JP2011259053A - Image processing apparatus and image processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing apparatus and an image processing method capable of performing image processing such as making a specific section of a body appear to be thin or swelling the section to the contrary.SOLUTION: The image processing apparatus captures a subject image (S1), detects the position of a face image in the subject image on the basis of the captured image (S9), specifies the area of the specific portion of the person of the detected face image as a correction area(13, S19), subjects the correction area to anti-aging image processing on the basis of the face age of the face image (S27), and displays an image obtained by subjecting the correction area to the anti-aging image processing (S29).

Description

  The present invention relates to an image processing device and an image processing method, and more particularly to an image processing device and an image processing method in an electronic camera or the like that can detect a face from a subject image and correct the body shape of the subject.

  In general, regardless of gender, a person becomes fat around the trunk due to the accumulation of subcutaneous fat with age. In particular, women tend to be worried about changes in their body shape due to aging, and hate to be shown in photographs, and they want to show their fat torso thin and rejuvenate.

  A technique for improving the appearance of a person in the subject image is to reduce the center of an image such as a photo that contains a person, enlarge and correct both ends of the image so that the aspect ratio of the image is changed, and center the image. There is a technology that makes a photographed person look slim and looks good. Such a slim function is mounted on some models such as a multifunction printer (MFP (Multifunction Peripheral) printer).

  Further, as a technique for improving the appearance of a person in a subject image, an electronic camera as disclosed in Patent Document 1 has been proposed in addition to the technique described above. The electronic camera captures a subject image with an image sensor, detects a face area in the shooting screen based on the output, extracts a feature amount of the subject's face from the face area, and based on the feature amount, Execute inference processing for either age or gender. Then, based on the result of this inference process, at least one of exposure correction, soft focus correction, beautiful skin correction for adjusting the skin color saturation, and correction for making a person look slim with respect to a recording image photographed by the image sensor. Run one.

JP 2007-280291 A

  The electronic camera disclosed in Patent Document 1 performs correction to make a person look slim, but this correction only changes the shooting state and can only make the whole body look slim. That is, it is not possible to make a part of the body thin, such as around the trunk of the body that has become thick due to the accumulation of subcutaneous fat or the like with aging. On the other hand, a specific part such as the buttocks can be bulged to show a youthful and attractive body line.

  The present invention has been made in view of such circumstances, and a specific part of the body such as visually showing a part of the body around the trunk that has become thick due to accumulation of subcutaneous fat with age, etc. It is an object of the present invention to provide an image processing apparatus and an image processing method capable of performing image processing such as thinning and conversely swelling.

  In order to achieve the above object, an image processing apparatus according to a first invention comprises a display means for displaying a captured image, a storage means for storing face age information indicating a relationship between a face image and age, and a display means. Face detection means for detecting the position of the face of the displayed image, and determination means for determining the face age of the face image detected by the face detection means based on the face age information stored in the storage means A body region corresponding to the face image detected by the face detection unit, a correction region specifying unit for specifying the region as a region to be corrected, and the specified face image based on the face age of the determined face image. Anti-aging processing means for performing slimming processing on the region of the trunk and the image displayed on the display means are changed to an image on which the slimming processing has been performed by the anti-aging processing means. Comprising a Display Change means.

  An image processing apparatus according to a second invention is the image processing apparatus according to the first invention, wherein the correction area specified by the correction area specifying means passes through the center of the nose and the center of the eyes and substantially bisects the face image. When the central axis is the Y axis, a portion having a large color change in a direction substantially perpendicular to the Y axis is specified as a virtual straight line in the image having the face image, and a portion having a large color change on the virtual straight line is specified. It is a rectangular region composed of one side as both ends and one side having a length close to the face image from the virtual straight line along the Y-axis direction by a predetermined distance.

  According to a third aspect of the present invention, in the first aspect, the correction area specified by the correction area specifying means passes through the center of the nose and the center of the eyes, and substantially bisects the face image. When the central axis is the Y axis, in the image having the face image, a line substantially orthogonal to the Y axis at a position approximately three times the size of the face image from the end of the face image along the Y axis direction. As a virtual straight line, one side having both ends of a portion having a large color change on the virtual straight line, and a side having a length approaching the face image from the virtual straight line along the Y-axis direction by a predetermined distance; Are rectangular regions.

An image processing apparatus according to a fourth invention is the image processing apparatus according to the second or third invention, wherein the anti-aging processing means passes through a center position of the specified rectangular correction region and has a direction perpendicular to the Y axis. In the case of the X axis, the angle between the straight line connecting the center position and the corner of the rectangular correction area and the X axis is θ, and the length of the straight line connecting the center position and the corner of the rectangular correction area is 1. To determine the shape of an ellipse, M is an image adjustment coefficient for aligning the corrected image with the original image, G is a coefficient representing the slimming degree, K is a coefficient set to be 1 when Y is SINθ. When the coefficients of A and B are
X ′ = (X ² / A ² + Y ² / B ² ) * K * M * COSθ
K = (1-G) / SINθ * Y + G
Y '= Y
Correct to satisfy.

An image processing apparatus according to a fifth invention is the image processing apparatus according to the second or third invention, wherein the anti-aging processing means passes through a center position of the specified rectangular correction region and has a direction perpendicular to the Y axis. In the case of the X axis, the angle between the straight line connecting the center position and the corner of the rectangular correction area and the X axis is θ, and the length of the straight line connecting the center position and the corner of the rectangular correction area is 1. To determine the shape of an ellipse, M is an image adjustment coefficient for aligning the corrected image with the original image, G is a coefficient representing the slimming degree, K is a coefficient set to be 1 when Y is SINθ. And S2 (where S1 = 1 or S1 = 1) and S2 (where S2 = 1 or S2 = −1), the coefficients representing the orientation of the ellipse are A and B, respectively.
X ′ = 2 * S1 + (X ² / A ² + Y ² / B ² ) * K * M * COSθ * S2
K = (1-G) / SINθ * Y + G
Y '= Y
Correct to satisfy.

