KR20060035198A - Camera auto zoom system using face recognition technique, mobile communication terminal equipped with it and camera auto zoom method using face recognition technique - Google Patents

Abstract

The present invention relates to an automatic camera zooming system using a face recognition technique, a mobile communication terminal equipped with the same and an automatic camera zooming method using a face recognition technique. Detects the face area and automatically zooms in or zooms out so that the detected face area is properly aligned with the entire area of the picture. It allows you to take portraits.

Camera, Auto Zoom, Face Detection, Zoom In, Zoom Out

Description

Camera auto zoom system using face recognition technique, mobile communication terminal equipped with it and camera auto zoom method using face recognition technique {Auto zooming system used face recognition technology and Mobile phone installed it and Auto zooming method used face recognition technology}

1 is a schematic diagram of a mobile communication terminal with a built-in camera

2 is a block diagram of an embodiment of a camera automatic zoom system using a face recognition technique according to the present invention.

3 is a diagram illustrating an example of a face photograph zoomed by a camera automatic zoom system using a face recognition technique according to the present invention;

4 is a diagram illustrating an example of an upper body photograph zoomed by a camera automatic zoom system using a face recognition technique according to the present invention;

5 is a flowchart according to an embodiment of a camera automatic zooming method using a face recognition technique according to the present invention.

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

100: mobile communication terminal 110: control unit

120: RF transceiver 130: display unit

140: voice processing unit 141: speaker

142: microphone 150: image processing unit

151: camera 160: memory

200: camera automatic zoom system 210: area detection unit

220: zoom processing unit 230: mode setting unit

The present invention relates to a camera automatic zoom system using a face recognition technique, a mobile communication terminal equipped with the same, and an automatic camera zooming method using a face recognition technique, wherein the face region is a whole region of the photo using the face recognition technique in the preview state. Camera automatic zoom system using face recognition technology that automatically zooms in or zooms out so that people can be shot at an optimized zoom level and a mobile communication terminal equipped with the same And an automatic camera zooming method using a face recognition technique.

When taking a picture using a mobile terminal equipped with a conventional camera, the user manually adjusts the zoom in or zoom out to a desired screen size by using a zoom in or zoom out button to capture a desired screen area. Photographed.

This manual zooming method has an inconvenience in that the user must manually adjust the zoom according to the position, size, and distance of the subject every time the picture is taken.

In order to compensate for the shortcomings of the manual zoom method, Korean Laid-Open Patent Publication No. 10-2004-0073720 (August 21, 2004) detects an upper edge of a corresponding image based on the center of a captured image, and detects from the center of the corresponding image. The distance to the upper edge of the imageable area and the top of the imageable area, the ratio of the distance to the upper edge of the measured image and the distance to the top of the imageable area is determined and determined as a zoom magnification. A method and apparatus for measuring an automatic zoom array for capturing an image at a zoom magnification are proposed.

However, the auto zoom technology that depends on such a distance has a problem that is not suitable when shooting a portrait. The reason for this is that in the case of portrait photography, only the face area of the person being photographed or the portrait area such as the upper body is preferably arranged on the whole picture screen properly. This is because if the area is detected as an edge, the desired portrait of the user cannot be obtained.

Accordingly, the present inventors detect a face region from the image data using face recognition technique in the preview state when photographing a person, and automatically zoom in or automatically arrange the detected face region appropriately over the entire region of the photo. By performing the Zoom Out, the research on the camera auto zooming technology using the face recognition technique that allows the person to shoot with the optimized zoom state has been conducted.

The present invention has been invented under the above-described aspect, and the automatic zoom in (Zoom out) or zoom out (Zoom Out) to enable the person to shoot in the optimized zoom state using the face recognition technique in the preview state (Preview) when photographing people An object of the present invention is to provide an automatic camera zooming system using a face recognition technique, a mobile communication terminal equipped with the same, and an automatic camera zooming method using a face recognition technique.

