KR100907597B1 - Face recognition system and method based on lighting control, and apparatus and server applied thereto - Google Patents

Abstract

The present invention discloses a lighting control-based face recognition system and method, and apparatus and server applied thereto. The system according to the present invention extracts the target face region from the photographed image of the object, determines the image variation of the target face region, and when the image distortion occurs due to illumination, based on the lighting control value for the image distortion generating region. And a terminal device for performing face recognition processing through the captured image which is reshaped after adjusting at least one flash. Accordingly, the present invention corresponds to an image shift due to illumination that interferes with face recognition from the captured image, and actively adjusts the flash according to the lighting situation of the target face region in the captured image, thereby preventing the target face region. As the recognition rate can be improved, it can be widely applied to many applications including user authentication.

Face recognition, lighting, image shift

Description

TECHNICAL AND METHOD FOR LIGHTING MODULATION-BASED FACE RECOGNITION, AND APPARATUS AND SERVER APPLIED TO THE SAME}

The present invention relates to a face recognition technique, and more particularly, to respond to image variations due to illumination that interferes with face recognition from a photographed image, and actively flashes according to lighting conditions of a target face area in the photographed image. The present invention relates to a face recognition system and method based on lighting control for improving the recognition rate of a corresponding target face region, and an apparatus and a server applied thereto.

In general, it is very difficult to accurately recognize a face because a human face appears as a very different face image according to a change in lighting, facial expression, age, when the image was acquired, noise, and the like. The core of the face recognition system is to realize stable face recognition performance without being affected by the image variation of the face. The development of a face recognition system with stable performance is a security system or a human computer interface in a company, a laboratory, a bank, etc. It can be very important in the field.

In order to recognize a face, there was a method of using a local geometric feature of a face or applying a template matching, but this method uses a large amount of memory due to the formation of a large number of intermediate images in order to recognize a face shape having a lighting change or a facial expression change. There is a problem that increases and takes a lot of time to calculate. Therefore, in order to reduce the amount of memory and the recognition time, a face image is converted into one feature vector in a vector space, and the feature vector of the face region of the captured image and the face of the recognition target (or a face implemented by a standard template) are used. By comparing feature vectors, a method of recognizing a face has been studied and typically extracts a face region from a feature based approach (FBA) using a feature point of a face included in a predetermined image and the captured image. There is an Appearance Based Approach (ABA) that uses image data that forms a preprocessed image that is transformed by harmonics. Examples of each of these face recognition applications are the Eigenface method and the Fisherface method.

The eigenface method obtains the eigenvalues and eigenvectors from the variance matrix representing the variance of the data for the intermediate processed image and expresses the face image as the coordinates of the eigenvectors corresponding to the large eigenvalues. The coordinates thus obtained are specific vectors representing one face image. In the actual recognition step, the face is recognized by comparing the feature vector obtained by linearly transforming the face image extracted from the captured image as an input with the feature vectors previously obtained offline. By applying PCA (Principal Component Analysis) on the face image, the dimension of face vector space is effectively reduced, so that the entire face images are compared by comparing only a few feature vectors that have been linearly transformed. Fast has the advantage.

However, in this method, feature vectors obtained from face images with changing lighting or facial expressions with partial occlusion or face images with partial occlusion are not easily separated between classes, resulting in poor recognition rate. There are disadvantages. This is because the eigenface method performs eigenvalue analysis of the variance matrix of the entire face image vectors instead of the variance matrix and inter-class variance matrix in each class.

The Fisher Face method is a method of applying a FLD (Fisher Linear Discrimination) using a matrix representing data distribution between classes and a matrix representing data distribution between classes in addition to a method of recognizing a face by applying PCA. FLD has the advantage of classifying feature vectors relatively accurately by using linear transformation that maximizes class separation between linearly changed feature vectors as well as the effect of dramatically reducing the dimension of face vector space. The Fischer Face method which recognizes a face by applying FLD shows better recognition performance than the eigenface method for the face image with lighting or facial expression change. In order to obtain a matrix representing intra-class dispersion and inter-class dispersion, a large amount of memory and computation time are required, and the recognition rate is still degraded for a face image with severe illumination change or occlusion.

