KR102339478B1 - Method for representing face using dna phenotyping, recording medium and device for performing the method - Google Patents

Abstract

A face estimation method using DNA information includes: modeling a correlation between face shape and single nucleotide polymorphism (SNP) information from image information and DNA information of the face; analyzing the DNA of the obtained biological sample; extracting SNP information from the DNA analysis information; and estimating the face shape based on the SNP information. Accordingly, it is possible to estimate an objective and accurate face using the genetic material and create a montage.

Description

Face estimation method using DNA information, recording medium and apparatus for performing the same

The present invention relates to a method for estimating a face using DNA information, a recording medium and an apparatus for performing the same, and more particularly, modeling the relationship between facial features and DNA information to determine the appearance of face parts only with DNA information left at a crime scene. The present invention relates to a face estimation method for estimating, a recording medium and an apparatus for performing the same.

Creating a montage for estimating a criminal's face is one way to solve a criminal case, to find the characteristics and similarities of the suspect based on the memories of those who have witnessed it, and to apply various approaches to generate the predicted facial image of the suspect. create

Existing montage creation techniques allow a person to draw a face by hand or use a computer to create a face by combining or synthesizing an overall impression based on the eyewitness statement. All of these methods were possible to create only when clues were given through eyewitness statements or CCTV screens about the appearance of the montage object.

On the other hand, the use of DNA information in criminal investigations has been used only for DNA analysis to identify the true criminal by comparing the DNA of the arrested suspect with the DNA left at the crime scene. Therefore, there was a limit to using DNA information in a situation where the suspect was not covered.

KR 10-2014-0059076 A

Accordingly, it is an object of the present invention to provide a method for estimating the face of a criminal using DNA information, which is direct evidence of a suspect left at a crime scene.

Another object of the present invention is to provide a recording medium in which a computer program for performing the face estimation method using the DNA information is recorded.

Another object of the present invention is to provide an apparatus for performing a face estimation method using the DNA information.

In the face estimation method using DNA information according to an embodiment for realizing the object of the present invention, the correlation between the face shape and SNP (single nucleotide polymorphism, single nucleotide polymorphism) information from image information and DNA information of the face is modeling; analyzing the DNA of the obtained biological sample; extracting SNP information from the DNA analysis information; and estimating the shape of the criminal's face based on the SNP information.

In an embodiment of the present invention, modeling the correlation between facial features and SNP information from the image information and DNA information of the face includes: collecting face image information and DNA information; extracting a feature component related to a face shape from the face image information; extracting SNP information related to a face shape from the DNA information; and analyzing and modeling a correlation between the face shape and the SNP information.

In an embodiment of the present invention, the step of analyzing the DNA of the obtained biological sample includes extracting at least one of gender, race, and ancestry information from the DNA, and initially based on at least one of the gender, race, and ancestry information The method may further include estimating the face shape.

In an embodiment of the present invention, the method for estimating a face using the DNA information may further include estimating an attribute value for each face part classified from the SNP information.

In an embodiment of the present invention, the method for estimating a face using the DNA information may further include applying a weight to the estimated attribute value for each face part to the initial face shape.

In an embodiment of the present invention, the method for estimating a face using the DNA information may further include supplementing the shape of each part of the face estimated based on a statement of a witness or image information of CCTV.

In an embodiment of the present invention, the method for estimating the face of a criminal using the DNA information may further include quantifying and providing the reliability of the estimated face shape.

In a computer-readable storage medium according to an embodiment for realizing another object of the present invention, a computer program for performing a method of estimating a criminal's face using DNA information is recorded.

Criminal face estimation apparatus using DNA information according to an embodiment for realizing another object of the present invention is between face shape and SNP (single nucleotide polymorphism, single nucleotide polymorphism) information from image information and DNA information of the face. Offline unit for modeling correlation; a DNA analysis unit that analyzes the DNA of the obtained biological sample; SNP extraction unit for extracting SNP information from the analysis information of the DNA; and a face shape estimation unit for estimating the shape of the criminal's face based on the SNP information.

In an embodiment of the present invention, the offline unit includes: a collecting unit for collecting face image information and DNA information; a facial feature component extracting unit for extracting a feature component related to a face shape from the face image information; a SNP analysis unit for extracting SNP information related to a face shape from the DNA information; and a modeling unit for modeling by analyzing a correlation between a face shape and SNP information.