According to an aspect of the present invention for achieving the above object, the camera automatic zoom system using the face recognition technique according to the present invention, and the mobile communication terminal and the camera automatic zoom method using the face recognition technique in accordance with the present invention when previewing portraits In the Preview state, face detection is detected from image data using face recognition, and zoom in or zoom out are performed automatically so that the detected face area is properly arranged over the entire area of the picture. It is characterized by the implementation.

Accordingly, when the person is photographed, the person may be photographed in the optimized zoom state in the preview state.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily understand and reproduce the present invention.

First, before describing the present invention, a brief description will be made of a mobile communication terminal having a camera.

1 is a schematic diagram of a mobile communication terminal incorporating a camera. As shown in the figure, the mobile communication terminal 100 having a built-in camera includes a controller 110, an RF transceiver 120, a display 130, an audio processor 140, and an image processor 150. And a memory unit 160.

The controller 110 controls the entire mobile communication terminal, and mainly MSM (Mobile Switching Modem) of Qualcomm is used.

The RF transceiver 120 performs communication by communicating voice or data with a base station under the control of the controller 110.

The display unit 130 displays a screen under the control of the controller 110, and typically, a liquid crystal display (LCD) is used.

The voice processor 140 processes the voice output through the speaker 141 or the microphone 142 under the control of the controller 110.

The image processor 150 processes an image captured by the camera 151 under the control of the controller 110.

The memory unit 160 stores various data requested by the mobile communication terminal.

The camera automatic zoom system using the face recognition technique according to the present invention exists in the form of software executed by the controller 110 or the image processor 150 of the mobile communication terminal having the camera shown in FIG. It can be extended to devices equipped with camera functions such as digital cameras.

2 is a block diagram of an embodiment of a camera automatic zoom system using a face recognition technique according to the present invention.

The camera automatic zoom system 200 using the face recognition technique according to the present invention detects a face region from image data using face recognition technique in a preview state when photographing a person, and the detected face region is applied to the entire region of the picture. Perform Zoom In or Zoom Out automatically to be arranged at the ratio set for the The ratio set for the entire picture area is preferably set in software by a ratio between the entire picture area and the displayed face area so that the detected face area is properly arranged for the whole picture area.

In detail, the camera automatic zoom system 200 using the face recognition technique according to the present invention includes an area detector 210 and a zoom processor 220 as shown in FIG. 2.

The area detector 210 detects a face area from image data in a preview state. At this time, the area detection unit 210 extracts edge information from the image data using a face recognition technique, detects feature elements including eyes, nose, and mouth from the image area in the extracted edge information, and detects The face area is calculated according to the feature element.

When the user enters the camera photographing mode by operating the mobile communication terminal, the user enters the preview state, and the screen shot by the camera is previewed on the LCD of the mobile communication terminal by several frames per second. In this case, in the case of a portrait picture, the camera automatic zoom system 200 using the face recognition technique according to the present invention uses edge information from image data displayed on the preview screen through the area detector 210 using a face recognition technique. Is extracted, a feature element including an eye, a nose, and a mouth is detected from the image region in the extracted edge information, and a face region is calculated according to the detected feature element.

The technique of extracting a face region using the face recognition technique is a conventional technique that is already known and implemented variously before this application, and thus a detailed description thereof will be omitted.

On the other hand, judging whether or not a portrait or a portrait photo may be implemented to automatically determine that the face area is detected, if it is not detected, a non-portrait picture, the user manually portrait or non-portrait It can also be implemented to select photos.

The zoom processing unit 220 appropriately arranges the face area detected by the area detecting unit 210 in the entire picture area. At this time, when the detected face area is relatively smaller than the reference area, the zoom processor 220 zooms in the face area and arranges the picture at a set ratio with respect to the entire area of the picture. On the contrary, if the detected face region is relatively larger than the reference region, the zoom processor 220 zooms out the face region and arranges the face region at a predetermined ratio.