As described above, the face recognition method according to the related art is a method for coping with various image variations such as face pose, illumination, facial expression, or occlusion, and the maximum limit through a preprocessing process for a manually provided photographed image. The focus was on the implementation of face recognition algorithms for efficient face recognition.

However, this should be an image within a range that can be recognized by executing the face recognition algorithm provided in the previous step for the face recognition.

As a result, even if a photographed image formed by photographing a predetermined object in an extremely poor lighting condition is developed, even if the recognition rate is improved through an excellent face recognition algorithm, its limitations are clearly generated. There is a need for measures to overcome.

Accordingly, the present invention has been made to solve the above problems, and an object of the present invention is to correspond to an image shift caused by illumination that interferes with face recognition from a captured image, and illuminates a target face region within the captured image. An object of the present invention is to provide a face recognition system and method based on lighting control, and an apparatus and a server applied thereto to actively adjust a flash according to a situation to improve a recognition rate of a corresponding face region.

In addition, another object of the present invention is to determine the video variance of the photographed image by interworking between the terminal device and the service management server through a communication network, and if the determination result is image distortion due to lighting, the camera of the terminal device and actively The present invention provides a face recognition system and method based on lighting control for improving the recognition rate of a corresponding target face area by adjusting an adjacent flash, and an apparatus and a server applied thereto.

In addition, another object of the present invention is to adjust the at least one flash adjacent to the camera of the terminal device to reset the lighting environment, the user through the face recognition data formed by performing the face recognition processing based on the re-formed photographed image A lighting control based face recognition system and method for executing authentication and application content providing service, and apparatus and server applied thereto.

In accordance with the first aspect of the present invention, there is provided a face recognition system based on lighting control by extracting a target face region from a photographed image of an object, and determining an image variation of the target face region. When the distortion occurs, the terminal device for performing the face recognition processing through the re-formed image after adjusting the at least one flash based on the illumination control value for the image distortion generating region.

Preferably, the lighting control-based face recognition system is connected to the terminal device and the communication network, and further comprises a service management server for receiving a face recognition data from the terminal device to execute a user authentication and application content providing service It is characterized by.

Preferably, the terminal device determines a facial feature element for the target face region, and detects an image variation that is an obstacle to face recognition through a pattern change amount based on a facial feature point constituting the face feature element, and a sensor. The image distortion by the illumination is determined using the ring result.

Preferably, the terminal apparatus extracts at least one or more face regions from the captured image, and sets a face region having a large proportional area among the at least one or more face regions as the target face region.

Preferably, the terminal apparatus sets the target face area to be a single area.

Preferably, the terminal device extracts at least one or more face areas from the captured image, and sets the at least one or more face areas to be the target face area.

Preferably, the terminal device sets any one of the at least one or more face areas to be the target face area, and performs a process of determining the image variation to reach the face recognition processing.

Preferably, the terminal apparatus sets the average brightness value for the target face area, and sets the area of the image distortion generating area to a region having a brightness value less than a predetermined level based on the average brightness value. It features.

Preferably, the image distortion generating region is formed by extending additional regions interconnected through CCL (Connected Component Labeling) processing using brightness values lower than the predetermined level as initial values.

Preferably, the image distortion generating region is formed as an area forming an area larger than a predetermined level in proportion to the area of the target face region.

Preferably, the illumination control value is formed by comparing and discriminating between the average brightness value for the target face region and the brightness value for the image distortion generating region, and further comparing and determining the position in the image of the image distortion generating region. It is characterized by being formed.

Preferably, the at least one flash is characterized in that to adjust the intensity and the illumination direction of the brightness value differently according to the illumination control value.

In addition, the terminal device based on the illumination control according to the second aspect of the present invention for achieving the above object, a photographing unit for photographing the object in at least one direction, extracting the target face region from the photographed image of the object A face region extractor for detecting the image variation based on the amount of change in the pattern based on the feature points in the target face region, and then an image variation sensor sensor for setting the image distortion generation region based on the determination result. An illumination control unit for adjusting at least one flash by forming an illumination control value for an area, and a face recognition execution unit for executing face recognition processing on the reconstructed captured image after reconstructing the captured image. Characterized in that.

