KR100641455B1 - Apparatus and Method for complexing image in mobile communication terminal - Google Patents

Abstract

The present invention provides a method for synthesizing an image in a mobile communication terminal, wherein a background image is selected by a user, an input image is selected by the user, and object boundary information desired to be extracted from the input image is provided to the user. And segmenting the object from the input image by performing color segmentation on the object according to the input object boundary information, and synthesizing the separated object with the selected background image. By using a technology, a user extracts a desired object from an input image and synthesizes it on a background, so that the user can make an interesting composite image and use the interesting composite image for a mobile communication service.

Image Synthesis, Object, Background Image

Description

Apparatus and Method for complexing image in mobile communication terminal             

1 is a block diagram schematically showing the configuration of an image synthesizing apparatus in a mobile communication terminal according to an embodiment of the present invention.

2 is a flowchart illustrating a method of generating a composite image in a mobile communication terminal according to an embodiment of the present invention.

3A to 3B are screens illustrating a method of separating an object from an input image according to an exemplary embodiment of the present invention.

4A and 4B are screens illustrating an object boundary input method according to an exemplary embodiment of the present invention.

5 is a flowchart illustrating a method of separating an object from an input image according to an exemplary embodiment of the present invention.

6A to 6C are screens illustrating a method of separating an object from an input image according to an exemplary embodiment of the present invention.

7 is a flowchart illustrating a character background synthesis method of an object according to an exemplary embodiment of the present invention.

8A to 8B are diagrams illustrating a character background synthesis screen of an object according to an exemplary embodiment of the present invention.

9 is a flowchart illustrating a frame image background synthesis method according to an exemplary embodiment of the present invention.

10A to 10D illustrate a frame image background synthesis screen according to an exemplary embodiment of the present invention.

11A to 11F illustrate a manual editing screen of a composite image according to an exemplary embodiment of the present invention.

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

100: input image receiving unit 110: image storage unit

120: user interface unit 130: object extraction unit

140: image synthesizer 150: synthesized image storage unit

According to an embodiment of the present invention, when an object region desired by a user is designated for an input image of a mobile communication terminal, a mobile communication terminal can be used for various mobile communication terminal application services by extracting an accurate object region from the input image and combining it with a background image. The present invention relates to a method and apparatus for image synthesis.

Mobile terminals equipped with cameras and capable of watching TV or movies through video streaming are no longer just phones for voice calls. Young people are showing interest in various services related to still images / videos on mobile terminals, and taking pictures using mobile cameras and transferring the still images or videos to friends or downloading them to a computer It is becoming the main entertainment provided by mobile terminals.

However, the services provided on the mobile terminal cannot meet the quantity or quality of the terminal development speed.

Recently released terminals provide a feature that allows a user to take a picture by matching a face well with a face by processing a face area of a character similar to a person. However, this function requires the user to align his / her face to the character face area by itself, and does not have the function of automatically detecting or composing faces from still / movies, and only selects the background when the user takes a picture with the camera. As you look, you need to adjust your posture so that your face naturally fits in the proper size area.

Therefore, a technique for extracting or tracking an object region from an image has been reported in recent years with increasing importance.

The general object region extraction method can be divided into a case where an image acquired by a still camera or an image acquired by a moving camera is targeted. Since images acquired with a moving camera are much more difficult to extract an object (interest) region than images acquired with a stationary camera, most images are acquired with a still camera.

Separation of the object region from the image acquired by the still camera is mostly performed by extracting the moving region. However, in addition to moving objects due to noise, the images acquired by the camera extracts objects that are distorted compared to the original object area due to motion being found in a stationary background or shadows in an object boundary area.

Therefore, it is difficult to extract the exact object region by motion information alone. Therefore, region separation using color or text is used. For example, in one frame, areas of the same brightness are separated using a known area separation algorithm called watershed using color brightness information. These separated areas are grouped together with similarities in motion information and color to form a single object area. However, this method has a long processing time problem.

The refinement process is performed to correct the given approximate object region back to the correct object region. The refinement process is mainly performed using color information. For example, when the region having the same color does not match the boundary region of a given object, the refinement process may be modified to the boundary region of the region having the same color.

