KR101436884B1 - Method for recognizing user by using footprint energy image and Apparatus thereof - Google Patents

Abstract

A method for recognizing a user using a footprint energy image, the method comprising steps of: generating a footprint energy image by dividing a left foot and a right foot by inputting a continuous footprint pressure image, calculating a similarity between the generated left footprint energy image and a left foot reference image Calculating a degree of similarity or non-relativeness of the left footprint energy image and the right footprint energy image and the right foot reference image, and calculating the similarity or non-relativeness of the left footprint energy image or the similarity of the left footprint energy image or the similarity of the right footprint energy image, And recognizing the user using the footprint energy image.

Description

FIELD OF THE INVENTION [0001] The present invention relates to a method and apparatus for recognizing a user using a footprint energy image,

The present invention relates to a method of recognizing a user using a footprint energy image, and more particularly, to a method of generating a footprint energy image from a continuous footprint pressure image and using the similarity of the footprint energy image and a reference image, A recording medium thereof, and a user recognition apparatus.

Among the pattern recognition, fingerprint recognition, iris recognition, face recognition, and hand recognition are typical examples of biometrics. They typically identify the best matching user in a pre-built reference database when a user's data is entered for testing. Conventional biometric methods require cumbersome processing methods such as physical contact or intentional recognition procedures. This procedure has the problem of causing a sense of user rejection.

A first problem to be solved by the present invention is to provide a user recognition method using a footprint energy image.

A second problem to be solved by the present invention is to provide a user recognition apparatus using a footprint energy image.

It is another object of the present invention to provide a computer-readable recording medium storing a program for causing a computer to execute the above-described method.

In order to achieve the first object of the present invention, there is provided a method of generating a footprint energy image, the method comprising steps of: generating a footprint energy image by dividing a left foot and a right foot by inputting successive footprint pressure images; Calculating a similarity or non-relative degree of the left footprint energy image and the right foot reference energy image, and calculating a similarity or non-relativeness of the left footprint energy image or the right foot reference image using the similarity of the left footprint energy image or the similarity of the right footprint energy image, The method comprising the steps of:

According to an embodiment of the present invention, the step of generating the footprint energy image may include generating a binary image by separating a left foot and a right foot by tracking a center point of the inputted footprint pressure image, And generating a left footprint energy image and a right footprint energy image using the extracted footprint image, wherein the step of generating the binary image includes attaching a label to the input footprint image, The method comprising the steps of: searching for a center point of a labeled footprint pressure image; tracking the center point along a frame of the footprint pressure image to distinguish a first foot from a second foot; By using the pixel-by-pixel pressure value, Calculating a termination time of each foot based on the direction of the foot, determining whether each of the divided feet corresponds to a left foot or a right foot, And generating an image.

According to another embodiment of the present invention, the step of generating the footprint energy image may further include the step of rotating the footprint energy image so that the direction of the generated footprint energy image is aligned with the walking direction of the footprint, The step of rotating the footprint energy image may include calculating an eigenvector and an eigenvalue of the generated footprint energy image using a covariance matrix, determining an eigenvector having the eigenvalue greater than the eigenvector as a major axis, And the direction of the footprint energy image is made to coincide with the walking direction using a difference in angle between the long axis and the walking direction.

According to another embodiment of the present invention, the step of calculating the degree of similarity or non-affinity may be a user recognition method characterized in that the degree of similarity or non-affinity is calculated using a k-nearest neighbor algorithm (kNN) .

According to another aspect of the present invention, there is provided a footprint energy image generation apparatus for generating a footprint energy image by separating a left foot from a right foot by receiving a footprint pressure image, Calculating a degree of similarity or non - degree of similarity of the left footprint energy image and the right foot reference image, and comparing the similarity degree of the left footprint energy image with the right footprint energy image using the similarity or non - There is provided a user recognition apparatus including a user recognition section for recognizing a user.

According to another aspect of the present invention, there is provided a computer-readable recording medium storing a program for causing a computer to execute a method of recognizing a user using a footprint energy image.

