WO2016153309A1

WO2016153309A1 - Image synthesis apparatus and method

Info

Publication number: WO2016153309A1
Application number: PCT/KR2016/003037
Authority: WO
Inventors: 전수영; 권지용
Original assignee: 스타십벤딩머신 주식회사
Priority date: 2015-03-25
Filing date: 2016-03-25
Publication date: 2016-09-29
Also published as: KR101555879B1

Abstract

An image synthesis according to an embodiment of the present invention comprises: an extraction unit which extracts a designated image to be synthesized from a source image; a synthesis unit which synthesizes the designated image with a target image; and a correction unit which corrects a synthesized image which has been generated by the synthesis of the designated image and the target image, wherein the correction unit comprises at least one of an image correction unit for correcting the synthesized image on the basis of a ratio of illumination values, a saturation correction unit for correcting the synthesized image on the basis of a saturation value, and a brightness distribution correction unit for correcting the synthesized image on the basis of a brightness histogram.

Description

Image Synthesis Device and Method

The present invention relates to an image synthesizing apparatus and method, and more particularly, to an image synthesizing apparatus and method for providing a natural synthesis result.

The present invention claims the benefit of the filing date of Korean Patent Application No. 10-2015-0041759, filed March 25, 2015, the entire contents of which are incorporated herein.

In general, for image synthesis, only a specific region is extracted from a source image, and the extracted image is pasted into a target image.

Since the image synthesis synthesizes different images, a separate process is required for the synthesis result to look natural.

An example of a technique for the synthesis result to look natural is Korean Patent No. 10-0495191 (name of the invention: image synthesizer and image synthesis method, publication date: July 26, 1999).

The technique of separating a specific image from the source image is called matting.However, even if the specific image is separated using the matting technique, if the color difference between the separated image and the target image is severe, the viewer may synthesize the image. This felt unnatural.

Conventionally, such problems have been solved through candidate candidates, but in video, source images and target images are changed in real time, and it takes a lot of effort and time to solve these problems through candidate candidates.

Therefore, there is a demand for a technology capable of correcting synthesized images in a short time.

On the other hand, the background art described above is technical information that the inventors possess for the derivation of the present invention or acquired in the derivation process of the present invention, and is not necessarily a publicly known technique disclosed to the general public before the application of the present invention. .

One embodiment of the present invention is to provide an image synthesizing apparatus and method for providing a natural synthesis result.

As a technical means for achieving the above-described technical problem, an image synthesizing apparatus according to an embodiment of the present invention comprises an extraction unit for extracting a specified image to be synthesized from the source image; A synthesizer which synthesizes the designated image with a target image; And a corrector configured to correct a synthesized image generated by combining the designated image and the target image, wherein the corrector corrects the synthesized image based on an illumination value ratio, and the synthesized image based on a chroma value. And a brightness distribution corrector for correcting the synthesized image based on a saturation corrector and a brightness histogram.

The image corrector may calculate a correlation color temperature of each of the designated image and the target image, and correct the synthesized image by using an illumination value ratio based on each illumination value obtained from the correlation color temperature.

The image corrector generates a corrected designated image by multiplying the designated image by a power of a ratio of an illumination value of the target image to an illumination value of the designated image, and generates a corrected image of the designated image with respect to an illumination value of the target image. The corrected target image may be generated by multiplying the target image by a power of a ratio of illumination values.

The number of times the power of the ratio of the illumination value of the target image to the illumination value of the target image and the number of times the power of the ratio of the illumination value of the target image to the illumination value of the target image may be based on correction information. have.

The image corrector may correct only the target image when the correction information is 0, and correct only the designated image when the correction information is 1.

The image corrector may correct the synthesized image based on Equation 1 and Equation 2.

Equation 1

S ' _t = (L _T / L _S ) ^m * S _t

Formula 2-

T ' _t = (L _S / L _T ) ^(1-m) * T _t

{Where S _t is the specified image at time t, T _t Is the target image at time t, L _S is the illumination value of S _t , L _T is the illumination value of T _t , S ' _t is the corrected designated image, T' _t is the corrected target image, m is correction information}

The saturation correction unit may correct the synthesized image by correcting an average of respective saturation values when converting each of the designated image and the target image into a Hue Saturation Value (HSV) color space.