In other words, the color difference between the surrounding pixels is obtained based on the boundary pixel of the region using the object region that is basically included, and the color difference between the two pixels is smaller than the threshold and the distance between the surrounding pixel and the boundary pixel of the current ROI is critical. If the value is smaller than the value, the pixel is included in the current object area. Otherwise, the pixel is not included in the current object area. This method produces relatively good results when the boundary of the reference area is very close to the boundary of the actual object area.

However, if the existing area is far from the boundary of the real object area, if you apply the algorithm introduced in the existing technology, you may make an incorrect boundary.

However, the technique of separating partial regions from the input image based on the conventional color group as described above relatively separates the region from the input image, but it is a color-based region and is not an object region having meaning, and it takes a lot of processing time. there is a problem.

In addition, the method of separating the object using the difference image and the edge image is easy to process because the picture information used is simple, but can not be separated in a complex screen, basically the background is stationary and the moving object is an object Since the separation is performed, there is a problem that cannot be applied in a mobile camera environment.

Accordingly, an object of the present invention is to extract a desired object from the input image and synthesize it in the background by using the user's manual input and color segmentation technology, so that the user can make an interesting composite image and insert the interesting composite image into the mobile communication service. The present invention provides a method and apparatus for synthesizing images in a mobile communication terminal that can be used.

Another object of the present invention is to provide an image synthesizing method and apparatus in a mobile communication terminal that enables an interesting service that utilizes a user's personality using photo synthesis, background synthesis, frame synthesis, and character / animation synthesis.

It is still another object of the present invention to provide a method and apparatus for synthesizing an image in a mobile communication terminal in which a user can use his or her personality in a mobile communication terminal and transmit various images made to a friend through multi-mail.

According to an aspect of the present invention to achieve the above object, in a method for synthesizing an image in a mobile communication terminal, a background image is selected by a user, an input image is selected by the user, and with respect to the input image The object boundary information to be extracted is input by the user, color segmentation is performed on the object according to the input object boundary information to separate the object from the input image, and the separated object is separated from the selected background image. Provided is a method for synthesizing an image in a mobile terminal for synthesizing.

When an editing command for the synthesized image is received from the user, the synthesized image is edited and stored according to the editing command.

The background image includes a general photograph image, a character background image, a frame background image, and an animation background image, and the input image is an image photographed by a camera mounted on a mobile communication terminal, an image downloaded from a server, or from another terminal. It includes at least one of the image received, the image uploaded from the PC.

The object boundary information is input by the user using a button, a mouse, and a pen of the mobile communication terminal.

Separating the object from the input image by performing color segmentation on the object according to the input object boundary information may include generating a mask based on the object boundary information and then applying a color to an object corresponding to the object boundary information. To perform segmentation.

Generating a mask based on the object boundary information may be divided into an object area and another area in the input image according to the object boundary information.

The color segmentation obtains an inner object boundary with respect to the object boundary, obtains an average color value for an n * n area based on the obtained boundary object's boundary pixels, and calculates the average color value of each pixel within the inner object boundary. When the difference between the color values is obtained and the obtained difference is equal to or greater than a predetermined threshold, the pixel is removed from the object region, and when the difference is not equal to or greater than the threshold, the pixel is included in the object region and the morphology is performed on the predetermined object region.

When the background image is extracted from the image storage unit, the size and position of the object to be synthesized are obtained from the background image.

The synthesizing the separated object with the extracted background image may include determining the size and position of the object to be synthesized in the background image, and then adjusting the size of the object according to the identified size and adjusting the size to the position. Moves the adjusted object.

The editing command includes a size control, a position control, a rotation angle control, and a left and right flip as a command for an object of the composite image.

According to another aspect of the present invention, in the method for separating the object desired by the user from the input image input to the mobile communication terminal, when the object boundary information is input by the user, the internal object for the object according to the object boundary information Obtains a boundary, obtains an average color value for surrounding n * n pixels based on the obtained inner object boundary pixels, and compares the obtained average color value with a color value for each pixel in n * n around the inner object boundary pixel. A method of separating an object from an input image of a mobile communication terminal, wherein the difference is obtained and the obtained difference is greater than or equal to a predetermined threshold, the pixel is removed from the object area and the morphology is performed.