  An image processing apparatus according to a sixth invention is the digital camera according to any of the first to fifth inventions, wherein the image processing apparatus is capable of displaying a through image, and the display means displays the captured through image. The face detection means detects the face of the person imaged as the through image.

  According to a seventh aspect of the present invention, there is provided an image processing apparatus for converting a subject image into image data, a face detection unit for detecting a position of a face image in the subject image based on the image data, and a face image. Determination means for determining the face age of the face image detected by the face detection means based on the face age information stored in the storage means; Means, a correction area specifying means for specifying a region of the specific portion of the person in the face image detected by the face detection means as a region to be corrected, and the specific portion based on the face age of the determined face image. Anti-aging processing means for performing anti-aging image processing on the area, and display means for displaying the image subjected to the anti-aging image processing by the anti-aging processing means. To Bei.

  According to an eighth aspect of the present invention, there is provided an image processing apparatus comprising: a face detection unit that detects a position of a face image in a subject image; a storage unit that stores face age information indicating a relationship between the face image and age; and the storage unit A determination unit for determining a face age of the face image detected by the face detection unit based on the face age information stored in the image, and a region of a specific portion of the person in the face image detected by the face detection unit Correction area specifying means for specifying the area as a correction area, anti-aging processing means for performing anti-aging image processing on the area of the specific portion based on the face age of the determined face image, and the anti-aging processing means Display means for displaying the image subjected to the anti-aging image processing.

  An image processing method according to a ninth aspect includes a step of converting a subject image into image data, a step of detecting a position of a face image in the subject image based on the image data, and the detected face The step of specifying the region of the specific portion of the person of the image as the region to be corrected, and the face age information stored in the storage unit storing the face age information indicating the relationship between the face image and the age is read out, and the face age Determining a face age of the detected face image based on information, performing anti-aging image processing on the region of the specific portion based on the face age of the determined face image, and the anti-aging image Displaying the processed image.

  According to the present invention, a specific part of the body is shown thin, such as visually showing a part of the body around the trunk that has become thick due to the accumulation of subcutaneous fat, etc. with aging, etc. An image processing apparatus and an image processing method capable of performing image processing can be provided.

It is a block diagram which shows the electric constitution of the camera concerning 1st Embodiment of this invention. It is a figure explaining the image processing by an anti-aging process in the camera concerning 1st Embodiment of this invention. 6 is a flowchart illustrating processing in an anti-aging mode in the camera according to the first embodiment of the present invention. 6 is a flowchart illustrating processing in anti-aging correction in the camera according to the first embodiment of the present invention. It is a figure which shows the correction area | region and center point of anti-aging correction | amendment in the camera concerning 1st Embodiment of this invention. It is a figure which shows the 1st quadrant position in the correction area | region of anti-aging correction in the camera concerning 1st Embodiment of this invention. 4 is a graph showing coordinates after correction obtained at the time of anti-aging correction in the camera according to the first embodiment of the present invention. It is a figure which shows the coordinate calculation result after the correction | amendment in the 1st quadrant in anti-aging correction | amendment in the camera concerning 1st Embodiment of this invention. It is a figure which shows the position of the 1st quadrant-4th quadrant in anti-aging correction | amendment in the camera concerning 1st Embodiment of this invention. It is a figure which shows the coordinate calculation result after the correction | amendment in the 1st quadrant-4th quadrant in anti-aging correction in the camera concerning 1st Embodiment of this invention. It is a figure which shows an example of the relationship between the constant used at the time of calculation in anti-aging correction | amendment, and age in the camera concerning 1st Embodiment of this invention. It is a figure explaining the image processing by an anti-aging process in the camera concerning 2nd Embodiment of this invention. It is a flowchart which shows the process in anti-aging mode in the camera concerning 2nd Embodiment of this invention. It is a flowchart which shows the process in anti-aging correction | amendment in the camera concerning 2nd Embodiment of this invention. It is a graph which shows the coordinate calculation result after correction | amendment in the 1st quadrant in anti-aging correction | amendment in the camera concerning 2nd Embodiment of this invention. In the camera concerning 2nd Embodiment of this invention, it is a figure which shows the coordinate calculation result after correction | amendment in the 1st quadrant-4th quadrant in anti-aging correction | amendment. It is a flowchart which shows the process in anti-aging correction | amendment in the camera concerning 3rd Embodiment of this invention.

  Hereinafter, a preferred embodiment will be described using a camera to which the present invention is applied according to the drawings. The camera according to the first preferred embodiment of the present invention is a digital camera, has an imaging unit, converts a subject image into image data by the imaging unit, and converts the subject image based on the converted image data. A through image is displayed on the display unit arranged on the back of the main body. The photographer determines the composition and photo opportunity by observing the through image display. Further, when a through image is displayed, if a face is included in the subject image, an anti-aging process such as making a specific part such as a torso part of the subject look narrow is performed. At the time of the release operation, image data is recorded on the recording medium, and when the anti-aging process is performed, the processed image is recorded. The image data recorded on the recording medium can be reproduced and displayed on the display unit when the reproduction mode is selected.

  FIG. 1 is a block diagram mainly showing an electrical configuration of a camera according to the first embodiment of the present invention. The camera 100 is a digital camera, and includes an image processing and control unit 1, a photographing optical system 2, a lens control unit 2a, an imaging unit 3, a temporary storage unit 7, a flash ROM 7a, a display unit 8, a recording unit 9, an operation unit 10, and the like. Consists of

  The photographing optical system 2 is a zoom lens composed of a plurality of lenses, and forms a subject image on an image pickup element in the image pickup unit 3. The lens control unit 2a moves back and forth on the optical axis, and the photographing optical system 2 is focused. As this focusing, an automatic focus adjustment method such as a so-called hill-climbing method in which the lens of the photographing optical system 2 is moved so that the contrast signal of the image data output from the imaging unit 3 has a peak value may be used.

