JP2009253324A - Image processing unit, image processing method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To effectively perform smoothing processing of an image. <P>SOLUTION: A face region detection section 51 detects a face region including an image of a face, where a face portion of a person on a target image is photographed. A correction section 52 specifies a compensation value based on the position of a prescribed region in an image region indicating a face in the face region, and corrects the color tone of the image by the compensation value. An output control section 53 generates display data or print data from the image data of the target image subjected to correction processing, supplies the display data to a display section for display, and supplies the print data to a printer engine for executing the print of the image based on the print data. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

The present invention relates to an image processing apparatus, an image processing method, and a program. In particular, the present invention relates to an image processing apparatus, an image processing method, and a program capable of effectively performing an image smoothing process.

Conventionally, a technique for correcting the color tone of an image of image data based on color image data is known. For example, in Patent Document 1, an image region in which a human face is captured in a captured image is detected, and the tone of the region is smoothed so that a bright skin color is obtained. By such image correction processing, spots and freckles on the face image can be eliminated (that is, so-called beautiful skin can be obtained), and a more impressive face image can be provided.
JP 2000-182043 A

However, in the method described in Patent Document 1, since the entire face image area is smoothed, it is not desired to perform the smoothing process. For example, a smoothing process is also performed on a part such as an eye or a mouth. It may be a little blurry.

Further, since the correction strength of the smoothing process is uniform, effective smoothing process cannot be performed.

The present invention has been made in view of such a situation, and makes it possible to effectively perform an image smoothing process.

An image processing apparatus of the present invention is an image processing apparatus that corrects the color tone of an image, and includes a face area detection unit that detects a face area including a face image in the image, and corrects the color tone of the image with a predetermined correction amount. And a correction unit, wherein the correction unit specifies a correction amount based on a position of a predetermined region in an image region representing a face in the face region.

The correction means obtains a correction intensity model having a face shape and a correction value representing the correction intensity, and maps the correction value set in the correction intensity model to the face area. The color tone of the face area can be corrected with the mapped correction value.

In the correction strength model, a correction amount according to the position of the face can be set.

The correction amount of the eye position and the correction amount of the cheek position can be different.

The correction unit can reduce the correction amount of the color tone stepwise toward the contour direction of the face area.

An image processing method or program according to the present invention is an image processing method of an image processing apparatus for correcting the color tone of a target image to be processed, or performs image processing for correcting the color tone of a target image to be processed. A program executed by a computer for detecting a face area including a face image on a target image, and a correction step for correcting the color tone of the face area with different correction strength depending on a portion in the face area; It is characterized by including.

In the image processing apparatus, the image processing method, or the program of the present invention, a face area including a face image on the target image is detected, and the color tone of the face area is corrected with different correction strength depending on the portion in the face area.

  According to the present invention, an image smoothing process can be performed effectively.

  Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram illustrating a hardware configuration example of a printer 1 to which the present invention is applied. The printer 1 is a color inkjet printer that supports so-called direct printing, in which an image is printed based on image data acquired from a memory card 18 or the like.

The printer 1 includes a CPU 11, an internal memory 12, an operation unit 13, a display unit 14, a printer engine 15, and a card interface (card I / F) 16.

A CPU (central processing unit) 11 controls each unit and executes various processes according to a program stored in the internal memory 12.

The CPU 11 includes, for example, an area including an image showing a person's face (hereinafter referred to as a face area FA).
In this case, smoothing is performed on an area (hereinafter referred to as a correction area FC) excluding a predetermined portion (for example, an image area such as an eye or a mouth) in the face area FA. (Hereinafter, this series of processes is referred to as a first skin beautifying process Z1). The CPU 11 also performs smoothing of the face area FA with different correction strength depending on the portion in the face area FA (hereinafter, a series of processes will be described as follows).
2nd skin treatment Z2).

