JP7548396B2 - Image processing device, image processing method, and program - Google Patents

Description

The present invention relates to an image processing device, an image processing method, and a program.

Technologies for correcting facial images have been proposed in the past. For example, Patent Document 1 describes a method for masking characteristic areas of the face, such as the eyes, nose, and mouth, and then performing a smoothing process on the remaining skin area to make fine skin roughness less noticeable and generate a facial image that reproduces a smooth skin condition.

JP 2009-70260 A

However, with the technology in Patent Document 1, it is difficult to correct only the unique areas that are different from the surrounding skin, and if correction processing is performed, there is a foreseeable problem that the difference between the surrounding areas that have not been corrected will become noticeable.

The present invention was made in consideration of these problems, and aims to make the corrections made to the subject image less noticeable when the image is corrected.

In order to solve the above problem, the image processing device of the present invention is characterized in that, when performing a specified image processing so as to make acne in a person image less noticeable and applying a specified correction processing limited to an area corresponding to the acne, a pair of protection maps generated so that the sizes of the areas targeted for the specified correction processing are different are separately applied to apply the specified correction processing to the targeted areas to generate a pair of corrected images, and the image processing device is equipped with a processing means for synthesizing the pair of generated correction images, and a setting means for setting the size difference between the pair of protection maps based on the size of pores in the person image .

In addition, the image processing method of the present invention is an image processing method executed by an image processing device, and when performing a specified image processing so as to make acne in a person image less noticeable and applying a specified correction processing limited to an area corresponding to the acne, the method comprises a processing step of separately applying a pair of protection maps generated so that the sizes of the areas targeted for the specified correction processing are different from each other to apply the specified correction processing to the targeted areas to generate a pair of corrected images, and a setting step of setting the size difference between the pair of protection maps based on the size of pores in the person image .

In addition , the program of the present invention is characterized in that, when performing a specified image processing so as to make acne in a person image less noticeable and applying a specified correction processing limited to an area corresponding to the acne, the program causes a computer to function as a processing means for separately applying a pair of protection maps generated so that the sizes of the areas targeted for the specified correction processing are different from each other, and applying the specified correction processing to the targeted areas to generate a pair of corrected images, and for synthesizing the pair of generated correction images, and a setting means for setting the size difference between the pair of protection maps based on the size of pores in the person image .

The present invention makes it possible to make corrections made to a subject image less noticeable when the image is corrected.

1 is a block diagram showing a functional configuration of an imaging apparatus according to an embodiment of the present invention. 2 is a diagram for explaining an outline of processing in an analysis unit and a second image processing unit in FIG. 1 . FIG. 2 is a diagram showing a process flow in an analysis unit and a second image processing unit in FIG. 1 .

The following describes in detail an embodiment of the present invention with reference to the accompanying drawings. Note that the present invention is not limited to the illustrated examples.

[Configuration of imaging device 1]
Fig. 1 is a block diagram showing the functional configuration of an imaging device 1 according to this embodiment. As shown in Fig. 1, the imaging device 1 is configured to include a control unit 101, a storage unit 102, a display unit 103, a communication unit 104, an operation unit 105, an imaging unit 106, a first image processing unit 107, an image memory 108, an analysis unit 109, a second image processing unit 110, a lighting control unit 111, a light emitting unit 112, etc. The control unit 101 and each unit are connected by a bus.

The control unit 101 is configured with a CPU (Central Processing Unit), RAM (Random Access Memory), etc., and executes various programs stored in the storage unit 102 to perform predetermined calculations and control each unit.

The storage unit 102 is composed of a non-volatile semiconductor memory, a hard disk, etc. The storage unit 102 stores system programs and various processing programs executed by the control unit 101, data required to execute these programs, etc.

The display unit 103 is composed of an LCD (Liquid Crystal Display) or the like, and displays, in accordance with a display control signal from the control unit 101, for example, a live view image showing the state captured by the imaging unit 106, or an image acquired by the imaging unit 106 in response to a shooting instruction.

The communication unit 104 is an interface for wireless or wired data communication with external devices.

The operation unit 105 includes various function buttons including a shutter key, and a transparent touch panel that is layered on the display unit 103, and accepts inputs such as pressing buttons, touching the touch panel, and sliding operations by the user, and outputs the operation information to the control unit 101.

