JP2005159626A - Image focus discrimination, image classification, and image correction - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a technology of enhancing the accuracy for focus discrimination when a photo picture is a portrait. <P>SOLUTION: A CPU 11 executes a computer program Pr to allow a portrait discrimination section 30 to discriminate whether or not a photo picture denoted by one image data Dp read from a hard disk drive 14 is a portrait image. When the discrimination indicates that the photo picture is the portrait image, a first processing section 32 applies focus discrimination processing for the portrait to the photo picture. On the other hand, when the portrait discrimination section 30 discriminates that the photo picture is a picture other than the portrait, a second processing section 34 applies focus discrimination processing for non-portrait to the photo picture. The first processing section 32 discriminates how much the focus of the photo picture is matched on the basis of "a skin color possessed by the photo picture and the intensities of luminances edges with respect to edge parts of the photo picture". <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a technique for determining how much a photographic image is in focus, and an image classification and image correction technique using the technique.

  In recent years, electronic still cameras, so-called digital cameras, have been developed and are in widespread use. Photo images taken with a digital camera can be easily processed and edited by the image processing software using a computer. As one of these processing processes, there is a process of automatically modifying the image quality such as “brightness” and “sharpness” of a photographic image, as disclosed in Patent Document 1. When correcting “sharpness”, the brightness difference of the edge portion is detected to determine how much the photograph image is in focus.

JP 2000-215306 A

  However, in the conventional technique, when the photographic image is a portrait image, it is often erroneously determined how much the image is in focus. Since it is common to determine how much the image is in focus based on the area ratio of the edge part to the entire image, in a photographic image that is in focus on a narrow part of a person such as a portrait, the area is This is because if the ratio is small, it is erroneously determined that “the subject is out of focus”.

  The problem to be solved by the present invention is to improve the accuracy of focus determination when a photographic image is a portrait.

  As means for solving at least a part of the problems described above, the following configuration is adopted.

The image focus determination device of the present invention is
An image focus determination device that performs a focus determination process for determining how much a photograph image is in focus,
Portrait determination means for determining whether the photographic image is a portrait image;
And a first processing unit that applies a first process as the focus determination process prepared in advance exclusively for a portrait to the photographic image when the portrait determination unit determines that the image is a portrait image. It is characterized by.

  According to the image focus determination device having the above-described configuration, when the photographic image is a portrait image, the focus determination process dedicated to the portrait can be performed on the photographic image. The accuracy of focus determination can be improved.

  In the image focus determination device, when the portrait determination unit determines that the image is not a portrait, a second process as the focus determination process prepared in advance for a non-portrait is applied to the photographic image. It can be set as the structure provided with the 2nd processing means to give.

  According to this configuration, it is possible to perform focus determination suitable for each photographic image by performing different focus determination processing on the photographic image of the portrait and the photographic image other than the portrait. Therefore, it is possible to improve the accuracy of photographic image focus determination.

  The first processing means is a first pixel that selects a pixel belonging to an edge portion having a skin color and having a luminance difference equal to or greater than a predetermined value from adjacent pixels from among the pixels constituting the photographic image. A first focus for calculating a focus rate indicating how much the photographic image is in focus based on the luminance difference for each pixel selected by the selection means and the first pixel selection means; It can be set as a structure provided with a focal rate calculating means.

  According to the above configuration, it is possible to determine how well the portrait is focused from the luminance difference of each pixel belonging to the edge portion in flesh color. Just by determining how much the focus is based on the brightness difference of each pixel belonging to the edge part, the portrait does not focus on the “person” that is the main subject, but seems to be focused on the background. However, according to the above configuration, it is possible to prevent such misjudgment by adding a skin color determination. be able to.

  The second processing means is a second pixel selection means for selecting a pixel belonging to an edge portion having a luminance difference of a predetermined value or more between adjacent pixels from among the pixels constituting the photographic image; The ratio of the total number of each pixel selected by the second pixel selection unit to the total number of each pixel constituting the photographic pixel is obtained, and based on the ratio, how much the photographic image is in focus is determined. It can be set as the structure provided with the 2nd focus rate calculation means which calculates the focus focus rate shown.

  According to the above configuration, in the case of a non-portrait photographic image, it is possible to determine how much the photographic image is in focus from the area ratio of the edge portion to the entire photographic image. Non-portrait photographic images, such as landscape photographs, are usually taken with pan focus (focus on the entire screen), and are often in focus because they often capture subjects that have fine details such as forests. In many cases, both the area and the area where the edge stands are wide. For this reason, in a photographic image that is not a portrait, it is possible to accurately determine whether the image is in focus by looking at the area ratio of the edge portion.

  As described above, the first processing unit includes the first image selection unit and the first focus ratio calculation unit, and the second processing unit includes the second image selection unit as described above. In the image focus determination apparatus configured to include the second focus in-focus ratio calculating unit, the predetermined value in the second image selecting unit is larger than the predetermined value in the first image selecting unit. be able to.

  According to the above configuration, the edge portion of the portrait photographic image can be reliably selected. In the case of portraits, there are many photographs with a shallow depth of field, but a shallow depth of field means that the entire skin-colored part is not always in focus, and the part that is visible when in focus However, there is a possibility that the edge is not as good as a non-portrait photographic image with a deep depth of field. On the other hand, according to the above-described configuration, the edge determination threshold is smaller in the portrait case, so that the edge portion of the portrait photographic image can be reliably selected.

  The portrait determination means includes an area ratio calculation means for calculating an area ratio of the skin color portion of the photographic image to the entire photographic image, and the photographic image is a portrait based on the area ratio calculated by the area ratio calculation means. A determination unit that determines whether the image is a rate image can be provided.

  Since portrait photographic images are taken around a person, the skin area of the person has a large area ratio with respect to the entire photographic image. For this reason, it is possible to easily determine whether or not the photographic image is a portrait by obtaining the area ratio of the skin color portion of the photographic image to the entire photographic image as in the above configuration.

The image classification device of the present invention is
Image focus determination means for performing a focus determination process for determining how much the focus is in each photographic image;
Classification means for classifying the plurality of photographic images based on a determination result of the focus determination process; and
The image focus determination means includes
Portrait determination means for determining whether the photographic image is a portrait image;
And a first processing unit that applies a first process as the focus determination process prepared in advance exclusively for a portrait to the photographic image when the portrait determination unit determines that the image is a portrait image. It is characterized by.

  According to the image classification device having the above-described configuration, when a photographic image is a portrait image, the focus determination process dedicated to the portrait can be performed on the photographic image. The accuracy of determination can be improved. Thus, since the photographic images are classified based on the determination result of the high-accuracy focus determination, the classification accuracy can be improved.

  In the image classification device, the image focus determination unit is a second process as the focus determination process prepared in advance for a non-portrait when the portrait determination unit determines that the image is not a portrait. Can be configured to include second processing means for applying to the photographic image.

  According to this configuration, it is possible to perform focus determination suitable for each photographic image by performing different focus determination processing on the photographic image of the portrait and the photographic image other than the portrait. Therefore, it is possible to improve the accuracy of classification by improving the accuracy of determining the focus of a photographic image.