The internal memory 12 includes a ROM (Read Only Memory) storing various programs executed by the CPU 11 and various data, and a RAM (Random Access Memory) temporarily storing programs and data to be executed by the CPU 11. Has been.

The operation unit 13 includes one or a plurality of buttons and a touch panel, and notifies the CPU 11 of the operation content by the user.

The display unit 14 is configured by a liquid crystal display, for example, and displays an image corresponding to the data supplied from the CPU 11.

The printer engine 15 is a printing mechanism that performs printing based on the print data supplied from the CPU 11.

The card interface (I / F) 16 is an interface for exchanging data with the memory card 18 inserted in the card slot 17. In this example, image data as RGB data is stored in the memory card 18, and the printer 1 acquires the image data stored in the memory card 18 via the card interface 16.

  The constituent elements of the printer 1 are connected to each other via a bus 19.

The printer 1 may further include an interface for performing data communication with other devices (for example, a digital still camera).

FIG. 2 is a block diagram illustrating a functional configuration example of the printer 1 for executing the first skin beautification process Z1. This function is realized by the CPU 11 executing a predetermined program stored in the internal memory 12.

The face area detection unit 21 serving as a face area detection unit is, for example, an image that is read from the memory card 18 and input to the printer 1 and that is the target of the first skin beautification process Z1 (hereinafter, the target image TI).
And a face area FA including a face image in which the face portion of the person is reflected on the target image TI is detected.

The non-correction area detection unit 22 as the non-correction area detection means performs a smoothing process on a predetermined part in the face area FA (for example, eyebrows, eyes, nostrils, mouth and other organs constituting the face). Image area (
Hereinafter, the non-correction region FB) is also detected as appropriate.

The correction area specifying unit 23 as the correction area specifying means specifies the area of the face area FA excluding the non-correction area FB as the correction area FC.

The correction unit 24 as correction means corrects the color tone of the specified correction area FC. In this example, a smoothing process is performed in which the brightness of the correction area FC is adjusted to the target brightness that is ideal brightness.

The output control unit 25 generates display data or print data from the image data of the target image TI that has been subjected to the smoothing process, supplies the display data to the display unit 14 for display, or causes the printer engine 15 to display the print data. And printing the image based on the print data.

FIG. 3 is a flowchart showing the flow of the first skin beautification process Z1. The first skin beautification process Z1 will be described with reference to this flowchart.

In step S1, the face area detection unit 21 detects the face area FA in the target image TI that is the target of the first skin beautification process Z1.

For example, the face area detection unit 21 detects the face area FA by interpreting an image based on a statistical model.

For example, the face shape expressed by the control points placed on the contours of the face and organs (eyebrows, eyes, nose, mouth, etc.) with high contrast, and the face shape is geometrically deformed so that it is based on the average face shape. Based on the model representing the face image, the shape and the texture are separately subjected to principal component analysis based on the shade pattern of the shape normalized face image, and the face image is projected on the eigenspace.

FIG. 4 is a diagram illustrating an arrangement example of control points in the statistical model. In this way, the control points are arranged on the contours of the face and the contours of the organs (eyebrows, eyes, nose, mouth, etc.).

FIG. 5 is a diagram showing an example of the detection result of the face area FA extracted by the control points shown in FIG. As described above, the face area FA is detected from the target image TI by the statistical model.

In step S <b> 2, the non-correction area detection unit 22 detects a non-correction area FB (that is, an area not subjected to the smoothing process) from the detected face area FA.

Specifically, using control points set around the eyebrows, eyes, nose, and mouth (FIGS. 4 and 5)
The area of the face area FA corresponding to the area formed by the control points is detected as the uncorrected area FB.

The non-correction area FB is specified by the coordinates of control points arranged on the outline of the non-correction area FB, for example. Further, in order to form a smoother region outline for the uncorrected region FB, each control point is connected by a spline curve.

Next, in step S3, the correction area specifying unit 23 specifies an area excluding the non-correction area FB of the face area FA as the correction area FC.

