JP2008084236A - Image processor, image processing method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To detect the size of a person and perform image correction only when needed. <P>SOLUTION: The image processor (1) comprises a first determination means (2) for determining whether a personal face is projected in an input original image or not; an extraction means (2) for extracting a face area when projection of the personal image is determined by the first determination means (2); a second determination means (2) for determining whether the area of the face area extracted by the extraction means (2) exceeds a predetermined value or not; and an image correction means (2) for performing predetermined image correction to the original image when the determination result by the second determination means (2) is affirmative. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an image processing apparatus, an image processing method, and a program, and is applied to, for example, an imaging apparatus such as a digital camera, image processing application software such as image retouching software, or a printing apparatus that prints a digital photograph or the like. The present invention relates to an image processing apparatus, an image processing method, and a program.

  Since digital cameras capture subject images as digital images, image processing is easy.For example, image processing application software such as image retouching software is used, and brightness, color, or Sharpness (sharpness) or the like can be finely adjusted as desired. However, making these adjustments manually is cumbersome and cumbersome, and requires appropriate techniques, so it is not for everyone.

  Therefore, for example, Patent Document 1 below discloses a technique for detecting a human skin region in an image and performing a required image correction.

JP 2006-179987 A

  However, the above-described prior art is merely to detect a human skin area in an image and perform a required image correction. The size of the human skin area, that is, the size of the person in the image is shown. No consideration is given to this. Therefore, in the above-described prior art, for example, even in the case of an image in which each person is small like a group photo of many people, the required image processing is performed. Even if the required image correction is performed on the face area, a great effect cannot be expected.

  Therefore, an object of the present invention is to avoid useless processing by detecting the size of a person and performing image correction only when necessary.

According to the first aspect of the present invention, it is determined by a first determination unit that determines whether or not a person's face is reflected in the input original image, and that the person's face is reflected by the first determination unit. The extraction means for extracting the face area in this case, the second determination means for determining whether the area of the face area extracted by the extraction means exceeds a predetermined value, and the determination result of the second determination means is positive In this case, the image processing apparatus includes image correction means for performing predetermined image correction on the original image.
According to the second aspect of the present invention, the image correction unit applies a predetermined image correction to the original image when the determination result of the second determination unit is positive, and determines the degree of the image correction in the face region. The image processing apparatus according to claim 1, wherein the image processing apparatus adjusts according to the area of the image.
The invention according to claim 3 is characterized in that the image correcting means applies predetermined image correction to the face area having the largest area when a plurality of face areas are detected by the extracting means. An image processing apparatus according to claim 1 or 2.
According to a fourth aspect of the present invention, the image correcting unit performs predetermined image correction on the face region detected most near the center of the screen when a plurality of face regions are detected by the extracting unit. 3. An image processing apparatus according to claim 1, wherein the image processing apparatus is characterized in that
According to a fifth aspect of the present invention, when a plurality of face regions are detected by the extracting unit, the image correcting unit is configured to use a face region having the largest area as a reference with respect to the extracted face regions. 3. The image processing apparatus according to claim 1, wherein predetermined image correction is performed.
According to a sixth aspect of the present invention, when the image correction means detects a plurality of face areas by the extraction means, the face area detected most near the center of the screen with respect to the extracted face areas. The image processing apparatus according to claim 1, wherein predetermined image correction is performed with reference to.
The invention according to claim 7 further includes a calculating means for calculating a first speed for image enlargement and a second speed for image movement when the determination result of the second determination means is affirmative, and the original image The size of the original image displayed on the display means is gradually enlarged according to the first speed, and the center of the face area in the original image is substantially the center of the screen of the display means. First display control means for gradually moving the display position of the original image according to the second speed so as to match, and elapse of a predetermined time after completion of image enlargement and image movement in the first display control means 7. The image processing apparatus according to claim 1, further comprising second display control means for returning the size of the image displayed on the display means to the size of the original image later. It is.
The invention according to claim 8 is characterized in that the second display control means returns the size of the image displayed on the display means to the size of the original image according to the first and second speeds. Item 8. The image processing device according to Item 7.
In the invention according to claim 9, it is determined that the person's face is reflected in the first determination step for determining whether or not the person's face is reflected in the input original image, and the first determination step. An extraction step for extracting the face region in the case, a second determination step for determining whether the area of the face region extracted by the extraction step exceeds a predetermined value, and the determination result of the second determination step is positive And an image correction step of applying a predetermined image correction to the original image.
The invention according to claim 10 is that the computer includes a first determination unit that determines whether or not a person's face is reflected in the input original image, and the person's face is captured by the first determination unit. Extraction means for extracting the face area when determined, second determination means for determining whether the area of the face area extracted by the extraction means exceeds a predetermined value, and determination by the second determination means When the result is affirmative, the program is a program for causing the original image to function as an image correction unit that performs predetermined image correction.