In an embodiment of the present invention, the DNA analysis unit extracts at least one of gender, race, and ancestry information from the DNA, and a base estimator for estimating an initial face shape based on at least one of the gender, race, and ancestry information may include more.

In an embodiment of the present invention, the face shape estimator may estimate an attribute value for each face part classified from the SNP information.

In an embodiment of the present invention, the face shape estimator may apply a weight to the estimated attribute value for each face part to the initial face shape.

In an embodiment of the present invention, the face estimation apparatus using the DNA information may further include a supplementary unit for supplementing the shape of each part of the face estimated based on the statement of the witness or the video information of the CCTV.

In an embodiment of the present invention, the apparatus for estimating a face using the DNA information may further include a reliability display unit that quantifies and provides reliability for the estimated face shape.

According to the face estimation method using such DNA information, unlike the existing method based on eyewitness statements or the indirect approach to the suspect who creates a montage by referring to CCTV images, the physical Therefore, it can be said that it is a direct approach to create a montage by estimating facial features using the suspect's biometric information. By estimating the face in a radically different approach from the existing montage writing method, it is possible to objectively write a montage that will give a new clue to solving the case, avoiding the disadvantages of inconsistent statements of witnesses and subjectively biased statements.

1 is a block diagram of an apparatus for estimating a face using DNA information according to an embodiment of the present invention.
2 is a block diagram of an online part of an apparatus for estimating a face using DNA information according to another embodiment of the present invention.
3 is a block diagram of an online part of an apparatus for estimating a face using DNA information according to another embodiment of the present invention.
4 is a block diagram of an online part of an apparatus for estimating a face using DNA information according to still another embodiment of the present invention.
5 is a flowchart of a face estimation method using DNA information according to an embodiment of the present invention.
6 is a detailed flowchart of a step of modeling a correlation between face shape and SNP information from image information and DNA information of the face of FIG. 5 .
7 is an example of classification criteria for attributes for each face part.
8 is an example in which eyebrows are classified by stage among face parts.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] Reference is made to the accompanying drawings, which show by way of illustration specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein with respect to one embodiment may be implemented in other embodiments without departing from the spirit and scope of the invention. In addition, 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 present invention. Accordingly, the detailed description set forth below is not intended 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 scope equivalents as those claimed. Like reference numerals in the drawings refer to the same or similar functions 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 estimating a face using DNA information according to an embodiment of the present invention.

The face estimation device (10, hereinafter device) using DNA information according to the present invention is computer-based based on the genetic material left at the scene when it is difficult to determine the suspect because a clue to the face of the criminal through the witness or CCTV is not given at the crime scene. Create a montage.

Referring to FIG. 1 , the device 10 according to the present invention is an offline unit 100 that models the correlation between face shape and SNP (single nucleotide polymorphism) information from image information and DNA information of the face in the offline process. ) and an online unit 300 for estimating a face from a biological sample obtained in the field through an online process.

The offline unit 100 may include a collection unit 110 , a facial feature extraction unit 130 , an SNP analysis unit 150 , and a modeling unit 170 .

The collection unit 110 collects face image information and DNA information. Specifically, the collection unit 110 may include a database for storing various face images by race, age, region, and country, and a database for storing DNA information corresponding to the face image.

The facial feature extraction unit 130 extracts a feature component related to a face shape from the face image information. Specifically, the face shape is divided into regions for each part, and this region is classified into stages according to feature criteria. As for the criterion of the facial feature, attribute values may be determined as in the example of FIG. 7 , and each attribute value may be expressed in stages as in the example of FIG. 8 . Here, it should be understood that the attribute value of the expressed face may be variably changed.

The SNP analysis unit 150 extracts SNP information that affects facial features from the DNA information. A genetic change or mutation that shows a difference in one nucleotide sequence (A, T, G, C) in the DNA sequence is called SNP (single nucleotide polymorphism) and is read as snip. The position at which two or more allele sequences that are present at a frequency of 1% or more in the population occur is called SNP. If it is, it is classified as a rare polymorphism.

Since SNP is a part that shows a lot of variation in each individual, it is mainly used for DNA fingerprint analysis. In the present invention, facial features are estimated through statistical analysis of SNP data based on SNPs that affect facial features.