Specifically, the correction area specifying unit 23 generates an image (hereinafter referred to as a mask image FM) that masks an area of the face area FA excluding the non-correction area FB, and the face area masked by the mask image FM. The FA area is specified as the correction area FC

FIG. 6 is a diagram illustrating an example of the mask image FM. This mask image FM is an image having the same contour as the face area FA, and the pixel value of the pixel in the area corresponding to the non-correction area FB (the white area in the figure) is 0, and the other values The pixel value of the pixel in the region (black region in the figure) is the value 1
It is said that.

That is, the correction area specifying unit 23 generates a mask image FM as shown in FIG. 6, superimposes the mask image FM on the face area FA, and the value 1 of the mask image FM of the face area FA is set. A region (that is, a masked region) composed of pixels located at positions corresponding to existing pixels is specified as the correction region FC.

In step S4, the correction unit 24 performs a smoothing process on the correction area FC of the face area FA. In the case of this example, the brightness of the correction area FC is adjusted to the target brightness that is ideal brightness.

  Here, the brightness adjustment processing will be described.

Image data represented by gradation values of the RGB color system in the correction area FC (hereinafter referred to as initial image data PID) is represented by gradation values of L ^* a ^* b ^* color system. (Hereinafter referred to as image data PIDL). And the brightness L of all the pixels of the image data PIDL
An average value La of ^* (that is, an average value of the lightness L ^* of the correction area FC) is calculated.
Thereafter, the brightness adjustment amount dL is calculated by the following equation (1).
dL = Lt−La (1)

Here, Lt is the target brightness which is the ideal brightness of the face area FA. This target brightness L
t is held in the internal memory 12, for example.

  Next, a tone curve is generated based on the calculated adjustment amount dL.

FIG. 7 is a diagram illustrating an example of a tone curve. In FIG. 7, the horizontal axis represents the lightness input value Li, and the vertical axis represents the lightness output value Lo.

That is, when the input value of lightness is 0, the output value is 0, and when the input value of lightness is 100, the output value is 100, and the input value of lightness is the value Lir (approximately 50), a quadratic curve whose output value increases by the previously calculated value dL is generated as a tone curve.

Next, an output value when the lightness of each pixel of the image data PIDL represented by the gradation value of the L ^* a ^* b ^* color system is used as an input value is obtained from the generated tone curve. Then, the brightness of each pixel of the image data PIDL is adjusted to the brightness obtained as the output value. Hereinafter, the adjusted image data is referred to as image data PIDLr. The image data PIDLr generated in this way is converted into image data PIDr represented by gradation values (0 to 255) of the RGB color system.

When the smoothing process is performed on the correction area FC in this way, the first skin beautification process Z1 is completed (FIG. 3).

  As described above, the first skin beautification process Z1 is performed.

As described above, the smoothing process can be selectively performed on the face area FA because the smoothing process is performed on the correction area FC excluding the non-correction area FB where the smoothing process is not desired. . That is, it is possible to perform the smoothing process only on an area that needs to be smoothed (for example, a skin area). For example, it is possible to prevent the smoothing process from being performed on an image region of a predetermined organ such as an eye or a mouth.

Also, as described above, the face area FA is first detected based on the face shape (FIG. 5), and the correction area FC is specified based on the face area FA. The correction region FC can be easily specified without being restricted by the above.

For example, there is a technique for specifying a correction area by skin color detection. In that case, a part that is obliquely illuminated or a part that is thickly decorated is not detected as a skin color and may not be specified as a correction area. On the other hand, in the present embodiment, if the region is within a general face-shaped region and is a region other than the non-correction region FB, the correction region FC is used. it can. For example, the correction area FC can be detected by combining face shape and skin color detection.

In the above description, the area within the outline of the face is the face area FA. However, for example, an area including an image such as a neck or ear may be the face area FA.