  The first processing means is a pixel selecting means for selecting a pixel belonging to an edge portion having a skin color and having a luminance difference of a predetermined value or more from adjacent pixels from among the pixels constituting the photographic image. A focus focus ratio calculating means for calculating a focus focus ratio indicating how much the photographic image is focused based on the luminance difference for each pixel selected by the pixel selecting means; can do.

  According to the above configuration, it is possible to determine how well the portrait is focused from the luminance difference of each pixel belonging to the edge portion in flesh color. Just by determining how much the focus is based on the brightness difference of each pixel belonging to the edge part, the portrait does not focus on the “person” that is the main subject, but seems to be focused on the background. However, according to the above configuration, it is possible to prevent such misjudgment by adding a skin color determination. be able to.

The image modification device of the present invention is:
An image correction device for correcting a photographic image,
Image focus determination means for performing a focus determination process for determining how much the photographic image is in focus;
Image correction means for correcting the photographic image based on the determination result of the focus determination process, and
The image focus determination means includes
Portrait determination means for determining whether the photographic image is a portrait image;
And a first processing unit that applies a first process as the focus determination process prepared in advance exclusively for a portrait to the photographic image when the portrait determination unit determines that the image is a portrait image. It is characterized by.

  According to the image modifying device having the above-described configuration, when the photographic image is a portrait image, the focus determination process dedicated to the portrait can be performed on the photographic image. The accuracy of determination can be improved. Then, since the photographic image is corrected based on the determination result of the high accuracy focus determination, the quality of the correction can be improved.

  In the image modification device, the image focus determination unit is a second process as the focus determination process prepared in advance for a non-portrait when the portrait determination unit determines that the image is not a portrait. Can be configured to include second processing means for applying to the photographic image.

  According to this configuration, it is possible to perform focus determination suitable for each photographic image by performing different focus determination processing on the photographic image of the portrait and the photographic image other than the portrait. Therefore, it is possible to improve the accuracy of classification by improving the accuracy of determining the focus of a photographic image.

  The first processing means is a pixel selecting means for selecting a pixel belonging to an edge portion having a skin color and having a luminance difference of a predetermined value or more from adjacent pixels from among the pixels constituting the photographic image. A focus focus ratio calculating means for calculating a focus focus ratio indicating how much the photographic image is focused based on the luminance difference for each pixel selected by the pixel selecting means; can do.

  According to the above configuration, it is possible to determine how well the portrait is focused from the luminance difference of each pixel belonging to the edge portion in flesh color. Just by determining how much the focus is based on the brightness difference of each pixel belonging to the edge part, the portrait does not focus on the “person” that is the main subject, but seems to be focused on the background. However, according to the above configuration, it is possible to prevent such misjudgment by adding the skin color according to the above configuration. be able to.

The image focus determination method of the present invention includes:
An image focus determination method for performing a focus determination process for determining how much a photograph image is in focus,
(A) a step of determining whether the photographic image is a portrait image;
(B) when it is determined in the step (a) that the image is a portrait, the step of performing a first process as the focus determination process prepared in advance exclusively for the portrait on the photographic image is provided. It is characterized by.

The first computer program of the present invention is:
A computer program for performing a focus determination process for determining how much a photograph image is in focus,
(A) a function of determining whether the photographic image is a portrait image;
(B) When it is determined that the image is a portrait image in the function (a), the computer is provided with a function of applying a first process as the focus determination process prepared in advance exclusively for a portrait to the photographic image. It is characterized by being realized.

  According to the image focus determination method and the first computer program of the present invention, as in the image focus determination apparatus of the present invention, it is possible to improve the accuracy of focus determination when a photographic image is a portrait. Play.

The image classification method of the present invention includes:
An image classification method for classifying a plurality of photographic images,
(A) a step of performing a focus determination process for determining how much the focus is obtained for each photographic image;
(B) a step of classifying the plurality of photographic images based on a determination result of the focus determination process; and
The step (a)
(A-1) a step of determining whether or not the photographic image is a portrait image;
(A-2) a process of performing, on the photographic image, the first process as the focus determination process prepared in advance for portraits when it is determined in the process (a-1) that the image is a portrait. It is characterized by having and.

The second computer program of the present invention is:
A computer program for classifying a plurality of photographic images,
(A) a function for performing a focus determination process for determining how much the focus is obtained for each photographic image;
(B) causing the computer to realize a function of classifying the plurality of photographic images based on a determination result of the focus determination process;
The function (a) is:
(A-1) a function of determining whether the photographic image is a portrait image;
(A-2) A function of applying, to the photographic image, a first process as the focus determination process prepared in advance for portrait use when it is determined that the image is a portrait image in the function (a-1). It is characterized in that and are realized on a computer.

  According to the image classification method and the second computer program of the present invention, as in the image classification apparatus of the present invention, the accuracy of the focus determination when the photographic image is a portrait is improved, and the accuracy of the photographic image classification is improved. The effect that can be improved.

The pixel correction method of the present invention includes:
An image modification method for modifying a photographic image,
(A) a step of performing a focus determination process for determining how much the focus is obtained for each photographic image;
(B) a step of classifying the plurality of photographic images based on a determination result of the focus determination process; and
The step (a)
(A-1) a step of determining whether or not the photographic image is a portrait image;
(A-2) A process of applying, to the photographic image, a first process as the focus determination process prepared in advance for portraits when it is determined in the process (a-1) that the image is a portrait. An image modification method comprising:

The third computer program of the present invention is:
A computer program for modifying a photographic image,
(A) a function for performing a focus determination process for determining how much the focus is obtained for each photographic image;
(B) causing the computer to realize a function of classifying the plurality of photographic images based on a determination result of the focus determination process;
The function (a) is:
(A-1) a function of determining whether the photographic image is a portrait image;
(A-2) A function of applying, to the photographic image, a first process as the focus determination process prepared in advance for portrait use when it is determined that the image is a portrait image in the function (a-1). It is characterized in that and are realized on a computer.

  According to the image classification method and the third computer program of the present invention, as in the image classification apparatus of the present invention, the accuracy of determining the focus when the photographic image is a portrait is improved, and the photographic image can be corrected. The effect that can be improved.

  The recording medium of the present invention is characterized by a computer-readable recording medium on which any one of the first to third computer programs of the present invention is recorded. This recording medium has the same operation and effect as each computer program of the present invention.

  The present invention includes other aspects as follows. The 1st aspect is an aspect as a program supply apparatus which supplies the computer program of this invention via a communication path. In this first aspect, the above-described method and apparatus are realized by placing a computer program on a server or the like on a computer network, downloading a necessary program to a computer via a communication path, and executing the program. Can do.

The best mode for carrying out the present invention will be described based on examples. This embodiment will be described in the following order.
A. Device configuration:
B. Computer processing:
C. Action / Effect Other embodiments:

A. Device configuration:
FIG. 1 is an explanatory diagram showing a schematic configuration of a computer system to which an embodiment of the present invention is applied. The computer system of this embodiment mainly includes a personal computer 10 constituting the image focus determination device of the present invention, and includes a display 20, a keyboard 22, and a mouse 24 as peripheral devices. Furthermore, a digital camera 26 and a printer 28 are connected to the personal computer 10.

