement using image-based finger angle estimation.

The method for measuring grip strength using image-based finger angle estimation according to the present invention uses a relatively easily available elastic body (eg, a rubber ball) and imaging devices such as a computer and a web cam to obtain data obtained by recognizing a person's hand for each finger. The angle is derived to measure the grip strength.

Referring to FIG. 7 , in the method for measuring grip strength using image-based finger angle estimation according to the present embodiment, an image of an examiner's hand is detected for each predetermined frame (step S10).

As the hand image, a frame for a predetermined time after the examiner's wrist is fixed may be obtained using an image capture device such as a camera or a web cam.

When the examiner holds a spherical elastic body, a finger bending angle is calculated based on the radius of the elastic body and the length of the examiner's finger (step S20).

In this case, the length of the examiner's fingers excluding the thumb may be measured and used to calculate the finger bending angle.

For example, a rubber ball may be used as the elastic body, and grip strength in different ranges may be measured using rubber balls having various sizes, elasticity, or pressure.

The area of the examiner's palm is derived (step S30). For example, the palm area may be derived by measuring the width of the examiner's palm and the length from the wrist to the tip of the middle finger.

In another embodiment, the area of the inspector's palm may be previously measured and input as an initial value before deriving an image.

When the examiner applies force to the elastic body, the examiner's grip strength is measured based on the change in the bending angle of the fingers and the area of the palm (step S40).

The angle when force is applied to the rubber ball can be calculated for each knuckle by Equation 1 based on the result of tracking the three-dimensional position of the finger joint.

In one embodiment, the tester may apply force to the rubber ball according to the signal and store an average of four knuckle angles measured for a predetermined time (eg, 3 seconds) while maintaining the force. Thereafter, a grip strength measurement value may be derived through the stored angle.

For accurate measurement, the grip force when the examiner applies force to the elastic body may be repeatedly measured a predetermined number of times (eg, 5 times). For example, the grip strength may be measured by averaging the bending angles of all the repeatedly measured fingers.

Referring to FIG. 8 , in the step of measuring the grip strength of the inspector (step S40), the grip strength when the inspector applies force to the elastic body is repeatedly measured a predetermined number of times (step S41). Thereafter, the repeatedly measured grip strength measurement values of the inspector are sorted in descending order (step S42), and a result is derived by averaging the grip strength measurement values up to a preset higher rank (eg, first and second ranks) (step S42). S43).

In another embodiment, in the step of measuring the examiner's grip strength (step S40), a weight may be assigned to an angle at a proximal interphalangeal joint (PIP) joint among finger joints.

In the step of measuring the examiner's grip strength (step S40), the grip strength of all fingers may be measured, or the grip strength may be measured based on the bending angle of each individual finger. Even in the case of measuring the bending angles of individual fingers, the grip force can be measured by repeatedly holding the elastic body a number of times and measuring the bending angles and averaging them.

The method for measuring grip strength using image-based finger angle estimation according to the present invention may further include modeling a relationship between a change in a finger bend angle, a palm area, and grip strength. In this case, the area of the palm can be more accurately modeled as a multi-dimensional term.

Such a method for measuring grip strength using image-based finger angle estimation may be implemented as an application or implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer readable recording medium may include program instructions, data files, data structures, etc. alone or in combination.

Program instructions recorded on the computer-readable recording medium may be those specially designed and configured for the present invention, or those known and usable to those skilled in the art of computer software.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. media), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like.

Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter or the like as well as machine language codes such as those produced by a compiler. The hardware device may be configured to act as one or more software modules to perform processing according to the present invention and vice versa.

Although the above has been described with reference to embodiments, those skilled in the art can variously modify and change the present invention without departing from the spirit and scope of the present invention described in the claims below. You will understand.

The present invention provides a program for measuring grip strength by calculating angles for each finger with data recognizing a human hand through a model of OpenCV and Mediapipe using an elastic body (eg, a rubber ball), a computer, and a webcam. do. Therefore, it is possible to effectively measure the grip strength without expensive equipment and use it usefully in the medical field such as sarcopenia diagnosis.