That is, when the face area is detected by the area detector 210, the camera automatic zoom system 200 using the face recognition technique according to the present invention zooms in or detects the detected face area to a preset area size. Zoom out and place the face area zoomed to a preset position to display the face area in the entire area of the picture.

When the user presses the shooting button in this state of automatic zoom adjustment, the zoomed portrait photographing is completed and the photographed picture is displayed on the LCD of the mobile communication terminal and stored in the memory according to the user's operation.

Accordingly, the present invention is automatically zoomed to capture a person in an optimized zoom state using a face recognition technique in a preview state when the person is photographed, so that a user can take a portrait picture with an optimized zoom state without any manipulation. It becomes possible.

Meanwhile, according to an additional aspect of the present invention, the camera auto zoom system 200 using the face recognition technique according to the present invention may further include a mode setting unit 230 for selecting and storing an auto zoom mode from a user. .

In this case, the auto zoom mode set by the mode setting unit 230 may be a face picture as shown in FIG. 3 or a torso picture as shown in FIG. 4 or a full body picture not shown in the drawing.

In other words, the portrait can be divided into a face picture that is usually taken only in the face of the person, the upper body picture taken up to the face and shoulders and chest of the person, a full body picture of the person's entire body, etc. The menu is divided into a face photo mode, a torso photo mode, and a full body photo mode, and the user selects a desired portrait mode from the user through the mode selector 230 so that various portraits can be taken. .

In this case, in relation to the detection of the area of the person included in the face picture, the upper body picture, and the whole body picture, it is possible to apply the feature element detection used in the face recognition technology to the upper body or the whole body, and thus the detailed description thereof will be omitted. Shall be.

The operation and effect of the present invention having the above configuration will be described with reference to FIG. 5.

5 is a flowchart illustrating an embodiment of a camera automatic zooming method using a face recognition technique according to the present invention.

When the camera enters the camera shooting mode and is in a preview state, the screen shot by the camera is previewed on the LCD of the mobile communication terminal by several frames per second. At this time, in the case of a portrait picture, first, a face area is detected from image data previewed on the LCD in the preview state in the area detecting step (S110). At this time, in the region detecting step S110, edge information is extracted from the image data by using a face recognition technique, and feature elements including eyes, nose, and mouth are detected from the image region in the edge information, and the detected features are detected. Calculate the face area according to the factor.

Next, in the zoom processing step S120, the face area detected in the area detection step S110 is appropriately arranged in the entire picture area. In this case, when the face area detected in the zoom processing step S120 is relatively smaller than the reference area, the face area is zoomed in and arranged at a set ratio with respect to the entire area of the picture, and the detected face area is If it is larger than the reference area, the face area is zoomed out and arranged at a set ratio with respect to the entire area of the picture.

When the user presses the recording button in this state of automatic zoom adjustment, the zoomed portrait photographing is completed, so that the user can take a portrait photograph in an optimized zoom state without any manipulation.

Thus, by the above it can achieve the object of the camera automatic zoom system using the face recognition method according to the present invention as described above, and the camera automatic zoom method using the mobile communication terminal and face recognition technique equipped with the same.

As described above, the camera automatic zoom system using the face recognition technique and the mobile communication terminal and the camera automatic zoom method using the face recognition technique according to the present invention uses the face recognition technique in the preview state when photographing a person. Since the camera is automatically zoomed in or zoomed out to capture a person in an optimized zoom state, the user can take a portrait in an optimized zoom state without any manipulation.

While the invention has been described with reference to the preferred embodiments, which are referred to by the accompanying drawings, it is apparent that various modifications are possible without departing from the scope of the invention within the scope covered by the following claims from this description. .