The modeling unit 170 models the correlation through statistical analysis between the attribute values for each part regarding the facial shape classified by the facial feature extraction unit 130 and the SNP information. Modeling can be expressed as a relational expression between face shape and SNP information.

When the correlation between the face shape and the SNP information is modeled in the modeling unit 170 , a face may be estimated using DNA information from a biological sample input in real time from the online unit 300 as an online processing process thereafter.

Specifically, referring to FIG. 1 , the online unit 300 may include a DNA analyzer 310 , an SNP extractor 330 , and a face shape estimation unit 350 .

The DNA analysis unit 310 analyzes the DNA of the obtained biological sample. In this case, at least one of information such as gender, race, and ancestry may be extracted from the DNA. The SNP extractor 330 may extract SNP information from the DNA analysis information.

The face shape estimator 350 estimates the face shape of the montage based on the SNP information. That is, the face shape estimating unit 350 inputs the SNP information extracted from the SNP extraction unit 330 into the analysis model of the correlation between the face shape and the SNP information generated by the modeling unit 170, The shape of the face can be estimated by predicting which attribute value α has with respect to each attribute classified by the facial feature extraction unit 130 . Accordingly, it is possible to easily access difficult-to-estimate parts by estimating each part group through the relationship between the group to which each part belongs and DNA rather than a specific measurement value of the facial features.

Meanwhile, as shown in FIG. 2 , the online unit 301 according to another exemplary embodiment may further include a base estimator 340 for estimating the initial face shape before estimating the face shape. In this case, the face shape estimator 350 may merge the shape of each part of the face by applying a weight to the attribute value for each face part to the estimated initial face. In addition, after the step of estimating the face for each part through DNA, it is possible to estimate a face part that is not estimated based on the result of the correlation analysis for each part obtained through the face database image analysis.

The base estimator 340 may estimate the initial face shape based on at least one of gender, race, and ancestry information extracted by the DNA analyzer 310 . Alternatively, the base estimator 340 may estimate an initial face shape from the SNP information.

The base estimator 340 may estimate various face shapes based on databases collected by many races and regions, which may be updated according to changes in the environment and the passage of time.

In addition, as shown in FIG. 3 , the online unit 303 according to another embodiment may further include a complementation unit 370 for supplementing the shape of each face part estimated based on a witness' statement or CCTV image information. .

Accordingly, the face of a criminal estimated using biometric information, which is direct evidence of the suspect, can be supplemented with indirect evidence such as eyewitnesses or CCTV. In this case, even if the information of the witness or CCTV is not complete, the accuracy of the montage can be increased by using the montage generated according to the present invention as supplementary data.

Also, as shown in FIG. 4 , the online unit 305 according to another exemplary embodiment may further include a reliability display unit 390 that quantifies and provides the reliability of the estimated shape for each face part.

Accordingly, the user can recognize how reliable the montage estimated according to the present invention is, and partial correction can be performed on the low reliability region.

In the device 10 of the present invention, software (application) for performing face estimation using DNA information may be installed and executed, and the configuration of the offline unit 100 and the online unit 300 includes the apparatus 10 ) can be controlled by software for performing face estimation using the DNA information executed in

The device 10 may be a separate terminal or may be a part of a module of the terminal. In addition, each component of the offline unit 100 and the online unit 300 may be formed of an integrated module or may be formed of one or more modules. However, on the contrary, each configuration may be formed of a separate module.

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

The device 10 may execute or manufacture various software based on an operating system (OS), that is, the system. The operating system is a system program for 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 series, Linux series, Unix series, It can include all computer operating systems such as MAC, AIX, and HP-UX.

5 is a flowchart of a face estimation method using DNA information according to an embodiment of the present invention. 6 is a detailed flowchart of a step of modeling a correlation between face shape and SNP information from image information and DNA information of the face of FIG. 5 .

The face estimation method using DNA information according to the present embodiment may proceed in substantially the same configuration as the device 10 of FIG. 1 . Accordingly, the same components as those of the device 10 of FIG. 1 are given the same reference numerals, and repeated descriptions are omitted. Also, the face estimation method using DNA information according to the present embodiment may be executed by software (application) for performing face estimation using DNA information.