The imaging unit 106 is configured with an imaging lens 106a, an imaging element such as an image sensor such as a CCD (Charge Coupled Device) or CMOS (Complementary Metal-Oxide Semiconductor) (not shown), and an A/D conversion circuit, and converts the optical image that passes through the imaging lens 106a into a two-dimensional image signal by the imaging element, and acquires image data of the subject (RGB image data).

The first image processing unit 107 performs color processing including pixel interpolation and gamma correction on the RGB data acquired by the imaging unit 106, and then converts it into image data (image data for each of the Y, U, and V components) consisting of a digital value luminance signal Y and color difference signals Cb and Cr.

The image memory 108 is, for example, a flash memory or the like, and is a recording means for recording image data captured by the imaging unit 106 and processed by the first image processing unit 107.

When the correction mode according to the present invention is set in advance, the analysis unit 109 analyzes the image data (subject image) of the subject acquired by the imaging unit 106 and processed by the first image processing unit 107 to acquire texture information (skin surface information) of the subject's skin and outputs the acquired texture information to the second image processing unit 110. The analysis unit 109 also analyzes an image area around a unique area (e.g., an area where a foreign object such as a pimple exists) different from the surrounding skin in the image data processed by the first image processing unit 107 to generate texture protection maps M11, M12 and shadow protection maps M21, M22 (see FIG. 2) used when performing correction processing on the unique area in the second image processing unit 110. Here, the texture protection maps M11, M12 and shadow protection maps M21, M22 are mask data for protecting (masking) image areas not to be corrected among image areas around the unique area when performing correction processing on the unique area.
The analysis unit 109 functions as a texture information acquisition means, an edge component acquisition means, a detection means, an analysis means, and a correction means.

The second image processing unit 110 performs correction processing such as smoothing on the unique regions of the image data acquired by the imaging unit 106 and processed by the first image processing unit 107, using the texture protection maps M11, M12 and the shadow protection maps M21, M22 generated by the analysis unit 109, and generates a corrected image by adding texture information to the processing result and combining it with the original image data (original image).
The second image processing unit 110 functions as a processing unit.

The analysis unit 109 and the second image processing unit 110 are executed by the control unit 101 in cooperation with the programs stored in the memory unit 102, but may also be realized by dedicated hardware.

The lighting control unit 111 (driver) is connected to each of the LEDs (Light Emitting Diodes) of the light-emitting unit 112, and controls the light intensity and on/off state of the light-emitting unit 112 according to instructions from the control unit 101.

The light-emitting unit 112 is composed of an LED or the like, and irradiates light onto the subject.

[Operation of imaging device 1]
Next, the operations of the analysis unit 109 and the second image processing unit 110 of the imaging device 1 will be described.
FIG. 2 is a diagram showing an outline of the processing executed by the analysis unit 109 and the second image processing unit 110. G1 in FIG. 2 is a diagram showing a unique region in the original image and its surrounding Y component image (luminance component image) using image data processed by the first image processing unit 107 as the original image. In G1 in FIG. 2, the diagonal lines 51 represent the unique region, the dots 52 represent the texture of the skin, and the shaded areas 53 represent the shadows cast on the skin. The shadows may be generated by unevenness due to facial organs or wrinkles, or may be generated by hair, eyelashes, eyebrows, or their shadows. In FIG. 2, the texture 52 exists throughout G1. In addition to the unique region 51 (an image of a foreign object such as a pimple), a shadow 53 exists around the unique region.

If a correction process is performed on the original image corresponding to this Y component image G1 to make the unique region 51 less noticeable, the skin surface condition (grain) of the region being corrected will disappear, resulting in an unnatural image. For example, G2 in Figure 2 shows an example in which the texture of the unique region has disappeared. If the region being corrected is expanded to the periphery, the shadows around the unique region will also disappear, resulting in an even more unnatural image.