Claims (20)

When taking a portrait, the face area is detected from the image data in the preview state, and automatically zoom in or zoom out so that the detected face area is arranged at a set ratio for the entire area of the picture. Camera automatic zoom system using face recognition technique that performs Zoom Out. The method of claim 1, The camera auto zoom system: An area detector for detecting a face area from image data in a preview state; A zoom processing unit for arranging a face area detected by the area detection unit at a set ratio with respect to the entire picture area; Camera automatic zoom system using a facial recognition technique comprising a. The method of claim 2, The area detection unit: Extracting edge information from the image data using a face recognition technique, detecting feature elements including eyes, nose, and mouth from the image region in the extracted edge information, and calculating a face region according to the detected feature elements Automatic camera zoom system using facial recognition. The method of claim 3, wherein The zoom processing unit: When the detected face area is relatively small compared to the reference area, the camera auto zoom system using the face recognition technique, which zooms in the face area and arranges it at a set ratio for the entire area of the picture. The method of claim 3, wherein The zoom processing unit: When the detected face area is relatively larger than the reference area, the camera auto zoom system using the face recognition technique, which zooms out the face area and arranges it at a set ratio for the entire area of the picture. The method according to any one of claims 2 to 5, The camera auto zoom system: A mode setting unit for selecting and storing an auto zoom mode from a user; Camera automatic zoom system using a facial recognition technique, characterized in that it further comprises. The method of claim 6, The camera automatic zoom system using a face recognition technique, characterized in that the automatic zoom mode set by the mode setting unit is a face photograph. The method of claim 6, And an auto zoom mode set by the mode setting unit is an upper body photograph. When taking a portrait, the face area is detected from the image data in the preview state, and automatically zoom in or zoom out so that the detected face area is arranged at a set ratio for the entire area of the picture. A mobile communication terminal equipped with a camera automatic zoom system using a face recognition technique that performs zoom out. The method of claim 9, The camera auto zoom system: An area detector for detecting a face area from image data in a preview state; A zoom processing unit for arranging a face area detected by the area detection unit at a set ratio with respect to the entire picture area; A mobile communication terminal equipped with a camera automatic zoom system using a face recognition technique comprising a. The method of claim 10, The area detection unit: Extracting edge information from the image data using a face recognition technique, detecting feature elements including eyes, nose, and mouth from the image region in the extracted edge information, and calculating a face region according to the detected feature elements A mobile communication terminal equipped with an automatic camera zooming system using a facial recognition technique. The method of claim 11, The zoom processing unit: When the detected face area is relatively smaller than the reference area, the camera auto zooming system using the face recognition technique using the face recognition method is characterized by zooming in and arranging the face area at a set ratio with respect to the entire area of the picture. Communication terminal. The method of claim 11, The zoom processing unit: If the detected face area is larger than the reference area, zoom-out the face area and arrange it at a set ratio for the entire area of the picture. Communication terminal. The method according to any one of claims 10 to 13, The camera auto zoom system: A mode setting unit for selecting and storing an auto zoom mode from a user; A mobile communication terminal equipped with a camera automatic zoom system using a face recognition technique characterized in that it further comprises. The method of claim 14, A mobile communication terminal equipped with a camera auto zoom system using a face recognition technique, characterized in that the auto zoom mode set by the mode setting unit is a face photograph. The method of claim 14, A mobile communication terminal equipped with a camera auto zoom system using a face recognition technique, characterized in that the auto zoom mode set by the mode setting unit is an upper body photograph. An area detecting step of detecting a face area from the image data in the preview state; A zoom processing step of arranging the face areas detected in the area detecting step at a set ratio with respect to the entire picture area; Camera automatic zoom method using a facial recognition technique comprising a. The method of claim 17, In the area detecting step; Extracting edge information from image data using a face recognition technique, detecting feature elements including eyes, nose, and mouth from the image region in the edge information, and calculating a face region according to the detected feature elements Automatic camera zooming method using face recognition technique. The method of claim 18, In the zoom processing step: When the detected face area is relatively smaller than the reference area, the camera zooms in and arranges the face area at a set ratio with respect to the entire area of the picture. The method of claim 18, In the zoom processing step: When the detected face area is larger than the reference area, the camera zooms out the face area and arranges it at a set ratio for the entire area of the picture.

Images