In the above, the correction area FC is smoothed with the brightness obtained from the tone curve generated based on the average value of the brightness of the correction area FC. However, if this is done, depending on the hue of the target image TI, the difference in brightness between the correction area FC and other areas will increase, and the outline part of the face area FA and the boundary part between the correction area FC and the non-correction area FB will not be present. May stand out naturally.

Therefore, the smoothing intensity can be decreased stepwise toward the contour direction of the face area FA or toward the boundary direction between the correction area FC and the non-correction area FB. That is, it is possible to make the brightness closer to the original brightness as the portion is closer to the contour or boundary. By doing so, there is not much difference in brightness between the correction area FC and the other areas in the contour area of the face area FA and in the boundary area between the correction area FC and the non-correction area FB. Can be less noticeable.

FIG. 8 shows a mask image generated by the correction area specifying unit 23 when the smoothing intensity is reduced stepwise toward the contour direction of the face area FA or the boundary direction between the correction area FC and the non-correction area FB. It is a figure which shows the example of FM.

In the example of FIG. 8, the pixel value of the pixel in the area corresponding to the non-correction area FB (the white area in the figure) is 0, and the contour portion of the face area FA and the correction area FC of the face area FA are not. The pixel value of the area corresponding to the boundary with the correction area FB (area shown by hatching in the figure) is set to 1, and the pixel value of the pixels in other areas (black area in the figure) Is a value of 2.

In the mask image FM shown in FIG. 8, the area corresponding to the area where the value 1 and the value 2 of the mask image FM are set in the face area FA is specified as the correction area FC.

Then, the brightness of each pixel in the area corresponding to the area where the value 2 of the mask image FM shown in FIG. 8 is set in the correction area FC is L read from the tone curve shown in FIG.
^* a ^* b ^* It is adjusted to image data PIDL represented by a color system gradation value.

Further, as described above, the brightness of each pixel in the area corresponding to the area where the value 1 of the mask image FM shown in FIG. 8 is set in the correction area FC is L ^* read out from the tone curve shown in FIG.
A value smaller than the image data PIDL represented by the a ^* b ^* color system gradation values (for example, FIG. 7).
To a value close to the dotted line TL shown in FIG.

Thus, by reducing the smoothing intensity stepwise in the contour direction or the boundary direction, the contour part of the face area FA and the boundary part of the correction area FC and the non-correction area FB are made less noticeable. Can do.

Next, the second skin beautification process Z2 (that is, the process of smoothing the face area FA with different correction strength depending on the portion in the face area FA) will be described.

FIG. 9 is a block diagram illustrating a functional configuration example of the printer 1 for executing the second skin beautification process Z2. This function is realized by the CPU 11 executing a predetermined program stored in the internal memory 12.
The face area detection unit 51 detects a face area FA including an image of a face in which a person's face part is reflected on the target image TI in the same manner as the face area detection unit 21 in FIG.

The correction unit 52 is a smoothing process for the face area FA based on an image model having a face outline and a correction value representing the correction strength (hereinafter referred to as a correction strength model MA). I do. The corrected intensity model MA is held in, for example, the internal memory 12, and is read from there.

Similar to the output control unit 25 in FIG. 2, the output control unit 53 performs the smoothing process on the target image T.
Display data or print data is generated from the image data I, and the display data is supplied to the display unit 14 for display, or the print data is supplied to the printer engine 15 to print an image based on the print data.

FIG. 10 is a flowchart showing the flow of the second skin beautification process Z2. The second skin beautification process Z2 will be described with reference to this flowchart.

In step S21, the face area detection unit 51 detects the face area FA using a statistical model, similarly to the case in step S1 of FIG.

In step S <b> 22, the correction unit 52 acquires the correction strength model MA from the internal memory 12.

FIG. 11 is a conceptual diagram of the correction intensity model MA. In the case of this example, the average face shape facing forward obtained by learning is divided into triangular regions consisting of three adjacent dots of dots placed on the contours of eyes, nose, mouth, etc. It has a configuration. Correction strength model M
The dots on A basically correspond to the control points on the face model by the statistical model.