  In the present invention, since the size of a person is detected and image correction is performed only when necessary, useless processing can be avoided.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings, taking application to a digital camera as an example. It should be noted that the specific details or examples in the following description and the illustrations of numerical values, character strings, and other symbols are only for reference in order to clarify the idea of the present invention, and the present invention may be used in whole or in part. Obviously, the idea of the invention is not limited. In addition, a well-known technique, a well-known procedure, a well-known architecture, a well-known circuit configuration, and the like (hereinafter, “well-known matter”) are not described in detail, but this is also to simplify the description. Not all or part of the matter is intentionally excluded. Such well-known matters are known to those skilled in the art at the time of filing of the present invention, and are naturally included in the following description.

  FIG. 1 is a configuration diagram of a digital camera. In this figure, a digital camera 1 includes a control unit 5 composed of a microprocessor, typically a one-chip microprocessor, including a CPU 2, a ROM 3, a RAM 4, various peripheral circuits (not shown), and the like. And at least the following units necessary for the digital camera.

  Although not particularly essential, the strobe light emitting unit 6 and the strobe driving unit 7 are directed from the strobe light emitting unit 6 toward the subject 8 under specific conditions such as insufficient brightness at the time of photographing under the control of the control unit 5. A strobe light 9 having a light amount adjusted according to a predetermined light amount or a distance to the subject 8 is emitted.

  The imaging unit 10 includes an optical system 11 including a photographing lens, a diaphragm mechanism, a focusing mechanism (and a zoom mechanism if necessary), and an imaging device 12 including a two-dimensional image sensor such as a CCD sensor or a CMOS sensor. The The operation of the imaging unit 10 (adjustment of the aperture size and zoom magnification, that is, the adjustment and focusing of the imaging angle of view α, and the exposure and readout operation of the imaging device 12) is an imaging control that receives an imaging operation instruction from the control unit 5. It is controlled by the control from the unit 13. The photographing operation instruction from the control unit 5 is a frame image reading operation instruction at a predetermined frame rate (for example, several tens to several hundreds of frames per second) for photographing composition confirmation (so-called through image) or moving image photographing. , High-resolution still image shooting operation instructions, and various prior operation instructions such as aperture value setting and zoom magnification setting necessary for these operations.

  In response to a shooting operation instruction from the control unit 5, the imaging unit 10 periodically reads frame images for shooting composition confirmation and moving images at the above frame rate, or a high-resolution still image. A picture frame image is read out. These frame images are converted into digital signals by the image processing unit 14 and are subjected to predetermined image processing (for example, white balance and gamma correction processing), and then taken into the control unit 5.

  The operation unit 15 includes various operators necessary for an input interface for user operation of the digital camera 1, such as a power switch, a mode switch for image capturing and image reproduction, a shutter button for performing still image capturing and moving image capturing, A menu button for displaying a setting menu, a selection button for selecting the menu item, and selecting an image desired to be reproduced in the image reproduction mode are included.

  The display control unit 16 converts various display data appropriately output from the control unit 5, for example, through-image display data, menu screen display data, image reproduction screen display data, and the like into a predetermined display format. Then, the data is output to the display unit 17 constituted by a small (for example, about 2 to 4 inches) flat display device such as a liquid crystal display. The display unit 17 is provided with a touch panel 18, and the touch detection unit 19 detects touch coordinates such as a finger or a pen on the touch panel 18 and outputs the detection result to the control unit 5.

  The image storage unit 20 is configured by a non-volatile mass storage device such as a flash memory, a hard disk, or an optical disk (the stored contents are not lost even when the power is turned off). Used to store and store the generated images. Each image stored and stored is, for example, a compressed file such as a JPEG format or an uncompressed raw data file (so-called RAW file). The storage area for these images may be directly under the root in the file system, or may be a folder having a single hierarchy or a multi-hierarchy structure appropriately created immediately under the root. In addition, the image storage unit 20 may be a fixed type, or may be a general-purpose memory device that can be detached from the digital camera 1 and attached to a personal computer (not shown), for example.

  The external interface 21 is, for example, a data input / output unit that supports a general-purpose protocol such as USB or IEEE 1394. The external interface 21 can capture a captured image with a personal computer (not shown) or the like as needed. Transfer (transfer images stored in the image storage unit 20 to a personal computer) and read (read images from the personal computer to the image storage unit 20) can be performed.

  The power supply unit 22 includes a rechargeable secondary battery or a disposable primary battery, and supplies a power supply voltage necessary for the operation of each unit of the digital camera 1 including the control unit 5.

<First Embodiment>
Next, operations unique to the digital camera 1 in the first embodiment will be described. The digital camera 1 according to the first embodiment can shoot still images and moving images and store and store the captured images in the image storage unit 20 as, for example, JPEG or RAW image files. When a desired image can be selected from the stored images and reproduced and displayed on the display unit 17 and a person is reflected in the captured image (or an image stored and stored in the image storage unit 20), the appearance of the person is improved. The predetermined image correction for the purpose can be performed.

