KR101000130B1 - Mobile terminal capable face recognition and method for face recognition thereof - Google Patents

Abstract

The present invention relates to a face recognizable terminal capable of facilitating face recognition through additional information such as shooting time and location of an image captured by a digital camera of the terminal, and a face recognition method thereof.

The face recognition method of the terminal of the present invention is a face recognition method for image data stored in a database of a terminal having a camera capable of capturing an image, and the background image information of the image data of the database by the face recognition and color element processor of the terminal. Performing face image recognition by removing the image; Removing the skin color from the face image by the face recognition and color element processor; When the face recognition and color element processor assigns an inherent characteristic value for the color element of the image data in an area other than the background image and the face image, the controller of the terminal is assigned an inherent characteristic value for the color element. Storing the photographing time information and the photographing position information in the image data as comparative image data in the database; And performing face recognition by comparing shooting time information, shooting position information, and color element information of the comparison image data with the image data stored in the database when face recognition of the stored image data is performed by the controller of the terminal. It provides a face recognition method of the terminal comprising a.

Face recognition

Description

Mobile terminal capable face recognition and method for face recognition according to the present invention.

The present invention relates to a face recognizable terminal capable of facilitating face recognition through additional information such as shooting time and location of an image captured by a digital camera of the terminal, and a face recognition method thereof.

Recently, digital image generation and dissemination have become easier due to the widespread activation of portable digital cameras and terminals equipped with cameras, and the accuracy of face recognition technology has been improved with the development of correction and analysis techniques for digital images.

Face Recognition is a biometric technology that can be used safely without fear of theft, loss, or forgetting.It is not only a sensor easily manufactured like iris or fingerprint, but also easily installed by using a camera that is already installed. Because ID's have photo data, a large amount of data is readily available.

In addition, the face is a means by which a person identifies a person, so that a manager can check the result later and is not a touch type, and thus a technology that can be easily applied as a monitoring means in a large public facility.

Face recognition first extracts facial regions by using edges, colors, and geometric components of facial components (eyes, noses, mouths), and extracts feature vectors that can distinguish subtle differences between different people.

The construction of a large-scale face database considering various environmental changes in face recognition is essential for improving and evaluating the performance of the face recognition system, and taking into account the color and direction of lighting, various expressions, various angles, and accessories.

Face recognition technology can be applied to access control using face recognition technology without the need for access control of offices, houses, passwords that can cause forgetting, keys and ID cards that can be stolen or lost, and facial information. In addition to increasing the level of security and smart card security, it can also provide personal authentication solutions for ATMs and Internet banking.

In addition, PC and server security solutions within the corporate network, as well as personal authentication and e-commerce through mobile communication devices such as mobile phones and PDAs, remote personal authentication for electronic banking and e-learning using mobile communication is possible.

In face recognition, it has a wide range of uses, such as an auto focus function that focuses on a face when shooting, a function of comparing a photo to authenticate a person, and an automatic data feature of a person. In areas where security is required, it is used to control access and screen criminals.

In addition, recently, a digital camera or a terminal with a camera is added to the face recognition function to provide an autofocus function.

However, even when the same person is photographed, there are many differences in the accuracy of face recognition according to the angle, exposure to light, change of background, picture quality, and computer performance.

In other words, in the conventional face recognition, since only the face recognition is performed while focusing mainly on the face of the person, there is a problem that a difference in face recognition may occur for the same person.

Accordingly, the present invention includes a face recognition capable terminal that can increase the accuracy and recognition speed for face recognition by including additional information and color information, such as the shooting time and location for the image data photographed through the digital camera of the terminal; Its purpose is to provide his face recognition method.

According to an aspect of the present invention, there is provided a terminal capable of face recognition of an image, including: a camera unit for capturing an image and transmitting the image to an image processor; An image processor which processes the image transmitted from the camera unit into digital image data and stores the image in a database; A face recognition and color element processing unit for recognizing a face from the digital image data processed by the image processing unit and giving unique characteristic values to color elements of an image data region other than the background and the face; A position detector for detecting position information of the terminal; A key input unit for inputting a control command or data input of the terminal user; A display unit configured to display an image input through the camera unit or an image input to a database and an image recognized or selected in a face recognition process and a color element process; A database storing image data processed by the image processor and comparative image data required for face recognition; And generating comparative image data including one or more of shooting time information and shooting position information and color element information with respect to the image data in which the face recognition and color elements are processed by the face recognition and color element processing unit among the image data stored in the database. The image data of the closest condition is classified into face recognition data by comparing shooting time information and / or shooting location information and color element information with respect to the comparison image data and the image data processed by the image processor, and stored in the database. A control unit; It provides a face recognition capable terminal comprising a.