The inner object refers to an area n pixels inward from the object boundary selected by the user in the input image.

According to another aspect of the present invention, in the device for synthesizing the video in the mobile communication terminal including an image storage, the input image receiving unit for receiving the input image, input image selection information or background image selection information from the user is received And a user interface unit which extracts a corresponding image from the image storage unit. An object extractor configured to obtain an object according to object boundary information input by the user from the input image selected through the user interface unit, and perform color segmentation on the obtained object to separate the object from the input image; An image synthesizer for synthesizing the background image selected through the object separated by the object extractor and editing the synthesized image according to a synthesized image editing command input by the user, and storing the image synthesized by the image synthesizer An image synthesizing apparatus is provided in a mobile communication terminal including a synthetic image storing unit.

The user interface unit provides a manual editing function to compensate for the misdetection of the object area and to enable natural synthesis for the image synthesized by the image synthesizing unit.

The object extracting unit generates a mask based on the object boundary and performs a morphology on the object area.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram schematically illustrating a configuration of an image synthesizing apparatus in a mobile communication terminal according to an exemplary embodiment of the present invention.

Referring to FIG. 1, an image synthesizing apparatus in a mobile communication terminal includes an input image receiver 100, an image storage unit 110, a user interface unit 120, an object extractor 130, an image synthesizer 140, and a synthesizer. The image storage unit 150 is included.

The input image receiving unit 100 receives an image acquired by an image acquisition unit such as a camera. That is, the image is an image input by using a camera mounted on the mobile terminal, downloading from the server, download from the user's PC.

The image storage unit 110 stores various types of input images or background images. That is, the image storage unit 110 stores various background images such as an image transmitted from the input image receiver, a character background, a frame background, and an animation background.

When the input image selection information is received from the user, the user interface unit 120 extracts a corresponding input image from the image storage unit 110 and transmits the input image to the object extracting unit 130.

In addition, when the background image selection information is received from the user, the user interface unit 120 extracts a corresponding background image from the image storage unit 110 and transmits the background image to the image synthesis unit 140.

In addition, the user interface 120 compensates for the misdetection of the object region with respect to the image synthesized by the image synthesizer 140 and enables the user to more naturally synthesize the size, position, brightness, saturation, Manual editing function to adjust the tilt angle is provided.

The object extractor 130 separates the corresponding object according to the object boundary information input by the user from the input image selected through the user interface 120. The object boundary information is to select a region that the user wants to separate from the input image. At this time, the user selects an object boundary by using a direction key of a mobile phone or a scroll mouse.

That is, when the object boundary information is input by the user, the object extractor 130 obtains an internal object boundary with respect to the object. Here, the internal object boundary refers to an area that enters n pixels into the object boundary selected by the user in the input image.

Then, the object extractor 130 obtains an average color value with respect to neighboring n * n pixels based on the inner object boundary pixels and calculates a difference between the color values of each pixel within n * n around the inner object boundary pixels. Obtain

Then, the object extractor 130 determines whether the obtained difference is greater than or equal to a predetermined threshold value, and if the threshold value is greater than or equal to the threshold value, removes the pixel from the object area and performs a morphology. Include as an area to perform the morphology.

The image synthesizer 140 synthesizes the background image selected by the user interface 120 and the object separated by the object extractor 130. Techniques for image synthesis include photo synthesis (meaning synthesizing two photos), character synthesis, frame synthesis, animation synthesis, and the like.

The photo collage is a synthesis of an arbitrary background photo image selected by a user and an arbitrary input photo image selected by the user. The background photo image and the input photo image can be taken directly by the terminal.

The character synthesis is to synthesize an arbitrary character and the object extracted by the user. Since the size and position to be synthesized in the character are predefined, the size and position of the object should be adjusted when the object is synthesized.

A detailed description of the character synthesis will be made with reference to FIG. 7.

The frame synthesis is to set the background image to appear even when the object region appears when any part of the background image is synthesized when the object region and the background image are synthesized. A detailed description of the frame synthesis will be given with reference to FIG. 9.