Preferably, the lighting control-based terminal device further comprises an interface for transmitting the face recognition data formed through the face recognition processing through a communication network.

Preferably, the lighting control unit forms the illumination control value by comparing and determining the average brightness value of the target face region and the brightness value of the image distortion generating region, and adjusts a position in the image of the image distortion generating region. And comparing and determining the lighting control value.

According to another aspect of the present invention, there is provided a face adjustment method based on lighting control according to a third aspect of the present invention, wherein (a) a terminal apparatus extracts a target face region from a photographed image after photographing an object in at least one direction. (B) determining an image variation using a pattern variation amount based on facial feature points in the target face region, and then setting an image distortion generation region based on the determination result, and (c) in the image distortion generation region. Adjusting at least one flash by forming an illumination control value for the image; and (d) performing face recognition processing on the reconstructed captured image after reconstructing the captured image. .

Preferably, the illumination control based face recognition method further comprises the step of (e) transferring the face recognition data formed through the face recognition processing to a service management server through a communication network.

Preferably, the lighting control-based face recognition method further comprises the step of (f) receiving the face recognition data by the service management server to execute a user authentication and application content providing service.

In addition, the lighting control-based face recognition system according to the fourth aspect of the present invention for achieving the above object, the terminal device for delivering a photographed image formed by photographing the object through a communication network and the target face region from the photographed image And a service management server for determining an image variation of the target face region and generating an illumination control value for the image distortion generating region and transmitting the image distortion to the terminal device. The terminal device adjusts at least one flash based on the lighting control value, reconstructs the photographed image, and transfers the reconstructed photographed image to the service management server, and the service management server regenerates the photographed image. And perform face recognition processing for.

Preferably, the service management server is characterized in that for executing the user authentication and application content providing service through the face recognition data formed by the face recognition processing.

In addition, the service management server based on light control according to the fifth aspect of the present invention for achieving the above object, an interface for receiving a captured image transmitted from the terminal device, for extracting the target face region from the captured image After detecting the image variation through the pattern change amount based on the facial feature point in the target face region, the image region sensor unit for setting the image distortion generating region based on the determination result, the image distortion generating region A lighting control unit for forming a lighting control value for the control unit, a control unit for transmitting the lighting control value to the terminal device through the interfacing unit, and controlling and reforming at least one flash based on the lighting control value from the terminal device After receiving a captured image, the face recognition program for the reconstructed captured image That includes a face detection execution for executing sesing characterized.

Preferably, the service management server further comprises a service execution unit for executing a user authentication and application content providing service through the face recognition data formed by the face recognition processing.

In addition, according to the sixth aspect of the present invention, the lighting control-based face recognition method according to the present invention comprises the steps of: (a) extracting a target face region from a photographed image provided by a service management server; (C) setting an image distortion generation region based on a result of the determination after determining the image variation based on a pattern change amount based on the facial feature point in the target face region; (c) an illumination control value for the image distortion generation region; Forming and transmitting the formed image to the terminal device; and (d) receiving a reformed captured image by adjusting at least one flash based on the illumination control value from the terminal device, and then receiving a face for the reformed captured image. Performing recognition processing.

Preferably, the light adjustment based face recognition method further comprises the step of (e) executing a user authentication and application content providing service through the face recognition data formed by the face recognition processing.

Accordingly, the present invention corresponds to an image shift due to illumination that interferes with the recognition of the face from the captured image, and actively adjusts the flash according to the lighting situation of the target face region in the captured image, thereby preventing the target face region. As the recognition rate can be improved, there is an advantage that it can be widely applied to many applications including user authentication.

Hereinafter, with reference to the accompanying drawings will be described in detail a preferred embodiment of the lighting control-based face recognition technology according to the present invention in detail.

