KR101420189B1 - User recognition apparatus and method using age and gender as semi biometrics - Google Patents

Abstract

The present invention relates to an apparatus and method for recognizing a user using age and sex, and a user recognition apparatus using age and sex according to an aspect of the present invention includes a database for storing unique age information and gender information of a plurality of persons, A first extracting unit for extracting age and gender information of the user from the user data, and extracting the extracted age and gender information, the unique age information and intrinsic gender information stored in the database, A first probability calculating unit for calculating a first probability that a user recognized from the outside is a probability that a plurality of persons recognized from the outside are stored in the database and a user recognizing unit for recognizing the user using the first probability.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a user recognition apparatus and method using age and gender,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus and method for recognizing a user using age and gender. More particularly, the present invention relates to a user recognition apparatus and method for identifying a user using video and audio information of a user.

The present invention is derived from research carried out as part of the IT original technology development project of the Ministry of Knowledge Economy. [Project Assignment Number: 2008-F-037-01, Title: u-Robot HRI Solution and Core Device Technology Development]

Conventionally, biometric information (face, fingerprint, iris, voice) is used to recognize a user. However, since the identification method based on such biometric information is generally for security purposes, it is presupposed that the environment is strictly regulated and the user actively cooperates to obtain information about the user.

Particularly, when the real-life space is a space where only limited persons such as home environment, office, and the like are used, it is inefficient to recognize the user by using biometric information that requires active cooperation of the user.

Therefore, it is necessary to use a variety of information in addition to biometric information so that the user can be recognized more efficiently and stably in the case of a limited space such as a home environment or an office.

Disclosure of Invention Technical Problem [8] The present invention has been made in order to provide an apparatus and a method for more effectively and stably recognizing a user in a limited space such as a home environment or an office. The present invention provides a user recognition apparatus using age and gender information that is more efficient than using biometric information alone.

Another problem to be solved by the present invention is to provide a method of recognizing a user using age and gender information more efficiently than when biometric information alone is used when the real space is limited.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

According to another aspect of the present invention, there is provided an apparatus and method for recognizing a user using age and sex, the apparatus comprising: a database for storing unique age information and gender information of a plurality of persons; Extracts the age and gender information, extracts unique age information and inherent gender information stored in the database, and calculates a first probability that the user is a probability for each of the plurality of persons based on the comparison result And a user recognition unit for recognizing the user using the first probability.

According to another aspect of the present invention, there is provided a method of recognizing a user using age and sex, comprising the steps of: extracting age, sex and biometric information of a user from input user data; extracting age and gender information; Comparing the unique age information and inherent gender information of the plurality of persons stored in the database with each other and calculating a first probability that is a probability of the user for each of the plurality of persons based on the comparison result; Calculating a second probability that is a probability of a user for each of the plurality of users based on the comparison result, and recognizing the user using the first probability and the second probability.

According to the present invention, when age and gender are used, the user can be recognized more simply and efficiently than when biometric information is used. In particular, there is an advantage that the user's identity can be easily recognized when there is a limited user in a limited space.

1 is a conceptual diagram of a user recognition method according to an embodiment of the present invention.
2 is a block diagram of a user recognition apparatus using age and sex according to an embodiment of the present invention.
3 is a block diagram of a user recognition apparatus using age and sex according to another embodiment of the present invention.
4 is a flowchart of a method of recognizing a user using age and sex according to an embodiment of the present invention.
5 is a flowchart of a method of recognizing a user using age and sex according to another embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention and the manner of achieving them will become apparent with reference to the embodiments described in detail below with reference to the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Is provided to fully convey the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the drawings, the same reference numerals are used to designate the same or similar components throughout the drawings. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

A user recognition method according to an embodiment of the present invention will be described with reference to FIG. 1 is a conceptual diagram of a user recognition method according to an embodiment of the present invention.