The synthesized image storage unit 150 stores an image synthesized by the image synthesizer 120, and the stored synthesized image is used as various application services.

For example, the composite image may be used for a background screen of a mobile communication terminal, a video mail in a mobile communication, a mobile terminal caller display service, an image search field, and hot swap data extraction.

Hereinafter, the operation of the system configured as described above will be described.

First, when an image is input, a user inputs boundary information of an object that is desired to be extracted from the input image. A method of inputting a boundary of the object may be input using a tool such as a direction key, a pen, a mouse, or the like.

After receiving a user's input manually, the object extractor 110 separates the received object from the image. In this case, since the user's input may not be an exact boundary of the object, the object extracting unit automatically performs color segmentation. Then, the image synthesizing unit synthesizes the background image selected by the user and the separated object using a synthesis method desired by the user and uses the same for the mobile communication terminal application service.

2 is a flowchart illustrating a method of generating a composite image in a mobile communication terminal according to an exemplary embodiment of the present invention, and FIGS. 3A to 3B illustrate a method of separating an object from an input image according to an exemplary embodiment of the present invention. 4A and 4B are screens illustrating an object boundary input method according to an exemplary embodiment of the present invention.

Referring to FIG. 2, a user selects a desired background image from an image storage unit or a background image taken by a camera mounted on a terminal.

Then, the terminal extracts the corresponding background image from the image storage unit according to the background image selection information selected by the user (S200).

Then, when the input image as shown in Figure 3a is selected (S202), the terminal receives the object boundary information as shown in Figure 3b selected by the user to extract from the input image (S204).

That is, the user selects a boundary for the object to be extracted with respect to the input image. When the user selects a boundary for an object, a mobile communication terminal inputs an object boundary using a button, a mouse and a pen of the mobile communication terminal, and a PC or a keyboard or a mouse.

The input image may be an image input by using a camera mounted on a terminal, a download from a server, a download from a user's PC, or an image selected by the image storage unit.

Referring to FIGS. 4A and 4B for a method of inputting the object boundary, the user moves by using a direction key or a mouse of the terminal and presses the confirmation key when it is considered to be an object boundary. When the user presses the check point, the previous check point and the current check point are connected, and when the last check point is pressed, the first check point is connected to the first check point, and an object area is created from the check points that follow.

When the user inputs boundary information, the terminal generates a mask based on the object boundary. That is, the inside of the boundary selected by the user becomes '1' and the rest becomes '0'.

After performing step 204, the terminal separates the object from the input image according to the received object boundary information (S206).

That is, the terminal separates an object from the input image according to the object boundary information as shown in FIG. 3C, and performs color segmentation on the separated object to extract an object as shown in FIG. 3D. A detailed description of a method of separating an object from the input image is shown in FIG. 5.

When the object is separated from the input image by performing step 206, the terminal synthesizes the separated object with the extracted background image (S208).

A method of synthesizing the separated object and the background image will be described with reference to FIGS. 7 to 10.

If step 208 is performed, the terminal inquires whether or not to manually edit the composite image (S210). That is, the terminal determines whether a composite image editing command is received from the user.

As a result of the determination in step 210, when a composite image editing command is received from the user, the terminal edits and outputs the composite image according to the composite image editing command (S212). Editing of the synthesized image will be described with reference to FIGS. 11A to 11F.

After synthesizing the object with the background image, the user may edit the synthesized image for the mobile communication service. The editing function may include a function of moving an object position, rotating an object, adjusting an object size, and flipping left and right of the object area.

The image editing function may be performed using a menu key and a function key in a mobile communication terminal. For example, to move an image, select an image shift from a menu key and then move the image using the up, down, left and right keys of the function key. Object size can be adjusted by selecting the object size from the menu key and using the up, down, left, and right keys of the function keys.

After performing step 212, the terminal stores the edited composite image (S214). The synthesized image is used for a background screen, a caller ID image, and a multi-mail.

If it is determined in step 210 that the composite image editing command is not received from the user, the terminal outputs and stores the composite image (S216).

5 is a flowchart illustrating a method of separating an object from an input image according to an exemplary embodiment of the present invention, and FIGS. 6A to 6C are screens illustrating a method of separating an object from an input image according to an exemplary embodiment of the present invention. to be.