The correction intensity model MA also has a data structure in a 100 × 100 section with a section corresponding to a pixel as one unit, and a correction value representing the correction strength is set in each section. In FIG. 11, the shade of the color represents the magnitude of the correction value, the correction value for the dark color portion is a large value, and the correction value for the light color portion is a small value. That is, the magnitudes of the eye position correction amount and the cheek position correction amount are different. In addition, correction values for some of the areas around the buttocks, nose, and mouth are large. In the correction strength model MA, for example, data representing the coordinate values of the sections and the correction values of the sections are prepared as a table.

Next, in step S23, the correction unit 52 acquires the acquired correction strength model MA (FIG. 11).
) Is mapped to the face area FA.

  FIG. 12 is a diagram conceptually showing how correction values are mapped to the face area FA.

  Here, a method for mapping correction values to the face area FA will be described.

FIG. 13 is a diagram showing the principle of image deformation in a triangular area used in this mapping.

In the example of FIG. 13, an image of a triangular area stu having points s, t, and u as vertices is represented by points s ′, t ′
, U ′ as a vertex, the image is transformed into an image of a triangular area s′t′u ′.

The deformation of the image was calculated by calculating which position in the image of the triangular area stu before the deformation the position of a certain pixel in the image of the triangular area s't'u 'after the deformation corresponds to. This is performed by setting the pixel value in the image before deformation at the position as the pixel value of the image after deformation.

For example, in FIG. 13, the position of the pixel of interest p ′ in the image of the triangular area s′t′u ′ after deformation corresponds to the position p in the image of the triangular area stu before deformation. The calculation of the position p is performed as follows. First, a coefficient m1 and a coefficient m2 for expressing the position of the pixel of interest p ′ as a sum of a vector s′t ′ and a vector s′u ′ as shown in the following equation (2) are calculated.

Next, by using the calculated coefficient m1 and coefficient m2, the position p is obtained by calculating the sum of the vector st and the vector su in the triangular area stu before deformation according to the following equation (3). .

When the position p in the untransformed triangular area stu obtained by calculation coincides with the center position of a predetermined pixel of the image before deformation, the pixel value of the pixel is set as the pixel value of the image after deformation. . On the other hand, when the position p in the triangular area stu before deformation obtained by the calculation is a position deviated from the center position of the predetermined pixel of the image before deformation, the pixel values of the pixels around the position p are changed. The pixel value at the position p is calculated by the interpolation operation such as the bicubic used, and the calculated pixel value is set as the pixel value at the position p ′ of the image after deformation.

By calculating the pixel value for each pixel in the image of the transformed triangular area s′t′u ′ as described above, the image of the triangular area stu can be transformed into the image of the triangular area s′t′u ′. Done.

In other words, if this principle is applied to correction value mapping, the correction unit 52 divides the face area FA into triangular areas at the control points, and for each triangular area of the face area FA, For each pixel, the coefficient m1 and the coefficient m2 are calculated by Expression (2). Then, the correction unit 52 calculates the sum of the vector st and the vector su in the triangular area of the correction intensity model MA corresponding to the triangular area of the face area FA by using the calculated coefficient m1 and coefficient m2. Thus, the position on the correction intensity model MA corresponding to the pixel of the face area FA is obtained. Then, the correction unit 52 maps the correction value obtained from the correction value of the section at the obtained position or the correction value around the obtained position to the face area FA.

  As described above, the correction value is mapped to the face area FA.

Next, in step S24 (FIG. 10), the correction unit 52 performs a smoothing process on the face area FA according to the mapped correction value.

