JP2006119844A - Image processor, image processing method and image processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a device, method and program for image processing, capable of selecting a facial image most suitable for viewing for every person and synthesizing it to a "background" template image. <P>SOLUTION: An eye opening and closing detection part specifies eye areas where the eyes are present in a plurality of facial images of the same person. The eye areas can be determined based on the relative positional relation between a facial contour and the eyes. The eye opening and closing detection part detects vertical black pixel numbers in the eye areas of the plurality of facial images, respectively. The eye opening and closing detection part specifies a facial image with the closed eyes based on the vertical black pixcel number in each eye area E. A face selection part 13 selects one facial image except the facial image with the closed eyes from facial images classified by person as a best shot facial image. A synthesis part 15 arranges the best shot facial image fn* in a synthesis area Pn, and synthesizes the facial image fn* with a template image. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to an image processing apparatus, an image processing method, and an image processing program, and more particularly, to an apparatus, a method, and a program for extracting a face portion of a person and synthesizing it at a predetermined position of a template image.

Conventionally, various techniques for easily synthesizing a face image, which is an image of a face portion of a person image, a background image, and a clothing image have been developed. For example, according to Patent Document 1, while specifying two points as a reference for synthesis in a background image, a clothing image, and the like, the hair region of the face image and the inside of the face outline are used as a region for synthesis, Specify two points. Two points serving as a reference for the synthesis of the face image are specified so that the midpoint of the line connecting the two points is on the tip of the jaw on the horizontal line passing through the tip of the jaw and the length is the width of the face. Then, the portrait image is generated by mapping the region used for the synthesis of the face image so that the two points designated for the face image and the two points designated for the background image overlap.
Japanese Patent Laid-Open No. 10-222649

  By the way, recently, the character character's face part is blanked out, and a so-called “skin” -like template is created by inserting a face image extracted from an image obtained by photographing a plurality of persons into the blank part. Images are being developed. In the technique of Patent Document 1, when there are a plurality of persons recorded in a photographed image from which a face image is extracted, it is impossible to select which person's face image is to be combined. In other words, it cannot meet the need to compose only the face of a specific person such as a good friend from a group photo into a template. The present invention has been made in view of such problems, and an object of the present invention is to provide an image processing apparatus, method, and program capable of selecting a desired face image and synthesizing it into a “crisp” template image. .

  In order to solve the above-described problems, an image processing apparatus according to the present invention includes a captured image input unit that inputs a captured image in which a person's face portion is recorded, a detection unit that detects a person's face portion, and a detected face A face selection unit that accepts selection of a desired face part from a part, an extraction part that extracts a face image that is an image of the selected face part from a photographed image, and a synthesis that is a blank area in which the extracted face image is placed A template image input unit for inputting a template image having a region, and a composition in which the extracted face image is arranged in a template image synthesis region, and a composite image is created by synthesizing the face image arranged in the synthesis region and the template image. A section.

  According to the present invention, selection of an arbitrary face part from a face part detected from a photographed image input from a digital camera or a recording medium is accepted, and a face image that is an image of the selected face part is extracted. It is possible to create a composite image that is synthesized with the blank portion of the template image in the form of a “blade”. That is, it is possible to provide an interesting image in which only a face image of a specific person such as his / her friend is combined with a template image from the group photo.

  The face selection unit may accept selection of a desired face portion from a terminal connected via a network. Alternatively, an operation unit that receives an operation input may be further provided, and the face selection unit may receive a selection of a desired face portion from the operation unit.

  A captured image selection unit that accepts selection of a desired captured image from the input captured images may be further included, and the detection unit may detect a face portion from the selected captured image.

  You may further provide the output part which outputs a synthesized image to a predetermined | prescribed apparatus.

  The predetermined device is a terminal connected via a network. Alternatively, the predetermined device is a printer or a media writer.