The saturation correction unit may correct the synthesized image based on Equations 3 and 4.

Formula 3

Sat (S ′ _t ) = Sat (S _t ) + m (Sat _T -Sat _S )

Equation 4

Sat (T ′ _t ) = Sat (T _t ) + (1-m) (Sat _S -Sat _T )

{Sat (S ′ _t ) is the average chroma value on each pixel of the corrected designated image, Sat (T ′ _t ) is the average chroma value on each pixel of the corrected target image, Sat (S _t ) is the designated image at time t The average chroma value on each pixel of, Sat (T _t ) is the average chroma value on each pixel of the target image at time t, m is correction information, and Sat _S and Sat _T are HSV (designated image and target image at time t, respectively). Hue Saturation Value) Mean of S (saturation) value when converted to color space}

The brightness distribution corrector may correct the distribution of brightness values of the synthesized image based on a histogram transformation to correct the synthesized image.

The brightness distribution corrector may correct the composite image based on Equation 5 and Equation 6.

Equation 5

V (S ′ _t ) = (1-m) V (S _t ) + mA _T ^-1A _S (V (S _t ))

Equation 6

V (T ′ _t ) = mV (T _t ) + (1-m) A _S ^-1A _T (V (S _t ))

{Where V (S ' _t ) is the brightness value of the corrected target image, V (T' _t ) is the brightness value of the corrected target image, and A _S and A _T are the accumulated values of the specified image and the target image for time t, respectively. Monotonically increasing function for the histogram, V (S _t ) is the brightness value V (T _t ) of the target image at time t}

A method of correcting an image by an image correcting apparatus according to an embodiment of the present invention, the method comprising: extracting a designated image to be synthesized from a source image; Synthesizing the designated image with a target image; And correcting the synthesized image generated by combining the designated image and the target image, wherein the correcting comprises correcting the synthesized image based on at least one of an illumination value ratio, a saturation value, and a brightness histogram. do.

The correcting may include calculating a correlation color temperature of each of the designated image and the target image when correcting the composite image based on the ratio of the illumination value, and calculating an illumination value based on each illumination value obtained from the correlation color temperature. The composite image may be corrected using a ratio.

Correcting the composite image by using an illumination value ratio based on each illumination value obtained from the correlated color temperature comprises applying the designated image to a power of a ratio of an illumination value of the target image to an illumination value of the designated image. The corrected target image may be generated by multiplying and generating a corrected target image by multiplying the target image by a power of a ratio of the illumination value of the target image to the illumination value of the target image.

The correcting may include correcting only the target image when the correction information is 0, and correcting only the designated image when the correction information is 1.

In the correcting, the composite image may be corrected based on Equation 1 and Equation 2.

Equation 1

S ' _t = (L _T / L _S ) ^m * S _t

Equation 2

T ' _t = (L _S / L _T ) ^(1-m) * T _t

{Where S _t is the designated image at time t, T _t is the target image at time t, L _s is the illumination value of S _t , L _T is the illumination value of T _t , S ' _t is the corrected specified image, T ' _t is the corrected target image, m is the correction information}

In the correcting step, when the composite image is corrected based on the saturation value, the average of each saturation value is corrected when each of the designated image and the target image is converted into a Hue Saturation Value (HSV) color space. The composite image may be corrected.

In the correcting, the synthesized image may be corrected based on Equations 3 and 4.

Formula 3

Sat (S ′ _t ) = Sat (S _t ) + m (Sat _T -Sat _S )

Equation 4

Sat (T ′ _t ) = Sat (T _t ) + (1-m) (Sat _S -Sat _T )

In the correcting step, when correcting the synthesized image based on the brightness histogram, the synthesized image may be corrected by correcting a distribution of brightness values of the synthesized image based on a histogram transformation.

The correcting may include calculating a histogram on each of the designated image and the target image, and correcting the composite image by converting brightness values such that the calculated histograms have a similar shape.

The correcting may include correcting the composite image based on Equation 5 and Equation 6.

Equation 5-

V (S ′ _t ) = (1-m) V (S _t ) + mA _T ^-1A _S (V (S _t ))

Equation 6

V (T ′ _t ) = mV (T _t ) + (1-m) A _S ^-1A _T (V (S _t ))

According to any one of the problem solving means of the present invention described above, an embodiment of the present invention can provide an apparatus and method for providing a natural synthesis result.