  The imaging unit 3 includes an exposure control unit such as a shutter / aperture, an imaging device, a driving and reading circuit for the imaging device, an AD conversion circuit, and the like, and converts the subject image formed by the imaging optical system 2 into image data by the imaging device. This is output as a digital signal. In this specification, a signal based on an image signal output from the image sensor is referred to as image data including an image processed signal.

  The image processing and control unit 1 includes a face detection unit 4, a unit detection unit 4 a, a lens aberration correction / anti-aging processing unit 5, and a compression unit 6. The image processing and control unit 1 is a control unit including a microcomputer having an image processing function, and controls the entire sequence of the camera 10 in accordance with a program stored in the flash ROM 7a.

  The lens aberration correction / anti-aging processing unit 5 receives image data output from the imaging unit 3 and performs aberration correction and anti-aging processing of the photographing optical system 2. The photographing optical system 2 is composed of a plurality of lenses, and optical distortion occurs in the subject image. Therefore, the lens aberration correction / anti-aging processing unit 5 performs an electrical correction process on the optical distortion to remove the distortion.

  The face detection unit 4 receives the image data from which the lens aberration has been removed by the lens aberration correction / anti-aging processing unit 5, and whether or not the face is included in the subject image. The position and size, the face center position, etc. are detected. In addition, when a face is included, the face detection unit 4 estimates age, sex, and the like based on the feature amount of the face. That is, the flash ROM 7a described later stores face age information indicating the relationship between the face image and the age, and the age of the person in the face image is determined based on the face age information and the feature amount of the face.

  The part detection unit 4a is connected to the face detection unit 4 and detects the position of a specific part of the human body such as around the torso when the face detection unit 4 detects the presence of a face. The output of the part detection unit 4a is connected to the lens aberration correction / anti-aging processing unit 5, and the lens aberration correction / anti-aging processing unit 5 applies to the detected part based on the detection result of the part detection unit 4a. To perform anti-aging processing.

  That is, the lens aberration / anti-aging processing unit 5 performs the anti-aging process using the lens aberration correction process. In the anti-aging process, when the face detection unit 4 detects the position of the face, a region of a specific part of the human body such as a body part corresponding to the face image is specified as a correction region, and the face detected by the face detection unit 4 Based on the age, image processing such as slimming processing is performed on the correction region. This anti-aging process will be described later with reference to FIGS.

  The lens aberration correction / anti-aging processing unit 5 and the image processing control unit 1 are connected to the temporary storage memory 7 and the flash ROM 7a. The temporary storage memory 7 is an electrically rewritable volatile memory such as DRAM (Dynamic Random Access Memory), and temporarily stores data during lens aberration correction processing, anti-aging processing, and other control processing. The The flash ROM 7a is an electrically rewritable nonvolatile memory, and includes a program executed by the control unit, lens aberration correction data, anti-aging process data, face age information indicating the relationship between the face image and age, and the like. It is remembered.

  The output of the lens aberration correction / anti-aging processing unit 5 is connected to the display unit 8. The display unit 8 includes a display panel such as a liquid crystal panel or an organic EL panel disposed on the back surface of the camera 100, and is image data captured by the imaging unit 3 and processed by the lens aberration correction / anti-aging processing unit 5. To display a through image before shooting. The face detection unit 4 described above detects the face of a person imaged for a through image. When the anti-aging mode is set, a through image subjected to anti-aging processing is displayed. The photographer can observe the through image display and determine the composition and timing. In addition, the display unit 8 performs quick review display for displaying a captured image after still image shooting, and reading and displaying image data of a recorded image recorded in the recording unit 9 described later. Further, the display unit 8 displays camera information and a menu screen. Note that the still image face detection may be performed during quick review display or still image playback display during still image shooting, and anti-aging processing may be performed when a face is detected.

  The output of the lens aberration correction / anti-aging processing unit 5 is connected to the compression unit 6. The compression unit 6 performs compression processing of the image data processed by the lens aberration correction / anti-aging processing unit 5. The output of the compression unit 6 is connected to the recording unit 9, and the compressed image data is recorded. Further, the compression unit 6 performs an expansion process on the image data read from the recording unit 9 and outputs it to the display unit 8.

  The operation unit 10 includes various operation members such as a release button, a power switch, a reproduction mode setting button, a menu button, and the like, determines the operation state of these operation members, and sends a determination result to the image processing and control unit 1. The image processing and control unit 1 controls shooting and reproduction in a predetermined sequence according to the operation state of the operation member. The anti-aging mode is set on the menu screen, but an anti-aging mode setting operation button may be provided and set using this operation button.

  Next, the slimming process as the anti-aging process in the present embodiment will be described with reference to FIG. FIG. 2A shows an image before the slimming process, and the optical distortion of the photographing optical system 2 is corrected by the lens correction / anti-aging processing unit 5 in this image. FIG. 2B is an image that has undergone slimming processing, and is an image that has been subjected to slimming processing on a specific portion (here, a body part) and corrected so that the body part is slimmed.

  In the example shown in FIG. 2B, the abdomen is detected from the body part of the person, and only that part is thinned. In general, the female body shape changes with age, and the change in the abdomen increases with age (see, for example, Industrial Structure Improvement Business Association Apparel Study No. 15, age-related changes in adult women in various parts of the body). Therefore, by thinning only the abdomen, it becomes possible to rejuvenate a body shape that seems to have aged due to the accumulation of subcutaneous fat.

  Next, the operation of the anti-aging mode for performing the anti-aging process in the camera 100 shown in FIG. 1 will be described using the flowchart shown in FIG. Note that this flowchart and the flowchart shown in FIG. 4 (including FIGS. 13, 14, and 17 in the second and third embodiments described later) are based on the image processing and control unit according to the program stored in the flash ROM 7a. 1 is executed. The flow of the anti-aging mode starts when the anti-aging mode is set on the menu screen.

