JP2008243059A - Image processing device and method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To create an image, on which natural skin improvement processing is carried out, by easy operation. <P>SOLUTION: The image processing device is provided with an image input part, an image correction part performing correction processing on an input image, an external input means for inputting various instructions, an image display part, an object detection part detecting a specific object person from the input image, a skin color setting part setting information about a skin color from the detected object person, a skin color information reading part reading information about a previously defined skin color, a skin color extraction part extracting pixels of a skin color similar to the set skin color from the image based on the information of the set skin color, an area setting part setting a parameter by merging the extracted skin color pixels as a correction target area for each area and setting mask information for correcting only the correction target area, and an image output part creating output image data from the input digital image data, the corrected image data, and the mask information. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an image processing apparatus and an image processing method, and more particularly to an image processing apparatus and an image processing method for extracting a subject person from an image and performing image processing such as skin beautification processing.

  2. Description of the Related Art Conventionally, there is known an image processing apparatus that creates a composite image by combining an image with a predetermined region of an original image. For example, a cosmetic product that combines and displays an image with makeup applied to a skin region. Is used for performing a makeup simulation for confirming the effect of the cosmetic when the cosmetic is purchased.

As such an image processing apparatus, for example, a predetermined processing range of an original image indicating a face to be processed and a range of attributes such as pixel color gradation, luminance, hue, and saturation are specified, and the processing range Extract the pixels belonging to the attribute range, for example, recognize the skin area, synthesize the composition image (make-up image) to the area (skin area), and create a composite image A display has been proposed (see, for example, Patent Document 1).
JP 2005-78158 A

  However, although the above prior art is intended to easily perform region recognition based on the original image, there is a problem that confirmation and modification of the finish is complicated and troublesome, and is not necessarily simple. is there.

  The present invention has been made in view of such circumstances, and an object thereof is to provide an image processing apparatus and an image processing method capable of creating an image subjected to natural skin beautification through a simpler operation. To do.

  In order to achieve the above object, an invention according to claim 1 is directed to an image input unit that inputs digital image data, an image correction unit that performs correction processing on the digital image data, and various instructions to the image processing apparatus. An external input means for inputting the image, an image display unit for displaying the input image and the image subjected to the correction process, and a subject detection unit for detecting a specific subject person from the digital image data, A skin color setting unit for setting skin color information from the detected subject person, a skin color information reading unit for reading skin color information defined in advance, and a skin color similar to this skin color based on the set skin color information A skin color extraction unit for extracting the pixels of the image from the digital image data, and setting the parameters collectively for each region using the extracted skin color pixels as the correction target region An area setting unit for setting mask information for applying correction only to the correction target area, the input digital image data, the image data subjected to the correction process, and output image data from the mask information And an image output unit configured to check the finish of the image by displaying on the image display unit, and to perform correction correction according to an instruction from the external input unit.

  As a result, it is possible to easily check the finish of the corrected image and correct it, and to create a natural skin-beautifying image.

  The image processing apparatus according to claim 1, further comprising: comparing skin color information set from the detected subject person with the predefined skin color information. And means for determining whether or not the skin color information set from the detected subject person falls within a predetermined range of the predefined skin color information, and the skin color information set from the detected subject person is included. When the information does not fall within a predetermined range of the predefined skin color information, the skin color information set from the detected subject person is discarded.

  As a result, for example, even when an object other than the face of the subject person is detected as a face, an inappropriate correction process due to the failure can be avoided.

  According to a third aspect of the present invention, the image processing apparatus according to the first or second aspect further includes a correction intensity setting unit that sets an intensity to be corrected, according to a position of the image to be corrected. Thus, the intensity of the correction is changed.

  Thereby, the correction strength can be appropriately changed according to the subject and the position in the image.