Further, according to any one of the problem solving means of the present invention, it is possible to correct the synthesized video in a short time based on the ratio of the illumination value.

In addition, according to any one of the problem solving means of the present invention, the synthesized video can be corrected in a short time based on the saturation.

Further, according to any one of the problem solving means of the present invention, it is possible to correct the synthesized image in a short time based on the brightness histogram.

The effects obtainable in the present invention are not limited to the above-mentioned effects, and other effects not mentioned above may be clearly understood by those skilled in the art from the following description. will be.

1 is a block diagram of an image synthesizing apparatus according to an embodiment of the present invention.

2 is a block diagram of a correction unit according to an embodiment of the present invention.

3 is a flowchart illustrating an image synthesizing method according to an embodiment of the present invention.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and like reference numerals designate like parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, which means that it may further include other components, except to exclude other components unless otherwise stated.

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

An image synthesizing apparatus according to an embodiment of the present invention includes an input unit 100 for receiving a source image and a target image. According to an embodiment of the present invention, the input unit 100 may receive an alpha map image.

In the present specification, the source image refers to an image containing an image to be synthesized, the designated image refers to the image to be synthesized, and the target image refers to a target to which the designated image is synthesized.

The image synthesizing apparatus according to the embodiment of the present invention may further include an extractor 200 for extracting a designated image.

The user may select and designate the image of the specific region from the source image as a designated image to synthesize an image of a certain region of the source image into the target image, that is, add it to the target image, and the extractor 200 may According to a user's instruction, a designated image may be designated among the source images, and the specified image may be extracted. According to an embodiment of the present invention, the designated image may be a foreground, a region of interest (ROI) set by a user, or set by a device.

The extractor 200 according to an embodiment of the present invention may extract the designated image from the source image based on the alpha map image. Extracting a designated image using an alpha map is a known technique, and a description thereof will be omitted.

Meanwhile, in the present specification, the source image may be a still image or a video, and the target image may also be a still image or a video. Hereinafter, the source image and the target image are assumed to be video.

The synthesis unit 300 synthesizes the extracted designated image with the target image. The synthesizer 300 synthesizes the designated image and the target image. Therefore, the synthesized image may include the target image and the extracted designated image.

The correction unit 400 corrects the synthesized image. A detailed process of correcting the synthesized image to the natural image by the correction unit 400 will be described later.

The output unit 500 outputs the corrected image. The output unit 500 may output the corrected image to a display device provided separately or through a separate printing device.

The above-described image synthesizing apparatus may be implemented as an electronic device. In this case, the electronic device may be a server itself, or may be implemented as a computer, a portable terminal, a television, a wearable device, or the like, which may be connected to a remote server through a network as a user terminal, or may be connected to another user terminal and a server. .

Meanwhile, the image synthesizing apparatus may be implemented by one electronic device, or may be implemented by various electronic devices. For example, the image synthesizing apparatus may be implemented on a user terminal or on a server communicating with a client installed with a client through a network.

Next, each configuration of the correction unit 400 according to an embodiment of the present invention will be described with reference to FIG. 2.

2, the corrector 400 according to an embodiment of the present invention may include at least one of an illumination value corrector 410, a saturation corrector 420, and a brightness distribution corrector 430. .

Hereinafter, it is assumed that the image at time t of the designated image is S _t , the image at time t of the target image is T _t , the corrected designated image is S ' _t , and the corrected target image is T' _t . In addition, m is assumed to be correction information. In the present specification, the correction information may be a parameter indicating the degree of correction. According to an embodiment of the present invention, the correction unit 400 may determine the degree of correction of the designated image and the target image based on the correction information.

The illumination value correction unit 410 according to the embodiment of the present invention corrects the composite image based on the ratio of the illumination values.

The image corrector 410 according to the embodiment of the present invention calculates the color temperature and calculates an illumination value based on the calculated result value. Color temperature is a numerical representation of the color of a light source using absolute temperature. Color temperature can be used to infer which light source the image was taken from. Color temperature is also closely related to the white balance of the image.

In particular, the image corrector 410 according to the embodiment of the present invention may calculate a correlated color temperature and correct the synthesized image based on the calculated result value. In more detail, the image correction unit 410 may obtain the illumination value L _S based on the correlation color temperature value for the designated image S _t and obtain the illumination value L _T based on the correlation color temperature value for the target image T _t . Where L _S is the illumination value of S _t and L _T is the illumination value of T _t .