  The personal computer 10 includes a memory 13, a hard disk drive 14, an input control unit 15, a display control unit 16, and the like connected to each other by a bus 12 around a CPU 11 as a central processing unit. The memory 13 stores various data and becomes a work area of the CPU 11. The hard disk drive 14 stores a computer program Pr as software for the image focus determination device. The hard disk drive 14 stores a large number of image data Dp of photographic images (color photographic images) taken by the digital camera 26. The image data Dp is represented by gradation values of R (red), G (green), and B (blue) of each pixel constituting the image.

  The input control unit 15 is a control unit that captures input operations from the keyboard 22 and the mouse 24 and captures image data from the digital camera 26. The display control unit 16 is a control unit that controls signal output to the display 20.

  The computer program Pr is originally stored in a CD-ROM (not shown) as a recording medium, and is installed in the hard disk drive 14 from the CD-ROM by starting a predetermined installation program. is there. When the CPU 11 executes this computer program Pr, various constituent requirements of the image focus determination device of the present invention are realized.

  In FIG. 1, various constituent requirements are shown by blocks of functions implemented in the CPU 11, that is, the CPU 11 executes one computer image read from the hard disk drive 14 by executing the computer program Pr. The portrait determination unit 30 determines whether or not the photographic image indicated by the data Dp is a portrait image. When it is determined that the photographic image is a portrait image, the first processing unit 32 determines that the photographic image is a portrait image. The image is subjected to portrait focus determination processing. On the other hand, when the portrait determination unit 30 determines that the image is not a portrait, the second processing unit 34 performs non-portrait on the photographic image. A rate focus determination process is performed. Here, the focus determination process is a process for determining how much the photograph image is in focus.

  This computer program Pr is actually an application program for photo retouching, and the functions of the portrait determination unit 30, the first processing unit 32, and the second processing unit 34 described above are personalized by some of the modules therein. This is realized by the computer 10.

  The computer program Pr is provided as a configuration stored in another portable recording medium (portable recording medium) such as a flexible disk, a magneto-optical disk, and an IC card in place of the CD-ROM. It can be. Further, the computer program Pr can be provided via a network from a specific server connected to an external network. The network may be the Internet or a computer program obtained by downloading from a specific homepage. Alternatively, it may be a computer program supplied in the form of an email attachment.

B. Computer processing:
Since the computer program Pr is an application program for photo retouching as described above, it has various functions in addition to the portrait determination unit 30, the first processing unit 32, and the second processing unit 34 described above. These functions provided in the computer program Pr are roughly divided into three. The first function is a function for inputting image data TDp to be subjected to image modification from a plurality of image data Dp stored in the hard disk drive 14. The first function includes a portrait determination unit 30, a first processing unit 32, and a second processing unit 34. How it is included will be described later. The second function is a function for executing image processing on the image data TDp input by the first function and performing image modification. This second function includes an automatic image correction function for automatically correcting the image quality of the image data TDp. The third function is a function of saving the image data TDp subjected to the image modification in the hard disk drive 14 or printing out from the printer 28.

  In this embodiment, the first function and the second function will be described, and the third function will not be described because it is not related to the present invention. First, the first function will be described. FIG. 2 is a flowchart showing an image input routine for realizing the first function. This flowchart is a general flowchart showing an outline of processing.

  As shown in the figure, when the process is started, the CPU 11 of the personal computer 10 first executes a process of displaying a list of thumbnails of a plurality of image data Dp on the display 20 (step S100). Specifically, the list is displayed in an application window which is a display area displayed on the display 20.

  FIG. 3 is an explanatory diagram showing the application window WD. The application window WD constitutes a graphical user interface (GUI). As shown in the figure, the application window WD is provided with a toolbar FL1, a file designation field FL2, and a work field FL3. . The file designation field FL2 is a field for designating the storage location of the image data Dp using “folder” or “film”. This designation follows the input operation of the mouse 24 by the operator. In addition to the hard disk drive 14, the storage location on other recording media such as a CD-ROM can be specified, and the recording medium of the digital camera 26 can also be specified directly.

  The work field FL3 displays a list of image data stored in the file or folder designated in the file selection field FL2 in thumbnails, and the list is displayed in response to a click operation of the mouse 24 by the operator. This is a field for selecting a desired one from the image data. In the work field FL3, a candidate area A1 shown in the drawing and a non-candidate area not shown in the drawing can be selectively displayed.

  The candidate area A1 is an area for displaying a list of image data (hereinafter referred to as candidate image data) that are candidates for image data input by the image input routine. The non-candidate area is an area for displaying a list of image data (hereinafter referred to as non-candidate image data) that has been temporarily displayed in the candidate area A1 and then changed to a non-candidate by an operation described later. The operator can cause the candidate area A1 to be displayed in the work field FL3 by clicking on the “input candidate” tab TB1 with the mouse 24 as shown in the figure. Further, the operator can switch the display of the work field FL3 from the candidate area A1 to the non-candidate area by clicking on the “non-candidate” tab TB2 with the mouse 24.

  As shown in the figure, thumbnails of candidate image data are displayed in the candidate area A1, but when the processing moves to step S100, it is stored in the file or folder specified in the file selection field FL2. All the image data is displayed as candidate image data in this candidate area A1.

  In the upper part of the candidate area A1, a button switch BT1 “out of candidates” is provided. The button switch BT1 is used to instruct to switch (change) the candidate image data displayed in the candidate area A1 to the non-candidate image data. The worker selects and instructs one or more of the candidate image data displayed in the candidate area A1 determined to be unnecessary by clicking with the mouse 24, and thereafter By clicking the “outside candidate” button switch BT1, one or a plurality of candidate image data instructed to be selected can be switched to non-candidate image data. The operator can narrow down candidate images that are candidates for input by repeatedly performing the operation of switching such candidate image data to non-candidate image data many times.

  A “sort” button switch BT2 is provided to the right of the “outside candidate” button switch BT1. The “sort” button switch BT2 is used to instruct to sort the candidate image data in the order of good image quality. The order in which the image quality is good here refers to the focus on the photographic image, and the order from the highest focus ratio to the lowest focus ratio.

  Returning to FIG. 2, after execution of step S100, the CPU 11 executes sort processing (step S200). This sort process is started when the “sort” button switch BT2 is clicked by the operator. In this sorting process, a plurality of candidate image data displayed in the candidate area A1 are sorted in the order of good image quality (in the order of high focus ratio), the details of which will be described later.

  Thereafter, the CPU 11 selects a thumbnail in the candidate area A1 in accordance with the input operation of the mouse 24 by the operator, and subsequently receives the click operation of the “out of candidate” button switch BT1 to receive the selected thumbnail. A process for changing the image data of the image to the non-candidate image data is performed (step S300).

  After execution of step S300, the CPU 11 performs a process of selecting one final image from the plurality of candidate image data displayed in the candidate area A1 (step S400). This process selects an instructed image in response to a click operation using the mouse 24 by the operator.