This will be described in detail below.
FIG. 2 is a conceptual diagram showing the storage space of the RAM 4. The RAM 4 is used as a work area (an area for loading a control program stored in the ROM 3 and executed by the CPU 2) of the control unit 5, and as a storage space for performing the above-mentioned “predetermined image correction”. Is also used. Therefore, as shown in FIG. 2, the RAM 4 has at least two image storage areas 4a and 4b. The first image storage area 4a is a storage area for a photographed image (a target image for predetermined image correction and a high-resolution still image with particularly good image quality), and the second image storage area 4b is a photographed image. This is a storage area for a duplicate image of an image. Hereinafter, for convenience of explanation, an image (captured image) stored in the first storage area 4a is referred to as an “original image”, and an image (copy image of the captured image) stored in the second storage area 4b is “replicated”. It will be called “image”.

  In the first embodiment, when a still image is captured and the captured image (original image) is stored in the first storage area 4a, it is first determined whether or not a person's face is reflected in the original image. To do. If the image is not captured, the original image is converted into a JPEG image, for example, and stored in the image storage unit 20 as usual without performing the above-described “predetermined image correction”. When a person's face is reflected, (a) a duplicate image of the original image is stored in the second storage area 4b, (b) a “Gaussian blurring process” is applied to the duplicated image, and (c) Gaussian blurring is performed. The composite image after processing and the original image are screen-synthesized, and the original image stored in the first storage area 4a is updated with the composite image, and then the updated original image is converted into, for example, a JPEG image Then, a characteristic operation of storing and saving in the image storage unit 20 is executed.

  Here, Gaussian blur is a process that produces a blur effect (or blur effect) on an image by diffusing the information of the pixels that make up the image to the surroundings. By adjusting, the effect of blur can be strengthened or weakened. Note that although Gaussian blur is used here, the present invention is not limited to this, and any image processing may be used as long as the image processing is performed to make a person beautiful.

  FIG. 3 is a diagram for explaining the effect of blur caused by Gaussian blur. In this figure, (a) is an original image 23, (b) is a duplicate image 24 with Gaussian blurring, and (c) is an original image (hereinafter referred to as a composite image 25) obtained by synthesizing the duplicated image 24 after Gaussian blurring. It is. Note that these images are monochrome images that have undergone dithering, but this is for convenience of illustration and is actually a high-resolution color image.

  When comparing the original image 23 in (a) and the duplicate image 24 with Gaussian blurring in (b), the duplicated image 24 with Gaussian blurring on the sharp original image 23 in focus is the subject. The image is blurred as if it were blurred, producing an effect that looks as if it were shot using a special filter such as a soft focus lens or a foggy filter.

  The shooting technique for producing such a blur effect is often used particularly in a portrait photograph of a woman using the above-described focus lens, special filter, etc. In the first embodiment, only the blur effect is used. There is also a point in that it is devised to improve the sweetness of the focus that accompanies the bokeh effect rather than gaining.

  That is, if only the blurring effect of the image is to be obtained, only the duplicate image 24 with the Gaussian blur of (b) is sufficient. That is, the original image stored in the first storage area 4a may be overwritten and updated with the duplicate image 24 subjected to the Gaussian blur. However, simply applying Gaussian blur tends to produce a so-called “no-focus” sweet image, which is inappropriate as a work.

  Therefore, in the first embodiment, the duplicate image 24 after the Gaussian blurring process and the original image 23 are screen-synthesized, and the original image 23 stored in the first storage area 4a is updated with the synthesized image. I am doing so. The composite image 25 of (c) has been updated in this way. Comparing the duplicate image 24 with Gaussian blur (b) and the synthesized image 25 (c), it is recognized that the sweetness of the focus is improved. Therefore, by combining the duplicate image 24 and the original image 23 that have been Gaussian-blured in this way, and updating the original image 23 stored in the first storage area 4a, a predetermined blur effect can be obtained. It is possible to improve the sweetness of the focus and to produce a composite image 25 with a quality that can be sufficiently endured as a work.