A method of obtaining a correlation color temperature value according to an embodiment of the present invention will be briefly described. First, a color value RGB of a specific image is converted into an XYZ stimulus value of a CIE coordinate system. Where X, Y, and Z are the stimulus values received by cone cells receiving short, medium, and long wavelengths, respectively. Thereafter, the XYZ stimulus value when Y is equal to or greater than a predetermined reference value is extracted to calculate an average value, and the calculated average value is converted into a color temperature.

The present invention is applicable to the case of obtaining a correlation color temperature value based on a known method in addition to the above method.

The image corrector 410 according to the embodiment of the present invention may correct the synthesized image based on Equations 1 and 2 below.

Equation 1

S ' _t = (L _T / L _S ) ^m * S _t

Equation 2

T ' _t = (L _S / L _T ) ^(1-m) * T _t

Referring to Equations 1 and 2, the image corrector 410 corrects the composite image based on the ratio of the illumination values. In addition, the image corrector 410 may correct the synthesized image based on an illumination value of each of the designated image and the target image.

Referring to Equation 1, the power is proportional to the power of the ratio of the illumination value of the target image to the illumination value of the corrected designated image S ′ _t specified image. In more detail, the illumination value correcting unit 410 generates a corrected designated image by multiplying the specified image by a power of a ratio of the illumination value of the target image to the illumination value of the designated image.

Referring to Equation 2, the ratio of the corrected target image T ′ _t target image to the illumination value of the designated image is proportional to the power square. The image corrector 410 generates the corrected target image by multiplying the target image by a power of a ratio of the illumination value of the designated image to the illumination value of the target image.

Referring to Equations 1 and 2, the number of powers of the ratio of the illumination values of the target image to the illumination values of the target image and the number of powers of the ratio of the illumination values of the target image to the illumination values of the target image Based on the correction information m. Also, as the illumination value corrector 410 multiplies the specified image by the ratio of the illumination value of the target image to the illumination value of the specified image, the target image is not squared by the ratio of the illumination value of the specified image to the illumination value of the target image. You may not.

The image corrector 410 corrects only the target image without touching the designated image when m is 0, and corrects only the designated image without touching the target image when m is 1. The value of m may be preset or determined by user input. It may also be calculated through a separate algorithm.

The saturation correction unit 420 according to the embodiment of the present invention corrects the synthesized image based on the saturation value. In addition, the saturation correction unit 420 may correct the synthesized image based on the chroma values of each of the designated image and the target image. In more detail, the saturation correction unit 420 may correct the synthesized image by correcting the saturation average value of the synthesized image.

When the saturation correction unit 420 converts each of S _t and T _t into a Hue Saturation Value (HSV) color space, when the average of S (saturation) values is Sat _S and Sat _T , respectively, Equations 3 and 4 Based on the synthesized image can be corrected. Since the present invention utilizes the average of the S (saturation) values, the correction can be performed with high efficiency.

Formula 3

Sat (S ′ _t ) = Sat (S _t ) + m (Sat _T -Sat _S )

Equation 4

Sat (T ′ _t ) = Sat (T _t ) + (1-m) (Sat _S -Sat _T )

In Equation 3 and Equation 4, Sat (S ′ _t ) is the average chroma value on each pixel of the corrected designated image, Sat (T ′ _t ) is the average chroma value on each pixel of the corrected target image, and Sat (S _t ) is the designated image. The saturation average value on each pixel of, Sat (T _t ) may mean a saturation average value on each pixel of the target image.

The saturation correction unit 420 may correct the synthesized image based on the difference between Sat _T and Sat _S. Referring to Equation 3, the saturation correction unit 420 may correct Sat (S _t ) based on the value of Sat _T minus Sat _S. Referring to Equation 4, the saturation correction unit 420 may determine from Sat _S Sat (T _t ) can be corrected based on subtracting Sat _T.

More specifically, the saturation correction unit 420 may correct a Sat (S _t) to Sat (S _'t) plus m times the ppaengap Sat Sat _S from _T. In addition, the saturation correction unit 420 may correct a Sat (T _t) for the ppaengap (1-m) times in addition Sat (T _'t) to Sat Sat _T from _S. That is, the number of values added to Sat (S _t ) and Sat (T _t ), respectively, may be based on the correction information m.