  Thereafter, the CPU 11 reads out the image data corresponding to the one image selected in step S400 from the storage location to the memory and performs a process of displaying it on the display 20 (step S500). Specifically, the work field FL3 of the application window WD is once cleared, and the image data is displayed in the work field FL3. Thereafter, the image input routine ends. According to the image input routine having such a configuration, the operation of inputting the image data TDp stored in the recording medium such as the hard disk drive 14 and subject to image modification is completed.

  FIG. 4 is a flowchart showing details of the sort process executed in step S200. As shown in the figure, when shifting to the sorting process, the CPU 11 first determines whether or not the “sort” button switch BT2 has been clicked with the mouse 24 (step S210). If it is determined that the button has not been clicked, the process returns to “return” and the sort process is temporarily terminated.

  If it is determined in step S210 that the “sort” button switch BT2 has been clicked, the process proceeds to step S220. First, the CPU 11 selects one image data Dp displayed in the candidate area A1. Perform the import process. Specifically, a process of reading one image data Dp corresponding to the thumbnail displayed in the candidate area A1 from the storage source of the image data Dp is performed.

  Next, the CPU 11 executes an image focus determination process for determining how much the photograph image indicated by the image data Dp captured in step S220 is in focus (step S230). The detailed contents of this image focus determination process will be described later, and by this process, a focus in-focus ratio FS indicating how much the photographic image is in focus is obtained.

  Thereafter, the CPU 11 stores the focus ratio FS obtained in step S230 in the sort key table in the memory 13 as the sort key of the image data Dp captured in step S220 (step S240). Subsequently, the CPU 11 determines whether or not the image data Dp captured in step S220 is the final image data Dp displayed in the candidate area A1 (step S250). If it is determined that it is not the final one, the process returns to step S220, the next image data is fetched from the plurality of image data displayed in the candidate area A1, and the step is performed for this image data. The processes from S220 to S250 are repeatedly executed.

  On the other hand, if it is determined in step S250 that the image data is final, the process proceeds to step S260. In step S260, using the sort key stored in the sort key table in step S240, a process of rearranging the display of the image data displayed in the candidate area A1 in the order of the sort key is executed. Since the value of the focus in-focus ratio FS is used as it is, the sort key has a larger value as the photographic image is in focus. Therefore, the image data in the candidate area A1 are rearranged in the order in which they are in focus by the above rearrangement process.

  After executing step S260, the CPU 11 advances the process to “return” and once ends this sort process.

  FIG. 5 is a flowchart showing details of the image focus determination process executed in step S230 of FIG. As shown in the figure, when the processing shifts to this image focus determination processing routine, the CPU 11 first executes a portrait determination processing (step S232). This portrait determination process is a process for determining whether or not the photographic image indicated by the image data Dp captured in step S220 is a portrait image, and for realizing the function of the portrait determination unit 30 described above. Is.

  FIG. 6 is a flowchart showing details of the portrait determination process. As shown in the figure, when the process proceeds to the portrait determination process routine, the CPU 11 first performs a process of reducing the size of the image data Dp captured in step S220 to a size equal to or smaller than a predetermined value (step S600). This reduction processing is a well-known method such as a simple thinning processing method in which pixels (pixels) constituting the image data Dp are simply thinned, and a color averaging processing method in which thinning is performed after averaging colors with adjacent pixels. It can be realized by various processing methods. When the size of the image data Dp is too large, only the processing time required for the subsequent determination process is increased, and even if the image data Dp is reduced, there is no significant difference in the determination result. The predetermined value is, for example, a size of 1000 pixels in the vertical and horizontal directions. If the image size is less than a predetermined value, the reduction process is not performed.

  The image data Dp that has been reduced in step S600 or the image data Dp that has not been reduced to a predetermined size or less is hereinafter referred to as target image data Dx. In this embodiment, as described above, the reduction processing is performed on the image data Dp in order to shorten the processing time. However, as a configuration in which the reduction processing is not performed, the image data Dp is directly used as the target image data Dx. You can also.

  After execution of step S600, the CPU 11 performs processing for clearing the three variables TS, TH, and N to 0 (step S610). The variable TS is a variable for counting the total number of pixels (pixels) of the target image data Dx, and the variable TH is a variable for counting the number of skin color pixels of the target image data Dx. The variable N is a variable for indicating the vertical position of the target image data Dx.

  Thereafter, the CPU 11 clears the variable M for indicating the position of the target image data Dx in the horizontal direction to a value of 0. Subsequently, the CPU 11 determines the R, G, and B gradation values (RGB values) for the pixel P (M, N) whose position is determined by the variables M and N of the target image data Dx (hereinafter referred to as the target pixel). Obtaining (step S630), the RBG value is converted into a YCbCr value (step S640). The conversion from the RBG value to the YCbCr value is performed using the following conversion formulas (1) to (3) used in the case of a television or the like.

Y = 0.30R + 0.59G + 0.11B (1)
Cr = R−Y (2)
Cb = BY (3)

  Thereafter, the CPU 11 determines whether or not the target pixel P (M, N) is a person's flesh color using the color differences Cb and Cr obtained in step S640 (step S650). This determination is made based on whether or not the color differences Cb and Cr satisfy the following relational expression (4).

-2.4625 (Cr-8) ≦ Cb ≦ −0.77419 (Cr-8) (4)

  Relational expression (4) is a relational expression obtained as a result of collecting a large number of portraits of Japanese women and taking statistics on the skin part. When it is determined that the target pixel P (M, N) satisfies the relational expression (4), the target pixel P (M, N) is determined to be a skin color. The relational expression (4) is not necessarily limited to the above numerical values, and there are some changes depending on the race and the skin color to be targeted.

  If it is determined in step S650 that the target pixel P (M, N) is a flesh color, the CPU 11 increments the variable TH indicating the number of flesh color pixels by a value 1 (step S660). Thereafter, the CPU 11 increments the variable TS indicating the total number of pixels by the value 1 (step S670). If it is determined in step S650 that the target pixel P (M, N) is not a skin color, step S660 is skipped, and in step S670, the variable TS indicating the total number of pixels is incremented.

  In order to perform the totaling process for totalizing the number of skin color pixels and the total number of pixels by incrementing the variables TH and TS on the entire target image data Dx, as shown in FIG. P (M, N) is scanned laterally from the left end to the right end, then lowered by one step in the vertical direction, scanned laterally from the left end to the right end, and then lowered by one step in the vertical direction. By repeating, it is necessary to perform the processing of steps S630 to S670 with all the pixels constituting the target image data Dx as the target pixel P (M, N). Therefore, the CPU 11 increments the variable M for indicating the horizontal position of the target image data Dx by a value 1 (step S680), and the variable M exceeds the constant Mmax indicating the right end position of the target image data Dx. It is determined whether or not (step S690). Here, if it is determined that the value does not exceed, the process returns to step S630 to execute the process for the target pixel P (M, N) shifted by one in the right lateral direction.

  On the other hand, when it is determined in step S690 that the variable M has exceeded the constant Mmax, the variable N for indicating the vertical position of the target image data Dx is incremented by 1 (step S692). Then, it is determined whether or not a constant Nmax indicating the lower end position of the target image data Dx has been exceeded (step S694). If it is determined that the value does not exceed, the process returns to step S620 to process the target pixel P (M, N) shifted by one in the vertical downward direction (the horizontal direction has shifted to the left end). Execute.