Referring to FIG. 1, a user recognition method according to an exemplary embodiment uses biometric information and biometric information of a user. The biometric information includes a face, a speaker, an iris, a fingerprint, and a Gait, and the biometric information includes sex, age, clothes color, and key. Hereinafter, the user recognition apparatus 200, 201 and method using age and sex, which are features of the present invention, will be described with reference to FIG. 2 to FIG.

Referring to FIG. 2, a user recognition apparatus using age and sex according to an embodiment of the present invention will be described. 2 is a block diagram of a user recognition apparatus using age and sex according to an embodiment of the present invention.

Referring to FIG. 2, the user recognition apparatus 200 using age and sex according to an embodiment includes a first extracting unit 210, a database 220, a first probability calculating unit 230, (240).

The first extracting unit 210 extracts the age and gender information of the user from the user data inputted from the outside. Here, the user data inputted from the outside includes at least one of video and audio information and all other information that can be converted into data. For example, image information obtained from a camera provided in the apparatus can be digitized and presented as a bitmap pattern.

The first extracting unit 210 includes an age information extracting unit 211 and a sex information extracting unit 212. The age information extracting unit 211 extracts the age information of the user from the input data, The unit 212 extracts the gender information of the user from the input data.

The database 220 stores unique age information and unique gender information of a plurality of persons. The unique age and gender information of members of the home or office through the user interface are stored in the database 220 in advance. Here, the unique age and unique gender information of a plurality of persons can be stored in a layered manner. For example, the gender may be classified into two categories, male and female, and the age information may be stored in the database 220 in a category of one or more categories.

 The first probability calculation unit 230 may calculate the age information extracted by the age information extraction unit 211 and the gender information extracted by the gender information extraction unit 212 based on the unique age and gender information of the user stored in the database 220 And calculates a first probability that a user who transmits video and audio information from the outside based on the comparison result has a probability of being a plurality of users stored in the database 220, respectively.

 The first probability can be calculated using the comparison result and the age weight and the sex weight. Here, the age weight and the sex weight may be determined according to the accuracy of the age information extracting unit 211 and the sex information extracting unit 212. For example, the gender information extracting unit 212 extracts gender from the video and audio data of the user, and may erroneously recognize an actual male as a woman due to errors of the apparatus itself or surrounding environment. The accuracy of the gender information extracting unit 212 can be measured by measuring the frequency of occurrence of such an error experimentally. Likewise, the age weight can be determined by measuring the accuracy of the age information extracting unit 211 by measuring the frequency of occurrence of an error that is determined experimentally as an age different from the actual age.

Alternatively, the age and gender weights may depend on the sex and age distribution of users stored in the database 220. For example, when there is only one person in a certain age range in the user information stored in the database 220, since only the age is recognized, the gender information can be ignored and only one user information stored in the database 220 If you are a woman, age information can be ignored.

Specifically, the sex is divided into two hierarchies, male and female, and the N hierarchies are stored in the database 220. In the nth hierarchy of age, there are F (n) female and M (n) male A (n) * (1 / F (n) * Q) is a first probability for a user when the user corresponding to the corresponding layer is recognized, * (1 / M (n) * Q). Where A (n) is the age weight and Q is the gender weight.

The user recognition unit 240 recognizes the user using the first probability. Specifically, a user who transmits video and audio information from the outside calculates a first probability that is a plurality of users stored in the database 220, and recognizes the highest probability as a user who delivers video and audio information from the outside And outputs the result.

Referring to FIG. 3, a user recognition apparatus using age and sex according to another embodiment of the present invention will be described. 3 is a block diagram of a user recognition apparatus using age and sex according to another embodiment of the present invention. The same reference numerals are used for components having the same functions as those shown in FIG. 2, and a detailed description of the components will be omitted.

Referring to FIG. 3, unlike the user recognition device of FIG. 2, the user recognition device 201 using age and sex recognizes a user by using biometric information together with age and gender. More specifically, the user recognition apparatus 201 using age and sex further includes a second extraction unit 310 and a second probability calculation unit 330. The database 221 further stores a plurality of unique biometric information do. The user recognition unit 241 recognizes the user using the first probability and the second probability.

