JP2009251634A - Image processor, image processing method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To achieve image correction for improving appearance of a face image more naturally. <P>SOLUTION: A printer 1 is a color ink jet printer conforming to printing of an image based on image data acquired from a memory card 18 or the like, which is called direct printing. A face area detection unit 21 analyzes a target image TI, input to the printer 1, to be an object for face correction process, and detects a face area FA including a face image where a face part of a person on the target image TI is photographed. A correction unit 23 performs image correction for a specified correction area FC. <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 that are preferably applied to face image correction.

Due to the difference in appearance between a 3D object and a 2D object, the face of a person shown on an image (ie, a 2D face) is usually more than an actual face (ie, a 3D face). It is said to look big. So make the face look slender against the image of the person,
Image correction has been developed to improve the appearance of face images.

Patent Document 1 discloses image correction for detecting an area of an image in which a person's face portion is captured from a person's image and deforming the contour portion of the face in that area so that the width of the cheek becomes narrower. Has been. By performing such image correction, the face image appears to be a slender face.

Japanese Patent Laid-Open No. 2004-318204

However, in this method, since the outline of the face itself is deformed, the peripheral portion of the face may be distorted, resulting in an uncomfortable face image.

The present invention has been made in view of such a situation, and more naturally makes it possible to improve the appearance of a face image.

An image processing apparatus according to the present invention is an image processing apparatus for correcting a color tone of an image, for detecting a face area including a face image in the image, and for masking a part constituting the face in the face area. Using a part mask, specifying means for specifying a correction area for performing color tone correction from the face area, and correction means for performing color tone correction for the correction area.

The specifying unit generates a part mask image in which the part mask corresponds to the size of the face area, detects a skin color area from the area of the face area FA masked by the part mask image, and corrects the detected skin color area It can be.

A plurality of part masks are provided according to the face direction, and the specifying unit detects the face direction based on the face region, acquires the part mask corresponding to the detected face direction, and acquires the acquired part mask Can be used to specify the correction area.

A correction weight is set for the part mask, and the correction means is based on the correction weight,
Color correction can be performed on the correction area.

An image processing method or program according to the present invention is an image processing method of an image processing apparatus that corrects the color tone of an image, or a program that causes a computer to execute image processing that corrects the color tone of an image. A detection step for detecting a face area including the image of the image, and a specifying step for specifying a correction area for performing tone correction from the face area using a part mask for masking a part constituting the face in the face area; And a correction step for performing color tone correction on the correction area.

In the image processing device, the image processing method, or the program of the present invention, a face area including a face image in the image is detected, and a part mask for masking a part constituting the face in the face area is used, From the face area, a correction area for performing tone correction is specified, and tone correction is performed on the correction area.

According to the present invention, it is possible to improve the appearance of a face image more naturally.

  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 (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. For example, the CPU 11 performs image correction processing (hereinafter referred to as face correction processing Z) for making a face look slender with respect to an image including a face image.
1).

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 composed of a liquid crystal display or the like, and displays an image corresponding to 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 diagram illustrating a functional configuration example of the printer 1 for executing the face correction process Z1.
This function can be realized by the CPU 11 executing a program stored in the internal memory 12.

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

The correction area specifying unit 22 as the specifying means corrects a predetermined part of the face area FA (a correction area (
Hereinafter, it is specified as a correction area FC). For example, as will be described later, the part mask is used to identify the portion of the face area FA as the correction area FC.

In the case of this example, a mask (hereinafter referred to as cheek mask MA) that specifies the cheek periphery is used, and the area around the cheek of the face area FA is specified as the correction area FC. The cheek mask MA is stored in the internal memory 12, for example.

The correction unit 23 as a correction unit performs image correction on the specified correction area FC. In this example, as described later, the color tone of the correction area FC (for example, the area around the cheek) is corrected.

The output control unit 24 generates display data from the image data of the target image TI that has been subjected to image correction (in this example, color correction), and supplies the display data to the display unit 14 for display or printing. Data is generated and supplied to the printer engine 15 to print an image based on the print data.

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

In step S <b> 1, the face area detection unit 21 performs a target image T that is a target of the face correction process Z <b> 1.
A face area FA including a face image in which the face portion in I is shown is detected.

Specifically, the face area detection unit 21 analyzes the target image TI and extracts a rectangular area that is assumed to include a face image as the face area FA. The detection of the face area FA is, for example, a human eye,
The detection can be performed using a known detection method such as a pattern matching method using a template representing a basic shape such as a nose and a mouth (see Japanese Patent Application Laid-Open No. 2006-279460).