According to the present invention, a user can be recognized using a footprint energy image, thereby reducing the cumbersome processing methods such as physical contact or intentional recognition procedures, which have been proposed in conventional biometric methods, It is possible to place the sensor and perform user recognition while the user is walking naturally. In addition, a left foot and a right foot are separated to generate a footprint energy image, and the user can be recognized using the two footprint energy images, thereby increasing the accuracy of recognizing the user.

1 is a block diagram of a user recognition apparatus using a footprint energy image according to an embodiment of the present invention.
2 is a block diagram of a user recognition apparatus using a footprint energy image according to another embodiment of the present invention.
3 is a flowchart illustrating a method of recognizing a user using a footprint energy image according to an exemplary embodiment of the present invention.
4 is a flow diagram of a step of generating a footprint energy image in accordance with another embodiment of the present invention.
5 is a flowchart of a step of generating a binary image according to another embodiment of the present invention.

Prior to the description of the concrete contents of the present invention, for the sake of understanding, the outline of the solution of the problem to be solved by the present invention or the core of the technical idea is first given.

A method of recognizing a user using a footprint energy image according to an embodiment of the present invention includes steps of generating a footprint energy image by separating a left foot and a right foot by receiving a footprint image, Calculating a similarity or non - similarity between the generated right - footed - energy image and the right - footed reference image, and comparing the similarity or non - relativeness of the left footprint energy image with the right footprint energy image, To recognize the user.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. It will be apparent to those skilled in the art, however, that these examples are provided to further illustrate the present invention, and the scope of the present invention is not limited thereto.

BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description of the present invention when taken in conjunction with the accompanying drawings, in which: It is to be noted that components are denoted by the same reference numerals even though they are shown in different drawings, and components of different drawings can be cited when necessary in describing the drawings. In the following detailed description of the principles of operation of the preferred embodiments of the present invention, it is to be understood that the present invention is not limited to the details of the known functions and configurations, and other matters may be unnecessarily obscured, A detailed description thereof will be omitted. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. It is noted that " comprises, " or "comprising," as used herein, means the presence or absence of one or more other components, steps, operations, and / Do not exclude the addition.

1 is a block diagram of a user recognition apparatus using a footprint energy image according to an embodiment of the present invention.

A user recognition apparatus using a footprint energy image according to an embodiment of the present invention includes a footprint energy image generation unit 110 and a user recognition unit 120.

The footprint energy image generation unit 110 receives the footprint image, separates the left foot and the right foot, and generates a footprint energy image.

More specifically, the user recognition apparatus according to an embodiment of the present invention recognizes a user using a footprint energy image of a user. The user recognizes the footprint energy image using a footprint image generated by a user walking on a pressure sensor, . The footprint pressure image generated by the user walking on the pressure sensor is continuous over time. The footprint pressure image may be discontinuous or a footprint pressure image. The footprint energy image generation unit 110 generates a footprint energy image that can be compared with a reference image using the continuous footprint pressure image. The pressure sensor may be obtained by a Mat-type pressure sensor.

The footprint energy image generation unit 110 generates a binary image by separating the left foot and the right foot by tracking the center point of the inputted footprint pressure image, and generates a binary image using the generated left foot footprint energy image and the right foot footprint energy Images can be generated. The generated binary image may be a continuous binary image according to the pressure image of the footprint. The footprint pressure image may be in the form of a foot part, depending on the pressure of the part where the foot touches the sensor, rather than the shape of the foot. That is, when the user walks over the pressure sensor, the portion contacting the pressure sensor over time becomes part of the foot, not the foot, and the pressure also changes continuously. Therefore, an image of the foot mass should be generated using the image of the foot part. In order to generate an image of the footprint, a binary image is first generated using the continuous gray scale footprint pressure image. Further, the footprint pressure images may include both the right foot and the left foot images, and distinguish the right foot from the left foot.