Here, the face recognition and color element processor extracts and removes a background from image data stored in the database, extracts face image information by removing a skin color from a face region, and color elements of image data other than the background and face image. It is desirable to process the to give a unique characteristic value according to the color element.

In addition, when the terminal is a mobile terminal, the location detecting unit transmits and receives various signals for a mobile communication service of the terminal, and is an antenna for receiving base station information (Cell ID) that the terminal is serving, or for receiving GPS information. At least one of the GPS receivers is preferred.

The database may include an image database area for storing image data processed by the image processor and a comparison image database area for storing comparative image data for face recognition.

On the other hand, the color element characteristic value is preferably an intrinsic characteristic value of hue, lightness and saturation.

In order to achieve the above object, the present invention provides a face recognition method for image data stored in a database of a terminal having a camera capable of capturing an image, wherein the face recognition and color element processing unit of the terminal has a background image from the image data of the database. Performing face image recognition by removing information; Removing the skin color from the face image by the face recognition and color element processor; When the face recognition and color element processor assigns an inherent characteristic value for the color element of the image data in an area other than the background image and the face image, the controller of the terminal is assigned an inherent characteristic value for the color element. Storing the photographing time information and the photographing position information in the image data as comparative image data in the database; And performing face recognition by comparing shooting time information, shooting position information, and color element information of the comparison image data with the image data stored in the database when face recognition of the stored image data is performed by the controller of the terminal. It provides a face recognition method of the terminal comprising a.

Here, when the image is captured using the camera and stored in the database, the terminal preferably stores the image data including the photographing time information and the photographing position information.

The intrinsic color element characteristic value is preferably one or more of the characteristic values of hue, lightness, and saturation.

In addition, when assigning the unique characteristic value, it is preferable to compare the color of the clothes, makeup, and accessories of the person, the brightness of the surroundings of the person, and the brightness of the clothes, makeup, and accessories of the person.

Meanwhile, the controller of the terminal selectively displays the face recognition image data on the display unit of the terminal, face recognition of the image data selected by the user through a key input unit of the terminal among the displayed image data. The method may further include determining whether the image is completed, and storing the image data including the unique identifier through the key input unit in the database when the face recognition is completed.

According to the present invention as described above by using the color element information in addition to the shooting time information or shooting position information with respect to the image data photographed from the terminal equipped with a digital camera, a fast, accurate face without expensive program or processor for face recognition There is a recognizable effect.

Hereinafter, a preferred embodiment of a face recognizable terminal and a face recognition method thereof according to the present invention will be described in detail with reference to the accompanying drawings.

In addition, the terminology used in the present invention was selected as a general term that is widely used at present, but in certain cases, the term is arbitrarily selected by the applicant, and in this case, since the meaning is described in detail in the corresponding part of the present invention, a simple term It is to be understood that the present invention is to be understood as a meaning of terms rather than names.

In addition, in describing the embodiments, descriptions of technical contents which are well known in the technical field to which the present invention belongs and are not directly related to the present invention will be omitted. This is to more clearly communicate without obscure the subject matter of the present invention by omitting unnecessary description.

1 is a block diagram illustrating a terminal capable of face recognition according to an embodiment of the present invention, and FIG. 2 is a view for explaining one image data in an image database according to an embodiment of the present invention.

The face recognition capable terminal 100 according to the present invention includes a camera unit 10, an image processing unit 20, a database 30, a face recognition and color element processing unit 40, a key input unit 50, and a display unit 60. ), The position detection unit 70 and the control unit 80 is configured.

The camera unit 10 captures an image and transmits the captured image to the image processor 20.

The image processor 20 processes the analog image photographed by the camera unit 10 as digital image data and stores it in the database 30.

The database 30 includes an image database area 31 storing an image processed by the image processor 20 and a database area 32 storing a comparison image for comparing face recognition.

The face recognition and color element processor 40 extracts face image information from the digital image data stored in the database 30, and then processes color elements of image data other than the background and face image to obtain unique characteristic values according to the color elements. Grant.

Here, in order to extract face image information, the face recognition and color element processor 40 first extracts and removes background image information, and extracts face image information by removing skin color from the face.

Then, for image data other than a background image and a face image, as a color element, the current color of the element for one or more of the three elements of color, hue, brightness and saturation. Give unique values for brightness and saturation.

 Here, hue is a unique property that only magnetism has, and it has a characteristic value of 20 colors of redness, lightness is the brightness of color, black has 0 characteristic value of 10, saturation is the clearness of color, gray 0, yellow and red have 14 characteristic values.