The face estimation method using DNA information according to the present embodiment includes an offline step and an online step. In the offline stage, it consists of a stage of extracting feature components related to parts or the overall shape of a face image, and a stage of modeling by analyzing the correlation between each part of the face and gender, race, ancestry, and SNP. In the online stage, the SNP is analyzed through the DNA obtained from the actual field, first, a basic face image is created through gender, race, ancestry, etc., and a face is inferred based on the analyzed SNP to create a montage. These steps are to organize the relationship between facial features and DNA information, and to infer a montage through it.

Referring to FIG. 5 , the face estimation method using DNA information according to the present embodiment is an offline step. The correlation between the face shape and SNP (single nucleotide polymorphism, single nucleotide polymorphism) information from image information and DNA information of the face is first. to model (step S10).

The step of modeling the correlation between facial features and SNP information from the image information of the face and the DNA information (step S10) will be described in detail with reference to FIG. 6 .

Referring to FIG. 6 , the step of modeling the correlation between the facial features and SNP information from the image information and DNA information of the face (step S10) includes the steps of collecting face image information and DNA information (step S11), Extracting feature components related to the face shape from the face image information (step S12), extracting SNP information related to the face shape from the DNA information (step S13), and analyzing the correlation between the face shape and SNP information It may include the step of modeling (step S14).

Thereafter, as an online step, the DNA of the obtained biological sample is analyzed (step S30). In this case, the method may further include extracting at least one of information such as gender, race, and ancestry from the DNA, and estimating an initial face shape based on at least one of information such as gender, race, and ancestry.

SNP information is extracted from the DNA analysis information (step S50). In this case, the method may further include the step of estimating the initial face shape from the SNP information (step S70).

Next, the face shape of the montage is estimated based on the SNP information (step S90). The shape of the face can be estimated by inputting it into the analysis model of the correlation between the initial face shape and the SNP information, and predicting which attribute value the face part has for each classified attribute. Accordingly, it is possible to easily access difficult-to-estimate parts by estimating each part group through the relationship between the group to which each part belongs and DNA rather than a specific measurement value of the facial features.

In this case, a weight may be applied to the initial face shape for each face part. In the face estimation method using DNA information according to an embodiment, the face parts that are not estimated after the step of estimating the faces by parts through DNA are estimated based on the results of the correlation analysis for each part obtained through face database image analysis. can

As another embodiment according to the present invention, the step of supplementing the shape of each face part estimated based on the statement of the witness or the video information of the CCTV may be further included, and the reliability of the shape for each part of the face is quantified and provided It may further include the step of

Such a face estimation method using DNA information may be implemented as an application or implemented in the form of program instructions that may be executed through various computer components and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination.

The program instructions recorded in the computer-readable recording medium are specially designed and configured for the present invention, and may be known and available to those skilled in the computer software field.

Examples of the computer-readable recording medium include hard disks, magnetic media such as floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floppy 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 not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules for carrying out the processing according to the present invention, and vice versa.

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

The present invention can create a montage by estimating facial features using biometric information that is direct evidence of a suspect even when there is no indirect evidence such as a witness or CCTV. Therefore, it provides the possibility of efficient application of montage in the case of criminal investigation.

10: Face estimation device using DNA information
100: offline part
300, 301, 303, 305: Online part
110: collection unit
130: facial feature extraction unit
150: SNP analysis unit
170: modeling unit
310: DNA analysis unit
330: SNP extraction unit
350: face shape estimation unit
340: base estimator
370: complement
390: reliability display unit

Claims (15)