1 is a block diagram of a face recognition system based on lighting control according to an embodiment of the present invention. As shown by way of example only in Fig. 1, the illumination control-based face recognition system forms a photographed image by capturing a predetermined object, extracts a target face region from the formed photographed image, and then features facial features of the target face region. By determining the factors, the sensor detects the image variation that is an obstacle to face recognition through the pattern variation based on the facial feature points forming the facial feature elements. By adjusting the at least one flash 113 on the basis of the lighting control value for the image distortion generating region specified through this, and comprises a terminal device 100 for performing the face recognition processing for the reconstructed captured image .
Here, the terminal device 100 refers to an image capturing terminal device for capturing an image of a predetermined object. Hereinafter, the terminal device 100 will be referred to as the terminal device 100.

In addition, the face recognition system based on the lighting control is connected to the terminal device 100 through a communication network, and receives the face recognition data formed by the execution of the face recognition processing from the terminal device 100 to provide a user authentication and application content providing service. It is also possible to further include a service management server 200 for execution.

The terminal device 100 extracts at least one or more face regions included in the captured image and determines one or more face regions having a large proportional area among the extracted one or more face regions, thereby determining the image variation of the specific face region. It is set to be the target face area for executing the process from the process of the process to the face recognition processing.

Here, it is preferable to set the target face area by setting a face area having the largest proportional area to each other and specifying a single area.

In addition, the terminal device 100 extracts at least one or more face regions from the photographed image, and sets the extracted face region to be a target face region for executing a process ranging from image variation to face recognition processing. It is also possible.

Herein, when setting at least one or more face areas to be the target face area, a process of setting any one or more face areas to be the target face area and determining the image variation and then performing face recognition processing is performed. After the execution, the process of resetting the other one of the at least one or more face areas as the target face area and re-executing the process of determining the image variation and performing the face recognition processing is performed to correspond to each face area. Therefore, the corresponding algorithm is preferably applied independently.

The terminal device 100 forms an average brightness value for the set target face area, and determines an area where an image shift has occurred in a region having a brightness value lower than a predetermined level based on the formed average brightness value, thereby distorting the image. Set the generation area.

The image distortion generating region may be formed by extending additional regions interconnected through CCL (Connected Component Labeling) processing with initial values of brightness lower than a predetermined level.

In addition, it is preferable that the image distortion generating area is an area of the target area that is larger than a predetermined level in proportion to the area of the target face area, and that of the area that is smaller than the predetermined level. It is desirable not to apply as being to improve the efficiency of the overall processing.

As a method for setting the lighting control value, it is formed by comparing and discriminating between the average brightness value for the target face region and the brightness value for the image distortion generating region, and further determining the position in the image of the image distortion generating region by It is preferably formed.

The at least one flash 113 controlled based on the illumination control value may be driven all at once to adjust the intensity and illumination direction of the corresponding brightness value to form an illumination environment for solving the image distortion generating region, As a part is driven and adjusted in the intensity and illumination direction of the corresponding brightness value, it is possible to create an illumination environment for solving the image distortion generating region.

2 is a block diagram of the terminal device 100 shown in FIG. As shown only as an example in FIG. 2, the terminal device 100 includes a photographing unit 110 for photographing an object in at least one direction, and a face region extracting unit for extracting a target face region from a photographed image of the object. 120, after determining the image variation through the pattern variation based on the facial feature points specified from the target face region, the image variation sensor 130 for setting the image distortion generating region based on the determination result, and generating the image distortion. An illumination control unit 140 for adjusting the at least one flash 113 by forming an illumination control value for the area, and a face for performing face recognition processing on the reconstructed captured image after reconstructing the captured image. The recognition execution unit 150 is included.

The terminal device 100 may further include an interfacing unit 160 for transferring the face recognition data formed through face recognition processing to the service management server 200 through a communication network.

The photographing unit 110 includes a camera 111, a display 112, and at least one flash 113, and the display 112 may not be provided according to an implementation direction.

3 is a conceptual diagram illustrating an arrangement of a flash 113 provided in the terminal device 100 illustrated in FIG. 1. As shown only as an example in FIG. 3, the terminal device 100 forms an illumination control value for the image distortion generating region, and at least one or more adjacent to the camera 111 based on the formed illumination control value. Adjust the brightness intensity and direction for the flash 113.