Wherein the binary image searches for a center point of the labeled footprint pressure image and tracks the center point along the frame of the footprint pressure image to distinguish the first foot from the second foot, Calculating a starting time and an ending time of each foot by using a non-zero pixel-by-pixel pressure value of the foot, determining whether each of the separated feet corresponds to the left foot or the right foot by using the direction of the footing, Can be generated using the footprint pressure image for the time and end time.

As described above, since the footprint pressure image sensed while the user is walking is not an image of the footprint, a footprint energy image of the footprint should be generated using the footprint pressure images. To this end, a label is attached to distinguish each foot in the successive footprint pressure image. The label can be obtained by performing labeling on a blob (binary large object) of each footprint pressure image by Equivalence class method. After attaching the label to the footprint pressure image, the center of the foot (COA) of each footprint energy image with the label attached is searched.

The first foot is distinguished from the second foot calculated in the previous frame through the blobs having the label calculated from the center point of each foot and the current frame. The first input, that is, the frame that takes the first foot (time) t _{FIRST ,} keeps track of the center of the blops at the next frame from the center of the first foot at _START . Using a foot maximum size threshold L _{MAX _ FOOT} in the tracking process distant blob than the threshold should tell whether the second foot blob whether each blob that first foot blob according to the principle belongs to the other foot. In addition, it is possible to distinguish the start frame of the second foot by determining whether the center of the whole foot changes over a critical distance in the tracking process. Since the foot is connected, suddenly the center point can not be changed. When the division of each foot with respect to the center point is completed, the start time and the end time of each foot are calculated using the pressure values of the non-zero pixels of the first foot and the second foot. A time when the person's foot touched the ground is the start time, and a time when the foot touched the ground falls from the ground again is the end time. T _{FIRST , START} , t _{SECOND , START} and the end times t _{FIRST , END} , t _{SECOND , END} of the first and second foot. Nonzero pixel values (nonzero pixels) are measured and found in each of the identified foot regions. The time at which the non-zero pixel-by-pixel pressure value starts to occur is the start time, and the time at which the non-zero pixel-by-pixel pressure value disappears may be the end time. For reference, in the case where the user does not run, each time always satisfies the relationship of the following equation (1).

Calculating a starting time and an ending time of each foot, determining whether each of the separated feet corresponds to the left foot or the right foot using the direction of the walking, and using the footprint pressure image for the start time and the end time of each foot, Generates a binary image of each foot. The foot having the center point on the left side is the left foot and the foot on the right side is the right foot. Therefore, it is judged whether or not each of the above-described separated feet is the left foot or the right foot. Wherein the binary image of each foot exists by a pressure value per pixel using a gray scale footprint pressure image and is 1 when a point in which the pressure value per pixel exists in each foot area, . The method of generating the binary image is shown in Equation (2).

Where F (x, y, t) is a continuous time axis, a gray-scale footprint pressure image on t and B _i (x, y, t) is a binary image. B _i (x, y, t) is B _LEFT (x, y, t) and B _RIGHT (x, y, t)

When the binary image is generated, the footprint energy image generator 110 generates the left footprint energy image and the right footprint energy image using the generated binary image. One binary image may be an image of each foot, but a binary image generated as an input image while walking may be an image of a foot part, and an image of a foot part should be generated by a binary image of the foot part. Since the binary image B _i (x, y, t) generated for each foot is the footprint image for time t, the footprint image of the foot is calculated by calculating the average of the footprint image during the time t. The equation for generating the footprint energy image is shown in Equation (3).

Here, FEI _i is the foot energy image of each foot (i is LEFT or RIGHT). The average obtained by summing up the binary images from the start time to the end time of each foot becomes the foot energy image of the foot.

A Gait Energy Image, a Motion Silhouette Contour Templates (MSCT), or a Motion Silhouette Image (MSI) image as well as the footprint energy image from a footprint image for user recognition. ) Can be used.

The Motion Silhouette Contour Templates (MSCT) combines the outline of the frame of each footprint pressure image. MSCT is represented by the following equation (4).

