JP2006173824A - Image processing apparatus and method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To obtain an output image with high quality by using a LUT (Look-Up Table) optimum to the image. <P>SOLUTION: An image processing apparatus includes: an image input means for receiving an image; a skin color region discrimination means for discriminating whether or not a skin color region exists in the input image; a LUT selection means for selecting a LUT on the basis of a discrimination result by the skin color region discrimination means; a color conversion means for converting colors of the input image by using the LUT selected by the LUT selection means ; and an image output means for outputting an image whose colors are converted by the color conversion means. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a technique for selecting an optimal lookup table according to an input image.

  In recent inkjet printers, improved color materials used for ink and added inks with hues other than C (cyan), M (magenta), Y (yellow), and K (black) (hereinafter referred to as special color inks) By printing in this way, it becomes possible to output colors with higher saturation than before, and the color reproduction range (hereinafter referred to as color gamut) tends to be expanded.

  However, along with the expansion of the color gamut of inkjet printers, for example, by adding a special color ink with an orange hue, the color gamut of the orange area is greatly expanded as shown in FIG. In this case, the conversion curve in the saturation direction is as shown in FIG. 7, and when trying to obtain a smooth gradation, the saturation of the skin color area becomes high, resulting in an unnatural output result. If the saturation is to be maintained, a large gradation change occurs between the skin color area and the orange area, which causes a tone jump.

  In order to solve the above problem, Patent Document 1 describes a method of changing an output density curve based on information of an input image.

Also, Patent Document 2 prepares a plurality of LUTs composed of a total of four color inks obtained by dividing an LUT for each hue, sandwiching a special color ink, and adding K ink to any two adjacent colors of the hue. A method of switching the LUT to be used for data is described.
JP 2003-244632 A JP 2001-136401 A

  However, the method of Patent Document 1 has a problem in that the parameter characteristics of the sufficiently tuned LUT are subtly broken due to the output density curve, which causes a pseudo contour.

  In the method of Patent Document 2, since the color separation lookup table is created after the types of special color ink to be used are limited in advance, it is not limited to whether or not a skin color area is included in the input image. There is a problem that only a specific LUT can be used.

  The present invention has been made in view of the above problems, and when selecting an LUT for performing color conversion, it is determined whether or not a skin color area exists based on information of input image data, If there is an LUT that does not enhance the saturation of the orange area and retains the saturation of the skin color area, conversely, if the skin color area does not exist, the saturation of the orange area is enhanced and the LUT that maintains the gradation It is an object of the present invention to provide a method for outputting an image using an optimum LUT for an input image.

  In order to achieve the above object, the present invention provides an image input means for inputting an image, a skin color area determination means for determining whether or not a skin color area exists in the input image, and a determination result by the skin color area determination means. LUT selection means for selecting an LUT based on the image, color conversion means for converting the color of the input image using the LUT selected by the LUT selection means, and image output for outputting an image color-converted by the color conversion means Means.

  According to the present invention, an LUT optimum for an image can be used, and a high-quality output image can be obtained.

(First embodiment)
Hereinafter, an embodiment according to the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 1 is a block diagram showing a configuration of an image processing apparatus according to an embodiment of the present invention. 1 is an image processing apparatus according to an embodiment of the present invention. An image data storage unit 2 stores image information to be output, such as a hard disk or a CD-ROM. 3 is an image input unit for reading image data from the image data storage unit 2 into the image processing apparatus 1. 4 is a color distribution calculation unit for calculating the color distribution of the input image. Reference numeral 5 denotes a skin color area calculation unit that calculates how many pixels of the skin color area exist in the color distribution calculated by the color distribution calculation unit 4. Reference numeral 6 denotes an LUT selection unit for selecting an LUT used for color conversion based on the ratio of pixels included in the skin color region calculated by the skin color region calculation unit. An LUT storage unit 7 stores an LUT used for color conversion. A color conversion unit 8 performs color conversion processing on the image input by the image input unit 3 using the LUT stored in the LUT storage unit 7. An image output unit 9 outputs the image data converted by the color conversion unit 8. Reference numeral 10 denotes an image output device such as an ink jet printer that actually performs printing based on the image data output from the image output unit 9.