FIG. 4 is a diagram illustrating an example of the detection result of the face area FA. As described above, the face area FA is a rectangular area including images of both eyes, nose, mouth, and jaw of the face image of the person included in the target image TI. The face area detection unit 21 specifies the face area FA based on, for example, the coordinates of the vertices of the face area FA.

In step S2, the correction area specifying unit 22 uses the cheek mask MA to specify a portion around the cheek of the person as the correction area FC (hereinafter referred to as a correction area specifying process Z2).
Execute.

FIG. 5 is a flowchart showing the flow of the correction area specifying process Z2. The correction area specifying process Z2 will be described with reference to this flowchart.

In step S11, the correction area specifying unit 22 reads the cheek mask MA from the internal memory 12.
To get.

FIG. 6 is a diagram illustrating an example of the cheek mask MA. This cheek mask MA has a data structure composed of 32 × 32 sections, with a section corresponding to a pixel (hereinafter, appropriately referred to as a pixel) as one unit. In the drawing, a value of 1 is set in a hatched area, and a value of 0 is set in a hatched area (that is, a white area in the figure).

FIG. 7 is a diagram three-dimensionally showing the values set in each section of the cheek mask MA in FIG.
In a section in which the value 1 is set, a cube having a height corresponding to the size of the value 1 is set up.

Note that the cheek mask MA is prepared as a table in which, for example, coordinate values of sections and data representing value 1 or value 0 are associated with each other.

Next, in step S12, the correction area specifying unit 22 generates an image (hereinafter referred to as a cheek mask image FM) in which the cheek mask MA is associated with the size of the face area FA.

Specifically, when the size of the face area FA is larger than the size of the cheek mask MA (that is, when the number of pixels of the face area FA is larger than the number of pixels of the cheek mask MA),
Pixel complementation is performed according to the ratio of both sizes (that is, the enlargement ratio), and a cheek mask image FM having the same size as the face area FA is generated. Further, when the size of the face area FA is smaller than the size of the cheek mask MA (that is, when the number of pixels of the face area FA is smaller than the number of pixels of the cheek mask MA), the size of both of the faces of the cheek mask MA is larger. The pixels are thinned out according to the ratio (that is, the reduction ratio), and a cheek mask image FM having the same size as the face area FA is generated.

Next, in step S <b> 13, the correction area specifying unit 22 performs the cheek mask image F of the face area FA.
The area masked with M is specified as an area that can become the correction area FC (hereinafter referred to as a correction candidate area FB). Specifically, the correction area specifying unit 22 superimposes the cheek mask image FM on the face area FA, and the pixel at the position corresponding to the pixel of the face area FA whose pixel value is 1 in the cheek mask image FM. Is identified as the correction candidate region FB.

FIG. 8 is a diagram conceptually showing the correction candidate area FB. In the example of FIG. 8, a region to which hunting is applied (that is, a region of a pixel in the face region FA at a position corresponding to a pixel whose pixel value of the cheek mask image FM is 1) is a correction candidate. It is specified as a region FB.

In step S <b> 14, the correction area specifying unit 22 determines the correction area F from the correction candidate area FB.
C is specified.

Specifically, the skin color area is specified from the correction candidate area FB. Here, the correction candidate area FB
A method for specifying the skin color area from the above will be described.

First, the correction area specifying unit 22 calculates the RGB color system gradation value of each pixel in the correction candidate area FB,
Convert to gradation value of HSB color system.

Then, the correction area specifying unit 22 performs the HSB color system hue (H) of each pixel in the correction candidate area FB.
), Saturation (S), and lightness (B), it is determined whether the skin color.

The hue (H) is a value representing an angle from 0 degrees to 360 degrees, for example, and indicates the type of color. For example, 0 degree indicates a red hue (H). The saturation (S) is a value from 0 to 255, for example, and indicates the vividness of the color. It means that whiteness increases, so that the value of saturation (S) is large. For example, the saturation (S) of the gray scale is 0. The brightness (B) is, for example, the value 0
To a value of 255, indicating the brightness of the color. For example, the brightness (B) of black is 0.

FIG. 9 shows hue (H), saturation (S), and brightness (
It is a figure which shows the example of the range of B).