The image correction in the first embodiment will be specifically described below.
FIG. 4 is a flowchart of a control program executed by the CPU 2 of the control unit 5. In this flowchart, first, image data (original image 23 in FIG. 3A) is acquired (step S1). Next, a face is detected from the original image 23 (step S2). As for this face detection, for example, skin color data is extracted from an original image, and a cluster of photometric points determined as a skin color range is used as a face (Japanese Patent Laid-Open Nos. 52-156624 and 53-145621). , JP-A-53-145622), converting photometric data into H (hue) and S (saturation) to create a two-dimensional histogram of H and S, and dividing this histogram into single peaks. The candidate area of the face is extracted by determining which of the divided peaks each pixel of the original image belongs to and dividing the pixel, and whether the face is a human face from the contour and internal structure of the face candidate area (Japanese Unexamined Patent Publication No. 4-346333), a method of detecting a face whose size, position, and direction are unknown under a complicated background and estimating the face direction (“independent of background and face direction” Face detection and face direction estimation ", Since various things are known, such as Ki et al., The Institute of Electronics, Information and Communication Engineers, IEICE Technical Report PRMU 2001-217 pp. 87-94, 2002-01), these known technologies can be used alone or Any combination may be used.

  Once face detection is performed in this way, it is next determined whether or not face detection is present (step S3). If no face is detected, it is determined that the person is not captured, for example, an image obtained by shooting a landscape, and the flowchart ends. If there is face detection, the largest face area is displayed next. Is determined to be greater than or equal to a predetermined area (step S4). Here, the “face region” refers to the size of the face detected in the previous step S2, more precisely the size (area) of a group of pixels in a portion regarded as a face. Note that there may be a plurality of faces detected in the previous step S2. That is, this is a case where a plurality of persons are shown in one original image 23. The “maximum face area” refers to the face having the largest area among the faces of the plurality of persons. In the subsequent correction process, a predetermined correction process (Gaussian blur process) is performed on the basis of the maximum face area. This is because the person photographed in the largest face area can be said to be the main subject (central subject) in the image, and it is most reasonable to perform Gaussian blurring on the basis of the main subject. This is because of the idea.

  In step S4, if the maximum face area is not equal to or larger than the predetermined area, the face of the person shown in the original image 23 is small, for example, a person accidentally reflected in a landscape photo, The group photograph is determined to be a group photo of a large number of people. In such a case, there is no need to perform a predetermined correction process (Gaussian blurring process), so the flowchart ends.

  On the other hand, if the maximum face area is greater than or equal to the predetermined area in step S4, the following correction process is executed. That is, the area of the maximum face area (hereinafter referred to as Z) is acquired (step S5), and then the original image 23 stored in the first storage area 4a is copied to the second storage area 4b. Thus, a duplicate image 24 of the original image 23 is created (step S6). The duplicate image 23 is subjected to Gaussian blur processing having a strength corresponding to the area Z of the maximum face region (step S7), and the duplicate image 24 and the original image 23 subjected to Gaussian blur are screen-synthesized. Then, the original image 23 stored in the first storage area 4a is updated (step S8) to form the composite image 25, and then the flowchart ends.

  For example, the following expression (1) is an expression of a two-dimensional Gaussian function that can be used for Gaussian blurring.

(X, y): coordinates of the target pixel
G: Correction value for the coordinates
π: Pi ratio
e: base of natural logarithm
σ: Coefficient of blur effect

  In the above equation (1), the value of the coefficient σ is determined depending on the area Z of the maximum face region. In the screen composition in step S8, the background and foreground values are bg and fg (where 0 ≦ bg and fg ≦ 1), respectively, and the foreground opacity is α (where 0 <α <1). Then, although it can obtain | require by following Formula (2), the value of this opacity (alpha) is also decided depending on the area Z of the largest face area | region.

  FIG. 5 is a correspondence diagram between the area (Z) of the face region and the Gaussian blur effect. As shown in this figure, the degree of Gaussian blurring increases as the area (Z) of the face region increases. Specifically, the value of the coefficient σ in the above equation (1) is increased. This is because, for example, a strong Gaussian blur looks better for a face shot up, and conversely, a moderately suppressed Gaussian blur is more beautiful for a small face. Because it looks like. In addition, in this figure, although it is set as the linear correspondence, it is not limited to this. It may be a linear correspondence. In short, it is only necessary to have a correspondence relationship that increases the degree of Gaussian blur as the area (Z) of the face region increases. The same applies to the opacity α of the foreground in the screen composition. That is, when the value of the opacity α is determined depending on the area Z of the maximum face region, the opacity α may be increased as the area (Z) of the face region increases.

Further, here, the predetermined image processing is performed depending on the area of the maximum face area. However, the present invention is not limited to this, and the predetermined image processing may be performed depending on the area of the face closest to the center. good.
In addition, predetermined image processing may be performed only on the maximum face area (which may include the surrounding area).
In addition, predetermined image processing may be performed only on the face region (which may include the periphery thereof) located closest to the center.

  As described above, according to the first embodiment, a face is detected from the original image 23, the area Z of the face region is extracted, and the degree of Gaussian blurring on the duplicate image 24 is determined according to the area Z. Since the duplicate image 24 with Gaussian blurring and the original image 23 are combined on the screen to form a composite image 25, a soft-focus composite image 25 with excellent aesthetics can be obtained. Therefore, it is possible to obtain an image with an excellent aesthetic sense by applying a soft focus to a person, and further, by detecting the size of the person and performing image correction only when necessary, it is useless. Processing can be avoided. In addition, since the duplicate image 24 subjected to Gaussian blur and the original image 23 are screen-synthesized, it is possible to obtain an excellent composite image 25 as a work that not only loses the focus of focus but also loses the focus.