<Overall processing>
Here, FIG. 2 is a flowchart of image processing performed in the image processing apparatus 1. Hereinafter, an embodiment according to the present invention will be described in detail with reference to the drawings. First, in S <b> 201, image data is read from the image data storage unit 2 to the image processing apparatus 1 by the image input unit 3. Next, in S202, the color distribution calculation unit 4 calculates the color distribution in the RGB space of the input image read in S201. In S203, the skin color area calculation unit 5 calculates the ratio of pixels existing in the skin color area from the color distribution calculated in S202 (details will be described later). In S204, the LUT selection unit 6 retains the saturation-enhanced LUT or the skin color region from the LUTs stored in the LUT storage unit 7 based on the ratio of the skin color region pixels calculated in S203. The most suitable color conversion LUT is selected from the LUTs. In S205, the color conversion unit 8 performs color conversion of the image input in S201 using the LUT selected in S204. In S <b> 206, the image data color-converted in S <b> 205 is output from the image output unit 9 and printed by the image output device 10.

<Skin color area calculation>
Next, the details of the skin color area calculation, which is step S203, will be described with reference to FIG.

  FIG. 3 shows an example of the color distribution in the RGB color space for the input image. A skin color region as shown by an ellipse in FIG. 3 is provided in the RGB space, the number of pixels included in the ellipse is calculated, and the ratio of the skin color pixels in all the pixels of the image is greater than a preset threshold value. If it is larger, the LUT holding the skin color area is used, and if it is smaller than the threshold value, the saturation-enhanced LUT is used.

  However, here, the color distribution is calculated in the RGB color space. However, the color distribution is not limited to this, and any color space that can separate the skin color pixels in the input image from the other pixels may be used. For example, a CIELab space or a CMYK space may be used.

  As described above, according to the first embodiment, in the printer capable of enhancing the saturation of the orange area using the special color ink, an image in which the skin color area exists based on the color distribution in the input image. Then, using an LUT that retains skin color, and using an LUT that enhances the saturation of the orange region in images other than those described above, the user can use the LUT that is optimal for the image without manually specifying the image contents. be able to.

(Second embodiment)
Hereinafter, a second embodiment according to the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 4 is a block diagram showing the configuration of the image processing apparatus according to this embodiment. Reference numeral 401 denotes an image processing apparatus according to an embodiment of the present invention. An image data storage unit 402 stores image information to be output, such as a hard disk or a CD-ROM. An image input unit 403 reads image data from the image data storage unit 402 into the image processing apparatus 401. Reference numeral 404 denotes a tag information reading unit for reading tag information added to the input image. Reference numeral 405 denotes an LUT selection unit for determining whether or not a skin color region exists based on the tag information read by the tag information reading unit 404 and selecting an LUT used for color conversion. An LUT storage unit 406 stores an LUT used for color conversion. A color conversion unit 407 performs color conversion processing on the image input by the image input unit 403 using the LUT stored in the LUT storage unit 406. Reference numeral 408 denotes an image output unit for outputting the image data converted by the color conversion unit 407. Reference numeral 409 denotes an image output device such as an ink jet printer that actually performs printing based on the image data output from the image output unit 408.

<Overall processing>
Here, FIG. 5 is a flowchart of image processing performed in the image processing apparatus 401. Hereinafter, an embodiment according to the present invention will be described in detail with reference to the drawings. First, in S <b> 501, the image input unit 403 reads image data from the image data storage unit 402 into the image processing apparatus 401. Next, in S502, the tag information reading unit 404 determines the scene of the input image based on the tag information added to the input image read in S501, and determines whether a skin color area exists in the input scene. . In S503, based on the scene information determined in S502 in the LUT selection unit 405, either the LUT stored in the LUT storage unit 406, the LUT with saturation enhancement, or the LUT holding the skin color area is selected. An optimal color conversion LUT is selected. In step S504, the color conversion unit 408 performs color conversion of the image input in step S501 using the LUT selected in step S503. In step S <b> 505, the image data color-converted in step S <b> 504 is output from the image output unit 408 and printed by the image output device 409.

<Tag information>
In the first embodiment, as the tag information for performing scene determination in step S502, for example, a shooting scene type tag of Exif information standardized as a digital camera recording method can be used. If the tag is a scene such as a portrait where there is a high possibility that a person is captured, an LUT that retains a skin color area may be used, and if it is another scene, a saturation-enhanced LUT may be used.

  However, it is needless to say that the tag information is not limited to Exif information, and may be information that can identify the scene of the input image.

  As described above, according to the second embodiment, in the printer capable of enhancing the saturation of the orange area using the special color ink, the skin color area exists based on the scene information added to the input image. For scenes to be used, an LUT that retains skin color is used, and for scenes other than the above, an LUT that enhances the saturation of the orange area is used, so that the user does not manually specify the scene and the LUT optimal for the image is selected. Can be used.