  When the anti-aging mode is started, first, image capturing is performed (S1). Here, image data of a subject image formed by the imaging optical system 2 is acquired by the imaging unit 3. Once image capture has been performed, image processing is next performed (S3). Here, image processing by the image processing and control unit 1 is performed on the image data captured by the imaging unit 3.

  Once image processing has been performed, lens aberration correction is then performed (S5). As described above, since the photographing optical system 2 has lens aberration, the subject image is distorted, and this distortion is corrected by the lens aberration correction / anti-aging processing unit 5 to remove the distortion of the subject image.

  Once lens aberration correction has been performed, the image is then recorded in a temporary storage memory (S7). Here, the aberration-corrected image data is temporarily stored in the temporary storage memory 7. When the image is temporarily stored, face detection is subsequently performed (S9). Here, the face detection unit 4 detects whether or not a face is included in the subject image based on the image data. If an image as shown in FIG. 2A is captured, the face detector 4 detects the face 20a of the subject 20.

  Once face detection is performed in step S9, it is next determined whether or not a face has been detected (S11). Here, it determines based on the detection result in step S9. When the above-described image of FIG. 2A is captured, the face 20a exists, so the determination here is Yes. If a face is detected as a result of the determination in step S11, the image is then read from the temporary storage memory (S12). As described above, in step S7, the lens data corrected for lens aberration is stored in the temporary storage memory 7. In this step, the temporarily stored image data is read out. When the image data is read, in steps S13 and S19, the lens aberration correction / anti-aging processing unit 5 identifies a correction region for correcting the body part region corresponding to the face image detected by the face detection unit 4. .

  When the image is read out, first, it is determined that the body part is a part having a large color change vertically downward from the face detection position and a little color change horizontally (S13). When detecting the face, the face detection unit 4 can obtain the center position of the nose in the face and the center positions of the right eye and the left eye. Therefore, in this step, the center axis that substantially bisects the image of the face 20a through the center of the nose and the eyes and the center of the face is defined as the Y-axis line 20b, and is substantially vertical in the image having the image of the face 20a. A portion having a large color change in the direction (a direction along the Y-axis line 20a) and a little color change in the horizontal direction is detected, and an orthogonal straight line that is substantially orthogonal to the Y-axis is specified as a virtual straight line. In the example shown in FIG. 2A, the virtual straight line corresponds to the line 20c, and the body portion corresponds to the boundary between the exposed skin portion and the seawater pants, that is, the upper side of the line 20c.

  When the body part is detected, the face size is determined as a correction area upward from the lower end of the body part (S19). In the example shown in FIG. 2A, a line 20d at a position substantially the same as the length h of the face 20a is obtained above the line 20c, and the subject 20 is located between the line 20c and the line 20d. A certain rectangular area is determined as a correction area. In addition, although it was set as 1 face, other values, such as 1.5 pieces or 2 pieces, may be sufficient. Further, the height may be based on other parts such as the shoulder width without using the size of the face as a reference.

  If the correction area is determined, then anti-aging correction is performed on the correction area (S27). Here, the lens aberration correction / anti-aging processing unit 5 determines the age of the person of the detected face image based on the face age information stored in the flash ROM 7a, and based on the determined age, For example, a slimming process as shown in FIG. 2B is performed on the body part region determined as the correction region. Details of the anti-aging correction will be described later with reference to a flowchart shown in FIG.

  If anti-aging correction is performed in step S27, or if the result of determination in step S11 is that a face has not been detected, then display is performed (S29). Here, the through image is displayed on the display unit 8 after the image is captured and processed in step S1. When a through image is displayed, if a face is detected in the image, an image subjected to anti-aging correction is displayed in step S27. If no face is detected, anti-aging processing is not performed. Display the captured image.

  Once displayed, it is next determined whether or not to shoot (S31). Here, the operation state of the release button in the operation unit 10 is determined, and the determination is made based on the release operation. If the result of this determination is that shooting has not been made, processing returns to step S1. When returning to step S1, the image capturing is performed again, the through image is updated, and when a face is detected, the anti-aging correction is also updated.

  If the result of determination in step S31 is shooting, recording is performed (S33). Here, when there is a detected face, image data on which anti-aging correction has been performed, and when there is no detected face, image data on which anti-aging correction has not been performed is stored in the recording unit 9. To be recorded.

  Once the image data has been recorded, it is next determined whether or not it is finished (S35). Here, it is determined whether or not the setting of the anti-aging mode has been canceled. If the result of this determination is not end, processing returns to step S1. On the other hand, if it is the end, the anti-aging mode is turned off after performing the anti-aging mode end processing.

  Next, the anti-aging correction in step S27 will be described using the flowchart shown in FIG. When the anti-aging correction is started, first, the center point of the correction area is determined as the correction center (S51). In the example shown in FIG. 2A, the correction region is a body portion of the person of the subject 20, and is a region having a substantially rectangular shape between the line 20c and the line 20d. As shown in FIG. 5, the intersection of straight lines connecting the vertices of a substantially rectangular shape, in other words, the center of gravity position is set as the center point 31, and this center point 31 is determined as the correction center.

  Once the correction center is determined, the correction calculation is started with the distance from the correction center to the upper right point of the correction area set to 1 (S53). Here, the upper right vertex of the substantially rectangular correction region is set as the upper right point 32, and the length of the line segment connecting the center point 31 and the upper right point 32 is set to “1”, and the correction calculation is started. A line connecting the center point 31 and the upper right point 32 is referred to as a reference line.