  FIG. 6 is a diagram showing a flowchart of a preferred improvement of the first embodiment. This flowchart is added and executed after step S8 of FIG. In this added flowchart, the position of the “mouth” is acquired from the face area (step S9), and the redness of the mouth area where the redness is strong (that is, the lip portion) is emphasized (step S10). . Then, the presence / absence of another unprocessed mouth area is determined (step S11), and if there is still an unprocessed mouth area, step S9 and the subsequent steps are repeated.

  FIG. 7 is a diagram illustrating a composite image 25 to which the improved example is applied. Since two women are shown in this composite image 25, there are two mouth areas. In this figure, the right female mouth area 26 and a strong reddish part (lip part) 27 in the mouth area 26 are shown as a representative. By executing the flowchart of FIG. 6, the lips of these two women can be emphasized so that the lips are more reddish and corrected to a healthy picture. Incidentally, although the redness is corrected here, the present invention is not limited to this, and any image correction may be used as long as it makes a person (particularly a woman) look beautiful. For example, the amount of magenta may be slightly increased.

  As a technique for acquiring the position of the “mouth” from the face area, for example, Japanese Patent Application Laid-Open No. 2006-113658 is known.

<Second Embodiment>
Next, a specific operation of the digital camera 1 in the second embodiment will be described. In the first embodiment, the object is to obtain an image with an excellent aesthetic feeling by applying soft focus to a person. In the second embodiment, the screen of the display unit 17 is further provided. The purpose of the above is to improve operability by enlarging and displaying the face of a person for a predetermined time and then returning it to its original size.

  In other words, most digital cameras are equipped with a liquid crystal display for monitoring, and the captured images can be displayed on the display for confirmation, but the size of the liquid crystal display is at most several inches ( Even a large one is as small as 2 to 4 inches). For example, in order to check the focus, there is a disadvantage that the button must be operated to enlarge and display an image. In order to eliminate this inconvenience, for example, in the technique described in Japanese Patent Application Laid-Open No. 2005-31888 (hereinafter referred to as the prior art), an object of interest such as a human face is detected from an image displayed on the screen. In accordance with the position and size of the subject of interest, a display area and an enlargement ratio for magnifying and displaying the subject of interest are determined, and the subject of interest is enlarged and displayed on the screen according to the display region and the enlargement ratio. .

  However, in this prior art, an attention subject such as a human face is enlarged and displayed on the screen, but there is no mention of returning the enlarged image to the original size. Therefore, since the image is “enlarged”, there is a problem that the size of the image must be restored to the original size manually, and the operability cannot be denied.

  The second embodiment described below has been made in view of the background as described above, and improves the operability by enlarging and displaying the face of a person for a predetermined time and then returning it to the original size. There is to plan.

  FIG. 8 is a diagram illustrating a flowchart of a control program executed by the CPU 2 of the control unit 5. In this flowchart, processing from acquisition of image data to detection of a face having a predetermined size or more (steps S1 to S4) is the same as that in the first embodiment, and a description thereof will be omitted.

  If a face area of a predetermined size or larger is detected, first, one of the face areas having a predetermined area or larger is selected (step S12), and will be described later from the ratio between the area of the selected face area and the area of the original image. The “image enlargement speed” is calculated (step S13), and the “movement speed” is also detected from the distance between the center of the original image and the center of the face area (step S14). Incidentally, these speeds are synchronized so that the center of the enlarged image (the center of the face area) is positioned at the center of the screen when the image is enlarged to the maximum. These speeds do not need to be constant, and may have acceleration.

  When the enlargement speed and the movement speed are calculated in this manner, the size of the image displayed on the screen of the display unit 17 is then gradually increased according to the “image enlargement speed” calculated in step S13. While enlarging, the center of the face area in the image is gradually moved toward the center of the screen of the display unit 17 according to the “movement speed” calculated in step S14 (step S15). Then, the completion of enlargement and movement is determined (step S16). When the completion is determined, it is then determined whether or not a predetermined waiting time has elapsed (step S17). This “predetermined waiting time” is a time that is sufficient to allow the user to see the image enlarged and displayed on the display unit 17 and confirm the degree of focus and the like.

  Then, when a predetermined waiting time has elapsed, the size of the image displayed on the display unit 17 is restored (step S18). When returning to the original size, the speed may be gradually returned by using the above speeds (image enlargement speed and movement speed) instead of instantaneously.