Where C _i (x, y, t) is a contour image transformed into a shape representing the shape of the outline of the footprint pressure image. α _i is the attenuation parameter. In order to use MSCT in footprint recognition, α _i is determined by Ni, the time at which each foot touches the ground. Further, when α _i is N _i for the i-th foot, C _i (x, y, t) represents all the outlines of the i-th foot.

When MSCT is used, it may further include generating a binary image and then generating each contour image C _i (x, y, t). If the chebyshev distance from the current pixel of the neighboring pixel is less than or equal to 3 to find the outline, the outline can be found by determining the current pixel as the outline pixel.

A motion silhouette image (MSI) combines the outline of the footprint pressure image. MSI is represented by the following equation (5).

Where B _i is the same as that of the B _i Equation 1, α _i is the same as in Equation 5 α _i.

The footprint energy image generation unit 110 may rotate the footprint energy image so that the direction of the generated footprint energy image matches the direction of the footprinting. For reference, when a person walks, the two feet of the person are not parallel, but walk in a slightly forward direction. The angle may vary from person to person and even from the same person, depending on the situation. If the angles of the footprint energy image and the reference image are different, the comparison may be difficult, so that the footprint energy image can be rotated in a direction coincident with the direction of the gait. The shape of the footprints is an ellipsoid shape having a long axis and a short axis, and can be arranged so that the long axes of the feet are parallel. For this purpose, the long axis of the footprint energy image is calculated, and the long axis is aligned with the direction of the gait. Also, to determine the long axis, an eigenvector and an eigenvalue of the generated footprint energy image are calculated using a covariance matrix, and an eigenvector having the eigenvalue larger than the eigenvectors is determined as a long axis. The eigenvector having the eigenvalue smaller than the eigenvector is shortened. The footprint energy image is rotated such that the direction of the generated footprint energy image coincides with the walking direction using the difference in angle between the determined long axis and the gait setting direction. The covariance matrix is expressed by Equation (6).

Where H _L is the covariance matrix and L (x ', y') is the pixel value of the image L at (x ', y').

The footprint energy image generation unit 110 may adjust the center point of the rotated footprint energy images to the same position. After aligning the footprint energy images in the same direction, the center point used in the comparison can be adjusted to the same position for each footprint energy image to make the comparison more efficient. If the center point is at the same position for each footprint energy image, the comparison of the images can be fast, and the same image can be searched in a short time. The position for adjusting the center point may be the center of the image.

The user recognition unit 120 calculates a similarity degree or a similarity degree between the left footprint energy image generated by the footprint energy image generation unit 110 and the left foot reference image or the similarity or the right foot reference energy image and the right foot reference energy image And recognizes the user using the similarity of the left footprint energy image or the similarity of the right footprint energy image or the non - reference figure. The similarity as well as the non-inference may be used. That is, the user of the footprint energy image can be recognized by comparing the footprint energy image with the reference image having the maximum similarity or the reference image having the least similarity. It is easy to see the configuration using the similarity from the configuration using the similarity as a concept corresponding to the similarity and the non-embodiment. Hereinafter, the configuration using the similarity will be explained.

More specifically, the user is recognized by determining which user's footprint energy image is the footprint energy image using the generated footprint energy image. To this end, the foot energy image of each foot is compared with a reference image of each foot. The reference image is a footprint energy image that generates and stores footprint energy images of users to be recognized in advance. The reference image may be stored in a footprint energy image database. The reference image may have a left foot reference image and a right foot reference image. The left footprint energy image calculates the similarity with the left foot reference image, and the right footprint energy image calculates the similarity with the right foot reference image. The user is recognized in consideration of the similarity of the left footprint energy image and the right footprint energy image. A reference image having a similarity value larger than the two similarity values is selected, and if the similarity degree is equal to or greater than a threshold value, the user of the footprint energy image corresponds to a user corresponding to the reference image. The threshold value of the degree of similarity is the maximum similarity that can be determined as the same footprint energy image, and it may be set in advance. The degree of similarity can be calculated using a k-nearest neighbor algorithm (kNN, k-Nearest Neighbor). Using the k-nearest neighbor algorithm, a distance D (R, T) between the generated footprint energy image T and the reference image R is first calculated, and a recognition rate . The method of calculating D (R, T) is shown in Equation (7).