  Similarly, in order to achieve the object, the invention according to claim 4 includes a step of inputting digital image data, a step of performing correction processing on the digital image data, the input image and A step of displaying the image subjected to the correction processing, a step of confirming a finish of the correction processing for the image based on the displayed image, a correction of the correction, and a determination from the digital image data Detecting the subject person, setting the skin color information from the detected subject person, reading the skin color information defined in advance, and the skin color based on the set skin color information. A process for extracting similar skin-color pixels from the digital image data, and setting the parameters for each region using the extracted skin-color pixels as correction target regions. And setting mask information for correcting only the correction target area, generating the input digital image data, the image data subjected to the correction processing, and output image data from the mask information And an image processing method comprising: confirming a finish level of an image that has been subjected to correction processing based on the displayed image, and correcting correction of the image.

  As a result, it is possible to easily check the finish of the corrected image and correct it, and to create a natural skin-beautifying image.

  The image processing method according to claim 4, further comprising: comparing the skin color information set from the detected subject person with the predefined skin color information. And determining whether or not the skin color information set from the detected subject person falls within a predetermined range of the predefined skin color information, and the skin color information set from the detected subject person is included. When the information does not fall within a predetermined range of the predefined skin color information, the skin color information set from the detected subject person is discarded.

  Accordingly, even if a processing failure occurs during image processing, it is possible to perform appropriate processing, and it is possible to perform more natural skin-beautifying processing with less failure.

  According to a sixth aspect of the present invention, the image processing method according to the fourth or fifth aspect further includes a step of setting a strength to be corrected, and depending on a position of the image to be corrected, The correction strength is changed.

  Thereby, the correction strength can be appropriately changed according to the subject and the position in the image.

  As described above, according to the present invention, it is possible to easily check the finish of the corrected image and to correct it, and to create a natural skin-beautifying image.

  Hereinafter, an image processing apparatus and an image processing method according to the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 1 is a block diagram showing a schematic configuration of an embodiment of an image processing apparatus according to the present invention.

  As shown in FIG. 1, the image processing apparatus 1 according to the present embodiment includes an image input unit 10, a subject detection unit 12, a skin color setting unit 14, a skin color information reading unit 16, a skin color extraction unit 18, a region setting unit 20, and image correction. A unit 22, an image output unit 24, an image display unit 26 and an external input unit 28 are configured.

  The image input unit 10 inputs digital image data such as an image acquired by photographing with a digital camera or an image acquired by reading with a scanner. Digital image data input from the image input unit 10 is sent to the subject detection unit 12, the image correction unit 22, and the image output unit 24.

  The subject detection unit 12 performs face detection processing for detecting the face of the subject person in the image represented by the input digital image data, and facial parts for detecting facial parts such as eyes, eyebrows, nose, and mouth in the face. A detection process is performed. An example of the face detection method is as follows. That is, first, an image represented by each color of R, G, and B is converted into an image represented by H (hue value), L (lightness value), S (saturation value), and hue value axes orthogonal to each other, Using a coordinate system consisting of a saturation value axis and a pixel number axis, a two-dimensional histogram for the hue value and the saturation value is obtained, and the obtained two-dimensional histogram is divided for each mountain, and clustering of the two-dimensional histogram is performed. Clustering of a large number of pixels is performed based on the clustered two-dimensional histogram peaks, the screen is divided based on the clustering, and a human face candidate area is extracted from the divided areas. The color area extracted as is further divided into circle or oval areas, and the face area is estimated based on the divided areas.

  The face detection may be automatically performed as described above, or the face of the subject person in the image displayed on the display screen of the image display unit 26 by the operator using the external input means 28 such as a mouse or a keyboard. The face area may be extracted by designating the area.

  The skin color setting unit 14 extracts skin color pixels with high reliability using the hue, saturation, and lightness histograms in the face area detected by the subject detection unit 12, and sets them as the skin color.

  The skin color information reading unit 16 reads the skin color information defined in advance and stored in the memory, and passes the skin color information to the skin color setting unit 14. For example, when the subject detection unit 12 cannot detect the subject (when face detection fails), the skin color information reading unit 16 reads the skin color information previously defined and stored in the memory and passes it to the skin color setting unit 14. The skin color setting unit 14 sets the skin color based on the skin color information.