Next, a corrected coordinate calculation is performed (S55). Here, for each pixel of the body part, the coordinate position is corrected using the following equation. The coordinate of the center point 31 is set to (0, 0), and the corrected coordinate position (X ′, Y ′) is calculated using the following formula for the coordinate position (X, Y) of each pixel.
X ′ = (X ² / A ² + Y ² / B ² ) * K * M * cos θ (1)
K = (1−G) / sin θ * Y + G (2)
Y ′ = Y (3)
Here, G is an arbitrary value, and M is also an arbitrary value.

  As shown in FIG. 6, the X axis and the Y axis passing through the center point 31 are determined, and the angle from the reference line passing through the center point 31 and the upper right point 32 to the X axis is θ. The lengths of the line segment n in the X-axis direction and the line segment m in the Y-axis direction in FIG. 6 are n = cos θ and m = sin θ, respectively, since the length of the reference line is 1. Therefore, the coordinates of the center point 31 are (0, 0), and the coordinates of the upper right point 32 are (cos θ, sin θ). The constant M described above corresponds to an image adjustment coefficient for aligning the corrected image with the original image, and the constant G described above corresponds to a coefficient representing the slimming degree. K is a coefficient set to be 1 when the coordinate Y is SINθ, and the variables A and B correspond to coefficients for determining the shape of the ellipse.

  In FIG. 6, 0 ≦ X ≦ cos θ and 0 ≦ Y ≦ sin θ in the shaded first quadrant, and in this first quadrant, X and Y are substituted into the equations (1) to (3), The corrected coordinate position (X ′, Y ′) is obtained. FIG. 7 shows a graph when θ = 45 °, A = 1, B = 1, G = 1, M = 1, X = cos θ, and 0 ≦ Y ≦ sin θ. FIG. 8 shows a shape change due to anti-aging correction in the first quadrant shaded in FIG.

  As shown in FIGS. 6 and 7, if correction calculation is performed on the pixels in the first quadrant, the correction calculation is also performed on the pixels in the second to fourth quadrants as shown in FIG. Apply. In this case, for the pixels in the second quadrant, only the sign of X is negative in the expressions (1) to (3). For the pixels in the third quadrant, only the sign of Y is negative in the expressions (1) to (3). Further, for the pixels in the fourth quadrant, the values of both the X and Y signs are negative in the expressions (1) to (3).

  As described above, in step S55, the corrected coordinate positions are obtained using the equations (1) to (3) for the coordinates of the respective pixels in the correction region. FIG. 10 shows changes in the correction area. That is, FIG. 10A shows a correction area before correction, and FIG. 10B shows a correction area after correction.

  Once the corrected coordinate calculation is performed in step S55, the coordinate position obtained by the corrected coordinate calculation is interpolated (S57). In step S55, the coordinate position of each pixel after correction is obtained. In order to display an image, the coordinate position of each pixel before correction, that is, each pixel lined up at regular intervals in the X and Y directions. The value of the pixel signal at the position is required. The corrected coordinate position obtained in step S55 is calculated by interpolation. This interpolation calculation is performed by interpolation calculation, and for example, interpolation calculations such as nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation can be used.

  When the interpolation process in step S57 is performed, the anti-aging process is terminated and the process returns to the original flow.

  Note that the variables A, B, K, M, and G in the expressions (1) and (2) are values according to the face age. As described above, since the lens aberration correction / anti-aging processing unit 5 determines the face age based on the face image, this determination result is used. FIG. 11 shows examples of these constants and the body slimming ratio (reduction ratio in the first quadrant) when these constants are substituted. As can be seen from FIG. 11, variables A, B, K, M, and G are set so that the reduction rate increases as the age increases. In FIG. 11, a plurality of constants are set according to each age. However, any one of these combinations may be determined, and a plurality of combinations may be prepared so that the user can select as appropriate. Also good.

  As described above, in the first embodiment of the present invention, when the subject includes a face (Yes in S11), the correction area is determined from the body part (S13, S19), and this correction area is determined. Is subjected to anti-aging correction (S27). When performing anti-aging correction, the face age is determined from the face image, and the slimming process is performed on the correction area of the body portion based on the determined face age. For this reason, a part of the body, such as around the trunk that has become thick due to the accumulation of subcutaneous fat or the like with aging, can be visually made thin.

  Next, a second embodiment of the present invention will be described with reference to FIGS. In the first embodiment, an anti-aging process for slimming the body part has been performed. In the second embodiment, as shown in FIG. 12, by performing anti-aging processing 2 that bulges the buttocks, it is possible to perform camera photography with a youthful and attractive body line. The configuration in the present embodiment is substantially the same as the configuration shown in FIG. Further, since the flowcharts shown in FIGS. 3 and 4 are replaced with FIGS. 13 and 14, this different flow will be described in detail.

  The flow of the anti-aging mode shown in FIG. 13 for executing the anti-aging process 2 starts when the anti-aging mode is set on the menu screen as in the case of the first embodiment. In the flow shown in FIG. 13, steps that execute the same processing as in the flowchart shown in FIG. 3 in the first embodiment are assigned the same step numbers, and detailed descriptions thereof are omitted.

  When the anti-aging mode is started, as in the case of the first embodiment, image capturing is performed (S1), image processing is performed on the captured image data (S3), and lens aberration is corrected (S5). The corrected image is recorded in the temporary storage memory (S7), and face detection is performed to determine whether a face image is included in the subject image (S9). Is determined (S11).

  If the result of determination in step S11 is that a face has been detected, then the image is read out from the temporary storage memory (S12), the color change is large in the vertical downward direction from the face detection position, and the color in the horizontal direction The body part is determined up to the part with little change (S13). In the example shown in FIG. 12, this body portion corresponds to the boundary between the portion where the skin is exposed and the seawater pants, that is, the upper side from the line 20c.