Where H is the height of the image and W is the width of the image. Determining a reference image corresponding to the footprint energy image in consideration of the similarity of the footprint energy image of each foot using the k-nearest neighbor algorithm (kNN, k-Nearest Neighbor) The user of the energy image is recognized as the user of the reference image. At this time, the user of the reference image having a larger similarity value among the similarities of the foot is determined as the end user. Alternatively, the two feet may be compared together with the reference image to calculate the total similarity to recognize the user. 2 is a block diagram of a user recognition apparatus using a footprint energy image according to another embodiment of the present invention.

The user recognition apparatus using the footprint energy image according to another embodiment of the present invention may be configured such that the footprint energy image generation unit 220 generates a footprint image using the footprint image obtained by the user walking on the pressure sensor 210, Energy image and right footprint energy image. The footprint energy image of each foot calculates a similarity using a kNN (k-nearest neighbor algorithm) using a reference image stored in a footprint database (DB) 250, identifies a user using each foot similarity (260) do.

3 is a flowchart illustrating a method of recognizing a user using a footprint energy image according to an exemplary embodiment of the present invention.

Step 310 is a step of receiving the continuous footprint image and separating the left foot and the right foot and generating a footprint energy image.

More specifically, the user inputs a continuous footprint pressure image inputted by the user on the pressure sensor to separate the left foot and the right foot, and generates a corresponding footprint energy image. The detailed description of this step corresponds to the detailed description of the footprint energy image generation unit 110 of FIG. 1 and is replaced with a detailed description of the footprint energy image generation unit 110 of FIG.

Step 320 is a step of calculating the similarity or non-similarity between the generated left footprint energy image and the left foot reference image and the similarity or non-comparison between the left foot footprint energy image and the right foot footprint energy image and the right foot reference image.

More specifically, in step 310, a similarity degree or non-affinity to the corresponding reference image is calculated for the foot energy image of each foot. The detailed description of this step corresponds to the detailed description of the calculation of the similarity of the footprint energy image generator 110 of FIG. 1 and is replaced with a detailed description of the footprint energy image generator 110 of FIG.

In operation 330, the user is recognized by using the similarity of the left footprint energy image or the similarity or non-similarity of the non-reference footprint and the right footprint energy image.

More specifically, the user is recognized using the similarity degree of each foot calculated in step 320. The user can be recognized as a user corresponding to a reference image having a larger similarity value among the respective similarities. The detailed description of this step corresponds to a detailed description of the user recognition of the user recognition unit 110 of FIG. 1, and is replaced with a detailed description of the footprint energy image generation unit 110 of FIG.

4 is a flow diagram of a step of generating a footprint energy image in accordance with another embodiment of the present invention.

In step 410, a center point of the inputted footprint pressure image is tracked to separate the left foot and the right foot, and a binary image is generated.

More specifically, a center point is tracked by receiving a footprint pressure image, and a left and a right foot are separated using the center point to generate a binary image corresponding to each foot. The detailed description of this step corresponds to the detailed description of the binary image generation by the user recognition unit 110 of FIG. 1, and is replaced with a detailed description of the footprint energy image generation unit 110 of FIG.

Step 420 is a step of generating the left footprint energy image and the right footprint energy image using the generated binary image.

More specifically, an average of the binary image is calculated using the binary image generated in step 410 to generate the left footprint energy image and the right footprint energy image. The detailed description of this step corresponds to the detailed description of the footprint energy image generation using the binary image of the footprint energy image generation unit 110 of FIG. 1, and detailed description of the footprint energy image generation unit 110 of FIG. Replace it with a description.

Step 430 is a step of rotating the footprint energy image such that the direction of the generated footprint energy image coincides with the walking direction of the footprint.

More specifically, the direction of the footprint energy image can be matched to efficiently compare the footprint energy image generated in operation 420 with the reference image. The detailed description of this step corresponds to a detailed description of the footprint energy image rotation of the footprint energy image generator 110 of FIG. 1, and is replaced with a detailed description of the footprint energy image generator 110 of FIG. 1 .