  If the pre-defined skin color information is defined and stored as a combination of various skin color information, it is automatically read by the skin color information reading unit 16. In addition, when a plurality of skin color information such as sex, age, and race are defined and stored, the skin color information reading unit 16 may read the information according to the designation of the operator. Furthermore, the skin color setting unit 14 does not read the skin color information defined in advance in this way, but, for example, in a large lab, the same image is often handled in large quantities, and therefore the currently processed image is not processed. Since similar images may be processed before and after, the skin color used in the previous and next images may be automatically read and set as the skin color.

  The skin color information reading unit 16 is not only configured to read the skin color information when the subject detection unit 12 fails to detect the subject as described above, but also when the subject detection unit 12 detects the subject. Alternatively, the skin color information defined in advance and stored in the memory may be read and passed to the skin color setting unit 14.

  In this case, the skin color setting unit 14 compares the skin color set from the detected subject with the skin color information read by the skin color information reading unit 16, and the skin color of the detected subject is read by the skin color information reading unit 16. The subject detection error is checked by determining whether or not it is within the predetermined range. That is, when the detected skin color of the subject is not within the predetermined range of the skin color information read by the skin color information reading unit 16, it is determined that the subject is not detected as a subject but is erroneously detected as a subject. However, the skin color information set from this subject is discarded, and thereafter, the subject is not treated as a subject and the processing is stopped.

  The skin color extraction unit 18 extracts a skin color region in the subject person by extracting, from the image, a skin color pixel similar to the set skin color based on the skin color set by the skin color setting unit 14.

  As a method for extracting the skin color area, for example, the hue, saturation, and brightness of a predetermined area adjacent to a pixel having a set skin color are examined, and an area that satisfies a predetermined condition is added as a skin color area. Expand and grow, perform further contour extraction etc. on this grown skin color area, further grow this area, and such processing will be done if there are no neighboring pixels to grow or such processing A method for extracting a skin color region by performing the repetition until the number of repetitions reaches a predetermined number is known, but the method is not particularly limited to this method.

  When two or more subjects (two subject persons) are detected by the subject detection unit 12, the result of combining the skin colors of the two is set as the skin color, and the skin color extraction unit 18 extracts the skin color pixels. You may make it do. Alternatively, at this time, the skin color of each of the two persons may be set separately as the skin color, and the skin color extraction unit 18 may extract the skin color pixels.

  Further, when two or more subjects (two subject persons) are detected by the subject detection unit 12, labeling may be performed so that the skin color region for each subject can be recognized. This labeling may be determined according to which skin color is close to. Alternatively, it is only necessary to label the one closer to the subject.

  The area setting unit 20 sets the extracted skin color area as a correction target area. In addition, the area setting unit 20 creates a mask image that can obtain an entire corrected image in which an entire image including a subject, which will be described later, is corrected, and an image in which the correction is applied only to the correction target area when being combined. To do.

  Note that the region setting unit 20 may perform segment processing or labeling processing on the extracted skin color region. Further, the region setting unit 20 may adjust the extracted skin color region so that the shape looks like skin. For example, a pixel that is white with a strobe or the like may be added.

  The image correction unit 22 performs skin beautification processing, smoothing, and noise suppression processing. That is, the image correction unit 22 corrects the correction target area based on a correction value that is a target after correction of the correction target area, for example, a difference between a predetermined brightness and an average value or an intermediate value of the brightness in the correction target area. A correction amount that is considered appropriate as a correction amount (a degree of correction for each predetermined component on the image) is calculated, and this is used as an initial value to correct the entire image including the subject person.

  The image output unit 24 generates an output image by combining the input image, the correction image, and the mask image, and outputs the output image. That is, the image output unit 24 has a predetermined weight represented by the mask image for each corresponding pixel between the entire corrected image by the image correcting unit 22 and the original input image including the subject person sent from the image input unit 10. In this way, a corrected image in which only the correction target area is partially corrected is created. Here, the entire corrected image includes skin beautification processing, and the weight represented by the mask image includes skin beautification strength information.