Accordingly, at least one flash 113 may be provided in four to perform an operation according to the lighting control value, or one or two may be provided to perform an operation according to the lighting control value, and a more detailed lighting environment may be provided. It is also possible to implement a larger number to create.

4 is a flowchart illustrating an operation process of a face recognition system based on light adjustment shown in FIG. 1. As shown by way of example only in Figure 4, the illumination control based face recognition method proceeds to the terminal device 100 to shoot the object to form a photographed image (S100).

Subsequently, after extracting the target face region from the photographed image (S102), the image variation is determined by the amount of pattern change based on the facial feature points in the extracted face region (S104).

An image distortion generating region is set based on the result determined in step S104 (S106), and an illumination control value for solving the image distortion generating region is formed (S108).

According to the lighting control value, at least one flash 113 is driven to generate an illumination environment such that an image shift due to illumination does not occur (S110), and a photographed image is reshaped based on the illumination environment (S112). .

Subsequently, face recognition data formed by performing face recognition processing on the reconstructed captured image is transmitted to the service management server 200 through a wired or wireless communication network (S114 and S116).

The service management server 200 executes a user authentication and application content providing service using the provided face recognition data (S118).

5 is a block diagram of a face recognition system based on lighting control according to another embodiment of the present invention. As shown only as an example in FIG. 5, the lighting control-based face recognition system includes a terminal device 300 for transmitting a captured image formed by photographing an object through a communication network, and photographing provided from the terminal device 300. After extracting the target face region from the image and checking the image variation of the extracted target face region to determine whether there is an image variation caused by lighting, if the image distortion caused by lighting occurs, the image distortion generating region is specified. It includes a service management server 400 for transmitting to the terminal device 300 the lighting control value formed to solve the generation area to create a suitable lighting environment.

Accordingly, the terminal device 300 reconstructs a captured image by adjusting at least one flash based on an illumination control value, and transmits the reconstructed captured image to the service management server 400.

The service management server 400 receiving the reconstructed photographed image executes face recognition processing on the reconstructed photographed image, and further provides a user authentication and application content providing service through face recognition data formed by face recognition processing. It is also possible to run

6 is a configuration diagram of the service management server 400 shown in FIG. As shown only as an example in FIG. 6, the service management server 400 may include an interface 410 for receiving a captured image transmitted from the terminal device 300, and a face region for extracting a target face region from the captured image. The image shift sensor 430 and the image distortion sensor for determining the image distortion generation region based on the determination result after determining the image variation through the pattern change amount based on the facial feature points in the target face region. An illumination control unit 440 for forming an illumination control value for the generation area, a controller 450 for transmitting the illumination control value to the terminal device 300 through the interface unit 410, and the terminal device 300. After receiving the reconstructed photographed image by adjusting the at least one flash from the light control value from the face recognition execution unit 460 for performing the face recognition processing for the reformed photographed image Include.

Furthermore, the service management server 400 may further include a service execution unit 470 for executing additional processing such as user authentication and application content providing service through face recognition data formed by face recognition processing.

FIG. 7 is a flowchart illustrating an operation process of a face recognition system based on light adjustment shown in FIG. 1. As shown only as an example in FIG. 7, in the lighting control-based face recognition method, the terminal device 300 photographs an object to form a photographed image (S200).

Subsequently, the terminal device 300 transmits the captured image to the service management server 400 through a wired or wireless communication network (S202), and the service management server 400 responding to the target face area from the captured image. After extraction (S204), the image variation is determined through the pattern change amount based on the facial feature points in the extracted target face region (S206).

An image distortion generating region is set based on the result determined in step S206 (S208), and an illumination control value for solving the image distortion generating region is formed (S210).

Thereafter, the service management server 400 transmits the formed lighting control value to the terminal device 300 (S212), and thus, the terminal device 300 drives at least one or more flashes according to the lighting control value to control the lighting. The lighting environment is created so that no image variation occurs (S214), and the photographed image is reformed based on the lighting environment (S216).