As shown in the upper side of FIG. 9, the hue (H) ranges from 250 degrees to 110 degrees (about 2 degrees).
For the range of 20 degrees), the saturation (S), the range from the value 10 to the value 90, and for the lightness (B), the range from the value 10 to the value 100 is the range determined as the skin color. For example,
When the HSB value of a pixel to be determined is within this determination range, the pixel is determined to be a skin color pixel.

The general skin color determination range is 3 for hue (H) as shown in the lower side of FIG.
For a range of 50 to 20 degrees (ie, a range of 30 degrees) and saturation (S), a value of 20 to a value of 6
The range of 0 and the brightness (B) are in the range of 30 to 70. That is, the skin color determination range used in the present embodiment is wider than the general skin color determination range, and the reason will be described later.

In this way, the skin color area is detected from the correction candidate area FB and specified as the correction area FC.

FIG. 10 is a diagram showing the correction area FC identified from the correction candidate area FB shown in FIG.
When the correction area FC is specified, the correction area specifying process Z2 ends, and the process proceeds to step S3 in FIG.

In step S3, the correction unit 23 performs color tone correction (hereinafter referred to as a shadow correction process Z3) on the correction area FC based on a predetermined correction amount. In this example, the brightness (B) of each pixel belonging to the correction area FC is lowered by a predetermined value TA. When the brightness (B) is lowered by the value TA in this way, when displayed or printed, the portion appears dark and appears to be shaded.

Note that the lightness (B) reduction value TA can be obtained by, for example, obtaining an average value of the lightness (B) of the correction area FC and the face area FA, and setting the average value or a predetermined percentage of the average value. Further, the standard deviation of the brightness (B) of the correction area FC and the face area FA can be obtained and used as the value.

Further, it is also possible to determine the lightness (B) reduction value TA using the pixel values of the pixels adjacent to the correction area FC other than the correction area FC of the face area FA.

Next, in step S4, the correction unit 23 determines the boundary between the correction region FC and another region (hereinafter referred to as the boundary of the correction region FC) for the correction region FC that has been subjected to the shadow correction processing Z3 in step S3. Processing for blurring (hereinafter referred to as blurring processing Z4) is performed.

When the brightness (B) of the correction area FC is lowered by the value TA, the correction area FC and the correction area FC
A difference in brightness (B) from other areas adjacent to the area increases, and the boundary of the correction area FC may become unnaturally conspicuous.

Therefore, for example, the area of the correction area FC in which the distance from the boundary of the correction area FC is within a predetermined range (
Hereinafter, the brightness (B) lowered by a predetermined value TA is returned, for example, by a half value TA.

That is, since the brightness (B) of the boundary portion of the correction area FC is lowered stepwise, the boundary portion of the correction area FC becomes inconspicuous.

As described above, first, the brightness (B) of the correction area FC is uniformly reduced so that the pixels in the boundary area are restored to some extent so that the boundary portion of the correction area FC is not noticeable. Each pixel value of the correction area FC is changed to the cheek mask M so that the pixel value of
Correction can also be made according to the pixel value (ie, weight) of the corresponding pixel of A.

FIG. 11 is a diagram three-dimensionally showing the weights set for each pixel for the cheek mask MA in which correction weights are set for each pixel.

In the example of FIG. 11, pixel values of the cheek mask MA as correction weights are set in stages. By using this cheek mask MA, the magnitude of the brightness (B) of the correction area FC can be lowered step by step.

As described above, when the blurring process Z4 is performed on the correction area FC, the face correction process Z1 ends (FIG. 3). The target image TI that has undergone the shadow correction process Z3 in the face correction process Z1 is supplied to the output control unit 24, where display data or print data is generated from the image data of the target image TI. .

  The face correction process Z1 is performed as described above.

  FIG. 12 is a diagram collectively showing the processing results in the face correction processing Z1 described above.

  In the uppermost part of FIG. 12, an image corresponding to the target image TI is shown.

In the next stage, an image corresponding to FIG. 8 is shown. In the figure, the darkened part is
This is the correction candidate area FB.

Further, in the next stage, an image corresponding to FIG. 10 is shown. In the figure, the darker portion is the correction area FC. In the example of FIG. 12, a part of the neck is also exposed, so that part is also detected as a skin color area and included in the correction area FC.