  Once the body part is determined, next, a half of the downward face size from the lower end of the body part is determined as the correction area (S14). In the example shown in FIG. 12A, a line 20e located at a position substantially the same as the length of the face 20a in the Y-axis direction is obtained below the line 20c, and the subject 20 is the line 20c and the line 20e. A substantially rectangular area between the two is determined as a correction area. This correction area substantially corresponds to the collar portion. In the present embodiment, the half of the face is used. However, other values such as 1/3, 2/3, etc. may be used as long as the face is substantially equivalent. In addition to the size of the face, other parts such as height and shoulder width may be used as a reference.

  If the correction area is determined, then anti-aging 2 correction is executed on the correction area (S28). Here, the face age of the detected face image is detected by the face detection unit 4, and the lens aberration correction / anti-aging processing unit 5 is applied to the buttocks area determined as the correction area based on the detected face age. However, for example, the processing as shown in FIG. Details of the anti-aging 2 correction will be described later with reference to a flowchart shown in FIG.

  If anti-aging 2 correction is performed on the correction area in step S28, or if the result of determination in step S11 is that there is no detected face, a through image display is displayed on the display unit 8 as in the first embodiment. It is performed (S29), and it is determined whether or not shooting is performed (S31). If the result of this determination is that there is no shooting, the process returns to step S1, while if it is shooting, image data is recorded (S33). If anti-aging 2 correction has been performed in step S28, the corrected image data is recorded. When the recording is finished, it is determined whether or not to end the anti-aging mode (S35). If not, the process returns to step S1. If the recording is finished, the anti-aging mode end processing is performed. Turn off anti-aging mode.

  Next, the anti-aging 2 correction process in step S28 will be described using the flowchart shown in FIG. When the anti-aging correction is started, as in the first embodiment, the center point of the correction area is determined as the correction center (S51), and then the correction calculation is performed by setting the distance from the correction center to the upper right point of the correction area as 1. Start (S53).

Next, post-correction coordinate calculation is performed (S56). Here, for each pixel in the correction region (see FIG. 16A) corresponding to the heel, the coordinate position is corrected using an ellipse formula. The coordinate of the center point 31 is set to (0, 0), and the corrected coordinate position (X ′, Y ′) is calculated using the following formula for the coordinate position (X, Y) of each pixel.
X ′ = 2 * X * S1 + (X ² / A ² + Y ² / B ² ) * K * M * cos θ * S2 (4)
K = (1−G) / sin θ * Y + G (5)
Y '= Y (6)
Here, G is an arbitrary value, and M is also an arbitrary value.
Also, S1: when anti-aging correction is 0, and when anti-aging 2 correction is 1
S2: At the time of anti-aging correction = 1, at the time of anti-aging 2 correction = −1.

  Similarly to the case of the first embodiment, X and Y are substituted into the equations (4) to (6) in the first quadrant of the correction region to obtain the corrected coordinate position (X ′, Y ′). FIG. 15 shows a graph when θ = 45 °, A = 1, B = 1, G = 1, M = 1, X = cos θ, 0 ≦ Y ≦ sin θ, S1 = 1, and S2 = −1. .

  As can be seen from FIG. 15, Equations (4) to (6) are part of an ellipse, and in the case of Equations (1) to (3), they are recessed toward the center. In the case of the formulas (4) to (6), it swells outward from the center. FIG. 15 shows only the first quadrant of the correction area, but FIG. 16 shows the corrected shape of the correction area. It can be seen that the overall image is swollen.

  If the post-correction coordinate calculation is performed in step S56, the coordinate position obtained by the post-correction coordinate calculation is interpolated next as in the first embodiment (S57). As in the first embodiment, for example, interpolation calculations such as nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation can be used for the interpolation calculation. When the interpolation process in step S57 is performed, the anti-aging process is terminated and the process returns to the original flow.

  Note that the variables A, B, K, M, and G in the equations (4) and (5) are values according to the face age, as in the first embodiment. As described above, since the face detection unit 4 determines the face age based on the face image, these constants may use the example shown in FIG.

  In the flow shown in FIG. 13, a correction region is set for the vicinity of the buttocks, and a process for applying a bulge to the region is performed. In addition to this process, as in the first embodiment, the body part If a correction area is set in this area and the slimming process is performed on this area, an image of a youthful body line as shown in FIG. 12B can be obtained.

  As described above, in the second embodiment of the present invention, when the subject includes a face (Yes in S11), a correction area is determined near the buttocks (S13, S14). On the other hand, anti-aging 2 correction is performed (S28). Then, when performing anti-aging 2 correction, the face age is determined from the face image, and based on the determined face age, a process of adding a bulge to the correction region in the vicinity of the buttocks is performed. For this reason, it is possible to create a youthful and attractive bodyline image.

  Next, a third embodiment of the present invention will be described with reference to FIG. In the first embodiment, the body part is determined based on the detection result of the portion where the color change is large from the lower side to the face. However, depending on the color of the clothes of the subject, the body part may not be determined. Therefore, in the third embodiment, even when the body part cannot be determined due to a change in color, the region corresponding to the body part can be determined as the correction region.

  The configuration in the present embodiment is substantially the same as the configuration shown in FIG. Also, since the flowchart shown in FIG. 3 is replaced with FIG. 17, this different flow will be described in detail. The flow of the anti-aging mode shown in FIG. 17 for executing the anti-aging process according to the present embodiment starts when the anti-aging mode is set on the menu screen, as in the first embodiment. In the flow shown in FIG. 17, steps that execute the same processes as those in the flowchart shown in FIG. 3 in the first embodiment are assigned the same step numbers, and detailed descriptions thereof are omitted.

  When the anti-aging mode is started, as in the case of the first embodiment, image capturing is performed (S1), image processing is performed on the captured image data (S3), and lens aberration is corrected (S5). The corrected image is recorded in the temporary storage memory (S7), and face detection is performed to determine whether a face image is included in the subject image (S9). Is determined (S11).

  If the result of determination in step S11 is that a face has been detected, the image is then read from the temporary storage memory (S12), and the color change is large in the vertical downward direction from the face detection position, and the color change horizontally. It is determined that there is a body part up to a small part (S13).