  In this way, when the size of the image displayed on the display unit 17 is restored, it is then determined whether or not an end command operation has been performed by the user (step S19), and the end command operation is performed. If it is, the flowchart is ended as it is, but if the end command operation is not performed, it is determined whether there is another face area larger than a predetermined area (step S20). If there is a face area, step S12 and the subsequent steps are repeated.

FIG. 9 is a conceptual diagram of image enlargement processing. In this figure, an image corresponding to the composite image 25 of FIG. 3 is displayed on the screen 28 of the display unit 17. In this image, for example, as shown in (a), one person 29 is shown, and the face area 30 of the person 29 is indicated by a dotted rectangle. Here, (b), the vertical size D _Y of the screen 28, a horizontal size with represented by D _X, likewise, E the vertical size of the face region 30 _Y, represent the horizontal size E _X To. The center point of the screen 28 is represented by D _P and the center point of the face region 30 is represented by E _P. (C) shows the screen 28 when the face area 32 after enlargement is displayed. The face area 32 after enlargement has a vertical size E _Y ′ and a horizontal size E _X ′. The center point E _P of the face area 32 substantially coincides with the center point D _P of the screen 28.

As described above, the “image enlargement speed” in step S13 is calculated from the ratio between the area of the selected face region and the area of the original image. This means that to calculate the ratio between D _Y × D _X and E _Y × E _X. For example, if the ratio of D _Y × D _X and E _Y × E _X is A, and calculates the rate of image enlargement which corresponds to this A, or, if smaller in B than the ratio is A, B The speed of low image enlargement corresponding to is calculated. The same applies to the “movement speed” in step S14. That is, for example, if D _Y × D _X and E _Y × E ratio of _X is A, and calculates the speed of movement corresponding to this A, or, if smaller in B than the ratio is A, The speed of the low movement corresponding to B is calculated.

  In this way, when the image displayed on the screen 28 of the display unit 17 is determined to be a person image, the attention area (face area 30) of the original image can be automatically enlarged and displayed to fill the screen 28. It is possible to check the focus condition without taking time and effort. Moreover, since the enlarged display is automatically returned to the original size image after a predetermined waiting time has elapsed (see step S17), it is not necessary to cancel the enlarged display every time. Therefore, even when the preview display after shooting is performed on the display unit 17 having a small size, since it is possible to smoothly check the focus state without requiring any special operation, the operability is extremely convenient. It is possible to provide a digital camera 1 excellent in the above.

In addition, according to this embodiment, the “image enlargement speed” and the “movement speed” are calculated from the ratio between the area of the selected face area and the area of the original image, so that zooming is performed. In this way, the face area can be enlarged and displayed, and the user can intuitively know which part has been enlarged.
Also, when the image enlargement is completed and the original image size is restored, if it follows the “image enlargement speed” and “movement speed”, an effect like an animation can be produced. Can be more preferable.

The essential items for the second embodiment are as follows.
First, when viewed as an image processing apparatus, it is determined by a first determination unit that determines whether or not a person's face is reflected in the input original image, and that the person's face is reflected by the first determination unit. The extraction means for extracting the face area in the case of the detection, the second determination means for determining whether or not the area of the face area extracted by the extraction means exceeds a predetermined value, and the determination result of the second determination means In the case of affirmation, a calculation means for calculating a first speed for image enlargement and a second speed for image movement, and displaying the original image on the display means and the size of the original image being displayed on the display means Is gradually enlarged according to the first speed, and the display position of the original image is gradually moved according to the second speed so that the center of the face area in the original image substantially coincides with the center of the screen of the display means. First display control means for causing said Second display control means for returning the size of the image displayed on the display means to the size of the original image after elapse of a predetermined time after completion of image enlargement and image movement in the one display control means. It is characterized by that.
Further, the second display control means returns the size of the image displayed on the display means to the size of the original image according to the first and second speeds.

Further, when viewed as an image processing method, it is determined that a person's face is reflected in the first determination step for determining whether or not a person's face is reflected in the input original image, and the first determination step. An extraction process for extracting the face area in the case of the detection, a second determination process for determining whether or not the area of the face area extracted by the extraction process exceeds a predetermined value, and a determination result of the second determination process When the result is affirmative, a calculation step of calculating a first speed for image enlargement and a second speed for image movement, and displaying the original image on a display means and the size of the original image being displayed on the display means Is gradually enlarged according to the first speed, and the display position of the original image is gradually moved according to the second speed so that the center of the face area in the original image substantially coincides with the center of the screen of the display means. The first display control step and the previous A second display control step of returning the size of the image displayed on the display means to the size of the original image after a lapse of a predetermined time from the completion of image enlargement and image movement in the first display control step. It is characterized by including.
Alternatively, the second display control step returns the size of the image displayed on the display means to the size of the original image according to the first and second speeds.