  When it is determined in step S694 that the variable N has exceeded the constant Nmax, the CPU 11 advances the process to step S696, assuming that the aggregation process has been completed for all pixels constituting the target image data Dx. In step S696, the variable TH indicating the number of flesh color pixels calculated in step S660 is divided by the variable TS indicating the total number of pixels to obtain the ratio of the number of flesh color pixels to the total number of pixels, and the ratio (= TH It is determined whether or not (TS) is greater than or equal to 0.1 (step S696).

  When an affirmative determination is made in step S696, that is, when it is determined that the area ratio of the skin color region in the image is 10% or more, the image indicated by the image data Dp is assumed to be a portrait, and the portrait A value 1 is set to the determination flag F (step S698). On the other hand, when a negative determination is made in step S696, that is, when the area ratio of the skin color region in the image is determined to be less than 10%, the image indicated by the image data Dp is a landscape photograph other than a portrait. For example, the value 0 is set in the portrait determination flag F (step S699). After executing step S698 or S699, the process returns to “RETURN” to end the portrait determination process.

  As described above, it is determined whether or not the image data Dp is a portrait. However, unlike this determination method, it is not always necessary to determine the portrait from the area ratio of the skin color region. It is good also as a structure which determines whether it is a portrait by other methods, such as determining from the shape of the edge of a skin color area | region. Further, the determination value of the area ratio of the skin color region need not be limited to 10% described above, and can be set to various values such as 0.9% and 1.2% instead.

  Returning to FIG. 5, after exiting the portrait determination process of step S232, the CPU 11 then determines whether or not the portrait determination flag F indicating the determination result of the portrait determination process is 1 (step S234). ). That is, it is determined whether or not the image indicated by the image data Dp is a portrait image. Here, if it is determined that the portrait determination flag F is not a value 1, that is, an image other than the portrait, a non-portrait focus in-focus ratio calculation process is executed (step S236). If it is determined that the determination flag F is 1, that is, a portrait image, portrait focus ratio calculation processing is executed (step S238). After executing step S236 or S238, the process returns to “RETURN” to end the image focus determination process once.

  The focus ratio calculation process is a process of calculating a focus ratio FS that is a parameter indicating how much the photographic image is focused. The following two ways can be considered to determine the degree of focus. The first determination method is a method for determining how much the focus is achieved based on the “area ratio of the edge portion”. The edge portion in the photographic image is detected, the ratio (area ratio) of the edge portion to the total area of the photographic image is calculated, and if the area ratio is greater than or equal to a predetermined value, the photographic image is in focus. It is said that is suitable. As the area ratio is larger, it is determined that the focus is good, and the degree of focus is determined.

  The second determination method is a method for determining how much the focus is achieved based on the “edge strength of the edge portion”. An edge portion in the photographic image is detected, and the distribution of the strength of the edge in the edge portion is detected, and it is determined from the distribution whether the focus is in focus. The more the edge strength is distributed in the stronger direction, the better the focus is, and the degree of focus is determined.

  8 and 9 are flowcharts showing details of the non-portrait focus in-focus ratio calculation process executed in step S236. This non-portrait focus focus rate calculation process calculates the focus focus rate FS by the first determination method described above, and is for realizing the function of the second processing unit 34 described above.

  As shown in the figure, this non-portrait focus focus ratio calculation process has many parts similar to the portrait determination process shown in FIG. Steps S700, S720, S730, and S770 to S794 in FIGS. 8 and 9 are the same as steps S600, S620, S630, and S670 to S694 in FIG.

  As shown in FIG. 8, in step S710, the CPU 11 performs a process of clearing the three variables TS, TE, and N to the value 0. The variables TS and N are the same as those used in the portrait determination process. The variable TE is a variable for counting the number of pixels at the edge portion in the image indicated by the target image data Dx.

  In step S740, a process of calculating the luminance Y of the target pixel P (M, N) from the RGB values acquired in step S730 is performed. This calculation process follows the above-described equation (1).

  After execution of step S740, RGB values are acquired for the four pixels around the target pixel P (M, N), respectively, as in steps S730 and S740, and luminances Y1 to Y4 are obtained from the RGB values. Calculate (step S742). Here, the peripheral four pixels are pixels in the vicinity of four adjacent in four directions, up, down, left, and right.

  Subsequently, the CPU 11 obtains absolute values dY1 to dY4 of deviations of the luminances Y1 to Y4 of the four neighboring pixels with respect to the luminance Y of the target pixel P (M, N) obtained in step S740 by the following equations (5) to (5): 8) is performed (step S744).

dY1 = | Y1-Y | (5)
dY2 = | Y2-Y | (6)
dY3 = | Y3-Y | (7)
dY4 = | Y4-Y | (8)

  Thereafter, the CPU 11 calculates the maximum value dYmax of the absolute values (hereinafter referred to as luminance differences) dY1 to dY4 calculated in step S744 (step S746). As a result of the processing in steps S742 to S746, the luminance difference of the portion having the largest luminance difference with respect to the target pixel P (M, N) is obtained among the pixels near the target pixel P (M, N). It will be. It should be noted that, in place of the pixels in the vicinity of the peripheral 4, the luminance difference of the portion having the largest luminance difference with respect to the target pixel P (M, N) among the pixels in the vicinity of the peripheral 8 of the target pixel P (M, N) It is good also as a structure to require.

  After execution of step S746, it is determined whether or not the maximum value dYmax obtained in step S746 is equal to or greater than a predetermined value E0 (step S750). The predetermined value E0 is a luminance difference for determining an edge portion, and is a predetermined value. Here, when it is determined that the maximum value dY is equal to or greater than the predetermined value E0, the target pixel P (M, N) is assumed to be an edge portion, and the CPU 11 advances the processing to step S760 to determine the edge portion. A variable TE indicating the number of pixels is incremented by a value of 1. On the other hand, if it is determined in step S750 that the target pixel P (M, N) is not an edge portion, the process of step S760 is not executed.

  When an affirmative determination is made in step S794 in FIG. 9, the counting for counting the variable TE indicating the number of pixels of the edge portion and the variable TS indicating the total number of pixels is completed for all the pixels constituting the target image data Dx. As a result, the CPU 11 advances the process to step S796. In step S796, by dividing the variable TE indicating the number of pixels of the edge portion calculated in step S760 by the variable TS indicating the total number of pixels calculated in step S770, the number of pixels of the edge portion relative to the total number of pixels is calculated. The ratio is calculated, and the ratio (= TE / TS) is multiplied by the coefficient R1 to determine the focus ratio FS. The coefficient R1 is a numerical adjustment coefficient for converting the ratio of the number of pixels into the focus ratio FS, and is a predetermined value. After the execution of step S796, the process returns to “return” to end the non-portrait focus focus ratio calculation process once.

  The non-portrait focus focus ratio calculation process having such a configuration corresponds to the first determination method described above, and determines how much the focus is achieved based on the “area ratio of the edge portion”.