(Other embodiments)
In the first embodiment and the second embodiment, the image output device is a printer. However, for example, it may be a CRT display or a liquid crystal projector.

  Further, in the first embodiment and the second embodiment, the LUT selection is to select one of two types of LUT that holds the skin color or LUT that emphasizes the saturation of the orange region. However, the selection candidate LUTs are not limited to the above two types, and an optimal one may be selected from three or more types of LUTs that change in stages.

  Note that the present invention can be applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, and a printer), and a device (for example, a copying machine and a facsimile device) including a single device. You may apply to.

  Another object of the present invention is to supply a storage medium storing software program codes for realizing the functions of the above-described embodiments to a system or apparatus, and the computer (or CPU or MPU) of the system or apparatus stores the storage medium. Needless to say, this can also be achieved by reading and executing the program code stored in.

  In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the storage medium storing the program code constitutes the present invention.

  As a storage medium for supplying the program code, for example, a floppy (registered trademark) disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD-R, magnetic tape, nonvolatile memory card, ROM, or the like is used. I can do it.

  Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an OS (operating system) operating on the computer based on the instruction of the program code. It goes without saying that a part of the actual processing is performed and the functions of the above-described embodiments are realized by the processing.

  Further, after the program code read from the storage medium is written to a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, the function expansion is performed based on the instruction of the program code. It goes without saying that the CPU or the like provided in the board or the function expansion unit performs part or all of the actual processing, and the functions of the above-described embodiments are realized by the processing.

1 is a block diagram illustrating an image processing apparatus according to a first embodiment. The flowchart explaining the flow of processing in the image processing apparatus of the first embodiment. Color distribution and skin color area in RGB space The block diagram which shows the image processing apparatus of 2nd embodiment The flowchart explaining the flow of processing in the image processing apparatus of the second embodiment. Example of color gamut difference with and without saturation enhancement An example of a saturation conversion curve when the saturation is not emphasized.

Claims (11)

  Image input means for inputting an image, skin color area determination means for determining whether a skin color area exists in the input image, LUT selection means for selecting an LUT based on a determination result by the skin color area determination means, Image processing comprising: color conversion means for converting the color of an input image using the LUT selected by the LUT selection means; and image output means for outputting an image color-converted by the color conversion means apparatus.   2. The skin color area determining means, based on a color distribution of an input image, determines whether or not the skin color image is based on a ratio of pixels included in a preset skin color area in a color space. The image processing apparatus described.   The image processing apparatus according to claim 1, wherein the skin color area determination unit determines whether the image is a skin color image from the scene type described in the tag based on tag information added to the input image.   2. The LUT selection unit selects one of two types of LUTs: an LUT that emphasizes the saturation of an orange region and an LUT that retains the saturation of a skin color region. Image processing apparatus.   The LUT selection means includes a plurality of LUTs in which the saturation enhancement degree of the orange region is changed stepwise in addition to the two types of LUTs, that is, the LUT that enhances the saturation of the orange region and the LUT that retains the saturation of the skin color region. The image processing apparatus according to claim 1, wherein any one of the LUTs is selected.   An image input step for inputting an image, a skin color region determination step for determining whether or not a skin color region exists in the input image, an LUT selection step for selecting an LUT based on a determination result by the skin color region determination step, An image processing comprising: a color conversion step for converting a color of an input image using the LUT selected in the LUT selection step; and an image output step for outputting an image color-converted by the color conversion step Method.   The skin color region determining step determines whether the skin color image is based on a color distribution of an input image based on a ratio of pixels included in a preset skin color region in a color space. The image processing method as described.   The image processing method according to claim 6, wherein the skin color region determination step determines whether or not the skin color image is based on the tag information added to the input image from the scene type described in the tag.   The LUT selection step selects one of two types of LUTs: an LUT that emphasizes the saturation of the orange region and an LUT that retains the saturation of the skin color region. Image processing method.   In the LUT selection step, in addition to two types of LUTs, an LUT that emphasizes the saturation of the orange region and an LUT that retains the saturation of the skin color region, a plurality of steps in which the degree of saturation enhancement of the orange region is changed stepwise The image processing method according to claim 6, wherein any one type is selected from the LUTs.   The program for implement | achieving the image processing method in any one of Claim 6 thru | or 10 with a computer.

Images