Further, when viewed as a program, the computer determines a first determination unit that determines whether or not a person's face is reflected in the input original image, and determines that the person's face is captured by the first determination unit. Extraction means for extracting the face area when it is done, second determination means for determining whether or not the area of the face area extracted by the extraction means exceeds a predetermined value, and a determination result of the second determination means Is positive, a calculation means for calculating a first speed for image enlargement and a second speed for image movement, and displaying the original image on the display means and the size of the original image being displayed on the display means The display position of the original image is gradually increased according to the second speed so that the center of the face area in the original image substantially coincides with the center of the screen of the display means. First display to move And a second unit for returning the size of the image displayed on the display unit to the size of the original image after a lapse of a predetermined time from completion of image enlargement and image movement in the first display control unit. This is a program for realizing display control means.
Alternatively, the second display control means is a program that returns the size of the image displayed on the display means to the size of the original image according to the first and second speeds.

  By providing such essential items, the attention area (face area) of the original image can be automatically enlarged and displayed on the full screen of the display means, and the focus condition can be reduced without much trouble. Can be confirmed. In addition, since the enlarged display is automatically returned to the original size image after a predetermined waiting time, it is not necessary to cancel the enlarged display every time. Therefore, even when the preview display after shooting is performed on a small-sized display means (for example, a liquid crystal display of several inches), it is possible to smoothly check the focus state without requiring any special operation. Therefore, it is possible to provide a digital camera that is extremely easy to use and excellent in operability. Furthermore, when the enlargement of the image is completed and the size of the original image is restored, the first and second speeds are followed, so that an effect like an animation can be produced.

  In the first and second embodiments described above, the predetermined correction processing is performed on a case where the detected maximum face area exceeds a predetermined size, but the present invention is not limited to this.

  FIG. 10 is another conceptual diagram of detection of a face area to be corrected. In this figure, an image 33 shown in (a) shows a background (here, a mountain for convenience) located at the center and a person 34 located on the right side, and an image 35 shown in (b). Shows a background (here, a mountain for convenience) located in the center and a person 36 also located in the center. As described above, in these two images 33 and 35, the persons 34 and 36 are shown, but it can be said that the person 36 shown in the center is the main subject. In many cases, the main subject is placed at the center of the composition.

  Therefore, in other words, a person who is out of the center of the composition (for example, the person 34 in the image 33) can be said to be an unnecessary subject that has been accidentally reflected. Assuming that the person 34 in the image 33 is a face area of the person 34 having a predetermined area or more, a predetermined correction process (Gaussian blurring process or the like) is performed on the basis of the face area of the person 34. Is a waste.

  As a countermeasure, it is only necessary to detect a face area closest to the center in the horizontal direction of the image and perform a predetermined correction process only when the face area exceeds a predetermined size. In this way, useless correction processing for the image 33 in (a) can be avoided, and predetermined correction processing can be performed only for the image 35 in (b).

  Moreover, although the above embodiment made the example application to imaging devices, such as a digital camera, it is not limited to this. The present invention can be applied to image processing application software such as image retouching software used in a personal computer, or can be applied to embedded software such as a printing apparatus (printer) for printing a digital photograph or the like.

  In addition, the main functions in the above embodiment are implemented exclusively in the control program shown in the flowchart of FIG. 4, FIG. 6 or FIG. 8, and these control programs are executed on a computer such as a CPU. Thus, it can be said that the characteristic technical matters in the above embodiments are included in those control programs. Therefore, the scope to be protected of the present invention naturally includes the control program, and the recording medium storing the program, as well as any medium capable of distributing the program via a network, include the control program. Included in the range.

  As described above, in the first embodiment, in short, image data holding means for holding digital image data, face detection means for performing face detection processing on image data, and predetermined image processing on image data. Image processing means for performing image display, and image display means for displaying image data. Face detection is performed by the face detection means for specified one of the image data held by the image data holding means. If a face is detected, the image is treated as a person image, the image processing means automatically performs image processing so that the person image looks beautiful, and the result is displayed on the image display means. It is possible to display an image with excellent aesthetics.

Further, if the processing by the image processing means is executed only for the face area detected by the face detecting means exceeding a predetermined size, for example, a group photo of a large number of people As described above, in the case of an image in which each person is small, it is possible to avoid unnecessary processing by not performing predetermined image processing.
Further, when a plurality of face areas are detected by the face detection means, efficient image correction can be performed if the execution of the process is determined based on the face area having the largest area among them. it can.

Further, more effective image correction can be performed by changing the degree of the effect of the processing by the image processing means in accordance with the area of the face area detected by the face detecting means.
In addition, when a plurality of face areas are detected by the face detection means, efficient image correction can be performed by determining the degree of processing effect based on the face area having the largest area among them. Can do.