The saturation correction unit 420 corrects only the target image without touching the designated image when m is 0, and corrects only the designated image without touching the target image when m is 1. The value of m may be preset or determined by user input. It may also be calculated through a separate algorithm.

The brightness distribution correction unit 430 according to an embodiment of the present invention corrects the synthesized image based on the brightness histogram. In addition, the brightness distribution correction unit 430 may correct the synthesized image based on the brightness histogram of each of the designated image and the target image. In more detail, the brightness distribution correction unit 430 may correct the synthesized image by histogram converting the distribution of brightness values of the synthesized image.

In correcting the synthesized image, the synthesized image may be corrected using only an average of the V (brightness) value, that is, the brightness value, during the HSV color space conversion. However, since the brightness value is closely related to the shape of the object in the image, the efficiency is low when the composite image is corrected using only the average of the brightness values.

Therefore, since the brightness distribution correction unit 430 according to an embodiment of the present invention corrects the composite image in consideration of the distribution of the brightness values as well as the brightness values, high efficiency can be guaranteed.

The brightness distribution correction unit 430 corrects the distribution of brightness values based on the histogram transformation. In more detail, the brightness distribution correction unit 430 calculates and calculates histograms H _S and H _T for the brightness values V (S _t ) and V (T _t ) of the respective images S _t and T _t . Each brightness value is converted so that each histogram is similar to each other.

At this time, in order to convert the brightness value, the brightness distribution correction unit 430 converts the brightness value based on Equations 5 and 6 below.

Equation 5-

V (S ′ _t ) = (1-m) V (S _t ) + mA _T ^-1A _S (V (S _t ))

Equation 6

V (T't) = mV (T t) + (1 - m) A S -1 · A T (V (S t))

Where V (S ' _t ) is the brightness value of the corrected target image, V (T' _t ) is the brightness value of the corrected target image, and A _S and A _T are the cumulative histograms of the target image and the target image for time t, respectively. The monotonic increasing function for, V (S _t ) is the brightness value V of the specified image at time t, (T _t ) is the brightness value of the target image at time t and m is correction information.

Next, an image synthesis method according to an embodiment of the present invention will be described with reference to FIG. 3.

The image synthesizing method according to the embodiment shown in FIG. 3 includes steps processed in time series in the image synthesizing apparatus shown in FIG. 1. Therefore, even if omitted below, the above description of the image synthesizing apparatus shown in FIG. 1 may be applied to the image synthesizing method according to the exemplary embodiment shown in FIG. 3.

The input unit 100 receives a source image and a target image (S401). The input unit may further receive an alpha map image.

The extractor 200 extracts a designated image from the source image (S403). The extractor 200 may extract the designated image from the source image based on the alpha map image.

The synthesis unit 300 synthesizes the designated image with the target image (S405).

The correction unit 400 corrects the synthesized image (S407). The corrector 400 may correct the synthesized image based on at least one of a ratio, a saturation value, and a brightness histogram of the illumination value. When the correction is performed based on a plurality of elements of the ratio of the illumination value, the saturation value, and the brightness histogram, the correction unit may correct the synthesized image in a predetermined order, and may simultaneously perform the correction.

The output unit 500 outputs the corrected image (S409).

The output unit 500 may output the corrected image to a display device provided separately or through a separate printing device.

The image synthesizing method according to the embodiment described with reference to FIG. 3 may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transmission mechanism, and includes any information delivery media.

In addition, the image synthesis method according to an embodiment of the present invention may be implemented as a computer program (or computer program product) including instructions executable by a computer. The computer program includes programmable machine instructions processed by the processor and may be implemented in a high-level programming language, an object-oriented programming language, an assembly language, or a machine language. . The computer program may also be recorded on tangible computer readable media (eg, memory, hard disks, magnetic / optical media or solid-state drives, etc.).

Accordingly, the image synthesizing method according to an embodiment of the present invention may be implemented by executing the computer program as described above by the computing device. The computing device may include at least a portion of a processor, a memory, a storage device, a high speed interface connected to the memory and a high speed expansion port, and a low speed interface connected to the low speed bus and the storage device. Each of these components are connected to each other using a variety of buses and may be mounted on a common motherboard or otherwise mounted in a suitable manner.