  In order to solve the above-described problem, an image processing method according to the present invention includes a captured image input step for inputting a captured image in which a human face portion is recorded, a detection step for detecting a human face portion, and a detection step. A face selection step for accepting selection of a desired face portion from the selected face portion, an extraction step for extracting a face image, which is an image of the selected face portion, from a photographed image, and a blank area for arranging the extracted face image A template image input step for inputting a template image having a certain synthesis area, and the extracted face image is arranged in the synthesis area of the template image, and a synthesized image is created by synthesizing the face image arranged in the synthesis area and the template image. And a synthesizing step.

  This image processing method has the same effects as the above-described image processing apparatus.

  In order to solve the above-described problems, an image processing program according to the present invention detects a photographed image input step for inputting a photographed image in which a person's face is recorded, a detection step for detecting a person's face. A face selection step for accepting selection of a desired face portion from the selected face portion, an extraction step for extracting a face image, which is an image of the selected face portion, from a photographed image, and a blank area for arranging the extracted face image A template image input step for inputting a template image having a certain synthesis area, and the extracted face image is arranged in the synthesis area of the template image, and a synthesized image is created by synthesizing the face image arranged in the synthesis area and the template image. And a synthesizing step to be executed by a computer.

  This image processing program has the same effects as the above-described image processing apparatus. The image processing program may be provided by being recorded on a CD-ROM, DVD, MO, or other computer-readable recording medium.

  According to the present invention, selection of an arbitrary face part from a face part detected from a photographed image input from a digital camera or a recording medium is accepted, and a face image that is an image of the selected face part is extracted. It is possible to create a composite image that is synthesized with the blank portion of the template image in the form of a “blade”. That is, it is possible to provide an interesting image in which only a face image of a specific person such as his / her friend is combined with a template image from the group photo.

  Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.

<First Embodiment>
[Schematic configuration]
FIG. 1 is a schematic functional configuration diagram of an image processing apparatus 100 and a composite photograph providing system using the apparatus according to a preferred first embodiment of the present invention. The composite photograph providing system is configured by connecting the image processing apparatus 100, the personal computer 200, and the storefront terminal 300 to each other via a network 400 such as the Internet. In this figure, only one personal computer 200 and one store terminal 300 are shown, but actually, a plurality of personal computers 200 and store terminals 300 are connected to the image processing apparatus 100. In this case, the image processing apparatus 100 identifies each of the personal computer 200 or the storefront terminal 300 with unique identification information. That is, the personal computer 200 or the storefront terminal 300 is a terminal connected to the image processing apparatus 100 in parallel via a network. Hereinafter, identification information of these terminals is represented by terminal IDs. The image processing apparatus 100 may authenticate the connection from the terminal with a password in addition to the terminal ID, and connect only the terminal for which authentication has been completed. The terminal ID may be information input by the user from the personal computer 200 and the operation unit 304 of the storefront terminal 300, or may be unique information previously assigned to the terminal such as a network address.

  The image processing apparatus 100 includes a processing unit 1 configured by a CPU, a one-chip microcomputer, a storage unit 2 configured by a semiconductor memory, a network I / F 3 that connects the processing unit 1 to a network 400, a media reader, a USB port, and the like It has a template input unit 4 composed of various data input devices and a photographed image DB 5 composed of various mass storage devices such as a hard disk. The processing unit 1 includes a captured image input unit 10, a captured image selection unit 11, a face detection unit 12, a face selection unit 13, a face extraction unit 14, a synthesis unit 15, and an output unit 16 that are programs stored in the storage unit 2. Read from the storage unit 2 as appropriate and execute. The captured image input unit 10 inputs a captured image digitally recorded by a digital still camera, a film scanner, or the like from the personal computer 200 or the store terminal 300 via the network 400 and the network I / F 3. The captured image input unit 1 can be realized by a file upload function of an FTP (File Transfer Protocol) server. The input captured image is stored in the captured image DB 5 in association with an image ID that is information for uniquely identifying the image.