Specifically, initial image data PID represented by gradation values of the RGB color system of the face area FA
Are converted into image data PIDL represented by gradation values of the L ^* a ^* b ^* color system. Then, an average value La of the lightness L ^* of all the pixels of the image data PIDL is calculated. Then, the brightness adjustment amount d
L is calculated by equation (1), and a tone curve as shown in FIG. 7 is generated based on the calculated adjustment amount dL. Then, image data PIDL is obtained according to the tone curve.

The processing up to this point is the same as the processing by the correction unit 24 in FIG. Thereafter, the correction unit 52 reads out the correction values (FIG. 12) mapped to the respective pixels of the face area FA, multiplies the image data PIDL previously obtained, and uses the brightness obtained as a result to determine the face area. The brightness of each pixel of FA is adjusted. That is, the greater the correction value, the greater the brightness can be adjusted. Then, the correction unit 52 converts the image data PIDLr generated in this way into RGB color system gradation values (0 to 0).
255) is converted into image data PIDr.

In this way, when the smoothing process according to the mapped correction value is performed on the face area FA, the process ends.

  As described above, the second skin beautification process Z2 is performed.

As described above, since the face area FA is smoothed with different correction strength depending on the portion in the face area FA, smoothing processing is performed with strong correction strength for a part of the face area FA, and for certain parts. Smoothing processing can be performed with weak correction strength. That is, an effective smoothing process can be performed.

In addition, as described above, the correction value is mapped to the face area FA using the correction intensity model MA, so that the correction value for the smoothing process can be set easily. For example, it is possible to actually detect wrinkles and spots from the face area FA and calculate the correction intensity according to the density, but according to the present embodiment, the correction intensity model MA is masked to the face area FA. Just do
A correction value can be set for the face area FA.

Also, as described above, since the correction value is mapped based on the principle of image deformation in the triangular area, for example, even when the face is facing the left, right, up, or down instead of the front, A correction value can be appropriately set in the face area FA.

In the above description, the case where one correction strength model MA is used has been described as an example. However, for example, a correction strength model MA may be provided for each age, sex, and race. For example, since the face of an older person has more wrinkles on the outer corner of the eye than a young person, a higher correction value is set for that area in order to increase the correction intensity of the outer corner. A model MA can be prepared.

When a plurality of corrected intensity models MA are prepared as described above, the corrected intensity model MA is selected according to a command (for example, input) such as age and sex from the user. It is also possible to detect the amount of wrinkles of the user by image processing and select the correction strength model MA based on the detection result.

In the above description, the case of performing the smoothing process by adjusting the brightness has been described as an example. However, the smoothing process using other parameters such as the saturation can be performed without being limited to the brightness. Further, as long as the image processing can be performed according to some correction strength, the present invention is applied not only to the smoothing processing but also to the processing of whitening the teeth and the processing of clarifying the eye outline, for example. Can do.

In the above description, the non-correction area FB is the image area of the organ, but other areas that are not subjected to color tone correction can be set as the non-correction area FB.

In the above description, the ink jet printer 1 has been described as an example. However, the present invention can be applied to a printer other than the ink jet method and can be applied to a digital camera or a photo viewer as long as the image is presented to the user. it can.

In the above, the processing shown in FIG. 3 and FIG. 10 is executed in the printer 1, but it can also be executed in a host computer connected to the printer 1, for example.

The above processing functions can be realized by a computer. In that case, a program describing the processing contents of the functions that the printer 1 should have is provided. By executing the program on a computer, the above processing functions are realized on the computer. The program describing the processing contents can be recorded on a computer-readable recording medium. Examples of the computer-readable recording medium include a magnetic recording device, an optical disk, a magneto-optical recording medium, and a semiconductor memory. Examples of the magnetic recording device include a hard disk device (HDD), a flexible disk (FD), and a magnetic tape. On the optical disc
DVD (Digital Versatile Disk), DVD-RAM, CD-ROM (Compact Disk ROM
CD-R (Recordable) / RW (ReWritable). For magneto-optical recording media, M
O (Magneto-Optical disk).