  Once the body part has been determined, it is next determined whether or not the body part has been detected (S15). In the determination of the torso part in step S13, a portion where the color change in the vertical direction is large and the color change in the horizontal direction is small is detected. There are cases where the portion cannot be detected. Therefore, in step S15, the color change part is determined, and it is determined whether or not the body part has been detected.

  If the result of determination in step S15 is that the torso part has been detected, the face size is determined as the correction region upward from the lower end of the torso part, as in the first embodiment (S19). On the other hand, if the result of determination in step S15 is that the body part could not be detected, the lens aberration correction / anti-aging processing unit 5 performs Y for the third face size in the vertical downward direction from the detected face lower side. The direction position is determined as the Y direction correction area (S17).

  In step S17, a line in the X-axis direction orthogonal to the Y-axis line is set as the lower side of the correction area at positions corresponding to three face sizes downward along the Y-axis line from the lower side of the detected face. This lower side is a line corresponding to the line 20c in the first embodiment. Similarly to the case of the first embodiment, an X-axis direction line orthogonal to the Y-axis line is set as the upper side of the correction area at a position corresponding to one face size along the Y-axis line. This upper side is a line corresponding to the line 20d in the first embodiment.

  If the Y direction correction area is determined in step S17 or S19, the area from the Y direction correction area to the portion where the color change is large in both the positive direction and the negative direction in the X direction is determined as the X direction correction area ( S21). In this step, the lens aberration correction / anti-aging processing unit 5 detects a large color change portion along the X-axis direction, and determines a portion corresponding to the left side and the right side of the correction region.

  Once the X direction correction area is determined in step S21, the X direction correction area is next detected (S23). In the determination of the X direction correction region in step S21, a portion where the color change in the X direction is large is detected. Depending on the relationship between the clothes of the subject person and the background, such a color change portion is detected. May not be possible. Therefore, in step S23, the color change portion is determined, and it is determined whether or not the X direction correction region has been detected.

  As a result of the determination in step S23, if the X direction correction area cannot be detected, the detected face long side size is determined as the X direction correction area (S25). Here, the lines in the Y direction determined by the size in the long side direction of the detected face are respectively corrected from the center point along the lower side line and the upper side line in the X-axis direction determined in step S17 or S19. Determine the left and right sides of the area. This makes it possible to determine a correction area including the upper side, the lower side, the left side, and the right side.

  If the X direction area is determined in step S25 or if the X direction correction area can be detected as a result of the determination in step S23, next, as in the first embodiment, with respect to the correction area. Anti-aging correction is performed (S27). In this step, anti-aging correction of the body part is performed based on the face age estimated from the face image. The anti-aging correction here is the same as the correction process described with reference to the flowchart shown in FIG.

  If anti-aging correction is performed on the correction area in step S27 or if the result of determination in step S11 is that there is no detected face, a through image is displayed on the display unit 8 as in the first embodiment. (S29), it is determined whether to perform photographing (S31). If the result of this determination is that there is no shooting, the process returns to step S1, while if it is shooting, image data is recorded (S33). If anti-aging 2 correction has been performed in step S28, the corrected image data is recorded. When the recording is finished, it is determined whether or not to end the anti-aging mode (S35). If not, the process returns to step S1. If the recording is finished, the anti-aging mode end processing is performed. Turn off anti-aging mode.

  As described above, in the third embodiment of the present invention, when a face image is included in the subject image (Yes in S11), a correction region is located near the body part from the color change in the X direction and the Y direction. However, if the correction area cannot be determined based on the color change, the correction area is determined based on the face size (S17, S25). When the correction area is set, the face age is determined from the face image, and the slimming process is performed on the correction area in the vicinity of the body part based on the determined face age. For this reason, even if it is a case where a correction area cannot be set based on a color change, it becomes possible to set a correction area based on the size of a body part.

  In this embodiment, when the color change in the Y direction cannot be detected, it is impossible to detect the position three times the reference size of the face and the color change in the X direction. In such a case, the position of the 1 × position on the basis of the face size is set as the range of the correction area. However, several times the size of the face may be appropriately changed as a design value, and other parts such as a shoulder width may be used as a reference in addition to the face.

  Further, in the present embodiment, the anti-aging process 2 described in the second embodiment is not executed, but as in the third embodiment, the position corresponds to the buttocks at a position based on a human body part such as a face. Of course, the correction area may be determined, and the anti-aging process 2 may be performed on the correction area.

  As described above, in each embodiment of the present invention, when a face image is detected in a subject image, a correction area corresponding to a specific portion such as a human body part or a hip part of the face image is determined. The correction area is subjected to anti-aging image processing such as slimming processing and bulging. For this reason, the image can be corrected to a youthful and attractive bodyline image.

  In each embodiment of the present invention, the body part and the buttocks have been described as examples of the specific part. However, the present invention is not limited to this, and the anti-aging image processing is applied to other parts such as the second arm. be able to. In each embodiment of the present invention, the age of the subject is determined based on the face image. However, the present invention is not limited to this, and the determination is made in consideration of the entire body shape and the part other than the face, such as the degree of bending of the waist. May be.

  Furthermore, in each embodiment of the present invention, the anti-aging image processing is performed at the time of displaying a through image at the time of shooting, but not limited to this, when playing back a recorded image after shooting, Anti-aging image processing may be performed. Furthermore, in each embodiment of the present invention, the ellipse formula is used in performing the anti-aging image processing for adding slimming and bulging. However, the present invention is not limited to this, and it may be replaced with an equation for adding slimming and bulging. Good.

  In the present embodiment, the digital camera is used as the photographing device. However, the camera may be a digital single-lens reflex camera or a compact digital camera, and may be used for moving images such as video cameras and movie cameras. It may be a camera, or may be a camera built in a mobile phone, a personal digital assistant (PDA), a game machine, or the like.