  FIG. 2 is a conceptual explanatory diagram of information stored in the photographed image DB 5. As shown in this figure, the captured image DB 5 stores an image ID and a captured image in association with each other. The image ID may be anything as long as it is unique information, and may be used as the image ID if the file name of the photographed image is unique.

  The captured image selection unit 11 receives selection of a desired captured image from the captured image stored in the captured image DB 5 from the personal computer 200 or the store terminal 300. The selected photographed image is stored in the storage unit 2. It should be noted that the images that can be selected according to the user operating the personal computer 200 or the storefront terminal 300 may be limited. In this case, as shown in FIG. 3, the photographed image DB 5 stores a user ID, which is user identification information, an image ID, and a photographed image in association with each other. A desired photographed image is selected from the photographed images corresponding to the user ID of the user who operates 300. The correspondence between the user ID and the image ID is a user assigned to a user belonging to a certain group such as a school class, an event participant, or a tour trip participant (for example, user IDs “u001” and “u002” in FIG. 3). If the same image ID is made to correspond to the ID (for example, the image ID “I001” in FIG. 3), members of the same group can select the same captured image.

  The face detection unit 12 detects a face portion of a person from a captured image stored in the storage unit 2 by a known face recognition technique. When a plurality of persons are recorded in the captured image, a plurality of face portions are individually detected. The detected face portion is stored in the storage unit 2.

  The face selection unit 13 receives a selection of a desired face part from the detected face part from the personal computer 200 or the store terminal 300. The face extraction unit 14 extracts a face image, which is an image of a face part that has been selected by the face selection unit 13, from the captured image. The extracted face image is stored in the storage unit 2.

  The template input unit 4 includes a media reader, a USB port, and the like, and accepts template image input from a CD-R or the like. As shown in FIG. 4, the template image has a synthesis area (Pn: n = 1 to 3 in this figure) that is a “clear” -shaped blank area that synthesizes the face image. The shape and number of composite areas and the design of the template image are not limited to those shown in the figure.

  The synthesis unit 15 creates a synthesized image by arranging the face image stored in the storage unit 2 in the template image synthesis area. The created composite image may be stored in the storage unit 2 or may be stored in the captured image DB 5 in association with the user ID for identifying the personal computer 200 or the store terminal 300 that has selected the captured image and the face portion. Good. The output unit 16 sends the created composite image to the personal computer 200 or the store terminal 300 via the network 400.

  The store terminal 300 is a terminal that receives a print order of a photographed image or a composite image for a fee, and prints it. The printer 301 that prints the composite image or the photographed image sent from the output unit 16, the composite image as a CD-R, or the like. A media writer 302 that writes to a predetermined storage medium, a display unit 303 configured by a liquid crystal display, an operation unit 304 configured by a touch panel, a pointing device, etc., a coin machine 305 that performs cash settlement of a print order fee, a CD-ROM And a media reader 306 for reading a photographed image from various recording media such as a compact flash or the like. Similarly, the personal computer 200 includes a media writer 302, a display unit 303, an operation unit 304, a media reader 304, and the like. In order to sell the print of the composite image in cash, the photographed image and the face portion can be selected only from the store terminal 300, and only the photographed image can be input from the personal computer 200. Although not shown, the image processing apparatus 100 or the personal computer 200 may be connected to a printer 301 that prints a composite image, or may include a media writer 302 that stores the composite image in a predetermined storage medium. Good.

[Process flow]
Next, the flow of the composite image providing process executed by the image processing apparatus 100 will be described based on the flowchart of FIG.

  In S <b> 1, the captured image input unit 10 inputs a captured image via the network 400 from the personal computer 200 or the media reader 306 of the storefront terminal 300. FIG. 6 is an example of a captured image input to the captured image input unit 10. In the photographed image, a plurality of persons Fn (here, n = 1 to 6) are recorded as a group photo. The subject of the captured image to be input is not particularly limited except that it includes a plurality of persons. The captured image input unit 10 assigns a unique image ID to the input captured image, and associates this with the captured image and stores it in the captured image DB 5.