The second extracting unit 310 extracts the biometric information of the user from the user data inputted from the outside. Here, the user data inputted from the outside includes at least one of video and audio information and all other information that can be converted into data. For example, image information obtained from a camera provided in the apparatus can be digitized and presented as a bitmap pattern.

The second probability calculation unit 330 compares the biometric information extracted by the second extraction unit 310 with the unique biometric information of the user stored in the database 221 and outputs the video and audio information from the outside based on the comparison result The transmitting user calculates a second probability, which is a probability of a plurality of users stored in the database 221, respectively.

One way to calculate the second probability is described below.

: 임의의 사용자 i

: 임의의 사용자 i의 생체 정보

: Any user i

: Biometric information of an arbitrary user i

: 사용자의 생체 정보 X의 추출 결과가, 데이터베이스에 저장 된 임의의 사용자 Ui의 생체 정보와 일치할 제2 확률

: If the extraction result of the user's biometric information X is the second probability that the biometric information of an arbitrary user Ui stored in the database coincides with the biometric information

X: Biometric information

μ: Biometric information extraction result

N: the number of users stored in the database)

Using the age and gender information, the user recognizing unit 241 recognizes the user who transmits video and audio information from outside by using the first probability and the biometric information, which are the probabilities of the plurality of users stored in the database 221, The user who transmits the video and audio information combines the second probability, which is the probability of the plurality of users stored in the database 221, to finally recognize who the user is.

In more detail, the user recognition unit 241 uses a weighted sum of the first probability and the second probability to calculate a weighted sum of a plurality of persons stored in the addition result database 221, . Here, the addition sum is calculated as follows using the weight determined by the first probability calculated from the age and sex information and the accuracy of the second probability calculated from the biometric information.

w * BM (i) + (1-w) * A (n) * Q *

BM (i): the second probability calculated from the biometric information

A (n) * Q * G (n): first probability calculated from age and gender information

w: Weight

The weighted sum method as described above is one embodiment of a user recognition method using sex and age, and includes all other methods.

A method of recognizing a user using age and sex according to another embodiment of the present invention will be described with reference to FIG. 4 is a flowchart of a method of recognizing a user using age and sex according to an embodiment of the present invention. The flowchart shown in FIG. 4 is only one example, and the present invention is not limited to the time-series order shown in FIG.

First, the user's age and gender information are extracted from the input user data (S410). Here, the user data inputted from the outside includes at least one of video and audio information and all other information that can be converted into data. For example, image information obtained from a camera provided in the apparatus can be digitized and presented as a bitmap pattern.

Next, a user who compares extracted age and gender information with unique age information and inherent gender information of a plurality of persons, and transmits video and audio information from the outside to each of a plurality of persons based on the comparison result, (S420). ≪ / RTI > The probability is calculated using the comparison result, the age weight, and the sex weight.

Here, the age weight and the sex weight are determined according to the accuracy of the age information extracting unit 211 and the sex information extracting unit 212. For example, the gender information extracting unit 212 extracts gender from the video and audio data of the user, and may erroneously recognize an actual male as a woman due to errors of the apparatus itself or surrounding environment. The accuracy of the gender information extracting unit 212 can be measured by measuring the frequency of occurrence of such an error experimentally. Likewise, the age weight can be determined by measuring the accuracy of the age information extracting unit 211 by measuring the frequency of occurrence of an error that is determined experimentally as an age different from the actual age.

Alternatively, the age and gender weights may depend on the sex and age distribution of users stored in the database 220. For example, when there is only one person in a certain age range in the user information stored in the database 220, since only the age is recognized, the gender information can be ignored and only one user information stored in the database 220 If you are a woman, age information can be ignored.

Using the probability, a person having the highest probability is recognized as a user transmitting video and audio information from the outside, and the result is output (S430).

Referring to FIG. 5, a method of recognizing a user using age and sex according to another embodiment of the present invention will be described. 5 is a flowchart of a method of recognizing a user using age and sex according to another embodiment of the present invention.