In the present invention, the color mainly compares the color of a person's clothes, makeup, accessories, and the like. This is because the same person is likely to have a similar color of clothes, makeup and accessories.

Brightness mainly compares the brightness around a person. This is especially aimed at increasing face detection in pictures with similar ambient brightness.

Saturation is intended to increase the possibility of face recognition by comparing the brightness of high-purity primary colors such as clothes, makeup, and accessories.

The key input unit 50 is used when inputting a control command or data input by a user of the terminal 100.

The key input unit 50 may include a user response input to a query of the terminal 100 for correct face recognition in a face recognition process or a color element processing process in the face recognition and color element processing unit 30, or a color element. Used to select a user for one.

The display unit 60 displays an image input through the camera unit 10 or an image input to the database 30 and an image recognized or selected in a face recognition process and a color element processing process.

The position detector 70 detects current position information of the terminal 100 when the camera unit 10 captures the image. To this end, the position detection unit 70 may be configured as an antenna unit 71 or a GPS receiver 72.

Here, when the terminal 100 is a mobile terminal, the antenna unit 71 transmits and receives various signals for the mobile communication service of the terminal 100 and receives base station information (Cell ID) that the terminal 100 is serving. . In addition, when the GPS receiver 72 is mounted on the terminal 100, the GPS receiver 72 detects location information received from the GPS receiver 72.

As shown in FIG. 2, the controller 80 captures the image data of the image data stored in the image database area 31 in which the face recognition and color elements are processed by the face recognition and color element processing unit 40. Month, day, hour, minute, second, etc.) (110) information 110, shooting position information 120 and color element information 130, the comparison image database 140 of the database 30 Store in

The controller 80 compares shooting time information and / or shooting location information and color element information with respect to the comparison image data 140 stored in the comparison image database area 32 and the image data stored in the image database area 31. By selectively recognizing only the closest face photographs and selectively displaying them on the display unit 60, and determining whether face recognition is completed for the selected image data according to a user's selection through the key input unit 50. By including the unique identifier (name) through the stored in the image database area 31 of the database it is possible to improve the recognition success rate and recognition speed for face recognition.

3 is a flowchart illustrating a face recognition method of a terminal according to an embodiment of the present invention.

The face recognition method of the terminal according to an embodiment of the present invention performs face recognition on image data stored in the image database area 31 of the database 30 (S10). Face recognition extracts (removes) the background in order to recognize the face in the face recognition and color element processor 40 (S10).

In operation S20, it is determined whether a person exists in the image data from which the background is extracted.

As a result of the determination (S20), face recognition is unnecessary in the case of the image data in which the person does not exist, and thus background extraction is performed on other image data.

However, if it is determined in operation S20 that a person exists, the face recognition and color element processor 30 removes flesh color from the face image area (S30).

Next, unique characteristic values are assigned to color elements in areas other than the background and the face image area (S40). In this case, a unique characteristic value for one or more color elements of color elements, that is, hue, brightness, and saturation may be given according to a user's selection. In this case, when all of the color, brightness, and saturation are selected, the face recognition is advantageous, but the comparison time according to the face recognition becomes long, and when only one of them is selected, the comparison time according to the face recognition can be shortened.

Accordingly, a unique characteristic value is assigned to one or more color elements of hue, lightness, and saturation for color elements favorable for face recognition among the color elements of hue, brightness, and saturation selected by the user.

As such, when the unique characteristic values for the face recognition and the color element of the image data are given, the image data is stored in the comparison image database area 32 as comparison image data in which shooting time information and shooting position information are assigned to the image data.

At this time, when comparing the color, the color of the clothes, makeup, accessories, etc. of the person is compared. This is because the same person is likely to have a similar color of clothes, makeup and accessories.

Brightness mainly compares the brightness around a person. This is especially aimed at increasing face detection in pictures with similar ambient brightness.

Saturation is intended to increase the possibility of face recognition by comparing the brightness of high-purity primary colors such as clothes, makeup, and accessories.

Subsequently, the controller 80 searches for image data in the image database area (S60), and compares the image data shooting time of the image data with the comparison image data in the comparison image database area 32 (S70). That is, the photographing time is performed by comparing the digital image data photographed and stored at the time most similar to the photographing time of the image data to be currently recognized for face recognition, thereby improving recognition success rate and recognition speed.

Then, the controller 80 compares the image position and the photographing position of the comparison image data of the comparison image database area 32 (S80). That is, even in the case of using the photographing position information, the recognition success rate and the recognition speed for face recognition may be improved when the comparison of the image data photographed at the position most similar to the photographing position information of the current comparison image data is performed.