  In S <b> 2, the photographed image selection unit 11 receives selection of a desired photographed image from the photographed images stored in the photographed image DB 5 from the personal computer 200 or the operation unit 304 of the store terminal 300. Note that the personal computer 200 or the storefront terminal 300 for inputting a captured image and the personal computer 200 or the storefront terminal 300 for selecting a captured image may be irrelevant. However, as described above, there is a restriction that a desired photographed image is selected from photographed images corresponding to the user ID assigned to the user who uses the personal computer 200 or the storefront terminal 300 to select the photographed image. You can also.

  In S <b> 3, the face detection unit 12 detects a human face portion from the selected captured image. In FIG. 6, face portions f1 to f6 of six persons F1 to F6 are detected. The detection result of the face portion is converted by the output unit 16 into data that can be viewed on the personal computer 200 or the store terminal 300 such as a Web page, and is sent to the personal computer 200 or the store terminal 300 and displayed on the display unit 303.

  In S <b> 4, the face selection unit 13 receives selection of a desired face part from the detected face part from the personal computer 200 or the operation unit 304 of the storefront terminal 300. The selection result is displayed on the display unit 303. In FIG. 6, the face portions f1, f5, and f6 are selected. Markers X 1, X 5, and X 6 are displayed around the selected face portion, so that it can be confirmed on the display unit 303 of the personal computer 200 or the store terminal 300 which face portion is selected.

  In S <b> 5, the face extraction unit 14 extracts (trims) a face image, which is an image of the face part that is selected by the face selection unit 13, from the captured image.

  In S6, the extracted face image is placed in the template image combining region and combined. Note that which face image is arranged in which composition area is arbitrary, and may be arranged randomly, or may be designated from the operation unit 304 of the personal computer 200 or the store terminal 300. For example, as shown in FIG. 7, the face image layout position may be specified by dragging and dropping the face portion selected by the operation unit 304 to a desired composition position. FIG. 8 conceptually shows a state in which the face images of the face portions f1, f5, and f6 are arranged and combined in the combining regions P1 to P3, respectively.

  In S <b> 7, the output unit 16 sends the created composite image to the personal computer 200 or the storefront terminal 300 via the network 400. The store terminal 300 prints the composite image sent from the output unit 16 with the printer 301 when the coin machine 305 settles the print charge of the composite image. The captured image input to the captured image input unit 10 may also be printed by the printer 301, and the captured image and the composite image may be provided as a set. The composite image sent from the output unit 16 may be recorded on various recording media such as a CD-R set in the media writer 302 at the same time as printing the composite image or at another time.

  A program for causing the processing unit 1 to execute the above-described steps S1 to 7, that is, the processing unit 1 is the captured image input unit 10, the captured image selection unit 11, the face detection unit 12, the face selection unit 13, the face extraction unit 14, and the synthesis. Programs that function as the unit 15 and the output unit 16 are stored in the storage unit 2. The program may be recorded on various computer-readable recording media such as a CD-ROM, and may be provided free of charge or via a network.

  As described above, an arbitrary photographed image is input from the personal computer 200 or the storefront terminal 300 and stored in the photographed image DB 5. The selection of an arbitrary photographed image is accepted from the photographed image and a face portion is detected from the selected photographed image. Accepting selection of a desired face portion from the detected face portion, extracting an image of the selected face portion and creating a composite image synthesized with a blank portion of a “crack” -shaped template image; It can be sent to the storefront terminal 300. That is, it is possible to provide an interesting image in which only a face image of a specific person such as his / her friend is combined with a template image from the group photo.