Referring to FIG. 5, when the object boundary information input by the user is received as shown in FIG. 6A (S500), the terminal obtains the boundary of the internal object as illustrated in FIG. 6B with respect to the corresponding object (S502).

The internal object refers to an area n pixels inward from the area selected by the user in the input image. When the internal object boundary is obtained, the terminal generates a mask based on the internal object as shown in FIG. 6C.

That is, the inside of the boundary selected by the user becomes '1' and the rest becomes '0'.

After performing step 502, the terminal calculates an average color value C1 for surrounding n * n pixels based on the internal object boundary pixels (S504). The color value C1 is assumed to be a color value inside the object.

After performing step 504, the terminal obtains a difference between the color value of each pixel and the obtained average color value within n * n around the boundary pixel of the internal object (S506), and determines whether the obtained difference is greater than or equal to a predetermined threshold. It is determined whether or not (S508).

If the difference is greater than the threshold as a result of the determination in step 508, the terminal removes the corresponding pixel from the object area (S510). Removing from the object area means that the portion marked with '1' in the mask is made '0'. The standard when compositing with other images after color segmentation is that the mask images are marked with '1' and '0'.

After color segmentation as described above, pixels whose color difference is greater than or equal to a threshold are removed. Therefore, the wrong selection by the user is removed from the object area.

However, the object's boundary is not clean because there are pixels removed from the object area. In order to clean the boundary of the object, the terminal performs an n * n morphology on the object (S512).

The n * n morphology is performed on a mask image. As mentioned above, it is a mask image that becomes a reference when compositing with other images after color segmentation.

If it is determined in step 508 that the obtained difference is not greater than or equal to a predetermined threshold value, the terminal includes the pixel in the object area (S514) and performs step 512.

This series of color segmentation processes are applied from the object area input by the user to the internal object area. In other words, the user's input is somewhat accurate boundary of the object, so there is no need for color segmentation inside the object.

Therefore, color segmentation is performed only from the object entered by the user to the boundary of the internal object.

This characteristic can be used to reduce processing time. Put the pixel value between the user's input boundary and the inner object's boundary and the user's input boundary and the inner object's boundary in an arbitrary buffer and read the pixel values in the arbitrary buffer without scanning the entire mask and go directly to the desired part. Over morphology can reduce processing speed by up to six times.

7 is a flowchart illustrating a character background synthesis method of an object according to an exemplary embodiment of the present invention, and FIGS. 8A to 8B are diagrams illustrating a character background synthesis screen of an object according to an exemplary embodiment of the present invention.

Referring to FIG. 7, the user selects a desired character background image from the image storage unit. Then, the terminal extracts the corresponding character background image from the image storage unit according to the character background image selection information selected by the user (S700).

Then, when the input image is received (S702), the terminal receives the object boundary information selected by the user to extract from the input image (S704). That is, the user selects object boundary information to be extracted with respect to the input image.

After performing step 704, the terminal separates the object from the input image according to the received object boundary information (S706).

When the object is separated from the input image by performing step 706, the terminal adjusts the size to fit the size of the region to be inserted of the character background image in order to synthesize the separated object with the extracted character background image (S708). In operation S710, the size-adjusted object is moved to the character background.

That is, since the size and position of the region in which the object is to be inserted in the character background are fixed, the size of the object needs to be adjusted when composing the object with the character background image.

Therefore, the terminal reads the size and position of the object insertion region from the character background image, adjusts the size of the object, and moves the scaled object to the read position before composing the object with the character background image. To synthesize.

For example, if a user separates a face region from the input image of FIG. 8A and synthesizes it with a character background, a screen as shown in FIG. 8B is output.

If step 710 is performed, the terminal inquires whether or not manual editing is desired for the composite image (S712). That is, the terminal determines whether a composite image editing command is received from the user.

As a result of the determination of step 712, when a composite image editing command is received from the user, the terminal edits and outputs the composite image according to the composite image editing command (S714) and stores it (S716).

If it is determined in step 712 that the composite image editing command is not received from the user, the terminal outputs and stores the composite image (S718).