  For a photographic image that is not a portrait, it is preferable to determine the degree of focus from the “area ratio of the edge portion”. Non-portrait photographic images, such as landscape photographs, are generally shot with pan focus, and often include subjects that are finely depicted, such as forests. Both are often large areas. For this reason, in a photographic image that is not a portrait, it is possible to accurately determine whether the image is in focus by looking at the area ratio of the edge portion.

  On the other hand, portrait photographic images are generally taken with a large person (especially a face) and a blurred background. The face has few details and close-up photography. For this reason, both the in-focus area and the edge-standing area often have very narrow areas. Accordingly, in a portrait photographic image, if the area ratio of the edge portion is viewed, even if the image is in focus, it is erroneously determined that the image is out of focus. In this embodiment, the above-described erroneous determination in the portrait is avoided by limiting the processing in step S236 for performing the focus determination based on the “area ratio of the edge portion” to the non-portrait photographic image.

  FIG. 10 and FIG. 11 are flowcharts showing details of the portrait focus rate calculation process executed in step S238. This portrait focus ratio calculation process calculates the focus ratio FS by an improvement of the second determination method described above, and is for realizing the function of the first processing unit 32 described above. Is.

  As shown in the figure, this portrait focus focus ratio calculation process has many parts that are similar to the non-portrait focus focus ratio calculation process shown in FIGS. Steps S800, S820 to S850, S860, and S880 to S894 in FIGS. 10 and 11 are the same as steps S700, S720 to S750, S760, and S780 to S794 in FIGS.

  As shown in FIG. 10, in step S810, the CPU 11 performs a process of clearing the three variables TE, IE, and N to 0. The variables TE and N are the same as those used in the non-portrait focus focus ratio calculation process. The variable IE is a variable for counting the total edge strength of the edge portion.

  If it is determined in step S850 that the maximum value dY is equal to or greater than the predetermined value E0, the CPU 11 proceeds to step S852, assuming that the target pixel P (M, N) is an edge portion. In step S852, the CPU 11 determines whether or not the target pixel P (M, N) is a human skin color. This determination process is the same process as step S650 of the portrait determination process.

  In this embodiment, step S750 and step S850 are the same processing, but instead of this, the predetermined value E0 to be compared with the maximum value dYmax is set to a value in step S850 rather than the value in step S750. It can be set as the structure made small. That is, in step S750, a process for determining whether or not the maximum value dYmax is equal to or greater than the predetermined value E01 is performed. In step S850, the maximum value dYmax is equal to or greater than the predetermined value E02 that is smaller than the predetermined value E01. It is assumed that the process for determining whether or not is performed.

  In the case of portraits, there are many photographs with a shallow depth of field, but a shallow depth of field means that the entire skin-colored part is not always in focus, and the part that is visible when in focus However, there is a possibility that the edge is not as good as a non-portrait photographic image with a deep depth of field. Therefore, according to this modification, the edge portion of the portrait photographic image can be reliably selected.

  If it is determined in steps S850 and S852 that the target pixel P (M, N) is an edge portion and a skin color, the CPU 11 sets a variable TE indicating the number of pixels in the edge portion to a value 1 in step S860. In addition to the increment, the total edge strength is calculated (step S870). The variable IE indicating the total edge strength is obtained by integrating the maximum value dYmax of the luminance difference obtained in step S846.

  If it is determined in step S850 that the target pixel P (M, N) is not an edge portion, or if it is determined in step S852 that the target pixel P (M, N) is not skin-colored, The processes of S860 and S870 are not executed.

  If an affirmative determination is made in step S894 in FIG. 11, for all the pixels constituting the target image data Dx, the summation for obtaining the variable TE indicating the number of pixels of the edge portion and the variable IE indicating the sum of the edge strengths is performed. Assuming that the processing has ended, the CPU 11 advances the processing to step S896. In step S896, the variable IE indicating the total edge strength of the edge portion calculated in step S870 is divided by the variable TE indicating the number of pixels of the edge portion calculated in step S860. The focus intensity ratio FS is obtained by obtaining the average value of the edge strengths of the pixels and multiplying the ratio (= IE / TE) by the coefficient R2. The coefficient R2 is a numerical adjustment coefficient for converting the average value of the edge strength of the pixel into the focus ratio FS, and is a predetermined value. By setting the coefficient R2 and the coefficient R1 used in the above-described non-portrait focus in-focus ratio calculation processing to appropriate values, it is possible to compare the in-focus between the portrait and the non-portrait equally. Has been made.

  After the execution of step S896, the process returns to “RETURN” to end the portrait focus rate calculation process once. In the focus focus ratio calculation process for portrait, an average value of edge strength is obtained from a variable TE indicating the number of pixels in the edge portion and a variable IE indicating the sum of the edge strengths. Although the focus in-focus rate FS is obtained from the value, the “focus intensity of the edge portion” may be obtained by another method, and the in-focus rate FS may be obtained from the value. As another method, there is a configuration in which a histogram representing an edge strength distribution in an edge portion is created, and “edge strength of the edge portion” is obtained from the histogram.

  The portrait focus rate calculation process having such a configuration follows a method obtained by improving the second determination method described above. In the second determination method, the degree of focus is determined based on the “edge strength of the edge portion”. Instead of this, in the focus focus ratio calculation process for portrait, “skin color” In addition, the degree of focus is determined by “the strength of the edge of the edge portion”.

  In the second method of judging by “edge strength of the edge portion”, the area ratio is not considered and the judgment is made by the strength of the focused portion of the focused portion. Is it the place that you wanted to focus on? On the other hand, in the focus focus ratio calculation process for portrait, since the focus is determined based on “the strength of the edge of the skin color and the edge portion”, the focus portion of the person's face is focused. It is possible to determine how much is matched. In addition, by limiting the process of step S238, which performs the focus determination based on the “skin color and edge strength of the edge portion”, to the portrait photographic image, the person who wants to focus on the portrait, that is, the person It is possible to determine whether or not the face portion of the subject is in focus. Therefore, even if it is a portrait, even if it is a photographic image that does not focus on the person who is the main subject and is focused on the background to be blurred, it is accurately determined that the subject is not in focus. can do.

  As described above, the focus in-focus ratio FS calculated by the non-portrait focus in-focus ratio calculation process or the portrait in-focus ratio calculation process is stored as the sort key of the image data Dp. Classification is made.

  Next, the second function of the application program for photo retouch will be described. As described above, the second function is a function of performing image processing on the image data TDp input by the first function and performing image modification. In this embodiment, the second function is obtained by sorting processing. Using the focus ratio FS as a modification parameter, image processing based on the degree of the modification parameter is performed. In other words, the smaller the in-focus ratio FS is, the higher the intensity of image processing for correcting out-of-focus, such as increasing the degree of “sharpness”.

C. According to the present embodiment configured as described above, when a photographic image is a portrait image, it is possible to perform a focus determination process exclusively for portrait on the photographic image. For this reason, it is possible to improve the accuracy of focus determination when a photographic image is a portrait. Further, in this embodiment, by performing different focus determination processing on a photographic image of a portrait and a photographic image other than the portrait, it is possible to perform a focus determination suitable for each photographic image. Therefore, it is possible to further improve the accuracy of determining the focus of a photographic image.