Here, the processor may process instructions within the computing device, such as to display graphical information for providing a graphical user interface (GUI) on an external input, output device, such as a display connected to a high speed interface. Instructions stored in memory or storage. In other embodiments, multiple processors and / or multiple buses may be used with appropriately multiple memories and memory types. The processor may also be implemented as a chipset consisting of chips comprising a plurality of independent analog and / or digital processors.

The memory also stores information within the computing device. In one example, the memory may consist of a volatile memory unit or a collection thereof. As another example, the memory may consist of a nonvolatile memory unit or a collection thereof. The memory may also be other forms of computer readable media, such as, for example, magnetic or optical disks.

In addition, the storage device can provide a large amount of storage space to the computing device. The storage device may be a computer readable medium or a configuration including such a medium, and may include, for example, devices or other configurations within a storage area network (SAN), and may include a floppy disk device, a hard disk device, an optical disk device, Or a tape device, flash memory, or similar other semiconductor memory device or device array.

The foregoing description of the present invention is intended for illustration, and it will be understood by those skilled in the art that the present invention may be easily modified in other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is shown by the following claims rather than the above description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention. do.

Claims

An extraction unit which extracts a designated image to be synthesized from a source image;

A synthesizer which synthesizes the designated image with a target image; And

A correction unit configured to correct a synthesized image generated by combining the designated image and the target image,

The image correction unit corrects the composite image based on an illumination value of each of the designated image and the target image, and a chroma correction unit corrects the synthesized image based on chroma values of each of the designated image and the target image. And a brightness distribution corrector configured to correct the synthesized image based on the brightness histogram of each of the designated image and the target image.

The image correction unit,

The designated image is corrected based on an illumination value of each of the designated image and the target image, and is corrected by multiplying the specified image by a power of a ratio of an illumination value of the target image to an illumination value of the designated image. And generating a corrected target image by multiplying the target image by a power of a ratio of an illumination value of the designated image to an illumination value of the target image.
The method of claim 1,

The number of times the power of the ratio of the illumination value of the target image to the illumination value of the target image and the number of times the power of the ratio of the illumination value of the target image to the illumination value of the target image is based on the correction information, Video Synthesis Device.
The method of claim 2,

The image correction unit,

And correct only the target image when the correction information is 0, and correct only the designated image when the correction information is 1.
The method of claim 1,

The image correction unit,

And correcting the synthesized image based on Equation 1 and Equation 2.

Equation 1

S ' t = (L T / L S ) m * S t

Formula 2-

T ' t = (L S / L T ) (1-m) * T t

{Where S t is the designated image at time t, T t is the target image at time t, L s is the illumination value of S t , L T is the illumination value of T t , S ' t is the corrected specified image, T ' t is the corrected target image, m is the correction information}
The method of claim 1,

The saturation correction unit,

And correcting the synthesized image by correcting an average of respective saturation values when converting each of the designated image and the target image into a Hue Saturation Value (HSV) color space.
The method of claim 5,

The saturation correction unit,

An image synthesizing apparatus for correcting a synthesized image based on Equations 3 and 4.

Formula 3

Sat (S ′ t ) = Sat (S t ) + m (Sat T -Sat S )

Equation 4

Sat (T ′ t ) = Sat (T t ) + (1-m) (Sat S -Sat T )

{Sat (S ′ t ) is the average chroma value on each pixel of the corrected designated image, Sat (T ′ t ) is the average chroma value on each pixel of the corrected target image, Sat (S t ) is the designated image at time t The average chroma value on each pixel of, Sat (T t ) is the average chroma value on each pixel of the target image at time t, m is correction information, and Sat S and Sat T are HSV (designated image and target image at time t, respectively). Hue Saturation Value) Mean of S (saturation) value when converted to color space}
The method of claim 1,

The brightness distribution correction unit,

And correcting the synthesized image by correcting a distribution of brightness values of the synthesized image based on a histogram transformation.
The method of claim 7, wherein

The brightness distribution correction unit,

And calculating a histogram on each of the designated image and the target image, and correcting the synthesized image by converting brightness values so that the calculated histograms have a similar shape.
The method of claim 7, wherein

The brightness distribution correction unit,

And correcting the synthesized image based on Equations 5 and 6.