Second Embodiment
The image processing apparatus 100 may be included in the store terminal 300. In this case, as shown in FIG. 9, the storefront terminal 300 according to the present embodiment has a configuration in which a printer 301 and a media writer 302 are connected to the output unit 16 of the image processing apparatus 100 of the first embodiment. The composite image is directly output to the printer 301 or the media writer 302 without going through the network. The store terminal 300 according to the present embodiment has a configuration in which the media reader 306 is connected to the captured image input unit 10 of the image processing apparatus 100 of the first embodiment, and the captured image is directly captured without a network. The image is input to the image input unit 10. Further, in the store terminal 300 according to the present embodiment, a display unit 303, an operation unit 304, and a coin machine 305 are connected to the processing unit 1 of the image processing apparatus 100 according to the first embodiment. The process executed by is the same as in the first embodiment. The storefront terminal 300 may or may not have the network I / F 3. This storefront terminal 300 can stand by itself and provide a composite image without going through the network 400.

1 is a schematic functional configuration diagram of an image processing apparatus according to a first embodiment. Conceptual explanatory diagram of information stored in photographed image DB Conceptual explanatory diagram of information stored in photographed image DB The figure which shows an example of a template image Flow chart showing flow of composite image providing process The figure which shows an example of the photographed image The figure which shows an example of arrangement | positioning designation | designated to the synthetic | combination area | region of a face part Diagram showing an example of a composite image Schematic functional block diagram of the storefront terminal according to the second embodiment

Explanation of symbols

1: processing unit, 2: storage unit, 3: network I / F, 4: template input unit, 10: captured image input unit, 11: captured image selection unit, 12: face detection unit, 13: face selection unit, 14 : Face extraction unit, 15: synthesis unit, 16: output unit

Claims (9)

A captured image input unit for inputting a captured image in which a person's face is recorded;
A detection unit for detecting a face portion of the person;
A face selection unit that accepts selection of a desired face part from the detected face part;
An extraction unit that extracts a face image that is an image of the selected face portion from the captured image;
A template image input unit for inputting a template image having a composite area which is a blank area in which the extracted face image is placed;
A composition unit that arranges the extracted face image in a composition area of the template image and creates a composition image obtained by combining the face image arranged in the composition area and the template image;
An image processing apparatus comprising:   The image processing apparatus according to claim 1, wherein the face selection unit receives selection of a desired face portion from a terminal connected via a network. It further includes an operation unit that accepts operation input,
The image processing apparatus according to claim 1, wherein the face selection unit receives selection of a desired face portion from the operation unit. A photographic image selection unit that accepts selection of a desired photographic image from the input photographic images;
The image processing apparatus according to claim 1, wherein the detection unit detects a face portion from the selected captured image.   The image processing apparatus according to claim 1, further comprising an output unit that outputs the composite image to a predetermined apparatus.   The image processing apparatus according to claim 5, wherein the predetermined apparatus is a terminal connected via a network.   The image processing apparatus according to claim 5, wherein the predetermined apparatus is a printer or a media writer. A captured image input step for inputting a captured image in which a person's face is recorded;
A detection step of detecting a face portion of the person;
A face selection step of accepting selection of a desired face portion from the detected face portion;
An extraction step of extracting a face image that is an image of the selected face portion from the captured image;
A template image input step of inputting a template image having a composite area which is a blank area in which the extracted face image is placed;
A composition step of placing the extracted face image in a composition region of the template image and creating a composite image obtained by compositing the face image disposed in the composition region and the template image;
An image processing method including: A captured image input step for inputting a captured image in which a person's face is recorded;
A detection step of detecting a face portion of the person;
A face selection step of accepting selection of a desired face portion from the detected face portion;
An extraction step of extracting a face image that is an image of the selected face portion from the captured image;
A template image input step of inputting a template image having a composite area which is a blank area in which the extracted face image is placed;
A composition step of placing the extracted face image in a composition region of the template image and creating a composite image obtained by compositing the face image disposed in the composition region and the template image;
An image processing program for causing a computer to execute.

Images