  In particular, in the present embodiment, when the photographic image is a portrait image, the focus determination is performed based on “the strength of the edge of the skin color and the edge portion”. Even a photographic image where the background is out of focus and the background is in focus can be accurately determined as “out of focus”.

  In this embodiment, since the classification is performed using the focus focus ratio FS that accurately indicates how much the photographic image is in focus as a sort key, the photographic images are accurately rearranged in the order in which they are in focus. Can do.

  In the present embodiment, since the focus in-focus ratio FS is used as a correction parameter for image correction, it is possible to correct the defocus correctly and improve the quality of the correction.

D. Other embodiments:
The present invention is not limited to the above-described examples and embodiments, and can be implemented in various modes without departing from the gist of the present invention. For example, the following modifications are possible.

(1) In the above-described embodiment, the plurality of pieces of image data targeted for focus determination are displayed in the candidate area A1, but need not necessarily have this configuration, and are displayed in other display areas. It may be a thing. Further, it is not necessary to be a photographic image displayed in the display area, and any photographic image data stored in a predetermined area of the recording medium can be set as a focus determination target.

(2) In the above-described embodiment, the plurality of pieces of image data targeted for focus determination are image data in the “folder” or “film” designated in the file designation field FL2 of the application window WD. For this reason, it is not limited to the image data of the photographic image taken by the digital camera 26, and the image data of the photographic image stored in another storage location can also be the sort target. Further, the image is not necessarily limited to a color photographic image, and may be a monochrome multi-tone photographic image.

(3) In the above-described embodiment, the image modification parameter is configured by the focus focus rate FS alone. Instead, in addition to the focus focus rate FS, parameters indicating other image quality characteristics are used. It is good also as a structure to include. The other parameters include “contrast”, “brightness”, “color balance”, “saturation”, and “sharpness” parameters.

(4) In the above-described embodiment, in the focus focus ratio calculation process for portrait, the degree of focus is determined by “the strength of the edge of the skin color and the edge portion”, and the focus for non-portrait is determined. In the focus rate calculation process, the degree of focus was determined by the “area ratio of the edge part”. Instead, both processes are the same process, that is, “the area ratio of the edge part”. The threshold for brightness when determining the edge of the image is determined by the focus focus ratio calculation processing side for the non-portrait focus ratio. It is good also as a structure set as a value smaller than the arithmetic processing side. That is, the portrait focus ratio calculation process shown in FIG. 10 is substantially the same as the non-portrait focus ratio calculation process shown in FIG. 8, and the difference is the predetermined value in the determination in step S750. E0 is set to a value smaller on the portrait focus ratio calculation processing side than on the non-portrait focus ratio calculation processing side. According to this configuration, it is possible to make a unique determination between a portrait and a non-portrait simply by changing the threshold value for determining an edge, and it is possible to improve the accuracy of photographic image focus determination.

It is explanatory drawing which shows schematic structure of the computer system to which one Example of this invention is applied. It is a flowchart which shows an image input routine. It is explanatory drawing which shows the application window WD. It is a flowchart which shows the detail of a sort process. It is a flowchart which shows the detail of an image focus determination process. It is a flowchart which shows the detail of a portrait determination process. It is explanatory drawing which shows a mode that the object pixel is moved. It is a flowchart which shows the detail of the first half part of the focus focusing ratio calculation process for non-portraits. It is a flowchart which shows the detail of the second half part of the focus focusing ratio calculation process for non-portraits. It is a flowchart which shows the detail of the first half part of the focus focus ratio calculation process for portraits. It is a flowchart which shows the detail of the second half part of the focus focus ratio calculation process for portraits.

Explanation of symbols

10 ... Personal computer 12 ... Bus 13 ... Memory 14 ... Hard disk drive 15 ... Input control unit 16 ... Display control unit 18 ... Mouse 20 ... Display 22 ... Keyboard 24 ... Mouse 26 ... Digital camera 28 ... Printer 30 ... Portrait determination unit 32 ... First processing unit 34 ... Second processing unit A1 ... Candidate area BT1. .. Button switch for "outside candidate" BT2 ... Button switch for "Sort" DB ... Dialog box WD ... Application window F ... Portrait determination flag Dp ... Image data

Claims (27)