  The image display unit 26 displays an image input to the image processing apparatus 1 and subjected to image processing, and displays a display screen (illustrated) such as an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube). (Omitted).

  The external input unit 28 is configured by a mouse, a keyboard, or other input unit, and the operator issues an instruction to the image processing apparatus 1 while viewing the display screen of the image display unit 26.

  As described above, in the present embodiment, by providing the image display unit 26 and the external input unit 28, it is possible to check the finish of the image on the display screen and easily modify the image.

  FIG. 2 shows an example of a detailed configuration of the image display unit 26 and the external input unit 28.

  As shown in FIG. 2, the image display unit 26 includes an image list display unit 30 that displays, for example, an image group in the designated folder or below the designated folder as thumbnail images on the display screen.

  The external input unit 28 also includes an image selection unit 32 for selecting an image from an image group (thumbnail image) displayed on the display screen by the image list display unit 30, and a correction condition to be set for each selected image. The function of the condition setting means 34 for instructing is provided.

  At this time, thumbnail images are displayed on the display screen by the image list display unit 30, and a plurality of images to be corrected under the same correction conditions are selected by the image selection unit 32, and then the plurality of selected images are displayed. Alternatively, the condition setting means 34 may instruct the same condition to be set.

  In the condition setting means 34, each correction parameter may be directly input, or may be selected from a plurality of predetermined parameter sets.

  As described above, in this embodiment, images are displayed as thumbnails, and it is possible to select whether or not to perform skin beautification, and to easily select the strength when skin beautifying is performed. .

  FIG. 3 shows another example of the detailed configuration in the vicinity of the image display unit 26 and the external input unit 28.

  In the example shown in FIG. 3, the external input unit 28 has functions of a subject selection unit 36 and a condition setting unit 34, and the detection result of the subject detected by the subject detection unit 12 is displayed on the display screen of the image display unit 26. For a subject that is displayed and cannot be detected, the subject may be additionally selected by subject selection means 36.

  For example, the face detection result may be displayed on the display screen, and the face that could not be detected may be designated as a rectangle by the subject selection means 36 while the operator looks at the display screen. At this time, this designation may designate both eyes and nose.

  In addition, the subject selection means 36 may display a detection result for the detected subject on the display screen, and may instruct to delete a portion that is erroneously detected as a subject although it is not a subject. For example, the face detection result may be displayed in a red frame, and the erroneously detected portion may be erased after designating the frame.

  Further, when there are a plurality of detected subjects, the subject selection means 36 displays the detection results for those subjects, and after specifying one or more of them, the condition setting means 34 for each subject. It may be instructed to set each correction parameter. For example, if you specify a woman for an image that shows men and women, a window will open allowing you to enter correction parameters for women.If you specify a man, you can enter correction parameters for men. May be.

  In addition, you may make it insert a mark about each to-be-photographed object. For example, when the face detection result is displayed in a red frame, the red frame of the face for which correction conditions are set may be changed to a blue frame. Alternatively, a pop window may be displayed when the mouse is brought close to the subject, and conditions may be described there.

  Further, in combination with the face authentication technology, when the condition for the subject has already been set in another image, the same condition may be automatically set for the subject in the image. In this case, you may make it insert the same mark as the above. Alternatively, a mark different from the above, for example, a green frame may be inserted.

  FIG. 4 shows another example of a detailed configuration in the vicinity of the image display unit 26 and the external input unit 28.

  In the example shown in FIG. 4, the external input means 28 functions as an image trimming unit 38 for instructing to trim a part of the image in order to enlarge a part of the face and skin and confirm the correction process. And a function as the condition setting means 34. The image display unit 26 also includes an enlarged image display unit 40 that instructs to enlarge a part of the trimmed image and display it on the display screen.

  The image trimming unit 38 receives both the result of the subject detection unit 12 and the result of the region setting unit 20 or at least one of the results, determines the image trimming range, and further receives the result from the image input unit 10. A trimmed image is created from both the input image and / or the corrected image that has been corrected by the image correction unit 22.