The lowermost part of FIG. 12 shows an image that has been subjected to the shadow correction process Z3 and the blurring process Z4. The shadow correction process Z3 makes the correction area FC appear dark and shaded, and the blurring process Z4 makes the boundary portion of the correction area FC inconspicuous. Each diagram in FIG. 12 schematically shows the processing result in the face correction processing Z1. Accordingly, the shade density and the degree of blurring in the lowermost stage in FIG. 12 are drawn differently from those in an actual photographic image, for example. FIG. 12 is for explaining the face correction processing Z1, and the image shown in FIG. 12 is not generated as a display image in the actual processing.

As described above, since the face image is corrected so that the brightness around the cheek is lowered and the cheek portion is slightly darkened, the face image can be corrected to a three-dimensional image with a shadow on the cheek portion. . That is, the face image can be corrected so that it looks like a slender face.

Further, as described above, since the color tone of the correction area FC is corrected, the face outline itself is not deformed and the surroundings are not distorted. That is, it can be seen as a slim face in a more natural manner. The darkness of the shadow may be set so that the face image after correction is close to the impression of the actual face, and as a so-called fan function, the face looks more slender than the impression of the actual face. It can also be done.

Further, as described above, the correction area FC is specified using the part mask (for example, cheek mask MA), and therefore the correction area FC is easily specified without being affected by the accuracy of detection of the face area FA. be able to. The part mask is created, for example, by cutting out eyes, mouths, or chin portions from many human face images and using them as learning data. For example, the cheek portion can be obtained by repeating a predetermined calculation based on the position of the mouth and the position of the contour without using the part mask.

In addition, as described above, an image around a person's face including a part of the neck and the background over the cheek is represented by the face region F.
A (FIG. 4), and the skin color determination range (upper side in FIG. 9) when specifying the correction area FC is wider than the normal skin color determination range (lower side in FIG. 9). Not only the cheeks but also the base of the face and neck can be shaded, and the face can be more effectively given a three-dimensional effect. For example, when only the face outline is set as the face area FA, the base of the face and the neck does not become the correction area FC. In addition, the hue (H), saturation (S), and brightness (B) of the image at the base of the face and neck are not usually in the range of the general skin color determination range (lower side in FIG. 9). When skin color is determined within a general skin color determination range, it is not determined as skin color and is not included in the correction area FC.

In the above description, the tone correction for the cheek periphery is performed, but the tone correction can be performed for other portions. For example, the brightness around the nose can be lowered so that the nose looks relatively high.

In the above description, the image is dark and shaded, but conversely, it can be made bright. For example, if the brightness of the nasal muscle portion is increased, the face can be shown through the so-called nasal muscle.

In the above, the case where one cheek mask MA is used has been described as an example. However, another cheek mask MA having a different shape of the cheek region to be masked is prepared, or different from the cheeks around the nose. Further prepare a part mask for specifying the part (that is, prepare a plurality of part masks for each part), and use the part mask according to the user's command (that is, upon request) to correct the correction area FC.
Can also be specified.

  By doing so, more effective color tone correction according to the application can be performed.

FIG. 13 is a diagram showing another example of the cheek mask MA. By using this cheek mask MA, it is possible to mask up to a deeper part of the cheek, so that a shadow can be added to a deeper part of the cheek.

In the above description, the correction area FC is specified using the part mask. However, the correction area FC can also be specified using a mathematical face model. Here, a mathematical face model is a mathematical expression of a face shape expressed by control points placed on the contour of a face with high contrast and the contour of an organ (eyebrows, eyes, nose, mouth, etc.). It is averaged.

In the above description, the image in which the user is facing the front has been described as an example. However, for example, by preparing the cheek mask MA corresponding to the face direction, the above-described case may be applied to a face image having a direction. The face correction process Z1 can be performed in the same manner as described above.

FIG. 14 is a flowchart showing the flow of the correction area specifying process Z2 (step S2 in FIG. 3) when the face correction process Z1 is executed on a face image having a direction. The correction area specifying process Z2 will be described with reference to this flowchart. Note that the processing (steps S1, S3, S4, and S5) other than step S2 in FIG. 3 is performed in the same manner as described above.

  In step S51, the correction area specifying unit 22 estimates the face orientation.

FIG. 15 is a diagram illustrating a face orientation detection method. In the example of FIG. 15, in the face area FA,
Three rectangular areas that are assumed to contain images of the right eye, left eye, or mouth are respectively the right eye area EA.
(R), a left eye area EA (l), and a mouth area EB (hereinafter referred to as an organ area if not individually distinguished). Similar to the detection of the face area FA, the detection of the organ area is performed using a known detection method such as a pattern matching method using a template. The organ area is specified by, for example, the coordinates of the vertices of each organ area.