An image focus determination device that performs a focus determination process for determining how much a photograph image is in focus,
Portrait determination means for determining whether the photographic image is a portrait image;
An image comprising: a first processing unit configured to apply a first process as the focus determination process prepared in advance dedicated to a portrait to the photographic image when the portrait determination unit determines that the image is a portrait image. Focus determination device. The image focus determination device according to claim 1,
A second processing unit configured to apply, to the photographic image, a second process as the focus determination process prepared in advance for a non-portrait when the portrait determination unit determines that the image is other than a portrait; Image focus determination device. The image focus determination device according to claim 1 or 2,
The first processing means includes
A first pixel selecting means for selecting a pixel belonging to an edge portion having a luminance difference of a predetermined value or more between adjacent pixels and a skin color from each pixel constituting the photographic image;
First focus ratio calculation means for calculating a focus ratio indicating how much the photographic image is focused based on the luminance difference for each pixel selected by the first pixel selection means. An image focus determination device comprising: The image focus determination device according to claim 2 or 3,
The second processing means includes
A second pixel selecting means for selecting a pixel belonging to an edge portion having a luminance difference of a predetermined value or more between adjacent pixels from among the pixels constituting the photographic image;
The ratio of the total number of each pixel selected by the second pixel selection unit to the total number of pixels constituting the photographic pixel is obtained, and based on the ratio, how much the photographic image is in focus is determined. An image focus determination apparatus comprising: a second focus focus ratio calculation unit that calculates a focus focus ratio shown. The image focus determination device according to claim 1 or 2,
The first processing means includes
A first pixel selection means for selecting a pixel belonging to an edge portion having a skin color and having a luminance difference equal to or greater than a first predetermined value from adjacent pixels among the pixels constituting the photographic image;
First focus ratio calculation means for calculating a focus ratio indicating how much the photographic image is focused based on the luminance difference for each pixel selected by the first pixel selection means. And
The second processing means includes
A second pixel that selects a pixel belonging to an edge portion having a luminance difference greater than or equal to a second predetermined value that is greater than the first predetermined value from neighboring pixels that constitute the photographic image; A selection means;
The ratio of the total number of each pixel selected by the second pixel selection unit to the total number of each pixel constituting the photographic pixel is obtained, and based on the ratio, how much the photographic image is in focus is determined. An image focus determination apparatus comprising: a second focus focus ratio calculation unit that calculates a focus focus ratio shown. The image focus determination device according to any one of claims 1 to 5,
The portrait determination means includes
An area ratio calculating means for calculating an area ratio of the skin color portion of the photographic image to the entire photographic image;
An image focus determination device comprising: determination means for determining whether the photographic image is a portrait image based on the area ratio calculated by the area ratio calculation means. An image classification device for classifying a plurality of photographic images,
Image focus determination means for performing a focus determination process for determining how much the focus is in each photographic image;
Classification means for classifying the plurality of photographic images based on a determination result of the focus determination process; and
The image focus determination means includes
Portrait determination means for determining whether the photographic image is a portrait image;
An image comprising: a first processing unit configured to apply a first process as the focus determination process prepared in advance dedicated to a portrait to the photographic image when the portrait determination unit determines that the image is a portrait image. Classification device. The image classification device according to claim 7,
The image focus determination means includes
A second processing unit configured to apply, to the photographic image, a second process as the focus determination process prepared in advance for a non-portrait when the portrait determination unit determines that the image is other than a portrait; Image classification device. The image classification device according to claim 7 or 8, wherein
The first processing means includes
A pixel selection means for selecting a pixel belonging to an edge portion having a skin color and having a luminance difference of a predetermined value or more from adjacent pixels from among the pixels constituting the photographic image;
An image classification apparatus comprising: a focus ratio calculation unit that calculates a focus ratio indicating how much the photographic image is focused based on the luminance difference for each pixel selected by the pixel selection unit . An image correction device for correcting a photographic image,
Image focus determination means for performing a focus determination process for determining how much the photographic image is in focus;
Image correction means for correcting the photographic image based on the determination result of the focus determination process, and
The image focus determination means includes
Portrait determination means for determining whether the photographic image is a portrait image;
An image comprising: a first processing unit configured to apply a first process as the focus determination process prepared in advance dedicated to a portrait to the photographic image when the portrait determination unit determines that the image is a portrait image. Modification device. The image modification device according to claim 10,
The image focus determination means includes
A second processing unit configured to apply, to the photographic image, a second process as the focus determination process prepared in advance for a non-portrait when the portrait determination unit determines that the image is other than a portrait; Image modification device. The image correction device according to claim 10 or 11,
The first processing means includes
A pixel selection means for selecting a pixel belonging to an edge portion having a skin color and having a luminance difference of a predetermined value or more from adjacent pixels from among the pixels constituting the photographic image;
An image correction apparatus comprising: a focus ratio calculation unit that calculates a focus ratio indicating how much the photographic image is focused based on the luminance difference for each pixel selected by the pixel selection unit. . An image focus determination method for performing a focus determination process for determining how much a photograph image is in focus,
(A) a step of determining whether the photographic image is a portrait image;
(B) an image comprising: a step of performing, on the photographic image, a first process as the focus determination process prepared in advance for a portrait when it is determined in the process (a) that the image is a portrait. Focus determination method. The image focus determination method according to claim 13,
(C) when it is determined in step (a) that the image is other than a portrait, a step of performing, on the photographic image, a second process as the focus determination process prepared in advance for a non-portrait. Image focus determination method. The image focus determination method according to claim 13 or 14,
The step (b) is:
(B-1) a step of selecting a pixel belonging to an edge portion having a skin color and having a luminance difference of a predetermined value or more from adjacent pixels from among the pixels constituting the photographic image;
(B-2) a step of calculating a focus rate indicating how much the photographic image is focused based on the luminance difference for each pixel selected in the step (b-1). Image focus determination method. An image classification method for classifying a plurality of photographic images,
(A) a step of performing a focus determination process for determining how much the focus is obtained for each photographic image;
(B) a step of classifying the plurality of photographic images based on a determination result of the focus determination process; and
The step (a)
(A-1) a step of determining whether or not the photographic image is a portrait image;
(A-2) A process of applying, to the photographic image, a first process as the focus determination process prepared in advance for portraits when it is determined in the process (a-1) that the image is a portrait. An image classification method comprising: An image modification method for modifying a photographic image,
(A) a step of performing a focus determination process for determining how much the focus is obtained for each photographic image;
(B) a step of classifying the plurality of photographic images based on a determination result of the focus determination process; and
The step (a)
(A-1) a step of determining whether or not the photographic image is a portrait image;
(A-2) A process of applying, to the photographic image, a first process as the focus determination process prepared in advance for portraits when it is determined in the process (a-1) that the image is a portrait. An image modification method comprising: A computer program for performing a focus determination process for determining how much a photograph image is in focus,
(A) a function of determining whether the photographic image is a portrait image;
(B) When it is determined that the image is a portrait image in the function (a), the computer is provided with a function of applying a first process as the focus determination process prepared in advance exclusively for a portrait to the photographic image. Computer program for realizing. A computer program according to claim 18, comprising:
(C) When it is determined in the function (a) that the image is other than a portrait, a function of applying a second process as the focus determination process prepared in advance for a non-portrait to the photographic image A computer program for realizing this. A computer program according to claim 18 or 19, comprising:
The function (b) is
(B-1) a function of selecting a pixel belonging to an edge portion having a skin color and having a luminance difference of a predetermined value or more from adjacent pixels from among the pixels constituting the photographic image;
(B-2) a function of calculating a focus rate indicating how much the photographic image is focused based on the luminance difference for each pixel selected by the function (b-1). Computer program. A computer program for classifying a plurality of photographic images,
(A) a function for performing a focus determination process for determining how much the focus is obtained for each photographic image;
(B) causing the computer to realize a function of classifying the plurality of photographic images based on a determination result of the focus determination process;
The function (a) is:
(A-1) a function of determining whether the photographic image is a portrait image;
(A-2) A function of applying, to the photographic image, a first process as the focus determination process prepared in advance for portrait use when it is determined that the image is a portrait image in the function (a-1). A computer program comprising: A computer program according to claim 21, comprising:
(A-3) When it is determined by the function (a-1) that the image is other than a portrait, a second process as the focus determination process prepared in advance for a non-portrait is applied to the photographic image. A computer program that allows a computer to implement the functions to be performed. A computer program according to claim 21 or 22,
The function (a-2) is
(A-2-1) a function of selecting a pixel belonging to an edge portion having a skin color and having a luminance difference of a predetermined value or more from adjacent pixels from among the pixels constituting the photographic image;
(A-2-2) Based on the luminance difference for each pixel selected by the function (a-2-1), a focus in-focus ratio indicating how much the photographic image is in focus is calculated. A computer program with functions. A computer program for modifying a photographic image,
(A) a function for performing a focus determination process for determining how much the focus is obtained for each photographic image;
(B) causing the computer to realize a function of classifying the plurality of photographic images based on a determination result of the focus determination process;
The function (a) is:
(A-1) a function of determining whether the photographic image is a portrait image;
(A-2) A function of applying, to the photographic image, a first process as the focus determination process prepared in advance for portrait use when it is determined that the image is a portrait image in the function (a-1). A computer program comprising: A computer program according to claim 24,
(A-3) When it is determined by the function (a-1) that the image is other than a portrait, a second process as the focus determination process prepared in advance for a non-portrait is applied to the photographic image. A computer program that allows a computer to implement the functions to be performed. A computer program according to claim 24 or 25, comprising:
The function (a-2) is
(A-2-1) a function of selecting a pixel belonging to an edge portion having a skin color and having a luminance difference of a predetermined value or more from adjacent pixels from among the pixels constituting the photographic image;
(A-2-2) Based on the luminance difference for each pixel selected by the function (a-2-1), a focus in-focus ratio indicating how much the photographic image is in focus is calculated. A computer program with functions.   A computer-readable recording medium on which the computer program according to any one of claims 18 to 26 is recorded.

Images