Collecting face image information and DNA information of a plurality of people;
extracting each face shape from the face image information of the plurality of people;
dividing the face shape of the face image information into parts;
Classifying the divided part regions of a plurality of people into a plurality of groups according to a pre-staged criterion for each of one or more facial attributes displayed in the region region - Among the face parts having the pre-staged corresponding facial attribute for each facial attribute It is a step-by-step criterion to classify into the same site type;
setting an attribute value for each classified group, wherein the attribute value is set to a value indicated by each group step-by-step with respect to the part shape expressed in the part regions of the plurality of persons having the same facial attribute;
extracting each of the SNP information related to the face shape from the DNA information of the plurality of people;
Modeling an analysis model between the face shape and SNP information by analyzing the correlation between the extracted face shape and SNP information - The modeling step analyzes the correlation between the attribute value for each group and the SNP information, so that the specific SNP information is including modeling to predict the attribute value for each group having a relationship with the specific SNP information when input to the analysis model;
analyzing the DNA of the obtained biological sample after the modeling;
extracting SNP information of the biological sample from the analysis information of the DNA; and
Including the step of estimating the face shape of the suspect who left the biological sample by applying the SNP information of the biological sample to the analysis model,
The step of estimating the shape of the suspect's face,
inputting the SNP information of the biological sample into the analysis model to predict an attribute value for each group having a correlation with the SNP information of the biological sample; and
A face estimation method using DNA information, comprising estimating the face shape of the suspect by estimating the staged part shape indicated by the predicted group attribute value for each part. delete According to claim 1,
If there is a part where face estimation is not performed based on the estimated attribute value,
Further estimating the face shape of the part where the face estimation is not performed based on the estimated attribute value based on the correlation analysis result for each part obtained by analyzing the face image information,
Face estimation method using DNA information. According to claim 1,
The step of analyzing the DNA of the obtained biological sample,
extracting at least one of gender, race, and ancestry information from the DNA;
Further comprising the step of estimating an initial face shape based on at least one of the gender, race, and ancestry information, the face estimation method using DNA information. 5. The method of claim 4,
The step of estimating the face shape by applying the SNP information of the biological sample to the analysis model further includes estimating the face shape by merging the initial face shape with the face shape for each part in which a weight is applied to the estimated attribute value. A face estimation method using DNA information. According to claim 1,
A face estimation method using DNA information, further comprising the step of supplementing the face shape estimated based on the statement of the witness or the video information of CCTV. According to claim 1,
A face estimation method using DNA information, further comprising the step of quantifying and providing reliability for the estimated face shape. A computer-readable recording medium having a computer program recorded thereon for performing the face estimation method using DNA information according to any one of claims 1 to 7. a collection unit for collecting face image information and DNA information of a plurality of people;
A facial feature extracting unit for extracting a face shape from the face image information of the plurality of people, the facial feature extracting unit,
The face shape of the face image information is divided into parts,
For each of the one or more facial attributes displayed in the region region, the divided region regions of a plurality of people are classified into a plurality of groups according to a pre-staged criterion. Staged criteria for classification by site type;
configured to respectively set an attribute value for each of the classified groups, wherein the attribute value is set to a value indicated in stages of each group with respect to the part shape expressed in the part regions of the plurality of persons having the same facial attribute;
SNP analysis unit for extracting each SNP information related to the face shape from the DNA information of the plurality of people;
A modeling unit that models the analysis model between the face shape and SNP information by analyzing the correlation between the extracted face shape and SNP information - The modeling unit analyzes the correlation between the attribute value for each group and the SNP information, so that the specific SNP information is further configured to model to predict an attribute value for each group having a relationship with the specific SNP information when input to the analysis model;
a DNA analysis unit that analyzes the DNA of the obtained biological sample;
a SNP extraction unit for extracting SNP information of the biological sample from the analysis information of the DNA; and
After the modeling, the face shape estimator for estimating the face shape of the suspect who left the biological sample by applying the SNP information of the biological sample to the analysis model - The face shape estimating unit,
inputting the SNP information of the biological sample into the analysis model to obtain an attribute value for each group having a correlation with the SNP information of the biological sample, and
Configured to estimate the face shape of the suspect by estimating the staged part shape indicated by the predicted group attribute value for each part -
Including, face estimation device using DNA information. delete 10. The method of claim 9,
The face shape estimating unit,
If there is a part where face estimation is not performed based on the estimated attribute value,
The face estimating apparatus using DNA information, further configured to estimate a face shape of a part for which face estimation is not performed based on the estimated attribute value based on a correlation analysis result for each part obtained by analyzing the face image information. 10. The method of claim 9,
The DNA analysis unit,
extracting at least one of gender, race, and ancestry information from the DNA;
The face estimation apparatus using DNA information, further comprising a base estimator for estimating an initial face shape based on at least one of the gender, race, and ancestry information. 13. The method of claim 12,
The face shape estimating unit,
and estimating the face shape by merging the initial face shape with the face shape for each part to which a weight is applied to the estimated attribute value for each face part. 10. The method of claim 9,
A face estimation device using DNA information, further comprising a supplementary unit for supplementing the face shape estimated based on the statement of the witness or the video information of the CCTV. 10. The method of claim 9,
A face estimation apparatus using DNA information, further comprising a reliability display unit that quantifies and provides reliability for the estimated face shape.

Images