The synthesized video as described above is used for an application service of a mobile communication terminal. The application service includes a background screen, a caller ID service, and a multimedia mail.

9 is a flowchart illustrating a frame image background synthesis method according to an exemplary embodiment of the present invention, and FIGS. 10A to 10D illustrate a frame image background synthesis screen according to an exemplary embodiment of the present invention.

Referring to FIG. 9, a user selects a desired frame background image from an image storage unit. Then, the terminal extracts the frame background image corresponding to the frame background image selection information selected by the user from the image storage unit (S900).

Then, the terminal acquires a mask for the extracted frame background image (S902). This means that the original image is synthesized only with the image inside the frame of the frame image, and not with the information of the frame image corresponding to the part placed above the picture such as the frame or the decoration attached to the frame.

Thus, a frame that separates the original image and the part that can be synthesized and the part that cannot be synthesized with respect to the frame image is constructed and referred to for real-time synthesis. For the part that can be composed, set the mask value to 1, and for the part that cannot be synthesized, set the mask value to 0. The value of is used as is.

After performing step 902, if an input image is received (S904), the terminal receives object boundary information selected by the user to extract from the input image (S706). That is, the user selects object boundary information to be extracted with respect to the input image.

After performing step 906, the terminal separates the corresponding object from the input image according to the received object boundary information (S908).

Then, the terminal synthesizes the portion of the frame of the frame with the separated object by using the mask obtained in step 902 (S910), and adds the portion of the frame of the frame to the composite image (S912).

That is, an area having a mask value of 1 is synthesized with the object, and an area having a mask value of 0 uses a value of a frame image as it is.

For example, the frame background image of FIG. 10A and the input image of FIG. 10C will be described. FIG.

The terminal classifies the framed background image into a region 1000a that can be synthesized and a region 1000b that cannot be synthesized, as shown in FIG. 10B. The synthesizeable region 1000a has a mask value of 1 and a region that cannot be synthesized. 1000b sets the mask value to zero.

Then, when an object is separated from the input image of FIG. 10C, the terminal synthesizes the separated object and the frame background image.

Then, a composite image as shown in FIG. 10D is output.

If step 912 is performed, the terminal inquires whether or not manual editing is desired for the composite image (S914). That is, the terminal determines whether a composite image editing command is received from the user.

When the composite image editing command is received from the user as a result of the determination in step 914, the terminal edits and outputs the composite image according to the composite image editing command (S916) and stores it (S918).

If it is determined in step 914 that the composite image editing command is not received from the user, the terminal outputs and stores the composite image (S920).

11A to 11F illustrate a manual edit screen of a composite image according to an exemplary embodiment of the present invention.

11A shows an input image, and FIG. 11B shows a background image, and the input image and the background image are synthesized as shown in FIG. 11C.

When the user performs vertical magnification for the vertical magnification of the object in the composite image as shown in FIG.

In addition, if the user wants to enlarge the object horizontally in the composite image as shown in FIG. 11C, it is output as shown in FIG.

In addition, if the user wants to turn the object counterclockwise in the composite image as shown in FIG.

As described above, the user may manually edit the synthesized image.

The present invention is not limited to the above embodiments, and many variations are possible by those skilled in the art within the spirit of the present invention.

As described above, according to the present invention, by using the user's manual input and color segmentation technology, the user extracts a desired object from the input image and synthesizes it in the background so that the user can make an interesting composite image, and have an interesting composite image. The present invention provides a method and apparatus for synthesizing images in a mobile communication terminal that can be used for a mobile communication service.

In addition, according to the present invention, it is possible to provide an image synthesizing method and apparatus in a mobile communication terminal that enables an interesting service that utilizes a user's personality using background synthesis, frame synthesis, and character / animation synthesis.

In addition, according to the present invention, it is possible to provide a method and apparatus for synthesizing an image in a mobile communication terminal in which a user can utilize his or her personality to a mobile communication terminal and transmit various images made to a friend through multi-mail.