The terminal device 300 transmits the reconstructed captured image to the service management server 400 (S218), and the service management server 400 executes face recognition processing on the reconstructed captured image (S220). .

Furthermore, the service management server 400 may further execute a user authentication and application content providing service using face recognition data formed by face recognition processing (S222).

Although the above has been described with reference to a preferred embodiment of the present invention, those skilled in the art will be variously modified and changed within the scope of the invention without departing from the spirit and scope of the invention described in the claims below. I can understand that you can.

In addition, the present invention corresponds to an image variation due to illumination that interferes with the recognition of the face from the captured image, and actively adjusts the flash according to lighting conditions of the target face region in the captured image, thereby recognizing the recognition rate of the target face region. According to the present invention, it is an invention with industrial applicability because the possibility of commercialization or business is not only sufficient but also practically obvious.

1 is a block diagram of a face recognition system based on lighting control according to an embodiment of the present invention,

FIG. 2 is a configuration diagram of the image capturing terminal device shown in FIG. 1;

3 is a conceptual diagram illustrating an arrangement of a flash provided in the image capturing terminal device illustrated in FIG. 1;

4 is a flowchart illustrating an operation process of a face recognition system based on light adjustment shown in FIG. 1;

5 is a block diagram of a face recognition system based on lighting control according to another embodiment of the present invention;

6 is a configuration diagram of a service management server shown in FIG. 5, and

FIG. 7 is a flowchart illustrating an operation process of a face recognition system based on light adjustment shown in FIG. 1.

<Description of Symbols for Main Parts of Drawings>

100, 300: video recording terminal 110: the recording unit

120, 420: face area extraction unit 130, 430: image shift sensor

140, 440: light control unit 150, 460: face recognition execution unit

160 and 410 interface unit 450 control unit

470: service execution unit

Claims (24)