Equation 5-

V (S ′ t ) = (1-m) V (S t ) + mA T -1A S (V (S t ))

Equation 6

V (T ′ t ) = mV (T t ) + (1-m) A S -1A T (V (S t ))

{Where V (S ' t ) is the brightness value of the corrected target image, V (T' t ) is the brightness value of the corrected target image, and A S and A T are the accumulated values of the specified image and the target image for time t, respectively. Monotonically increasing function for the histogram, V (S t ) is the brightness value of the specified image at time t, V (T t ) is the brightness value of the target image at time t, m is correction information}
In the method for correcting the image by the image correction device,

Extracting a designated image to be synthesized from the source image;

Synthesizing the designated image with a target image; And

Correcting a composite image generated by synthesizing the designated image and the target image,

The compensating may be performed based on at least one of an illumination value of each of the designated image and the target image, a saturation value of each of the designated image and the target image, and a brightness histogram of each of the designated image and the target image. To correct the image,

The correcting may include correcting the synthesized image based on an illumination value of each of the designated image and the target image, when correcting the synthesized image based on the illumination value, wherein the target with respect to the illumination value of the designated image is corrected. The corrected specified image is generated by multiplying the specified image by the power of the ratio of the illumination values of the image, and corrected by multiplying the target image by the power of the ratio of the illumination value of the specified image to the illumination value of the target image. An image synthesis method for generating a target image.
The method of claim 10,

The number of times the power of the ratio of the illumination value of the target image to the illumination value of the target image and the number of times the power of the ratio of the illumination value of the target image to the illumination value of the target image is based on the correction information, Image Synthesis Method.
The method of claim 11,

The correcting step,

And correcting only the target image when the correction information is 0, and correcting only the designated image when the correction information is 1.
The method of claim 10,

The correcting step,

And correcting the synthesized image based on Equation 1 and Equation 2.

Equation 1

S ' t = (L T / L S ) m * S t

Formula 2-

T ' t = (L S / L T ) (1-m) * T t

{Where S t is the designated image at time t, T t is the target image at time t, L s is the illumination value of S t , L T is the illumination value of T t , S ' t is the corrected specified image, T ' t is the corrected target image, m is the correction information}
The method of claim 10,

The correcting step,

When correcting the synthesized image based on the saturation value, correcting the synthesized image by correcting an average of each saturation value when converting each of the designated image and the target image into a Hue Saturation Value (HSV) color space. Image synthesis method.
The method of claim 14,

The correcting step,

And correcting the synthesized image based on Equations 3 and 4.

Formula 3

Sat (S ′ t ) = Sat (S t ) + m (Sat T -Sat S )

Equation 4

Sat (T ′ t ) = Sat (T t ) + (1-m) (Sat S -Sat T )

{Sat (S ′ t ) is the average chroma value on each pixel of the corrected designated image, Sat (T ′ t ) is the average chroma value on each pixel of the corrected target image, Sat (S t ) is the designated image at time t The average chroma value on each pixel of, Sat (T t ) is the average chroma value on each pixel of the target image at time t, m is correction information, and Sat S and Sat T are HSV (designated image and target image at time t, respectively). Hue Saturation Value) Mean of S (saturation) value when converted to color space}
The method of claim 10,

The correcting step,

And correcting the distribution of the brightness values of the synthesized image based on a histogram transformation when correcting the synthesized image based on the brightness histogram.
The method of claim 16,

The correcting step,

And calculating a histogram on each of the designated image and the target image, and correcting the synthesized image by converting brightness values so that the calculated histograms have a similar shape.
The method of claim 16,

The correcting step,

And correcting the synthesized image based on Equations 5 and 6.

Equation 5-

V (S ′ t ) = (1-m) V (S t ) + mA T -1A S (V (S t ))

Equation 6

V (T ′ t ) = mV (T t ) + (1-m) A S -1A T (V (S t ))

{Where V (S ' t ) is the brightness value of the corrected target image, V (T' t ) is the brightness value of the corrected target image, and A S and A T are the accumulated values of the specified image and the target image for time t, respectively. Monotonically increasing function for the histogram, V (S t ) is the brightness value of the specified image at time t, V (T t ) is the brightness value of the target image at time t, m is correction information}