  The enlarged image display unit 40 displays the trimmed image on the display screen. The operator adjusts each correction parameter using the function of the condition setting unit 34 of the external input unit 28 while viewing the display screen. For the trimming range, for example, the detected face may be enlarged. Or what is necessary is just to enlarge about skins other than the face periphery.

  FIG. 5 shows still another example of the detailed configuration in the vicinity of the image display unit 26 and the external input unit 28.

  What is shown in FIG. 5 relates to mask modification. The image display unit 26 includes a region information addition unit 42 and a region information addition image display unit 44. Further, the external input unit 28 has a function as the area information modification unit 46.

  The area information adding unit 42 allows an image to be displayed on a display screen in a form in which mask information is added to an input image input from the image input unit 10 or a corrected image subjected to correction processing by the image correcting unit 22. It is. For example, mask intensity information may be displayed in blue shades.

  The area information modifying means 46 modifies the area information of the area information added image. For example, a region where a portion that is not skin is extracted as skin or a region that is skin but could not be extracted is corrected.

  In addition, as a specific modification means in the area information modification means 46, for example, a brush tool such as “Photoshop” (registered trademark) may be directly designated. Alternatively, as the modifying means in the region information modifying means 46, for example, a region may be switched between a skin region and a non-skin region by specifying a labeled region.

  Hereinafter, the image processing method which is the operation of the present embodiment will be described along the flowcharts of FIGS.

  FIG. 6 is a flowchart showing the flow of the entire image processing, FIG. 7 is a flowchart showing details of a part related particularly to skin color setting, and FIG. 8 is a flowchart showing details of a part related to region setting.

  First, when image data is input from the image input unit 10 in step S100 of FIG. 6, the input images are sent to the subject detection unit 12 and the image correction unit 22, respectively.

  In step S110, the subject detection unit 12 detects a subject person in the input image. On the other hand, in step S120, the image correction unit 22 performs image correction processing on the entire input image.

  As described above, the subject detection unit 12 detects a subject person and its face or facial parts from the input image.

  In the next step S130, it is determined whether or not the subject detection unit 12 has detected a subject. If no subject has been detected, the process proceeds to step S140, and the skin color information reading unit 16 defines the skin color defined in advance. Read information. The read skin color information is sent to the skin color setting unit 14.

  In step S150, when the subject is detected, the skin color setting unit 14 sets the skin color using the pixels of the detected face portion of the subject person. At this time, if the subject is not detected, the skin color is set based on the skin color information read by the skin color information reading unit 16.

  In step S160, the skin color extracting unit 18 extracts skin color pixels from the entire image using the skin color set above. Next, in step S170, the region setting unit 20 collectively sets the extracted skin color pixels as a skin color region to be corrected. Further, as described above, the region setting unit 20 creates a mask image (mask information) so that correction is applied only to the set skin color region.

  Next, in step S180, the image output unit 24 combines the corrected image corrected by the image correcting unit 22, the input image and the mask image, and finally corrects the corrected image that has been corrected only in the correction target region. Created.

  FIG. 7 is a detailed flowchart of a portion related to skin color setting. The process shown in FIG. 7 relates to a face detection error, and such a process may be performed in addition to the overall flow of FIG.

  That is, the face detection error includes a case where a face is reflected in the image but cannot be detected, and a case where a non-face portion in the image is detected as a face. If it is detected that a non-face portion is a face, an incorrect skin color may be set and an unexpected correction may be made. Therefore, in order to cope with this, in the flowchart shown in FIG. 7, even when the subject is detected, the skin color information is read.

  That is, in step S110, subject detection processing is performed and a subject is detected (in FIG. 7, steps S130 and S140 in FIG. 6 are omitted), in step S150, the skin color is set in the skin color setting unit 14. In FIG. 7, in step S152, the skin color information reading unit 16 reads the skin color information defined in advance (even if the subject is detected), and the detected subject is detected. The skin color is compared with a predefined skin color.

  In step S154, if the detected skin color of the subject is not within the range of the predefined skin color information, in step S156, the detected skin color information of the subject is discarded and the detected face of the subject is detected. The result of is not used.