When distributing the program, for example, a DVD or CD on which the program is recorded
-Portable recording media such as ROM are sold. It is also possible to store the program in a storage device of a server computer and transfer the program from the server computer to another computer via a network.

The computer that executes the program stores, for example, the program recorded on the portable recording medium or the program transferred from the server computer in its own storage device. Then, the computer reads the program from its own storage device and executes processing according to the program. The computer can also read the program directly from the portable recording medium and execute processing according to the program. Further, each time the program is transferred from the server computer, the computer can sequentially execute processing according to the received program.

In the above embodiment, a part of the configuration realized by hardware may be replaced with software, and conversely, a part of the configuration realized by software may be replaced by hardware. .

FIG. 3 is a block diagram illustrating a hardware configuration example of a printer according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating a functional configuration example of a printer for executing first skin beautification processing in the printer illustrated in FIG. 1. It is a flowchart which shows the flow of the 1st skin beautification process performed in the printer shown in FIG. It is a figure which shows the example of arrangement | positioning of the control point in the statistical model performed in the printer shown in FIG. It is a figure which shows the example of the detection result of the face area | region performed in the printer shown in FIG. It is a figure which shows the example of the mask image FM at the time of processing in the printer shown in FIG. It is a figure which shows the tone curve at the time of processing in the printer shown in FIG. It is a figure which shows the other example of the mask image FM at the time of processing in the printer shown in FIG. It is a block diagram which shows the functional structural example of the printer for performing the 2nd skin beautification process in the printer shown in FIG. It is a flowchart which shows the flow of the 2nd skin beautification process performed in the printer shown in FIG. It is a figure which shows the example of the correction | amendment intensity | strength model at the time of processing in the printer shown in FIG. It is a figure which shows the example of the mapping result of the correction value to the face area FA performed in the printer shown in FIG. It is a figure explaining the mapping method of the correction value performed in the printer shown in FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Printer, 11 CPU, 12 Internal memory, 13 Operation part, 14 Display part, 15 Printer engine, 16 Card I / F, 21 Face area detection part, 22
Non-correction area detection unit, 23 correction area specifying unit, 24 correction unit, 25 output control unit,
51 Face Area Detection Unit (Face Area Detection Unit), 52 Correction Unit (Correction Unit), 53 Output Control Unit

Claims (7)

An image processing apparatus for correcting the color tone of an image,
Face area detecting means for detecting a face area including a face image in the image;
Correction means for correcting the color tone of the image with a predetermined correction amount,
The image processing apparatus, wherein the correction unit specifies the correction amount based on a position of a predetermined area in an image area representing a face in the face area. The correction means includes
A correction strength model having a face shape, wherein a correction strength model in which a correction value representing the correction strength is set is obtained,
The image processing apparatus according to claim 1, wherein the correction value set in the correction intensity model is mapped to the face area, and a color tone of the face area is corrected with the mapped correction value. The image processing apparatus according to claim 1, wherein a correction amount according to a face position is set in the correction intensity model. The image processing apparatus according to claim 1, wherein the magnitudes of the eye position correction amount and the cheek position correction amount are different from each other. The image according to any one of claims 1, 2, 3, and 4, wherein the correction unit gradually decreases a correction amount of a color tone in a contour direction of the face area. Processing equipment. An image processing method of an image processing apparatus for correcting the color tone of an image, comprising:
A face area detecting step for detecting a face area including a face image in the image;
A correction step of correcting the color tone of the image with a predetermined correction amount,
The image processing method in which the correction step specifies the correction amount based on a position of a predetermined area in an image area representing a face in the face area. A program for causing a computer to execute image processing for correcting the color tone of an image,
A face area detecting step for detecting a face area including a face image in the image;
A correction step of correcting the color tone of the image with a predetermined correction amount,
The correction step is a program for causing a computer to execute image processing for specifying the correction amount based on a position of a predetermined area in an image area representing a face in the face area.