A photographing unit for photographing an object in at least one direction; A face region extractor for extracting a target face region from the photographed image of the object; An image shift sensor unit for determining an image shift based on a pattern change amount based on a facial feature point in the target face area, and then setting an image distortion generation region based on the determination result; An illumination control unit for controlling at least one flash by forming an illumination control value for the image distortion generating region; And And an image capturing terminal including a face recognition executing unit configured to execute face recognition processing on the reconstructed captured image after reconstructing the photographed image. The facial recognition system of claim 1, wherein A service management server connected to the image capturing terminal device through a communication network and receiving face recognition data from the image capturing terminal device to execute a user authentication and application content providing service; Face control system based on the light adjustment, characterized in that it further comprises. The terminal of claim 1 or 2, wherein the image recording terminal device Determining a facial feature element for the target face region, and sensing an image variation that is an obstacle to face recognition through a pattern change amount based on the facial feature point forming the facial feature element, Face control system based on the illumination control, characterized in that for determining the image distortion by the illumination using the sensor results. The terminal of claim 1 or 2, wherein the image recording terminal device And extracting at least one face region from the photographed image, and setting a face region having a large proportional area among the at least one face region as the target face region. The apparatus of claim 4, wherein the image recording terminal device Face control system based on the illumination control, characterized in that for setting the target face area to be a single area. The terminal of claim 1 or 2, wherein the image recording terminal device And extracting at least one or more face regions from the photographed image, and setting the at least one or more face regions to be the target face region. The apparatus of claim 6, wherein the image recording terminal device And setting at least one of the at least one face area to be the target face area and performing the process of determining the image variation to reach the face recognition processing. The terminal of claim 1 or 2, wherein the image recording terminal device Set an average brightness value for the target face area, and set an area having a brightness value less than a predetermined level based on the average brightness value as the image distortion generation area; Recognition system. The method of claim 8, wherein the image distortion generating region is Illumination control-based face recognition system, characterized in that formed by extending the additional area interconnected through the Connected Component Labeling (CCL) processing with the initial value of the brightness lower than the predetermined level. The method of claim 9, wherein the image distortion generating region is The face recognition system based on the illumination control, characterized in that the area is formed in an area of more than a predetermined level in proportion to the area of the target face area. The method of claim 1, wherein the illumination control value is Is formed through comparison and discrimination between an average brightness value of the target face region and a brightness value of the image distortion generating region, Face recognition system based on the illumination control, characterized in that formed by further comparing and determining the position in the image of the image distortion generating region. 3. The flashlight of claim 1 or 2, wherein the at least one flash is Face control system based on the illumination control, characterized in that for controlling the intensity and the light direction of the brightness value differently according to the illumination control value. A photographing unit for photographing an object in at least one direction; A face region extractor for extracting a target face region from the photographed image of the object; An image shift sensor unit for determining an image shift based on a pattern change amount based on a facial feature point in the target face area, and then setting an image distortion generation region based on the determination result; An illumination control unit for controlling at least one flash by forming an illumination control value for the image distortion generating region; And And reconstructing the photographed image, and including a face recognition execution unit for executing face recognition processing on the reconstructed photographed image. The image capturing terminal device of claim 13, wherein And an interfacing unit for transmitting the face recognition data formed through the face recognition processing through a communication network. The method according to claim 13 or 14, wherein the lighting control unit The illumination control value is formed by comparison between the average brightness value of the target face area and the brightness value of the image distortion generating area. And a lighting control value by further comparing and determining a position in the image of the image distortion generating region. (A) image capturing by the terminal apparatus photographing an object in at least one direction and extracting a target face region from the captured image; (B) determining an image variation based on a pattern change amount based on facial feature points in the target face region, and then setting an image distortion generation region based on the determination result; (C) adjusting at least one flash by forming an illumination control value for the image distortion generating region; And And (d) reconstructing the photographed image and then performing face recognition processing on the reconstructed photographed image. The method of claim 16, wherein the light recognition based face recognition method (E) transmitting the face recognition data formed through the face recognition processing to a service management server through a communication network. The method of claim 17, wherein the light recognition based face recognition method (F) receiving a face recognition data received by the service management server further comprises the step of executing a user authentication and application content providing service light adjustment based face recognition method. An image capturing terminal apparatus for transmitting a photographed image formed by photographing an object through a communication network; And Extracting a target face region from the photographed image and determining an image variation with respect to the target face region, and when image distortion occurs due to illumination, forming an illumination control value for the image distortion generating region and transmitting it to the image recording terminal device. Includes a service management server for, The video recording terminal device, Reconstruct the photographed image by adjusting at least one flash based on the lighting control value, and then deliver the reconstructed photographed image to the service management server; The service management server, Face recognition system based on the illumination adjustment, characterized in that for performing the face recognition processing for the re-formed photographed image. 20. The method of claim 19, wherein the service management server And a user authentication and application content providing service through the face recognition data formed by the face recognition processing. An interfacing unit for receiving a captured image transmitted from an image photographing terminal device; A face region extractor for extracting a target face region from the photographed image; An image shift sensor unit for determining an image shift based on a pattern change amount based on a facial feature point in the target face area, and then setting an image distortion generation region based on the determination result; An illumination control unit for forming an illumination control value for the image distortion generating region; A controller for transmitting the lighting control value to the image capturing terminal device through the interfacing unit; And And a face recognition execution unit configured to perform face recognition processing on the reformed photographed image after receiving a reformed photographed image by adjusting at least one flash based on the illumination control value from the image photographing terminal device. Lighting control based service management server, characterized in that. The method of claim 21, wherein the service management server And a service execution unit for executing user authentication and application content providing service through face recognition data formed by the face recognition processing. (A) extracting, by the service management server, the target face region from the captured image provided from the image capturing terminal device; (B) determining an image variation based on a pattern change amount based on facial feature points in the target face region, and then setting an image distortion generation region based on the determination result; (C) forming an illumination control value for the image distortion generating area and transmitting the same to the image capturing terminal device; And (D) receiving a reconstructed captured image by adjusting at least one flash based on the illumination control value from the image capturing terminal device, and then performing face recognition processing on the reconstructed captured image; Face recognition method based on light control, characterized in that. The method of claim 23, wherein the face recognition method based on lighting control is performed. (E) executing the user authentication and application content providing service through the face recognition data formed by the face recognition processing.

Images