10: grip strength measuring device using image-based finger angle estimation
110: hand image tracking unit
130: initial angle calculation unit
150: palm area derivation unit
170: grip strength measuring unit

Claims (17)

a hand image tracking unit that detects an image of an examiner's hand at each predetermined frame;
an initial angle calculating unit that calculates a finger bending angle based on the radius of the elastic body and the length of the examiner's finger when the examiner holds a spherical elastic body;
a palm area derivation unit for deriving the area of the examiner's palm; and
A grip strength measurement device using image-based finger angle estimation, comprising: a grip strength measurement unit configured to measure the examiner's grip strength based on the area of the palm and the change in angle of bending of the fingers when the examiner applies force to the elastic body.
The method of claim 1, wherein the initial angle calculator,
An apparatus for measuring grip strength using image-based finger angle estimation, which measures the length of an inspector's fingers excluding the thumb and uses them to calculate the finger bending angle.
The method of claim 1, wherein the grip strength measurement unit,
An apparatus for measuring grip strength using image-based finger angle estimation, which repeatedly measures grip strength when an examiner applies force to an elastic body a predetermined number of times.
The method of claim 3, wherein the grip strength measuring unit,
An apparatus for measuring grip strength using image-based finger angle estimation, which measures grip strength by averaging the bending angles of all fingers.
The method of claim 3, wherein the grip strength measuring unit,
An apparatus for measuring grip strength using image-based finger angle estimation, which arranges the repeatedly measured grip strength measurements in descending order and derives a result by averaging the grip strength measurements up to a preset higher rank.
The method of claim 1, wherein the grip strength measurement unit,
An apparatus for measuring grip strength using image-based finger angle estimation, which weights the angle at a proximal interphalangeal joint (PIP) joint among finger joints.
The method of claim 1, wherein the grip strength measurement unit,
An apparatus for measuring grip strength using image-based finger angle estimation, which measures grip strength based on individual finger bending angles.
According to claim 1,
An apparatus for measuring grip strength using image-based finger angle estimation, which measures different grip strength ranges by using two or more elastic bodies having different pressures.
The method of claim 1, wherein the hand image tracking unit,
A grip strength measuring device using image-based finger angle estimation to track changes in hand shape centering on the examiner's hand.
The method of claim 1, wherein the palm area derivation unit,
A grip strength measuring device using image-based finger angle estimation, which derives the palm area by measuring the width of the examiner's palm and the length from the wrist to the tip of the middle finger.
According to claim 1,
An apparatus for measuring grip strength using image-based finger angle estimation, further comprising: a modeling unit that models a relationship between a change in angle of bending of a finger and an area of the palm and grip strength.
The method of claim 11, wherein the modeling unit,
A device for measuring grip strength using image-based finger angle estimation that models the area of the palm in multi-dimensional ways.
detecting an image of an inspector's hand for each predetermined frame;
calculating a finger bending angle based on a radius of the elastic body and a length of the examiner's finger when the examiner holds a spherical elastic body;
Deriving the area of the examiner's palm; and
A method of measuring grip strength using image-based finger angle estimation, comprising: measuring the examiner's grip strength based on the area of the palm and the change in bending angle of the fingers when the examiner applies force to the elastic body.
The method of claim 13, wherein the step of measuring the examiner's grip strength,
Step of repeatedly measuring the grip force when the examiner applies force to the elastic body a predetermined number of times;
arranging the repeatedly measured grip strength measurements of the inspector in descending order; and
A method for measuring grip strength using image-based finger angle estimation, comprising: averaging grip strength measurement values up to a preset upper rank to derive a result.
The method of claim 13, wherein the step of measuring the examiner's grip strength,
A grip strength measurement method using image-based finger angle estimation, wherein grip strength is measured based on an individual finger bend angle or grip strength is measured based on an individual finger bend angle.
According to claim 13,
A method of measuring grip strength using image-based finger angle estimation, further comprising: modeling a relationship between a change in angle of bending of a finger and an area of the palm and grip strength.
A computer-readable storage medium having a computer program recorded thereon for performing the method of measuring grip strength using the image-based finger angle estimation according to any one of claims 13 to 16.

Images