  On the other hand, if the detected skin color of the subject is within the range of the predefined skin color information in step S154, the skin color is set, and in step S160, the skin color is extracted with the skin color. Then, in the next step S162, it is determined whether or not there is another detected subject. If another subject is detected, the process returns to step S150 and the above processing is repeated. If there is no other subject, the process proceeds to step S170 in FIG. 6 and the next region setting process is performed.

  Further, the flowchart shown in FIG. 8 relates to area setting. The process shown in FIG. 8 is an example of a process in the case where two people are shown in the image and two people are detected as subjects. Similar to the process in FIG. 7, the entire process in FIG. Such processing may be performed in addition to the flow.

  In step S110 of FIG. 8, skin color setting (step S150) and skin color extraction (step S160) are first performed for one person, and it is determined whether there are other subjects in step S162. If there are other subjects, step S150 is performed. Returning to FIG. 5, the skin color setting (step S150) and the skin color extraction (step S160) are performed for other subjects.

  As described above, when two subjects are detected, the skin colors are different from each other, so that the skin color setting (step S150) and the skin color extraction (step S160) are performed for each subject. .

  Next, in step S164, the skin color information created for each subject is compared, and approximation determination is performed. Then, if it is determined that the skin colors are approximated according to preset approximation determination conditions, these skin colors may be combined into one, or if there are two or more subjects Alternatively, the information of the approximate skin color pixel may be attached to the other pixel. In step S166, it is determined whether or not the approximation determination has been completed for all the pixels, and the process is repeated until all the pixels are completed.

  As described above, in the present embodiment, even if processing in the middle of subject detection or the like fails, appropriate processing can be performed accordingly, and appropriate correction according to the subject and its position in the image can be performed. Processing can be performed. As a result, correction processing such as more natural skin beautification processing is realized with less breakdown. In addition, it is possible to output the input image, the skin beautification image, and the skin beautification strength information (mask image) in a format that can be easily corrected, for example, by saving and outputting the layer structure.

  Next, as an application example of the image processing apparatus of the present invention, a print order system as a network photo service system in which a photo studio and a laboratory are connected by a network will be described.

  FIG. 9 shows an outline of the print ordering system.

  As shown in FIG. 9, in this print ordering system 50, a photo studio 52 that accepts a photograph of a customer and receives a print order and a laboratory 54 are connected via a network 56 such as the Internet.

  The photo studio 52 accepts print orders from customers. However, the photo studio 52 may have a photo studio and take portraits of customers. The computer terminal 52a installed in the photo studio 52 is connected to the server 54a of the lab 54 via the network 56, inputs image data of a print ordered from a customer, and gives correction conditions to the image information. To the server 54a of the lab 54.

  In the computer terminal 52a of the photo studio 52, predetermined image processing conditions are set according to the customer's order. At this time, simple image processing may be performed by the computer terminal 52a, and the result of the image processing may be displayed on the display means connected to the computer terminal 52a to be shown to the customer.

  The server 54a of the lab 54 receives image data and image processing conditions transmitted from the computer terminal 52a of the photo studio 52. The lab 54 includes a digital minilab 54b having an image processing apparatus according to the present invention, and performs image processing based on image data (image information) and image processing conditions (condition information) received by the server 54a to create a print. . The created print is delivered or mailed to the photo studio 52 or a receiving store designated by the customer.

  FIG. 10 shows a schematic configuration of an order receiving system in the photo studio 52.

  As shown in FIG. 10, the computer terminal 52 a of the photo studio 52 includes an image input unit 60, an image display unit 62, an external input unit 64, a condition setting unit 66, and an image information condition information transmission unit 68.

  The image input unit 60 inputs digital image data such as an image acquired by photographing with a digital camera or an image acquired by reading with a scanner. The image data input from the image input unit 60 is sent to the image display unit 62.

  The image display unit 62 displays the image input from the image input unit 60, and has a display screen (not shown) for displaying an image such as an LCD (liquid crystal display) or a CRT (Cathode Ray Tube). Yes.