In addition, when a plurality of face areas are detected by the face detecting means, if the degree of processing effect is determined based on the face area detected most near the center in the horizontal direction of the image, The degree of processing effect can be determined based on the subject (in many cases, located near the center in the horizontal direction of the image).
Further, when a face is detected by the face detection means, if the image processing means performs enlargement / reduction processing so that the detected face area is zoomed in / out, the display image is moved. The display of the image can be interesting, and when a plurality of persons are captured, the person who is viewing can intuitively grasp who is zooming in on the face.

Further, if the processing by the image processing means is executed only for the face area detected by the face detecting means exceeding a predetermined size, for example, a group photo of a large number of people As described above, in the case of an image in which each person is small, it is possible to avoid unnecessary processing by not performing predetermined image processing.
Further, when a plurality of face areas are detected by the face detection means, the image processing means sequentially executes zoom-in / out image processing for those exceeding a predetermined size. For example, in the case of an image in which each person is small like a group photo of many people, it is possible to avoid unnecessary processing by not performing predetermined image processing.
Further, when the area of the image is smaller than a predetermined size (for example, a thumbnail image), if the face detection process is not performed, the predetermined image process is not performed and the unnecessary process is avoided. Can do.

It is a block diagram of a digital camera. 3 is a conceptual diagram showing a storage space of a RAM 4. FIG. It is a figure explaining the effect of the blur by Gaussian blurring. It is a figure which shows the flowchart of the control program run by CPU2 of the control part 5. FIG. It is a correspondence diagram of the area (Z) of the face area and the Gaussian blur effect. It is a figure which shows the flowchart of the preferable improvement example of 1st Embodiment. It is a figure which shows the synthesized image 25 to which the example of improvement is applied. It is a figure which shows the flowchart of the control program run by CPU2 of the control part 5. FIG. It is a conceptual diagram of an image expansion process. It is another detection conceptual diagram of the face area to be corrected.

Explanation of symbols

1 Digital camera (image processing device)
2 CPU (first determination means, extraction means, second determination means, image correction means,
Synthesis means, calculation means, first display control means, second display control means)
17 Display section (display means)
23 Original image 24 Duplicated image 25 Composite image

Claims (10)

First determination means for determining whether or not a human face is reflected in the input original image;
Extracting means for extracting a face area when it is determined by the first determining means that a person's face is reflected;
Second determination means for determining whether the area of the face region extracted by the extraction means exceeds a predetermined value;
An image processing apparatus comprising: an image correction unit that applies a predetermined image correction to the original image when the determination result of the second determination unit is positive.   The image correction unit applies predetermined image correction to the original image when the determination result of the second determination unit is affirmative, and adjusts the degree of the image correction according to the area of the face region. The image processing apparatus according to claim 1.   3. The image correction unit according to claim 1, wherein when the plurality of face regions are detected by the extraction unit, predetermined image correction is performed on the face region having the largest area. An image processing apparatus according to 1.   2. The image correction unit according to claim 1, wherein when a plurality of face regions are detected by the extraction unit, predetermined image correction is performed on the face region detected most near the center of the screen. Item 3. The image processing device according to any one of Items 2 to 3.   The image correction means, when a plurality of face areas are detected by the extraction means, performs predetermined image correction on the extracted face areas based on the face area having the largest area. The image processing apparatus according to claim 1, wherein the image processing apparatus is characterized.   When a plurality of face areas are detected by the extraction means, the image correction means performs a predetermined image correction on the basis of the face area detected closest to the center of the screen with respect to the extracted face areas. The image processing apparatus according to claim 1, wherein the image processing apparatus is applied. And a calculating means for calculating a first speed for image enlargement and a second speed for image movement when the determination result of the second determination means is affirmative;
The original image is displayed on the display means, the size of the original image being displayed on the display means is gradually enlarged according to the first speed, and the center of the face area in the original image is the screen of the display means First display control means for gradually moving the display position of the original image according to the second speed so as to substantially coincide with the center of
Second display control means for returning the size of the image displayed on the display means to the size of the original image after a lapse of a predetermined time from the completion of image enlargement and image movement in the first display control means; The image processing apparatus according to claim 1, further comprising:   8. The image processing apparatus according to claim 7, wherein the second display control unit returns the size of the image displayed on the display unit to the size of the original image according to the first and second speeds. A first determination step of determining whether a person's face is reflected in the input original image;
An extraction step of extracting the face area when it is determined in the first determination step that a human face is reflected;
A second determination step of determining whether the area of the face region extracted by the extraction step exceeds a predetermined value;
An image correction step of applying a predetermined image correction to the original image when the determination result of the second determination step is affirmative. Computer
First determination means for determining whether or not a human face is reflected in the input original image;
Extracting means for extracting a face area when it is determined by the first determining means that a person's face is reflected;
Second determination means for determining whether the area of the face region extracted by the extraction means exceeds a predetermined value;
A program for functioning as an image correction unit that applies a predetermined image correction to the original image when the determination result of the second determination unit is positive.

Images