First, the user's age, sex, and biometric information are extracted from the input user data (S510). Here, the user data inputted from the outside includes at least one of video and audio information and all other information that can be converted into data. For example, image information obtained from a camera provided in the apparatus can be digitized and presented as a bitmap pattern.

Next, the extracted age and gender information is compared with unique age information and inherent gender information of a plurality of persons, and a user who transmits video and audio information from the outside based on the comparison result transmits a plurality of users And calculates a first probability that is a probability of occurrence (S520). The first probability is calculated using the comparison result and the age weight and the sex weight. Here, the age weight and the sex weight are determined according to the accuracy of the age information extracting unit 211 and the sex information extracting unit 212. For example, the gender information extracting unit 212 extracts gender from the video and audio data of the user, and may erroneously recognize an actual male as a woman due to errors of the apparatus itself or surrounding environment. The accuracy of the gender information extracting unit 212 can be measured by measuring the frequency of occurrence of such an error experimentally. Likewise, the age weight can be determined by measuring the accuracy of the age information extracting unit 211 by measuring the frequency of occurrence of an error that is determined experimentally as an age different from the actual age.

Then, the extracted biometric information is compared with unique biometric information of a plurality of persons, and the second probability of the user is calculated for each of the plurality of persons (S530). For example, if the biometric information extracted from the outside is the user's face, the face image that can be recognized from the acquired image data is acquired from the database 221 , And if there is a recognizable face image, the face feature information is extracted. Next, the extracted facial feature information is compared with the facial feature information of the user stored in the database 221 to determine whether or not the user captured in the input image for all users stored in the database 221 has the second probability .

Lastly, a user who transmits image and audio information from outside uses a first probability and a biometric information, which are probabilities of a plurality of users stored in the database 221, (Step S540), and finally recognizes who the user is.

It will be understood by those skilled in the art that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. It is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

200, 201: User recognition device using age and sex
210: first extracting unit 220:
211: Age information extracting unit 230: First probability calculating unit
212: Gender information extracting unit 240: User identification unit

Claims (18)

A database storing unique age information and inherent gender information of a plurality of persons;
A first extracting unit for extracting a user's age and gender information from input user data;
Comparing the extracted age and gender information with the inherent age information and the unique gender information stored in the database, and if the user recognized from the outside for each of the plurality of persons based on the comparison result is the plurality of persons A first probability calculating unit for calculating a first probability which is a probability of occurrence; And
And a user recognition unit for recognizing the user using the first probability,
The first probability calculation unit may calculate,
Calculating the first probability using the extracted age and gender information, the age weight and the gender weight whose value is determined in association with the distribution of the unique age information and the unique gender information stored in the database
A user recognition device using age and sex. The apparatus of claim 1, wherein the first extracting unit
Extracting the age and gender information of the user from the user data including at least one of video and audio information
A user recognition device using age and sex. delete delete The method according to claim 1,
Wherein the database further stores a plurality of unique biometric information,
Wherein the user recognition device comprises: a second extracting unit for extracting biometric information of a user from the user data; And
And comparing the extracted biometric information with the unique biometric information stored in the database to determine a second probability that the user recognized from the outside for each of the plurality of persons is the probability of the plurality of persons stored in the database And a second probability calculation section for calculating a second probability,
Wherein the user recognition unit recognizes the user using the first probability and the second probability
A user recognition device using age and sex. The apparatus as claimed in claim 5, wherein the first extracting unit and the second extracting unit
Extracting the age, sex and biometric information of the user from the user data including at least one of video and audio information
A user recognition device using age and sex. 6. The apparatus of claim 5, wherein the user recognition unit
And recognizing, as the user, a person having the highest total sum of the plurality of persons as a result of calculation of the addition sum, using a weighted sum of the first probability and the second probability
A user recognition device using age and sex. 8. The method of claim 7,
Using the first probability calculated from the age and gender information and the weight determined by the accuracy of the second probability calculated from the biometric information
A user recognition device using age and sex.


delete delete delete delete delete delete delete delete delete delete

Images