Next, the center point Ce (r) of the right eye area EA (r) and the center point Ce (l) of the left eye area EA (l)
) (Hereinafter referred to as reference width Wr) and the distance between the center point Cm of the mouth region EB and the line segment CL (hereinafter referred to as reference height Hr) are respectively calculated. Is done.

Next, a ratio (Hr / Wr) between the reference height Hr and the reference width Wr is calculated as the determination index DI, and the face orientation is estimated based on the determination index DI. In the example of FIG. 15, when the value of the determination index DI is greater than or equal to the threshold T1 and less than the threshold T2, it is estimated that the orientation of the face image is the front direction. Further, when the value of the determination index DI is less than the threshold value T1, it is estimated that the orientation of the face image is upward or downward, and when the value of the determination index DI is equal to or greater than the threshold value T2, It is estimated that the orientation of the image is right-handed or left-handed.

Here, “upward swing” means the direction of the image with the face of the subject person facing up, and “downward swing” means the orientation of the image with the face of the subject person facing down. . Also, “right swing”
Means the direction of the image in which the face of the subject person is looking to the right when viewed from the viewer side of the image (ie, the person is actually facing the left). Means the orientation of the image facing the left as viewed from the viewer side of the image (that is, the person is actually facing the right). Note that the direction of the image is up or down is also referred to as “up and down”, and that of right or left is also referred to as “left and right”.

When the orientation of the face image is right-handed or left-handed, compared to the case of face-up,
While the reference height Hr hardly changes, the reference width Wr is considered to be small. Therefore, when the orientation of the face image is right-handed or left-handed, compared to the case of face-up,
The value of the determination index DI (= Hr / Wr) increases. On the contrary, when the orientation of the face image is upside down or downside, the reference width Wr is hardly changed, but the reference height Hr is considered to be small as compared with the case of facing the front. Accordingly, the determination index DI (= Hr / Wr) is greater when the face image is in the upward or downward direction than in the front direction.
The value of becomes smaller.

The threshold value T1 and the threshold value T2 are statistically determined from the determination index DI (ratio of the reference width Wr to the reference height Hr) of a predetermined number of face sample images. The predetermined threshold T1 and threshold T2 are stored in a predetermined area in the internal memory 12, and the determination index DI of the target image TI and the threshold T1 are stored.
Then, the face orientation is estimated using the threshold value T2.

Note that the left-right direction is determined by, for example, the width of the right-eye area EA (r) and the left-eye area EA.
It is detected by comparing with the width of (l). That is, for example, if the width of the right eye area EA (r) is larger, it is estimated that the camera is swung right, and if the width of the left eye area EA (l) is larger, it is estimated that it is swung left.

Further, the orientation of the upper and lower sides depends on the mouth area M with respect to the width of one eye area EA.
The ratio of the width of A is calculated, and if the value is larger than a predetermined threshold, it is estimated to be up, and if it is smaller than the predetermined threshold, it is estimated to be down.

  In this way, the face orientation is estimated.

Next, in step S <b> 52, the correction area specifying unit 22 acquires the cheek mask MA corresponding to the estimated face orientation from the internal memory 12. It is assumed that cheek masks MA for leftward swing, rightward swing, upward swing and downward swing are stored in the internal memory 12, respectively.

For example, as shown in the lower side of FIG. 16, the right-sided cheek area is wider and the left side of the person is compared with a face facing the front as shown in the upper side of FIG. 16. The cheek area becomes narrower. Although illustration thereof is omitted, in the left-handed face image, the region of the cheek portion on the left side of the person is widened and the region of the cheek portion on the right side is narrowed.

Further, as shown in the upper side of FIG. 17, in the upward face image, the region of the chin portion is broadened as a whole. On the other hand, as shown in the lower side of FIG. 17, in the downward swing image, the region of the jaw portion is narrowed as a whole.

Accordingly, the internal memory 12 has a right cheek mask MA having a wide right cheek area and a narrow left cheek area, a wide cheek mask area on the left cheek mask, and a right cheek area. Cheek mask MA for swinging left, the cheek mask MA for swinging up with a wide jaw region, and cheek for swinging down, with a narrow jaw region Each mask MA is stored.

That is, when the face orientation is left-handed, the correction area specifying unit 22 sets the left-handed cheek mask MA,
When the face orientation is right-handed, the right-handed cheek mask MA is used. When the face is face-up,
When the upward cheek mask MA is face down, the downward cheek mask MA is acquired from the internal memory 12.