  The external input means 64 is constituted by a mouse, a keyboard, or other input means, and an operator issues an instruction such as image processing (image correction) conditions to the condition setting section 66 while viewing the display screen of the image display section 62. Is.

  The condition setting unit 66 sets correction conditions for each image. In the condition setting unit 66, each correction parameter may be directly input from the external input unit 64 as described above, or may be selected from a plurality of predetermined parameter sets.

  The image information condition information transmission unit 68 assigns correction conditions to the image information and transmits them to the server 54 a of the lab 54. Further, the image information condition information transmission unit 68 may transmit the image information to which the correction condition is given while storing the image information.

  FIG. 11 is a block diagram showing a detailed configuration in the vicinity of the image input unit 60 and the image display unit 62 of the computer terminal 52a of the photo studio 52.

  As shown in FIG. 11, an image correction unit 61 may be provided between the image input unit 60 and the image display unit 62, and the result of correcting the input image by the image correction unit 61 may be displayed on the image display unit 62. .

  The display of the correction result is for presentation to the customer, so that the correction in that case may be a simple correction. Thus, by displaying and displaying the result of image correction (skin-beautifying process) to the customer, the customer can obtain an order after obtaining the approval of the customer, so that the customer can satisfy the print order. At this time, the image data and the correction parameters are transmitted to the laboratory 54 together.

  FIG. 12 shows a schematic configuration of an image processing apparatus incorporated in the server 54a and the digital minilab 54b of the laboratory 54.

  As illustrated in FIG. 12, the server 54 a includes an image information condition information reception unit 70 and an image selection unit 72. The image information condition information receiving unit 70 receives the image information with the correction condition transmitted from the image information condition information transmitting unit 68 of the computer terminal 52 a of the photo studio 52.

  The image selection unit 72 selects an image that requires image processing from the image received by the image information condition information reception unit 70 and sends the image to the digital minilab 54b. That is, the image sorting unit 72 sorts whether or not to flow an image to the next process (skin beautification process), particularly depending on the presence or absence of skin beautification information. If the skin beautifying process is divided for each correction condition, the image selecting unit 72 may select the skin beautifying process.

  Thus, in this embodiment, the image selection process in the laboratory 54 is simplified.

  On the other hand, the configuration of the image processing apparatus incorporated in the digital minilab 54b is the same as that of the image processing apparatus 1 shown in FIG. That is, the image processing apparatus of the digital minilab 54b includes an image input unit 80, a subject detection unit 82, a skin color setting unit 84, a skin color information reading unit 86, a skin color extraction unit 88, an area setting unit 90, an image correction unit 92, and an image output unit. 94, an image display unit 96 and an external input unit 98. The functions of the respective units are the same as the functions of the respective units in the image processing apparatus 1 of FIG.

  The image selected by the image selection unit 72 is input from the image input unit 80, and as described above, subject detection, skin color setting, skin color extraction, region setting, and the like are performed thereafter, while the image correction unit 92 performs a photo studio 52. A correction process (skin-beautifying process) is performed according to the condition information transmitted from. In this processing, the image to be subjected to image processing is displayed on the image display unit 96, and the operator inputs various instructions from the external input means 98 while checking the image finish on the display screen of the image display unit 96. Thus, the modification can be easily performed.

  As described above, according to the present embodiment, for example, it is possible to easily select an image as to whether or not to apply a beautifying process, to easily confirm the beautifying result, and to easily use a correction mask. It is possible to create a natural beautiful skin image by such a simpler operation.

  Although the image processing apparatus and the image processing method of the present invention have been described in detail above, the present invention is not limited to the above examples, and various improvements and modifications are made without departing from the gist of the present invention. Of course it is also good.