Therefore, in this embodiment, first, the analysis unit 109 generates a Y component image G1 of the unique region and its surrounding area from the original image. Next, as shown in Figure 2, the Y component image G1 is analyzed, and a texture protection map M11 (large), texture protection map M12 (small), shadow protection map M21 (large), and shadow protection map M22 (small) are generated based on the analysis results. Then, in the second image processing unit 110, a correction process is performed to make the unique region less noticeable in the original image using the generated texture protection maps M11, M12, and shadow protection maps M21, M22. In Figure 2, the image after correction process is shown as G2. In addition, the analysis unit 109 analyzes the Y component image G1 before correction to obtain information (texture information) that indicates the surface condition (texture) of the subject's skin, and the second image processing unit 110 performs processing to add the texture information obtained from the information before correction in the analysis unit 109 to the image G2 after correction processing, generating a corrected image G3 in which the texture and shadows have not been erased.

Here, the method of detecting the peculiar area to be corrected from the original image is not particularly limited, and any method may be used. For example, a region designated by the user using the operation unit 105 from the face region of the original image displayed on the display unit 103 may be detected as the peculiar area. Alternatively, a face region may be detected from the original image, an image of the detected face region may be cut out, and an area of pixel values (suddenly occurring pixel values) different from the surroundings may be extracted from data of the V component image data within the contour region of the face region with the eyes, nose, and mouth masked, and the peculiar area may be detected based on the size of the region.

FIG. 3 is a block diagram showing the functional configuration of the analysis unit 109 and the second image processing unit 110.
As shown in Fig. 3, the analysis unit 109 includes a skin analysis unit 20, a protection map data setting unit 21, a low-frequency data generation unit 22, an edge information generation unit 23, a region division unit 24, a shadow protection map generation unit 25, and a texture protection map generation unit 26. The second image processing unit 110 includes a protection map boundary reliability determination unit 27, a correction processing unit 28, a transparent synthesis processing unit 29, and a synthesis processing unit 30. The processing of the analysis unit 109 and the second image processing unit 110 will be described below with reference to Fig. 3.

First, the analysis unit 109 generates a Y component image composed of a Y (luminance) component from an original image having each of the YUV components, and then cuts out a rectangular area of a predetermined size that includes a unique area in the center detected from the face area of the Y component image, and inputs this to the skin analysis unit 20 and the edge information generation unit 23.

The skin analysis unit 20 analyzes the Y component image within the input rectangular area to detect the image area of the pores, and acquires pore size data (size) and contrast data (con) of the pore portion in this pore image area. Then, for the acquired pore size data, it calculates the average data (size_ave) of the pore size data and the standard deviation data (size_sd) of the pore size data, and outputs these to the protection map data setting unit 21 and the low-frequency data generation unit 22. For the acquired contrast data of the pore portion, it also calculates the average data (con_ave) of the contrast data of the pore portion and the standard deviation data (con_sd) of the contrast data of the pore portion, and outputs these to the skin texture protection map generation unit 26.

When correcting the unique region, the protection map data setting unit 21 generates protection maps M1, M2 consisting of mask data having two different sizes of elliptical protection exclusion regions 61, 62 (see FIG. 2) (large and small) so that other regions are not also corrected, and outputs these to the region dividing unit 24 and the texture protection map generating unit 26. The unique region is a substantially circular region where pimples such as acne or undulations that stand out from the surroundings are present, and the protection exclusion regions 61, 62 of the protection maps M1, M2 are elliptical in shape surrounding the unique region.
For example, the protection map data setting unit 21 first reads out a basic protection map having a protection exclusion region of a basic ellipse size stored in the storage unit 102. Next, the protection map data setting unit 21 calculates a radius of the pore size based on a value obtained by adding together the average data (size_ave) of the pore size data calculated by the skin analysis unit 20 and the standard deviation data (size_sd) of the pore size data, and generates a protection map M1 having a protection exclusion region in which the calculated radius is added to the radius of the ellipse of the basic protection map, and a protection map M2 having an ellipse size protection exclusion region in which the calculated radius is subtracted from the radius of the ellipse of the basic protection map.
In addition, since there is generally little individual difference in pore size, protection maps M1 and M2 of two different sizes may be generated in advance and stored in the storage unit 102. In addition, in the present embodiment, protection maps M1 and M2 of two different sizes are generated as templates, but this is not limited to this, and multiple types may be generated according to size. The more sizes there are, the more accurate correction of the peculiar area is possible.

The low-frequency data generation unit 22 smoothes the Y component image using an average filter whose parameter is the sum of the average data (size_ave) of the pore size data input from the skin analysis unit 20 and the standard deviation data (size_sd) of the pore size data, removes edge components in the Y component image, and generates low-frequency data (data in the low frequency band) that roughly indicates the state of shading. This makes it possible to remove the influence of pores from the shading of the skin. The low-frequency data generation unit 22 outputs the generated low-frequency data to the edge information generation unit 23 and the region division unit 24.

The edge information generating unit 23 generates and acquires positive (positive value) difference data and negative (negative value) difference data between the low-frequency data generated by the low-frequency data generating unit 22 and the Y component image. This makes it possible to extract texture in a frequency band higher than pores. The edge information generating unit 23 outputs this positive and negative difference data to the synthesis processing unit 30 as edge information (texture information) corresponding to the texture.

The area division unit 24, based on the low-frequency data input from the low-frequency data generation unit 22, identifies a shadow area within the annular area between the ellipse of the protection map M1 and the ellipse of the protection map M2 input from the protection map data setting unit 21, where correction would result in the shadow disappearing or otherwise affecting the original shadow expression, and divides this area from other areas.

Specifically, the region division unit 24 calculates a histogram of pixel values (pixel values of the low-frequency data) in a ring-shaped region that is the difference in size between the ellipse of protection map M1 and the ellipse of protection map M2 when the large and small protection maps M1 and M2 are superimposed on the low-frequency data, finds the most frequent value (peak) from this histogram, and divides the region of pixel values from the found most frequent value to the range where the minimum value exists as a shaded region from other regions. Then, information about the shaded region is output to the shaded protection map generation unit 25.

Based on the information on the shadow regions input from the region division unit 24, the shadow protection map generation unit 25 adds the shadow regions to the regions to be protected by the protection maps M1 and M2 to generate the shadow protection maps M11 and M12 as shown in FIG. 2. This makes it possible to add to the protection target the entire shadow region that is outside the unique region but falls into the protection exclusion region when processed using the protection maps M1 and M2, resulting in a lack of some or all (in most cases, some) information and making it unnatural. In other words, by having the correction processing unit 28 perform correction processing using the shadow protection maps M11 and M12, it becomes possible to perform correction processing excluding the shadow regions included in the protection exclusion regions 61 and 62. The shadow protection map generation unit 25 outputs the generated shadow protection maps M11 and M12 to the correction processing unit 28 and the protection map boundary reliability determination unit 27.

The texture protection map generating unit 26 adds the average data (con_ave) of the contrast data of the pores acquired from the skin analysis unit 20 and the standard deviation data (con_sd) of the contrast data of the pores, and finds pixels with positive edges (edges with higher brightness than the surroundings) and pixels with negative edges (edges with lower brightness than the surroundings) with a greater strength than the average data (con_ave). Next, the pixels of the positive edges and the negative edges in the pixel regions on the border with the protection exclusion regions in each of the protection maps M1 and M2 are added to the protection target regions of the protection maps M1 and M2 to generate the texture protection maps M21 and M22. In this way, pixels with edge strength equal to or greater than that of the pores on the border with the protection non-target region of the protection map can be excluded from the correction processing, and unnaturalness remaining in the corrected image can be eliminated. The texture protection map generating unit 26 outputs the generated texture protection maps M21 and M22 to the correction processing unit 28 and the protection map boundary reliability determination unit 27.

The protection map boundary reliability determination unit 27 determines the reliability of each of the image regions corrected using a large-sized protection map combining two large-sized protection maps M11, M21 generated by the shadow protection map generation unit 25 and the texture protection map generation unit 26, and a small-sized protection map combining two small-sized protection maps M12, M22. Then, in the transparent compositing process described below, a map is generated that increases the influence of pixels with higher reliability and decreases the influence of pixels with lower reliability, and outputs the map to the transparent compositing processing unit 29. Note that the reliability of each image region after the correction process may be determined before the correction process.

Here, for image regions where the protected regions of the large and small protection maps overlap, and for image regions where the protected regions of both overlap, the processing results are the same regardless of whether the large or small protection map is used for correction processing, and so the reliability is the same. Therefore, here, the reliability is determined mainly for each pixel in the image region sandwiched between the boundary with the protected region of the large protection map and the boundary with the protected region of the small protection map. In this embodiment, the reliability is determined to be higher for the region that is more elliptical in appearance. For example, the boundary sharing rate, area sharing rate, boundary regression analysis match rate, etc. are calculated for each pixel, and the reliability of the large and small protection maps is determined based on the calculation results.

Here, the boundary sharing rate is the ratio of the length of the boundary between the protection exclusion region in the large protection map and the protection exclusion region in the small protection map to the length of the boundary that coincides (shares) with the protection exclusion region in the large and small protection maps. If the protection exclusion region (i.e., the region to be corrected) in the large and small protection maps is an ellipse, the boundary between the protection exclusion region in the large and small protection maps is not shared, so the higher the ratio of the shared portion, the lower the reliability.
The area sharing ratio is the ratio of the area of the protection edge (the area added to the region to be protected) to the area of the protection map in each of the large and small protection maps. The smaller the ratio of the protection edge (the lower the sharing ratio), the higher the reliability.
The boundary regression analysis match rate is a value that indicates how many boundary values are within the range of the regression analysis results when a regression analysis is performed on the boundary with the protection exclusion area in each of the large-sized protection map and the small-sized protection map. If the boundary regression analysis match rate is low, the reliability is reduced.
It should be noted that the above-mentioned reliability calculation method is merely an example, and the concept of reliability determination and the specific method are not limited to this.

The correction processing unit 28 applies a large-sized protection map, which is a combination of the two large-sized protection maps M11 and M21 generated by the shadow protection map generating unit 25 and the texture protection map generating unit 26, to a rectangular area including a unique area of the image of each YUV component of the original image, to perform a correction process to make the boundary between the image area of the protection exclusion area surrounded by the protection maps and the other image areas and the unique state less noticeable. Similarly, the correction processing unit 28 applies a small-sized protection map, which is a combination of the two small-sized protection maps M12 and M22 generated by the shadow protection map generating unit 25 and the texture protection map generating unit 26, to a rectangular area including a unique area of the image of each YUV component of the original image, to perform a correction process to make the boundary between the image area of the protection exclusion area surrounded by the protection maps and the other image areas and the unique state less noticeable.
The above correction processing mainly involves smoothing processing (processing to smooth the skin condition and provide transparency), but in some cases color correction processing (processing to correct the skin color to a more natural color) may also be used.
The correction processor 28 outputs the YUV component images corrected using the large-sized protection map and the YUV component images corrected using the small-sized protection map to the transparent synthesis processor 29 .

Based on the map output from the protection map boundary reliability determination unit 27, the transparent synthesis processing unit 29 transparently synthesizes and outputs each YUV component image corrected using the large-sized protection map and each YUV component image corrected using the small-sized protection map, setting an alpha value for each pixel that is the subject of correction processing by the two protection maps so that the pixel determined to be more reliable has a greater influence.

The compositing processing unit 30 adds edge information corresponding to the texture input from the edge information generating unit 23 to the correction processing target area of each YUV component image transparently composited by the transparent compositing processing unit 29, alpha-blends the image with the texture state added (corrected image) with the original image at a predetermined blend ratio, and outputs the corrected image.

By carrying out the above processing in the analysis unit 109 and the second image processing unit 110, it is possible to carry out image processing that makes peculiar areas such as pimples less noticeable while preserving the shadows and texture caused by unevenness and wrinkles on the face, as shown in the corrected image G3 in Figure 2.

As described above, according to the imaging device 1, the analysis unit 109 acquires an image of the subject, and acquires surface condition information of the subject from the acquired image of the subject. The second image processing unit 110 processes the image of the subject based on the surface condition information acquired by the analysis unit 109.
Therefore, it is possible to obtain a subject image that retains the surface condition of the subject based on the surface condition information of the subject. Also, when the surface condition of the subject is lost due to correction of the subject image, it is possible to make the correction part less noticeable based on the surface condition information.

Also, for example, the analysis unit 109 acquires edge components in a predetermined frequency band in the image region of the subject image, and obtains the acquired edge components as surface condition information.
Therefore, it is possible to obtain a subject image that maintains the surface state of the subject, which is made up of edges in a predetermined frequency band.

For example, the second image processing unit 110 processes the subject image that has been subjected to a predetermined process based on the acquired surface condition information. Therefore, it is possible to add the surface condition of the subject to the subject image that has been subjected to a predetermined process.

Furthermore, for example, when a process for making a peculiar area in the subject image less noticeable, such as a smoothing process, is performed, the second image processing unit 110 performs processing based on the surface condition information acquired by the analysis unit 109. Therefore, even if the surface condition of the subject is lost as a result of performing a process for making a peculiar area in the subject image less noticeable, it is possible to perform processing based on the surface condition to make the processed area less noticeable.

For example, the second image processing unit 110 uses protection maps of multiple sizes that mimic the shapes surrounding the peculiar region, performs a predetermined process on each image region including the peculiar region surrounded by the protection maps, obtains reliability information for each image region that has been subjected to the predetermined process using each of the protection maps of multiple sizes, and combines the results of the predetermined processes using the multiple protection maps with different degrees of influence based on the obtained reliability information. Therefore, the processing results obtained using a more reliable protection map can be reflected in the subject image.

For example, the analysis unit 109 analyzes the luminance information of the subject image and modifies the shapes of multiple types of protection maps based on the analysis results. Therefore, it is possible to process the unique regions of the subject image using protection maps with mask shapes that correspond to the subject image.

In addition, the analysis unit 109 and the second image processing unit 110 of the imaging device 1 perform the above processing on a subject image that includes a human skin region, so that a subject image that preserves the texture of the person's skin can be obtained.

The second image processing unit 110 of the imaging device 1 also performs corrections to make the peculiar areas in the subject image less noticeable compared to the surrounding areas, and processes the corrected peculiar areas by adding the surface condition of the subject in the subject image before the correction. Therefore, when a correction is performed to make the peculiar areas of the subject image less noticeable, the correction areas can be made less noticeable.

Note that the description in the above embodiment is a preferred example of the present invention and is not limited to this.

For example, in the above embodiment, the image processing device of the present invention is described as being provided in an imaging device, but the image processing device of the present invention may be separate from the imaging device. For example, the image processing device may perform the processing described with reference to Figures 2 and 3 on image data received from the imaging device. In addition, the original image is not limited to a recorded image, but may be something like a live view image that is sequentially captured by the imaging unit 106 and sequentially displayed on the display unit 103. In this way, it is possible to provide the user with a subject image (face) that always reflects the corrected results.

In addition, in the above embodiment, an example was described in which YUV image data was used, but the type of image data is not particularly limited.

In the above embodiment, the case where both texture and shadow are protected has been described as an example, but it is also possible to protect only one of them.
When only the texture is to be protected, a plurality of texture protection maps with different sizes of protection exclusion areas are generated based on the Y component image of the original image, a correction process is performed on the YUV component image of the original image using each of the plurality of texture protection maps, a reliability of each of the image areas corrected using each of the plurality of texture protection maps is calculated, an α value is calculated for each pixel based on the reliability, and a transparent composite of a plurality of images corrected using each of the plurality of texture protection maps is performed. Also, texture information obtained from the Y component image is added to the transparent composite image and composited with the YUV component image of the original image at a predetermined α value.
When only shadows are to be protected, a plurality of shadow protection maps with different sizes of protection exclusion areas are generated based on the Y component image of the original image, a correction process is performed on the YUV component image of the original image using each of the plurality of shadow protection maps, a reliability of each of the image areas corrected using each of the plurality of shadow protection maps is calculated, an α value is calculated for each pixel based on the reliability, and a transparent composite of the plurality of images corrected using each of the plurality of shadow protection maps is performed, and the transparent composite image is then composited with the YUV component image of the original image using a predetermined α value.

For example, in the above description, a hard disk or a non-volatile semiconductor memory is used as a computer-readable medium for the program according to the present invention, but the present invention is not limited to this example. Portable recording media such as CD-ROMs can be used as other computer-readable media. Carrier waves can also be used as a medium for providing data for the program according to the present invention via a communication line.

In addition, the detailed configuration and operation of each device that constitutes the imaging device may be modified as appropriate without departing from the spirit and scope of the invention.

Although several embodiments of the present invention have been described, the scope of the present invention is not limited to the above-described embodiments, but includes the scope of the invention described in the claims and its equivalents.
The invention as described in the claims originally attached to this application is set forth below. The claim numbers in the appended claims are the same as those in the claims originally attached to this application.
[Additional Notes]
<Claim 1>
An acquisition means for acquiring a subject image;
a texture information acquiring means for acquiring texture information of the subject from the subject image acquired by the acquiring means;
a processing means for processing the subject image based on the texture information acquired by the texture information acquisition means;
An image processing device comprising:
<Claim 2>
an edge component acquiring means for acquiring edge components of a predetermined frequency band in an image region of the subject image,
2. The image processing apparatus according to claim 1, wherein said texture information acquiring means acquires the edge components acquired by said edge component acquiring means as said texture information.
<Claim 3>
Further comprising a processing means for performing a predetermined image processing on the subject image,
3. The image processing apparatus according to claim 1, wherein the processing means processes the subject image, which has been subjected to the predetermined processing by the processing means, based on the texture information acquired by the texture information acquisition means.
<Claim 4>
A detection unit is further provided for detecting a peculiar area different from the surrounding area in the subject image,
The image processing apparatus according to claim 3 , wherein the predetermined processing is processing for making the peculiar area in the subject image less noticeable.
<Claim 5>
The processing means includes:
using mask data of a plurality of sizes imitating shapes surrounding the peculiar region, the predetermined processing is performed on image regions including the peculiar region surrounded by the mask data;
a reliability information acquiring means for acquiring reliability information of each of the image regions to which the predetermined processing has been performed using each of the mask data of the plurality of sizes;
a synthesis means for synthesizing results of predetermined processes in each mask data processed by the processing means while changing the degree of influence based on the reliability information acquired by the reliability information acquisition means;
5. The image processing apparatus according to claim 4, further comprising:
<Claim 6>
an analysis means for analyzing luminance information of the subject image;
a correction means for correcting shapes of the plurality of types of mask data based on an analysis result by the analysis means;
6. The image processing apparatus according to claim 5, further comprising:
<Claim 7>
5. The image processing apparatus according to claim 4, wherein the predetermined processing is a smoothing processing.
<Claim 8>
8. The image processing device according to claim 1, wherein the subject image is an image including a human skin region.
<Claim 9>
An acquisition means for acquiring a subject image;
A detection means for detecting a peculiar area from the subject image that is different from its surroundings;
a correction means for correcting the peculiar area detected by the detection means so as to make it less noticeable compared to the surrounding area;
a control means for controlling a process to add a surface state of the subject in the subject image before the correction by the correction means to the unique region corrected by the correction means so as to be inconspicuous;
An image processing device comprising:
<Claim 10>
An acquisition means for acquiring a subject image;
a detection means for detecting a peculiar area different from a surrounding area in the subject image acquired by the acquisition means;
a processing means for performing a predetermined process on an image area including the peculiar area detected by the detection means and surrounded by a plurality of sizes of mask data imitating shapes surrounding the peculiar area;
a reliability information acquiring means for acquiring reliability information of each of the image regions to which the predetermined processing has been performed using each of the mask data of the plurality of sizes;
a synthesis means for synthesizing results of predetermined processes in each mask data processed by the processing means while changing the degree of influence based on the reliability information acquired by the reliability information acquisition means;
An image processing device comprising:
<Claim 11>
An image processing method in an image processing device, comprising:
acquiring an image of a subject;
acquiring texture information of the object from the acquired image of the object;
processing the subject image based on the acquired texture information;
13. An image processing method comprising:
<Claim 12>
An image processing method in an image processing device, comprising:
acquiring an image of a subject;
detecting a peculiar area from the subject image that is different from its surroundings;
A step of correcting the detected peculiar area so as to make it less noticeable compared to the surrounding area;
and performing a process of adding a surface state of the subject in the subject image before the correction to the peculiar area corrected to be less noticeable.
<Claim 13>
An image processing method in an image processing device, comprising:
acquiring an image of a subject;
detecting a peculiar area in the acquired subject image that is different from a surrounding area;
a step of performing a predetermined process on an image area including the peculiar area surrounded by mask data of a plurality of sizes imitating a shape surrounding the detected peculiar area;
acquiring reliability information for each of the image regions that have been subjected to the predetermined processing using each of the mask data of the plurality of sizes;
a synthesis means for synthesizing the results of the predetermined processing in each of the mask data by changing the degree of influence based on the acquired reliability information;
13. An image processing method comprising:
<Claim 14>
Computer,
An acquisition means for acquiring a subject image;
a texture information acquiring means for acquiring texture information of the subject from the subject image acquired by the acquiring means;
a processing means for processing the subject image based on the texture information acquired by the texture information acquisition means;
A program to function as a
<Claim 15>
Computer,
An acquisition means for acquiring a subject image;
A detection means for detecting a peculiar area from the subject image, the peculiar area being different from its surroundings;
a correction means for correcting the peculiar area detected by the detection means so as to make it less noticeable compared to the surrounding area;
a control means for controlling a process to add a surface state of the subject in the subject image before the correction by the correction means to the unique region corrected by the correction means so as to be inconspicuous;
A program to function as a
<Claim 16>
Computer,
An acquisition means for acquiring a subject image;
a detection means for detecting a peculiar area different from the surrounding area in the subject image acquired by the acquisition means;
a processing means for performing a predetermined process on an image area including the peculiar area detected by the detection means and surrounded by a plurality of sizes of mask data imitating shapes surrounding the peculiar area;
a reliability information acquiring means for acquiring reliability information of each of the image regions to which the predetermined processing has been performed, using each of the mask data of the plurality of sizes;
a synthesis means for synthesizing results of predetermined processes in each mask data processed by the processing means while changing the degree of influence based on the reliability information acquired by the reliability information acquisition means;
A program to function as a

REFERENCE SIGNS LIST 1 Imaging device 101 Control unit 102 Storage unit 103 Display unit 104 Communication unit 105 Operation unit 106 Imaging unit 106a Imaging lens 107 First image processing unit 108 Image memory 109 Analysis unit 20 Skin analysis unit 21 Protection map data setting unit 22 Low-frequency data generation unit 23 Edge information generation unit 24 Region division unit 25 Shadow protection map generation unit 26 Texture protection map generation unit 27 Protection map boundary reliability determination unit 110 Second image processing unit 28 Correction processing unit 29 Transparent synthesis processing unit 30 Synthesis processing unit 111 Illumination control unit 112 Light emission unit

Claims (5)

a processing means for performing a predetermined image processing so as to make acne inconspicuous in a person image and performing a predetermined correction processing only on an area corresponding to the acne, which applies a pair of protection maps generated so that the sizes of the areas targeted for the predetermined correction processing are different from each other to the targeted areas to generate a pair of corrected images by performing the predetermined correction processing on the targeted areas, and synthesizing the pair of corrected images generated;
a setting means for setting the size difference between the pair of protection maps based on a pore size in the person image;
An image processing device comprising: The processing means performs a smoothing process or a texture information adding process as the predetermined correction process.
2. The image processing apparatus according to claim 1, When the pair of corrected images is synthesized, the processing means determines a reliability of each pixel of the pair of corrected images, and synthesizes the pair of corrected images so that an influence of a pixel determined to have a higher reliability between the pair of corrected images is increased.
3. The image processing device according to claim 1, wherein the first and second inputs are input to the image processing device. An image processing method executed by an image processing device, comprising:
a processing step of performing a predetermined image processing so as to make acne inconspicuous in a person image and performing a predetermined correction processing only on an area corresponding to the acne, separately applying a pair of protection maps generated so that the sizes of areas targeted for the predetermined correction processing are different from each other to perform the predetermined correction processing on the targeted areas, thereby generating a pair of corrected images, and synthesizing the pair of generated corrected images;
a setting step of setting the size difference between the pair of protection maps based on a pore size in the person image;
13. An image processing method comprising the steps of: Computer,
a processing means for performing a predetermined image processing so as to make acne inconspicuous in a person image and performing a predetermined correction processing only on an area corresponding to the acne, the processing means applying a pair of protection maps generated so that the sizes of the areas targeted for the predetermined correction processing are different from each other separately to perform the predetermined correction processing on the targeted areas, thereby generating a pair of corrected images, and synthesizing the pair of generated corrected images;
a setting means for setting the size difference between the pair of protection maps based on a pore size in the person image;
A program characterized by causing the program to function as a

Images