Next, the controller 80 compares the color data of the corresponding image data with the comparison image data of the comparison image database area 32 (S90). That is, image data having the color element most similar to that of the current comparison image data is compared.

Accordingly, after selectively displaying only the closest face photographs on the display unit 60, it is determined whether face recognition is completed on the selected image data according to the user's selection through the key input unit 50 (S100).

As a result of the determination (S100), when the face recognition is completed, the image data is registered and stored in the image database area 31 of the database including a unique identifier (name) through the key input unit 50.

Such a face recognition terminal and a face recognition method of the present invention are expensive programs for face recognition by using additional information such as shooting time information, shooting position information, and color element information of the image data at the time of image data capture. Applicable to the field for performing face recognition without a processor or a processor.

1 is a block diagram illustrating a terminal capable of face recognition according to an embodiment of the present invention;

2 is a diagram for explaining comparative image data according to an embodiment of the present invention;

3 is a flowchart illustrating a face recognition method of a terminal according to an embodiment of the present invention.

<Explanation of symbols for the main parts of the drawings>

10: camera unit 20: image processing unit

30: database 40: face recognition and color element processing unit

50: key input unit 60: display unit

70: position detection unit 80: control unit

Claims (10)

As a terminal capable of face recognition of an image, A camera unit for photographing and transmitting an image to the image processor; An image processor which processes the image transmitted from the camera unit into digital image data and stores the image in a database; A face recognition and color element processing unit for recognizing a face from the digital image data processed by the image processing unit and giving unique characteristic values to color elements of an image data region other than the background and the face; A position detector for detecting position information of the terminal; A key input unit for inputting a control command or data input of the terminal user; A display unit configured to display an image input through the camera unit or an image input to a database and an image recognized or selected in a face recognition process and a color element process; A database storing image data processed by the image processor and comparative image data required for face recognition; And, Generating comparative image data including at least one of shooting time information and shooting position information and color element information with respect to the image data in which the face recognition and color elements are processed by the face recognition and color element processing unit among the image data stored in the database. The photographing time information and / or the photographing location information and the color element information are compared with respect to the comparison image data and the image data processed by the image processor to classify the image data having one or more information as face recognition data to the database. And a control unit for storing the face recognizable terminal. The method of claim 1, The face recognition and color element processor extracts and removes a background from image data stored in the database, extracts face image information by removing a skin color from a face region, and processes color elements of image data other than the background and face image. Face recognition terminal, characterized in that to give a unique characteristic value according to the color element. The method of claim 1, When the terminal is a mobile terminal, the location detection unit transmits and receives various signals for a mobile communication service of the terminal, and the terminal receives a base station information (Cell ID) in service, or a GPS receiver for receiving GPS information. Face recognition device, characterized in that one or more of. The method of claim 1, And the database comprises an image database area for storing image data processed by the image processor and a comparison image database area for storing comparative image data for face recognition. The method of claim 1, The color element characteristic value is a face recognition terminal, characterized in that the characteristic value of the hue, brightness and saturation. In the face recognition method for the image data stored in the database of the terminal having a camera capable of image recording, Performing face image recognition by removing background image information from image data of the database by a face recognition and color element processor of the terminal; Removing the skin color from the face image by the face recognition and color element processor; When the face recognition and color element processor assigns an inherent characteristic value for the color element of the image data in an area other than the background image and the face image, the controller of the terminal is assigned an inherent characteristic value for the color element. Storing photographic information and photographing position information in the image data as comparative image data in the database; And, Performing face recognition by comparing control time information, shooting position information, and color element information of the comparison image data with the image data stored in the database when face recognition of the stored image data is performed by the controller of the terminal; Face recognition method of the terminal comprising a. The method of claim 6, When photographing an image using the camera and storing the image in the database, the terminal stores the image data including the photographing time information and the photographing position information in the image data. The method of claim 6, The unique color element characteristic value is a face recognition method of a terminal, characterized in that at least one of the characteristic values of hue, brightness and saturation. The method of claim 6, In the case of giving the unique characteristic value, The face recognition method of the terminal, characterized by comparing the color of the clothes, makeup, accessories of the person, the brightness of the surroundings of the person and the brightness of the clothes, makeup, accessories of the person. The method of claim 6, The control unit of the terminal selectively displays the face recognition image data on the display unit of the terminal, whether the face recognition is completed for the image data selected by the user through the key input unit of the displayed image data And determining, when the face recognition is completed, storing the image data including the unique identifier through the key input unit in the database.

Images