Claims (21)

In the method for synthesizing the image in the mobile communication terminal, Receiving a background image selected by a user; Receiving an input image selected by the user and receiving object boundary information that the user wants to extract with respect to the input image; Separating the object from the input image by performing color segmentation on the object according to the input object boundary information; and Synthesizing the separated object with the selected background image; Image synthesis method in a mobile communication terminal comprising a. The method of claim 1, And if the editing command for the synthesized video is received from the user, editing and storing the synthesized video according to the editing command. The method of claim 1, And the background image comprises a general photograph image, a character background image, a frame background image, and an animated background image. The method of claim 1, The background image and the input image are images input using at least one of an image photographed by a camera mounted on a mobile communication terminal, an image downloaded from a server, an image transmitted from another terminal, and an image uploaded from a PC. Image synthesis method in a mobile communication terminal. The method of claim 4, wherein And the background image and the input image are images pre-stored in the terminal. The method of claim 1, The object boundary information is input by the user using a button, a mouse and a pen of the mobile communication terminal. The method of claim 1, Separating the object from the input image by performing color segmentation on the object according to the input object boundary information may include generating a mask based on the object boundary information; And performing color segmentation on the object corresponding to the object boundary information. The method of claim 7, wherein Generating a mask based on the object boundary information comprises separating the object into an object area and other areas in the input image according to the object boundary information. The method according to claim 1 or 7, Performing the color segmentation is Obtaining an internal object boundary with respect to the object boundary; Obtaining an average color value of n * n areas based on the obtained boundary pixels of the internal object; Obtaining a difference between the obtained average color value and a color value of each pixel in the inner object boundary; If the difference is greater than or equal to a predetermined threshold, removing the corresponding pixel from the object region, and if not, exceeding the threshold, including the pixel in the object region; And performing a morphology on the predetermined object area. The method of claim 1, And if the background image is selected, obtain a size and a position at which the object is to be synthesized from the background image. The method of claim 1, The synthesizing the separated object with the selected background image may include determining the size and position of the object to be synthesized in the background image, and then adjusting the size of the object according to the checked size, and adjusting the size to the position. A method of synthesizing an image in a mobile communication terminal, comprising moving an adjusted object. The method of claim 2, The editing command is a command for the object of the composite image, the image synthesis method in the mobile communication terminal, characterized in that it comprises a size adjustment, position adjustment, rotation angle adjustment, left and right flip. In the method for separating the object desired by the user from the input image input to the mobile communication terminal, Obtaining internal object boundaries with respect to an object according to the object boundary information when the object boundary information is input by the user; Obtaining an average color value of surrounding n * n pixels based on the obtained inner object boundary pixels; Obtaining a difference between the obtained average color value and a color value for each pixel in n * n around the inner object boundary pixel; If the obtained difference is greater than or equal to a predetermined threshold, removing the pixel from the object area and performing a morphology Separating the object from the input image of the mobile communication terminal comprising a. The method of claim 13, And if the difference is not greater than or equal to a predetermined threshold, further comprising: performing a morphology by including the corresponding pixel in an object area. The method of claim 13, And wherein the internal object refers to an area that is n pixels inward from the object boundary selected by the user in the input image. The method of claim 13, The morphology separates the object from the input image of the mobile communication terminal, characterized in that to clean the boundary of the object. An apparatus for synthesizing an image in a mobile communication terminal including an image storage unit, An input image receiver configured to receive an input image; A user interface unit configured to extract a corresponding image from the image storage unit when input image selection information or background image selection information is received from a user; An object extracting unit obtaining an object according to object boundary information input by the user from the input image selected through the user interface unit, and performing color segmentation on the obtained object to separate the object from the input image; and An image synthesizer configured to synthesize the background image selected through the user interface unit with the object separated by the object extracting unit, and edit the synthesized image according to a synthesized image editing command input by the user. Image synthesizing apparatus in a mobile communication terminal comprising a. The method of claim 17, And a synthesized image storage unit for storing the image synthesized by the image synthesizer. The method of claim 17, And the user interface unit provides a manual editing function to compensate for the misdetection of the object region and to perform natural synthesis for the image synthesized by the image synthesizer. The method of claim 17, And the object extracting unit generates a mask based on the object boundary. The method of claim 20, And the object extracting unit performs a morphology on the object area.

Images