Step 440 is to adjust the center point of the rotated footprint energy images to the same position.

More specifically, the center point of the energy images of the footprint is adjusted to the same position in order to make the comparison with the reference image and the footprint energy image rotated in step 430 more efficient. The detailed description of this step corresponds to a detailed description of the adjustment of the footprint energy image center point of the footprint energy image generation unit 110 of FIG. 1, and is a detailed description of the footprint energy image generation unit 110 of FIG. 1 do.

5 is a flowchart of a step of generating a binary image according to another embodiment of the present invention.

Step 510 is a step of attaching a label to the input footprint image.

More specifically, the inputted footprint pressure image is continuously input due to the user's walking, and a label is attached to indicate the input. The detailed description of this step corresponds to the detailed description of label attachment by the footprint energy image generation unit 110 of FIG. 1, and is replaced with a detailed description of the footprint energy image generation unit 110 of FIG.

Step 520 is a step of searching for a center point of the footprint pressure image attached with the label.

More specifically, in step 510, the center point of the label-attached footprint pressure image is searched. And discriminates which foot corresponds to the footprint pressure image and searches for a center point to be used for comparison with the reference image. The detailed description of this step corresponds to the detailed description of the center point search of the footprint energy image generator 110 of FIG. 1, and is replaced with a detailed description of the footprint energy image generator 110 of FIG.

In step 530, the center point is tracked along the frame of the footprint pressure image to distinguish the first foot from the second foot.

More specifically, the center point searched in step 520 is traced for each frame of the footprint pressure image to distinguish the first foot from the second foot. The beginning and end of the trace are derived from the other two feet, thereby distinguishing the first foot from the second foot. The detailed description of this step corresponds to the detailed description of the center point tracking of the footprint energy image generator 110 of FIG. 1, and is replaced with a detailed description of the footprint energy image generator 110 of FIG.

In operation 540, the starting time and the ending time of each foot are calculated using the non-zero pixel-by-pixel pressure values of the first foot and the second foot.

More specifically, the starting time and the ending time of each foot are calculated using the nonzero pixel pressure value of the first foot and the non-zero pixel of the second foot, respectively, that is, nonzero pixels. The detailed description of this step corresponds to the detailed description of the calculation of the start time and the end time of the footprint energy image generation unit 110 of FIG. 1, and is a detailed description of the footprint energy image generation unit 110 of FIG. 1 Instead.

In step 550, it is determined whether each of the legs corresponds to the left foot or the right foot using the direction of the gait, and a binary image of each foot is generated using the footprint pressure image for the start time and the end time of each foot .

More specifically, the image positioned on the left side of the gait direction corresponds to the left foot, the image positioned on the right side corresponds to the right foot, and the image is divided into a binary image of each foot from the start time to the end time calculated in step 540 Create an image. The detailed description of this step corresponds to the detailed description of the generation of the binary image up to the start time and the end time of the footprint energy image generating unit 110 of FIG. 1, and the detailed description of the footprint energy image generating unit 110 of FIG. It will be replaced with a detailed explanation.

Embodiments of the present invention may be implemented in the form of program instructions that can be executed on various computer means and recorded on a computer readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

As described above, the present invention has been described with reference to particular embodiments, such as specific elements, and specific embodiments and drawings. However, it should be understood that the present invention is not limited to the above- And various modifications and changes may be made thereto by those skilled in the art to which the present invention pertains.

Accordingly, the spirit of the present invention should not be construed as being limited to the embodiments described, and all of the equivalents or equivalents of the claims, as well as the following claims, belong to the scope of the present invention .