  The present invention is not limited to the above-described embodiments as they are, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage. In addition, various inventions can be formed by appropriately combining a plurality of components disclosed in the embodiment. For example, you may delete some components of all the components shown by embodiment. Furthermore, constituent elements over different embodiments may be appropriately combined.

DESCRIPTION OF SYMBOLS 1 ... Image processing and control part, 2 ... Imaging optical system, 3 ... Imaging part, 4 ... Face detection part, 4a ... Site | part detection part, 5 ... Lens aberration correction and anti Aging processing unit, 6 ... compression unit, 7 ... temporary storage memory, 7a ... flash ROM, 9 ... recording unit, 10 ... operation unit, 20 ... subject, 20a ... Face, 20b ... Y-axis line, 20c ... Line, 20d ... Line, 20e ... Line, 31 ... Center point, 32 ... Upper right point, 100 ... Camera

Claims (9)

Display means for displaying the captured image;
Storage means for storing face age information indicating a relationship between a face image and age;
Face detection means for detecting the position of the face of the image displayed on the display means;
Determination means for determining the face age of the face image detected by the face detection means based on the face age information stored in the storage means;
Correction area specifying means for specifying a body part area corresponding to the face image detected by the face detection means as a correction area;
Anti-aging processing means for performing slimming processing on the region of the identified torso portion based on the determined face age of the face image;
Display changing means for changing the image displayed on the display means to an image subjected to the slimming process by the anti-aging processing means;
An image processing apparatus comprising: The correction area specified by the correction area specifying means is
When the center axis that passes through the center of the nose and the eyes and bisects the face image is the Y axis, the color change in the direction substantially perpendicular to the Y axis in the image having the face image A large part is identified as a virtual straight line, and one side with both ends of the part with a large color change on the virtual straight line,
A side having a length close to the face image from the virtual straight line by a predetermined distance along the Y-axis direction;
The image processing apparatus according to claim 1, wherein the image processing apparatus is a rectangular area. The correction area specified by the correction area specifying means is
In the image having the face image, the edge of the face image along the Y-axis direction when the center axis that passes through the center of the nose and the eyes and substantially bisects the face image is defined as the Y-axis. The Y axis and a substantially orthogonal line at a position that is approximately three times the size of the face image from the part as a virtual straight line, and one side with the large color change on the virtual straight line as both ends;
A side having a length close to the face image from the virtual straight line by a predetermined distance along the Y-axis direction;
The image processing apparatus according to claim 1, wherein the image processing apparatus is a rectangular area. The anti-aging processing means is a straight line connecting the center position and the corner of the rectangular correction area when the direction perpendicular to the Y axis passes through the central position of the identified rectangular correction area as the X axis. Is θ, the length of the straight line connecting the center position and the angle of the rectangular correction region is 1, the image adjustment coefficient for matching the corrected image with the original image is M, and the slimming degree is Assuming that the coefficient to be expressed is G and the coefficient set to be 1 when Y is SINθ is K, and the coefficients for determining the shape of the ellipse are A and B,
X ′ = (X ² / A ² + Y ² / B ² ) * K * M * COSθ
K = (1-G) / SINθ * Y + G
Y '= Y
The image processing apparatus according to claim 2, wherein correction is performed so as to satisfy. The anti-aging processing means is a straight line connecting the center position and the corner of the rectangular correction area when the direction perpendicular to the Y axis passes through the central position of the identified rectangular correction area as the X axis. Is θ, the length of the straight line connecting the center position and the angle of the rectangular correction region is 1, the image adjustment coefficient for matching the corrected image with the original image is M, and the slimming degree is Coefficients to be represented are G, K is a coefficient set to be 1 when Y is SINθ, A and B are coefficients for determining the shape of the ellipse, and S1 is a coefficient representing the direction of the ellipse (where S1 = 0) Or S1 = 1), S2 (where S2 = 1 or S2 = −1)
X ′ = 2 * S1 + (X ² / A ² + Y ² / B ² ) * K * M * COSθ * S2
K = (1-G) / SINθ * Y + G
Y '= Y
The image processing apparatus according to claim 2, wherein correction is performed so as to satisfy.   The image processing apparatus is a digital camera capable of displaying a through image, the display means displays a captured through image, and the face detection means detects a human face imaged as the through image. The image processing apparatus according to claim 1, wherein: Imaging means for converting a subject image into image data;
Face detection means for detecting the position of the face image in the subject image based on the image data;
Storage means for storing face age information indicating a relationship between a face image and age;
Determination means for determining the face age of the face image detected by the face detection means based on the face age information stored in the storage means;
Correction area specifying means for specifying the area of the specific portion of the person in the face image detected by the face detection means as an area to be corrected;
Anti-aging processing means for performing anti-aging image processing on the region of the specific portion based on the face age of the determined face image;
Display means for displaying the image subjected to the anti-aging image processing by the anti-aging processing means;
An image processing apparatus comprising: Face detection means for detecting the position of the face image in the subject image;
Storage means for storing face age information indicating a relationship between a face image and age;
Determination means for determining the face age of the face image detected by the face detection means based on the face age information stored in the storage means;
Correction area specifying means for specifying the area of the specific portion of the person in the face image detected by the face detection means as an area to be corrected;
Anti-aging processing means for performing anti-aging image processing on the region of the specific portion based on the face age of the determined face image;
Display means for displaying the image subjected to the anti-aging image processing by the anti-aging processing means;
An image processing apparatus comprising: Converting a subject image into image data;
Detecting a position of a face image in the subject image based on the image data;
Identifying a region of a specific portion of the person in the detected face image as a region to be corrected;
Read the face age information stored in the storage unit that stores the face age information indicating the relationship between the face image and the age, determine the face age of the detected face image based on the face age information, and Applying anti-aging image processing to the region of the specific portion based on the determined face age of the face image;
Displaying the image subjected to the anti-aging image processing;
An image processing method comprising: