JP2006031195A - Image processing program, image processor and automatic photographing device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor and automatic photographing device capable of applying soft focusing only to a specified portion in the face of a person in an image. <P>SOLUTION: This device executes processing for extracting a plurality of nodes on the face from a photographic image; processing for generating a first mask image composed of one or more segment areas with a predetermined width obtained by connecting nodes of a predetermined combination and/or one or more polygonal areas surrounded by a segment connecting three or more nodes of a predetermined combination; processing for generating a second mask image by performing edge processing to the photographic image; processing for generating a blurred image by applying soft focusing processing to the photographic image; and processing for generating an overlap image by overlapping the photographic image for an area covered by the first mask image and the second mask image with the blurred image for out of the area covered by the first mask image and the second mask image. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to an image processing program, an image processing apparatus, and an automatic photography apparatus for performing partial soft focus processing on a photographic image including one or more human images, and in particular, identifying a face such as a cheek or forehead. The present invention relates to an image processing program, an image processing apparatus, and an automatic photography apparatus that can obtain a photographic image in which a soft focus is applied to a part to obtain a photographic image in which the eyes and nose stand and the outline are kept sharp.

  One of the image processes for photographic images taken with a person as a subject is soft focus processing.

This soft focus process makes the color and shade of the image uniform by emphasizing the low-frequency part of the spatial frequency of the image, and hides fine patterns such as pores and acne on the human skin surface. There is an effect, so it is possible to obtain a photographic image with a smooth texture and beautiful appearance. There is a tendency to become an image.
Japanese translation of PCT publication No. 2002-511617

  The present invention has been made in view of the above problems, and provides an image processing program, an image processing apparatus, and an automatic photography apparatus capable of applying a soft focus only to a specific part of a human face in an image. Its purpose is to provide.

  In addition, the present invention provides an image processing program, an image processing apparatus, and an automatic photography apparatus capable of performing a soft focus process on a specific portion such as a cheek or a forehead of a person's face while maintaining sharpness of an eye and nose and a sharp outline. The purpose is to provide.

  The present invention solves the above-described problem, and is an image processing apparatus for adding a partial soft focus to a photographic image in which one or more people's faces are photographed. A node extraction means for extracting from a photographic image, a first mask image composed of one or more predetermined-width line segment regions connecting the nodes of a predetermined combination, and / or three or more of a predetermined combination A first mask image generating means for generating a first mask image comprising one or more polygonal regions surrounded by a line segment connecting the nodes; and generating a second mask image by performing edge processing on the photographic image. Second mask image generating means for generating, a blurred image generating means for generating a blurred image obtained by applying a soft focus process to the photographic image, the first mask image, and the second mask image A superimposed image generating unit that generates a superimposed image by superimposing the photographic image on the area covered by the image and the blurred image on the area other than the area covered by the first mask image and the second mask image. An image processing apparatus characterized by comprising: an automatic photography apparatus comprising a photographing means for photographing a photographic image in addition to the above-mentioned means, or a part of a photographic image obtained by photographing one or more people's faces An image processing program for adding a soft focus, wherein the program connects a process of extracting a plurality of nodes on a face from the photographic image to a computer and a predetermined combination of the nodes. Three or more of the first mask image composed of the line segment region having the predetermined width and / or a predetermined combination. A process for generating a first mask image composed of one or more polygonal regions surrounded by a line segment connecting the nodes, a process for generating a second mask image by performing edge processing on the photographic image, A process of generating a blurred image obtained by adding a soft focus process to a photographic image, the photographic image of an area covered by the first mask image and the second mask image, and the first mask image and the second mask image. A program for executing a process of generating a superimposed image by superimposing the blurred image on a region other than a covered region.

  Nodes in the present invention, each of one or more people appearing in the captured image, pupils, eye corners, eyes, upper and lower eyelids, left and right ends and centers of upper and lower lips, nasal apex, upper nostril, and lower, between eyebrows, These are predetermined face parts such as the eyebrows, the eyebrows, and the center of the eyebrows, and such nodes are disclosed in WO99 / 08935 International Publication, or in Japanese and US based on this, Special Table 2002 -511617 and US Pat. No. 6,391,370 can be extracted by the method (elastic graph matching method).

  In addition, the first mask image of the present invention includes one or more line segments having a predetermined width obtained by connecting the nodes in a predetermined combination and / or three or more of the predetermined combinations. It is an image composed of one or more polygonal regions surrounded by a plurality of line segments connecting nodes.

  These line segment areas and polygonal areas are facial features such as the nose bridge, nose, lips, and eyebrows, but the changes in shades and shades are comparatively gentle. In the processing, it is preferable that the region is not necessarily detected as an edge region. For example, two line segments each having a predetermined width connecting the right and left eyebrows-brow head-brow center and the eyebrow center-brow edge, and the left-eye eye-eye corner -The upper and lower eyelids are connected in sequence to each of the four line segments with a predetermined width, the line segment with a predetermined width connecting the eyebrow-nose apex, etc. A quadrilateral having four points of 瞼 -lower heel as vertices can be used as the polygon region.

  The second mask image of the present invention is an image generated by performing edge processing on the captured image.

  Here, the edge process is a process performed to extract, as an edge area, a boundary area where the hue or shading changes abruptly, such as a person's eyes, lips, eyebrows, and face contours in an image. The second mask image can be obtained by using, as the edge region, pixels in which the high frequency portion of the captured image exceeds a certain threshold.

  In addition, the blurred image in the present invention is an image generated by applying a soft focus process to a captured image.

  Here, the soft focus process is a process that is performed in order to make the hue and shade of each part of the image uniform. For example, the output of the mid- and high-frequency parts of the spatial frequency of the captured image is reduced to reduce the low-frequency range. It is possible to obtain a blurred image by emphasizing a part.

  Further, the superimposed image in the present invention includes a captured image of an area covered by the first mask image and the second mask image, and an area other than the area covered by the first mask image and the second mask image. This is an image generated by superimposing the blurred image.

  That is, the pixel value of the pixel corresponding to the pixel in the captured image is given to the pixel included in the line segment area and / or the polygonal area in the first mask image and the edge area in the second mask image. In addition, a pixel that is not included in any of the line segment area, the polygon area, and the edge area is given the pixel value of the pixel corresponding to the pixel in the blurred image, so that a superimposed image is generated. .

  Therefore, in the present invention, as a superimposed image, for example, a region that does not belong to any of a line segment area, a polygon area, and an edge area, such as a cheek or a forehead, is subjected to a soft focus process, and acne and Fine patterns due to spots or pores are made inconspicuous, and are extracted by edge processing such as contours, and areas that are line segments and polygonal areas such as the eyes, nose, and mouth Since no soft focus processing is applied, it is possible to obtain a photographic image in which the sharpness of the image is not impaired.

  In the present invention, an unsharpness mask image in which the sharpness of the image is improved by performing unsharpness mask processing on the photographic image is generated, and the region covered by the first mask image and the second mask image is generated. It is also possible to generate a superimposed image by superimposing an unsharpness mask image and a blurred image for regions other than those covered by the first mask image and the second mask image. It is possible to further increase the sharpness.

  In the automatic photographing apparatus of the present invention, the standing position of the user is derived from the extracted node position, and based on this, the focal position and focal length of the photographing means are adjusted, or at the time of photographing. It is possible to adjust the illumination intensity, and thereby it is possible to take a picture under more appropriate conditions.

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

  FIG. 1 is an explanatory diagram showing a hardware configuration of an image processing apparatus 10 according to an embodiment of the present invention.

  As shown in the figure, the image processing apparatus 10 exchanges image information with a CPU 11, a recording apparatus 12 mainly composed of a ROM, a RAM, a hard disk, and the like, and external devices such as a CCD camera 13 and a printer 14. It is a personal computer provided with an interface 15 for performing the above.

  FIG. 2 shows functional blocks realized by the CPU 11 executing the image processing program of the present invention recorded on the recording device 12.

  As illustrated, the functional block of the image processing apparatus 10 includes a processing unit 20 and a recording unit 30. The processing unit 20 includes a node extraction unit 21, a first mask image generation unit 22, and a second mask image. The generation unit 23, the blurred image generation unit 24, and the superimposed image generation unit 25, and the recording unit 30 records a photographic image obtained by photographing one or more human faces captured from the CCD camera 13 or the like. A captured image recording unit 31, a first mask image generation unit 22, a second mask image generation unit 23, a blurred image generation unit 24, a first mask image generated by the superimposed image generation unit 25, a second mask image, A first mask image recording unit 32, a second mask image recording unit 33, a blurred image recording unit 34, and a superimposed image recording unit 3 for recording a blurred image and a superimposed image, respectively. It is constructed from.

Here, the node extracting means 21 is an elastic material described in WO99 / 08935 International Publication, or JP-T 2002-511617 and US Pat. No. 6,391,370 published in Japan and the United States based on this. Based on the graph matching method, 32 nodes indicated by the node numbers 0 to 31 on the face shown in Table 1 and FIG. 3 are extracted from the photographic image of the captured image recording unit 31.

Further, the first mask image generation means 22 connects the 34 combinations of nodes shown in Table 2 from the 32 nodes, so that the first mask composed of 34 line segment regions as shown in FIG. Generate an image.

  Here, each line segment region may be connected with a different line width for each line segment region, or all line segment regions may be connected with the same line width. Depending on the size of the face part in the image, such as increasing the line width of each line segment region, the greater the distance between the left and right pupil nodes of node numbers “0” and “1” It is preferable to adjust the line width of the line segment region.

  The second mask image generating means 23 generates a pixel pattern in which the high frequency portion of the spatial frequency of the photographic image of the photographed image recording unit 31 exceeds a certain threshold value as the second mask image (see FIG. 5). .

  Further, the blurred image generating means 24 reduces the output of the middle and high frequency portions of the spatial frequency of the photographic image of the photographed image recording unit 31 and emphasizes the low frequency portion to thereby enhance the low frequency portion. Is to be generated.

  The superimposed image generation unit 24 uses a composite mask image as shown in FIG. 6 obtained by combining the first mask image and the second mask image, and a portion other than the composite mask image becomes a blurred image. An image as shown in FIG. 7 is generated, and an image in which the portion of the composite mask image is a photographic image is superimposed on this to generate a superimposed image as shown in FIG.

  The superimposed images obtained in this way are used for edge regions such as facial contours and line segments such as the eyes, mouth, nasal bridge, nose and eyebrows, while sharp photo images are used. Parts such as cheeks and forehead that are not included in the area and line segment area have a soft texture and the image is beautiful and the sharpness of the image is not impaired because a soft-focused blurred image is used. .

  Subsequently, an embodiment according to the automatic photography apparatus of the present invention will be described.

  FIG. 9 is a cross-sectional explanatory view showing the internal structure of the automatic photography apparatus 40 according to one embodiment of the present invention, and FIG. 10 is a front view of a housing 50 provided in the automatic photography apparatus 40.

  As shown in the figure, the automatic photographing apparatus 40 includes a housing 50 and a photographing booth 70. The housing 50 has a first focus position and a focal length that can be adjusted. In addition to the second CCD cameras 51 and 52 and the liquid crystal monitor 53, a control device 80 and a printer 95, which will be described later, are provided.

  Further, reference numeral 54 in FIG. 9 denotes a half mirror. The half mirror 54 reflects the image on the liquid crystal monitor 53 in the direction of the display window 55 and also displays the user image from the display window 55 in the first CCD camera 51. It has a function of transmitting in the direction and enables confirmation of an image on the liquid crystal monitor 53 from the display window 55 and photographing from the first CCD camera 51 of the user located in front of the display window 55. is there.

  Furthermore, on the front surface of the housing 50, flashlights 56 and 57 whose illumination intensity can be adjusted and diffusion windows 58 and 59 for illuminating the user by diffusing the flashlight are provided.

  Further, the rear surface of the casing 50 is a graffiti corner, and an edit input device 60 having a touch panel monitor and a touch pen is provided for inputting graffiti on the images taken by the CCD cameras 51 and 52. It has been.

  In addition, a shooting space for accommodating a user is formed between the booth rear surface 71 of the shooting booth 70 and the housing 50, and a flashlight 72 whose illumination intensity can be adjusted on the ceiling of the shooting booth 70. 73, diffusion windows 74 and 75 thereof, and ceiling lighting 76 capable of performing illumination in various color tones.

Further, as shown in FIG. 10, in addition to the display window 55, the second CCD camera 52, and the diffusion windows 58 and 59, the first and second CCD cameras 51 and 52 are disposed on the front surface of the housing 50. Monitors 61 and 62 for displaying real-time captured images, an operation panel 63 for inputting various operations, a coin insertion slot 64 for accepting coin insertion, and a speaker 65 are provided.

The shooting booth 70 further includes two side surfaces (not shown) that further limit the shooting space formed by the casing 50 and the booth back surface 71 from the left and right sides. An opening used as an entrance / exit provided with an accordion door is provided.

  FIG. 11 is an explanatory diagram showing a system configuration of the automatic photography apparatus 40.

  The control device 80 includes a CPU 82 connected to each other by a bus 81, a ROM 83 for storing a basic program for controlling the CPU 82, a RAM 84 for recording work data and temporary data for the CPU 82, and an image processing program of the present invention. The personal computer includes a hard disk 86, a CD-ROM drive 87, and an interface (I / F) 85 in which programs and various data necessary for the operation of the photographic device 40 are stored. In accordance with the control, the camera control device 90 for controlling the photographing by the first and second CCD cameras 51 and 52 and the illumination control for controlling the illumination intensity and the illumination timing of the flashlights 56, 57, 72 and 73 Recorded on device 91 and hard disk 86 External devices such as an acoustic control device 92 for reproducing acoustic information and image information from the speaker 65, the liquid crystal monitor 53, and the like, an image control device 93, and an editing input device 60 for receiving editing input are connected. Signals can be exchanged with devices.

  The coin processing unit 94 detects coins inserted into the coin insertion slot 64, and notifies the CPU 82 when a predetermined usage fee is paid. Is printed on, for example, an A6 size photo sticker and discharged to a photo sticker discharge port (not shown).

  Hereinafter, the operation of the automatic photography apparatus 40 will be described with reference to the flowchart shown in FIG.

  When the CPU 82 receives a coin detection signal of a predetermined amount from the coin processing unit 94, the CPU 82 selects a plurality of theme options such as “snow”, “sunset”, “romantic”, “horror” on the liquid crystal monitor 53. The theme is displayed and the selection of the theme by the user is accepted (step S1).

  When the user selects any one of the themes by operating the buttons on the operation panel 63, video and audio corresponding to the selected theme are output from the liquid crystal monitor 53 and the speaker 65, and a predetermined value corresponding to this is output. At this timing, photography by the CCD cameras 51 and 52 is repeatedly executed a predetermined number of times (step S2).

  Here, the CPU 82 extracts the positions of the left and right pupils of the user, which is the subject, by the elastic graph matching method based on the momentary images acquired by the CCD cameras 51 and 52 in each photo shoot. The focal positions of the CCD cameras 51 and 52 are adjusted to the center position, and the user's standing position (the distance from the user to the CCD cameras 51 and 52) is derived from the distance between the left and right pupils. , 52 is adjusted.

  Further, when the distance from the user derived as described above to the CCD cameras 51 and 52 is large, the CPU 82 controls the illumination control device 91 so that the illumination intensity of the flashlights 56, 57 and 72 is increased. Accordingly, illumination light with sufficient brightness is always irradiated to the user regardless of the position of the user.

  Note that when there are a plurality of users as subjects, the CPU 82 uses the above-mentioned focal position, focal length, and distance based on the user with the largest distance between the left and right pupils extracted for each user. The illumination intensity is adjusted.

  When the photography step is completed, a narration that prompts the user to move to the scribing corner on the back of the housing 50 is output from the speaker 65 (step S3), and then an editing input step (step S4) is executed. Is done.

  The CPU 82 executes the image processing program of the present invention in parallel with the processing of the above steps S2 to S3, and superimposes by adding a partial soft focus to each photographed image. While generating an image, the process which synthesize | combines the frame image prepared for every theme selected in step S1 is performed.

  FIG. 13 shows functional blocks realized by the CPU 82 executing this image processing program.

  This functional block is the same as the functional block shown in FIG. 4 except for the face mask image generating unit 26, the frame composite image generating unit 27, the face mask image recording unit 36, and the frame image recording unit 37, and FIG. 4 has been described. Operates in a manner similar to the embodiment.

  That is, the node extracting means 21 uses the elasticity graph matching method to obtain 32 users shown in Table 1 and FIG. 3 for each user photographed in the photograph image. The nodes are extracted, and the first mask image generating means 22 connects the 34 combinations of nodes shown in Table 2 to form 34 line segment regions as shown in FIG. 4 for each user. The generated first mask image is generated, and the second mask image generating means 23 generates, as the second mask image, a region where the high frequency portion of the spatial frequency of each photographed image exceeds a certain threshold value (FIG. 5). The blurred image generation means 24 generates a soft-focused image by emphasizing the low frequency portion of the spatial frequency of each photographic image, and generates the first mask image and the second mask image generated thereby. Click image and blurring the image, the first mask image recording unit 32, respectively, the second mask image recording unit 33 is recorded in the blurred image recording unit 34.

  Further, the superimposed image generation means 25 uses a composite mask image as shown in FIG. 6 obtained by combining the first mask image and the second mask image, and a portion other than the composite mask image is a blurred image. An image as shown in FIG. 7 is generated, and an image in which the portion of the composite mask image is a photographic image is superimposed on the image to generate a superimposed image as shown in FIG.

  Further, the face mask image generation means 26 derives 11 positions such as chin, heel, temple, forehead, etc. for each user based on the 32 nodes extracted for each user. By connecting the lines, a face mask image composed of a polygonal region covering the face portion of each user as shown in FIG. 14 is generated and recorded in the face mask image recording unit 36.

  In addition, the frame image recording unit 37 records frame images prepared for each theme, such as an image of a pattern in which powder snow is dancing, for example, in the case of “snow” theme. The image generation unit 27 uses the frame image corresponding to the theme selected in step S1, the face mask image recorded in the face mask image recording unit 36, and the superimposed image recorded in the superimposed image recording unit 35. Thus, the mask area of the face mask image (polygonal area covering the face portion) is an overlay image, and the image other than the mask area of the face mask image is an image in which the frame image is combined with the overlay image as the foreground. A frame composite image is generated.

  In the edit input step (step S4), the frame composite image generated as described above for each photographed photographic image is displayed on the touch panel monitor of the edit input device 60, and according to the operation with the attached touch pen. Editing such as line drawing, stamp image pasting, frame processing, etc. can be performed on the frame composite image.

  When the editing input step (step S4) is completed, the layout receiving step (step S5) is executed, and the frame composite image edited in step S4 and the recommended layout are displayed on the touch panel monitor of the editing input device 60. The image print layout can be set by the user selecting an image and a layout that the user desires to print with an attached touch pen.

  After the layout setting is completed, the selected image and layout data are transmitted to the printer 71 by the CPU 82, and printing of the photo print (step S6) is executed, and the printed photo print is used from the photo discharge port. Provided to the person.

  As described above, the image processing program, the image processing apparatus, and the automatic photography apparatus according to the present invention have been described based on one embodiment. However, the present invention is not limited to the above-described embodiment, and is within the scope of the claims. Various modifications are possible within the scope of the description.

  For example, the combinations of the nodes shown in Tables 1 and 2 and the nodes for generating the line segment regions are illustrated as the most preferable forms, and only a part of the nodes shown in Table 1 are extracted and displayed. Nodes other than those shown in FIG. 1 can be extracted, and a line segment region can be generated by connecting nodes other than those shown in Table 2.

  In the above-described embodiment, the case where the first mask image is formed by one or more line segments having a predetermined width connecting nodes of a predetermined combination has been described. However, three or more nodes of a predetermined combination are used. The first mask image may be formed by one or more polygonal areas surrounded by the line segments connected to each other, or a combination of such polygonal areas and line segment areas.

  In addition, it is not always necessary to extract a node based on a still image in the present invention, and it is also possible to extract based on a moving image. Similarly, a first mask image, a second mask image, and a blurred image are also possible. The superimposed image, the unsharpness mask image, and the frame composite image can be generated as a still image or a moving image.

  In addition to soft focus processing and unsharpness mask processing, it is also possible to perform additional image processing such as color correction and density correction on photographic images, superimposed images, unsharpness mask images, and frame composite images. is there.

1 is an explanatory diagram illustrating a hardware configuration of an image processing apparatus according to an embodiment of the present invention. Explanatory drawing which shows the functional block implement | achieved by running the image processing program which concerns on one Embodiment of this invention. Explanatory drawing which shows the example node extracted in this invention. Explanatory drawing which shows an example 1st mask image. Explanatory drawing which shows an example 2nd mask image. Explanatory drawing which shows an example synthetic | combination mask image. Explanatory drawing which shows the state which applied the blurring image to parts other than a synthetic | combination mask image. Explanatory drawing which shows an example superimposed image. Cross-sectional explanatory drawing which shows the internal structure of the automatic photography apparatus which concerns on one Embodiment of this invention. The front view of the housing | casing with which the automatic photography apparatus concerning one Embodiment of this invention is provided. BRIEF DESCRIPTION OF THE DRAWINGS Explanatory drawing which shows the system configuration | structure of the automatic photography apparatus concerning one Embodiment of this invention. The flowchart which shows operation | movement of the automatic photography apparatus concerning one Embodiment of this invention. Explanatory drawing which shows the functional block implement | achieved by running the image processing program which concerns on one Embodiment of this invention. Explanatory drawing of an example face mask image.

Explanation of symbols

10 Image processing device 11 CPU
12 recording device 13 camera 14 printer 15 interface 20 processing unit 21 node extraction unit 22 first mask image generation unit 23 second mask image generation unit 24 blurred image generation unit 25 superimposed image generation unit 26 face mask image generation unit 27 frame synthesis Image generating means 30 Recording unit 31 Captured image recording unit 32 First mask image recording unit 33 Second mask image recording unit 34 Blurred image recording unit 35 Superposed image recording unit 36 Face mask image recording unit 37 Frame image recording unit 40 Automatic photograph Imaging device 50 Housing 51, 52 CCD camera 53 Liquid crystal monitor 54 Half mirror 55 Display window 56, 57, 72, 73 Flashlight 58, 59, 74, 75 Diffusion window 60 Editing input device 61, 62 Monitor 63 Operation panel 64 Coin Input port 65 Speaker 70 Shooting booth 71 Back of booth 76 Ceiling lighting 80 Controller 81 Bus 82 CPU
83 ROM
84 RAM
85 Interface 86 Hard disk 87 CD-ROM drive 90 Camera control device 91 Illumination control device 92 Sound control device 93 Image control device 94 Coin processing unit 95 Printer

Claims (12)

An image processing apparatus for adding a partial soft focus to a photographic image in which one or more faces of people are photographed,
Node extraction means for extracting a plurality of nodes on the face from the photographic image;
First mask image generation means for generating a first mask image composed of one or more line segments having a predetermined width connecting the nodes in a predetermined combination;
Second mask image generation means for generating a second mask image by performing edge processing on the photographic image;
A blurred image generating means for generating a blurred image obtained by applying a soft focus process to the photographic image;
The photographic image for the area covered by the first mask image and the second mask image and the blurred image for the area other than the area covered by the first mask image and the second mask image are overlapped. An image processing apparatus comprising: a superimposed image generation unit that generates a combined image.   The image processing apparatus according to claim 1, wherein a line width of the line segment region is changed according to a distance between two nodes selected from the plurality of nodes. An image processing apparatus for adding a partial soft focus to a photographic image in which one or more faces of people are photographed,
Node extraction means for extracting a plurality of nodes on the face from the photographic image;
First mask image generation means for generating a first mask image comprising one or more polygonal regions surrounded by a line segment connecting three or more nodes of a predetermined combination;
Second mask image generation means for generating a second mask image by performing edge processing on the photographic image;
A blurred image generating means for generating a blurred image obtained by applying a soft focus process to the photographic image;
The photographic image for the area covered by the first mask image and the second mask image and the blurred image for the area other than the area covered by the first mask image and the second mask image are overlapped. An image processing apparatus comprising: a superimposed image generation unit that generates a combined image.   The image processing apparatus according to claim 1, wherein the plurality of nodes are extracted by an elastic graph matching method. Further comprising unsharpness mask image generation means for generating an unsharpness mask image obtained by adding unsharpness mask processing to the photographic image,
The superimposed image generation unit is configured to perform the unsharpness mask image for the area covered by the first mask image and the second mask image, and the area other than the area covered by the first mask image and the second mask image. The image processing apparatus according to claim 1, wherein a superimposed image is generated by superimposing the blurred image. An image processing program for adding a partial soft focus to a photographic image in which a face of one or more persons is photographed,
The program is stored in a computer.
Extracting a plurality of nodes on the face from the photographic image;
Processing for generating a first mask image composed of one or more line segments having a predetermined width connecting the nodes in a predetermined combination;
Processing to generate a second mask image by performing edge processing on the photographic image;
Processing for generating a blurred image obtained by adding soft focus processing to the photographic image;
The photographic image for the area covered by the first mask image and the second mask image and the blurred image for the area other than the area covered by the first mask image and the second mask image are overlapped. A program for executing a process for generating a combined image. An image processing program for adding a partial soft focus to a photographic image in which a face of one or more persons is photographed,
The program is stored in a computer.
Extracting a plurality of nodes on the face from the photographic image;
Processing to generate a first mask image composed of one or more polygonal regions surrounded by a line segment connecting three or more nodes of a predetermined combination;
Processing to generate a second mask image by performing edge processing on the photographic image;
Processing for generating a blurred image obtained by adding soft focus processing to the photographic image;
The photographic image for the area covered by the first mask image and the second mask image and the blurred image for the area other than the area covered by the first mask image and the second mask image are overlapped. A program for executing a process for generating a combined image. Photographing means for photographing photographic images;
Node extracting means for extracting a plurality of nodes on the face from the photographic image photographed by the photographing means including one or more human faces;
First mask image generation means for generating a first mask image composed of one or more line segments having a predetermined width connecting the nodes in a predetermined combination;
Second mask image generation means for generating a second mask image by performing edge processing on the photographic image;
A blurred image generating means for generating a blurred image obtained by applying a soft focus process to the photographic image;
The photographic image for the area covered by the first mask image and the second mask image and the blurred image for the area other than the area covered by the first mask image and the second mask image are overlapped. An automatic photography apparatus comprising: a superimposed image generation means for generating a combined image. Photographing means for photographing photographic images;
Node extracting means for extracting a plurality of nodes on the face from the photographic image photographed by the photographing means including one or more human faces;
First mask image generation means for generating a first mask image comprising one or more polygonal regions surrounded by a line segment connecting three or more nodes of a predetermined combination;
Second mask image generation means for generating a second mask image by performing edge processing on the photographic image;
A blurred image generating means for generating a blurred image obtained by applying a soft focus process to the photographic image;
The photographic image for the area covered by the first mask image and the second mask image and the blurred image for the area other than the area covered by the first mask image and the second mask image are overlapped. An automatic photography apparatus comprising: a superimposed image generation means for generating a combined image.   10. The automatic photographing apparatus according to claim 8, further comprising a focal length adjusting unit that adjusts a focal length of the photographing unit according to a distance between two nodes selected from the node.   The illumination intensity adjusting means for adjusting the illumination intensity at the time of photographing by the photographing means according to the distance between two nodes selected from the nodes is further provided. The automatic photography apparatus described in the item. The automatic photograph photographing apparatus according to claim 8, further comprising a focal position adjusting unit that adjusts a focal position of the photographing unit based on a position of the node.

Images