110: footprint energy image generation unit
120:
210: Pressure sensor
250: footprint database

Claims (15)

Generating a footprint energy image by dividing a left foot and a right foot by receiving a continuous footprint pressure image generated while the user is walking;
Calculating a degree of similarity or a degree of similarity between the generated left footprint energy image and a left foot reference image and a degree of similarity or non-conformity between the generated right footprint energy image and a right foot reference image; And
Recognizing the user using the similarity of the left footprint energy image or the similarity of the right footprint energy image or the non-reference figure,
The continuous footprint pressure image may comprise at least one of:
Wherein the shape of the foot is not the shape of the foot. The method according to claim 1,
Wherein generating the footprint energy image comprises:
Separating the left foot and the right foot by tracking the center point of the input footprint pressure image and generating a binary image; And
And generating the left footprint energy image and the right footprint energy image using the generated binary image. 3. The method of claim 2,
Wherein the generating the binary image comprises:
Attaching a label to the input footprint image;
Searching for a center point of the labeled footprint pressure image;
Tracking the center point along the frame of the footprint pressure image to distinguish the first foot from the second foot;
Calculating a starting time and an ending time of each foot using the non-zero pixel-by-pixel pressure values of the first foot and the second foot; And
Determining whether each of the legs corresponds to the left foot or the right foot using the direction of the step of gait and generating a binary image of each foot using the footprint pressure image for the start time and the end time of each foot User recognition method. 3. The method of claim 2,
The footprint energy image of each foot,
And generating an average of the generated binary images of the foot. 3. The method of claim 2,
Wherein generating the footprint energy image comprises:
Further comprising rotating the footprint energy image such that the orientation of the footprint energy image matches the orientation of the footprint. 6. The method of claim 5,
Wherein rotating the footprint energy image comprises:
Calculating an eigenvector and an eigenvalue of the generated footprint energy image using the covariance matrix, determining an eigenvector having the eigenvalue greater than the eigenvector as a major axis, and calculating an angle between the long axis and the gaging direction Wherein the direction of the footprint energy image is made to coincide with the walking direction using the difference. 6. The method of claim 5,
Wherein generating the footprint energy image comprises:
And adjusting the center point of the rotated footprint energy images to the same location. The method according to claim 1,
Wherein the step of calculating the degree of similarity or non-
k-neighbor algorithm (kNN) is used to calculate the similarity or non-likelihood. A computer-readable recording medium storing a program for causing a computer to execute the method according to any one of claims 1 to 8. A footprint energy image generation unit for generating a footprint energy image by separating the left foot and the right foot by receiving a continuous footprint pressure image generated while the user is walking; And
Calculating a degree of similarity or non-similarity between the generated left footprint energy image and a left foot reference image and a similarity or non-similarity between the generated right footprint energy image and a right foot reference image, And a user recognition unit for recognizing the user using the similarity degree of the right footprint energy image or the non -
The continuous footprint pressure image may comprise at least one of:
Characterized in that it is in the form of a foot part, not in the form of a foot. 11. The method of claim 10,
Wherein the footprint energy image generator comprises:
Generating a binary image by separating a left foot and a right foot by tracking a center point of the inputted footprint pressure image and generating the left footprint energy image and the right footprint energy image using the generated binary image, Recognition device. 12. The method of claim 11,
The footprint energy image of each foot,
And generating an average of the generated binary images. 12. The method of claim 11,
Wherein the binary image comprises:
Searching for a center point of the labeled footprint pressure image and tracking the center point along the frame of the footprint pressure image to distinguish the first foot from the second foot, The starting time and the ending time of each foot are calculated using the pressure value of each pixel, the direction of the footing is used to determine whether each of the separated feet corresponds to the left foot or the right foot, And generating a footprint image using the footprint image. 11. The method of claim 10,
Wherein the footprint energy image generator comprises:
Calculating an eigenvector and an eigenvalue of the generated footprint energy image using the covariance matrix, determining an eigenvector having the eigenvalue greater than the eigenvector as a major axis, and calculating an angle between the long axis and the gaging direction Rotating the footprint energy image so that the direction of the generated footprint energy image is aligned with the walking direction using the difference,
And adjusts the center point of the rotated footprint energy images to the same position. 11. The method of claim 10,
The degree of similarity or non-
k neighboring algorithm (kNN).

Images