In step S53 to step S55, step S12 to step S in FIG.
Since the same processing as in the case of 14 is performed, the description thereof is omitted.

As described above, the correction area specifying process Z2 when the face image has a direction is performed.

In the above description, the inkjet printer 1 has been described as an example. However, the present invention can be applied to a printer other than the inkjet printer, 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 embodiment, the processes shown in FIGS. 3, 5, and 14 are executed in the printer 1. However, for example, the processes can be executed in a host computer connected to the printer 1. It is.

The above processing functions can be realized by a computer. In that case, a program describing the processing contents of the functions that the image processing apparatus 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. Optical disks include DVD (Digital Versatile Disk), DVD-RAM, CD-ROM (Compact Disk)
ROM), CD-R (Recordable) / RW (ReWritable), and the like. Magneto-optical recording media include MO (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. .

The process shown in FIG. 3, FIG. 5, or FIG. 14 is not necessarily performed in time series, as well as the process in which each step is performed in time series in the order described. ,
It includes processes that are executed in parallel or individually. For example, the process of step S4 in FIG. 3 can be omitted as appropriate.

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 diagram illustrating a functional configuration example for executing face correction processing in the printer illustrated in FIG. 1. 2 is a flowchart showing a flow of face correction processing Z1 executed in the printer shown in FIG. It is a figure which shows an example of the detection result of the face area FA performed in the printer shown in FIG. 3 is a flowchart showing a flow of correction area specifying processing Z2 executed in the printer shown in FIG. It is a figure which shows the example of the cheek mask MA at the time of processing in the printer shown in FIG. It is the figure which showed the pixel value of cheek mask MA of FIG. 6 in three dimensions according to the set value. FIG. 2 is a diagram conceptually showing a correction candidate area FB when processed in the printer shown in FIG. 1. It is a figure which shows the example of the range of the skin color determination at the time of processing in the printer shown in FIG. It is a figure which shows the example of the correction | amendment area | region FC at the time of processing in the printer shown in FIG. It is the figure which showed in three dimensions the pixel value of cheek mask MA at the time of processing in the printer shown in FIG. 1 according to the set weight. It is a figure which shows the photographic image corresponding to the process step in the image correction process Z1 performed in the printer shown in FIG. It is a figure which shows the other example of cheek mask MA at the time of processing in the printer shown in FIG. It is a flowchart which shows the flow of the correction area | region identification process Z2 performed in the printer shown in FIG. 1 when a face image has direction. It is a figure which shows the method of face direction estimation performed in the printer shown in FIG. It is a figure which shows the change of a face image with the direction of a face. It is another figure which shows the change of a face image with direction of a face.

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 (detection means), 22 Correction area specification part (specification means), 23 Correction Part (correction means), 24 output control part

Claims (6)

An image processing apparatus for correcting the color tone of an image,
Detecting means for detecting a face area including a face image in the image;
Using a part mask for masking a part constituting the face in the face area, specifying means for specifying a correction area for performing the color tone correction from the face area;
An image processing apparatus comprising: correction means for performing the color tone correction on the correction area. The specifying unit generates a part mask image in which the part mask is made to correspond to the size of the face area, detects a skin color area from the area of the face area FA masked by the part mask image, and detects the skin color The image processing apparatus according to claim 1, wherein an area is the correction area. A plurality of the part masks are provided according to the orientation of the face,
The identification unit detects a face direction based on the face region, acquires the part mask corresponding to the detected face direction, and specifies the correction region using the acquired part mask. The image processing apparatus according to 1. A correction weight is set in the part mask,
The image processing apparatus according to claim 2, wherein the correction unit performs color correction on the correction region based on the correction weight. An image processing method of an image processing apparatus for correcting the color tone of an image, comprising:
A detecting step for detecting a face area including a face image in the image;
A specifying step of specifying a correction area for performing the color tone correction from the face area using a part mask for masking a part constituting the face in the face area;
A correction step of performing the color correction on the correction region. A program for causing a computer to execute image processing for correcting the color tone of an image,
A detecting step for detecting a face area including a face image in the image;
A specifying step of specifying a correction area for performing the color tone correction from the face area using a part mask for masking a part constituting the face in the face area;
A program that causes a computer to execute image processing including: a correction step that performs the color correction on the correction area.

Images