1 is a block diagram showing a schematic configuration of an embodiment of an image processing apparatus according to the present invention. FIG. 2 is a block diagram illustrating an example of a detailed configuration of an image display unit and an external input unit in the image processing apparatus of FIG. 1. It is a block diagram which similarly shows another example of the detailed structure of an image display part and external input means vicinity. It is a block diagram which similarly shows the other example of the detailed structure of an image display part and external input means vicinity. It is a block diagram which shows the further another example of the detailed structure of an image display part and external input means vicinity. It is a flowchart which shows the flow of the whole image processing. It is a flowchart which shows the detail of the part regarding skin color setting. It is a flowchart which shows the detail of the part regarding area | region setting. 1 is a system configuration diagram showing an outline of a print ordering system. It is a block diagram which shows schematic structure of the order reception system in a photo studio. It is a block diagram which shows the detailed structure of the image input part and image display part vicinity of the computer terminal of a photo studio. It is a block diagram which shows schematic structure of systems, such as a server in a laboratory, and a digital minilab.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Image processing apparatus, 10 ... Image input part, 12 ... Subject detection part, 14 ... Skin color setting part, 16 ... Skin color information reading part, 18 ... Skin color extraction part, 20 ... Area setting part, 22 ... Image correction part, 24 Image output unit 26 Image display unit 28 External input unit 30 Image list display unit 32 Image selection unit 34 Condition setting unit 36 Subject selection unit 38 Image trimming unit 40 Enlarged image display unit 42... Region information adding unit 44. Region information adding image display unit 46. Region information modifying means 52 52 Photo studio 52 a Computer terminal 52 a 54 Laboratory 48 a Server 54 b Digital Minilab, 56 ... Internet

Claims (6)

An image input unit for inputting digital image data;
An image correction unit that performs correction processing on the digital image data;
External input means for inputting various instructions to the image processing apparatus;
An image display unit for displaying the input image and the image subjected to the correction process;
A subject detection unit for detecting a specific subject person from the digital image data;
A skin color setting unit for setting skin color information from the detected subject person;
A skin color information reading unit that reads information of a predefined skin color;
A skin color extraction unit that extracts skin color pixels similar to the skin color from the digital image data based on the set skin color information;
An area setting unit for setting mask information for applying correction only to the correction target area while setting the parameters collectively for each area using the extracted skin color pixels as the correction target area;
The input digital image data, the image data subjected to the correction process, and an image output unit for creating output image data from the mask information;
An image processing apparatus for checking the finish of the image by displaying on the image display unit and correcting the correction according to an instruction from the external input means.   The image processing apparatus according to claim 1, further comprising: comparing skin color information set from the detected subject person with the predefined skin color information and setting from the detected subject person. Means for determining whether the skin color information falls within a predetermined range of the predefined skin color information, and the skin color information set from the detected subject person is the predefined skin color information. If the image does not fall within the predetermined range, the skin color information set from the detected subject person is discarded.   The image processing apparatus according to claim 1, further comprising a correction intensity setting unit that sets an intensity to be corrected, so that the intensity of the correction is changed according to the position of the image to be corrected. An image processing apparatus characterized by that. Inputting digital image data;
Performing a correction process on the digital image data;
Displaying the input image and the corrected image; and
Checking the finish of the correction process for the image based on the displayed image, and correcting the correction;
Detecting a specific subject person from the digital image data;
Setting skin color information from the detected subject person;
Reading pre-defined skin color information;
Extracting the skin color pixels similar to the skin color from the digital image data based on the set skin color information;
Setting the mask information for applying correction only to the correction target area while setting the parameters collectively for each area as the correction target area with the extracted skin color pixels;
Creating output image data from the input digital image data, the image data subjected to the correction process, and the mask information;
An image processing method comprising: confirming a finish level of an image that has been subjected to correction processing based on the displayed image, and correcting correction of the image.   5. The image processing method according to claim 4, further comprising comparing the skin color information set from the detected subject person with the predefined skin color information and setting the detected subject person. Determining whether the skin color information falls within a predetermined range of the predefined skin color information, and the skin color information set from the detected subject person is the predefined skin color information. If not within the predetermined range, the skin color information set from the detected subject person is discarded.   6. The image processing method according to claim 4, further comprising a step of setting a strength to be corrected, wherein the strength of the correction is changed according to the position of the image to be corrected. A featured image processing method.

Images