JP2017092544A - Output control device, output control method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To more stably perform image quality adjustment with a face of a person in an image to be outputted defined as a reference.SOLUTION: An imaging apparatus 100 comprises: a face detection part 4b for detecting faces of persons from frame images that are successively captured by an imaging part 3; a first image quality adjustment part 4c for automatically adjusting the image quality of a frame image with a detected face of a person defined as a reference; a display control part 6a for outputting an image of which the image quality has been adjusted; and a first discrimination part 4d by which, if a detection state of a face of a person is changed from a state where the face of the person is being detected to a state where the face of the person is not being detected, it is discriminated whether a content of the image quality adjustment with the face of the person defined as a reference should be maintained.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an output control device, an output control method, and a program.

  When photographing a human, it may be desirable to adjust the image quality based on the human face. Therefore, exposure and white balance are automatically adjusted using the result of face detection. In addition, a technique for preventing erroneous white balance correction using a face detection function in auto white balance is also known (see, for example, Patent Document 1).

JP 2011-139481 A

  However, in the case of the above-mentioned patent document 1 or the like, if a human can no longer detect a face while taking a picture, the white balance adjustment contents change, and the human faces back to detect the face. When it becomes possible, the white balance adjustment content changes again, and there is a problem that the display of the live view image is not stable. Such a problem is not limited to auto white balance, and may occur even in automatic exposure adjustment.

  The present invention has been made in view of such problems, and an object of the present invention is to provide an output control device capable of performing image quality adjustment based on a human face of an output image more stably, An output control method and program are provided.

One aspect of the present invention for solving the above problems is an output control device,
Detecting means for detecting a human face from captured images sequentially imaged by the imaging means;
An adjustment unit that automatically adjusts the image quality of the captured image based on the human face detected by the detection unit;
Control means for outputting an image whose image quality has been adjusted by the adjusting means;
When the detection state of the human face by the detection unit changes from a state in which the human face is detected to a state in which the human face is not detected, the content of image quality adjustment based on the human face by the adjustment unit is Determining means for determining whether or not to maintain;
It is characterized by having.

  According to the present invention, the image quality adjustment based on the human face of the output image can be performed more stably.

It is a block diagram which shows schematic structure of the imaging device of Embodiment 1 to which this invention is applied. 3 is a flowchart illustrating an example of an operation related to a live view display process by the imaging apparatus of FIG. 1. 3 is a flowchart illustrating an example of an operation related to a non-face detection state process in the live view display process of FIG. 2. It is a figure which shows typically the live view image which concerns on a live view display process. It is a block diagram which shows schematic structure of the imaging device of Embodiment 2 to which this invention is applied. 6 is a flowchart illustrating an example of an operation related to a live view display process by the imaging apparatus of FIG. 5. 7 is a flowchart illustrating an example of an operation related to a non-face detection state process in the live view display process of FIG. 6.

  Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. However, the scope of the invention is not limited to the illustrated examples.

[Embodiment 1]
FIG. 1 is a block diagram illustrating a schematic configuration of an imaging apparatus 100 according to the first embodiment to which the present invention is applied.
As illustrated in FIG. 1, the imaging apparatus 100 according to the first embodiment specifically includes a central control unit 1, a memory 2, an imaging unit 3, a signal processing unit 4, an image processing unit 5, and a display unit. 6, an image recording unit 7, and an operation input unit 8.
The central control unit 1, the memory 2, the imaging unit 3, the signal processing unit 4, the image processing unit 5, the image recording unit 7, and the display unit 6 are connected via a bus line 9.

  The central control unit 1 controls each unit of the imaging device 100. Specifically, although not shown, the central control unit 1 includes a CPU (Central Processing Unit) and the like, and performs various control operations according to various processing programs (not shown) for the imaging apparatus 100.

  The memory 2 is composed of, for example, a DRAM (Dynamic Random Access Memory) or the like, and temporarily stores data or the like processed by the central control unit 1 or the signal processing unit 4.

  The imaging unit (imaging means) 3 captures a predetermined subject (for example, a human) and generates a frame image I (see FIG. 4A). Specifically, the imaging unit 3 includes a lens unit 3a, an electronic imaging unit 3b, and an imaging control unit 3c.

The lens unit 3a includes, for example, a plurality of lenses such as a zoom lens and a focus lens, and a diaphragm for adjusting the amount of light passing through the lens.
The electronic imaging unit 3b is configured by an image sensor (imaging device) such as a charge coupled device (CCD) or a complementary metal-oxide semiconductor (CMOS), for example. Then, the electronic imaging unit 3b converts the optical image that has passed through the various lenses of the lens unit 3a into a two-dimensional image signal.

  Although not shown, the imaging control unit 3c includes a timing generator, a driver, and the like. Then, the imaging control unit 3c scans and drives the electronic imaging unit 3b with a timing generator and a driver, and the optical imaging unit 3b converts the optical image that has passed through the lens unit 3a into a two-dimensional image signal for each predetermined period. Then, the frame image I is read for each screen from the imaging area of the electronic imaging unit 3b and is output to the signal processing unit 4.

  The signal processing unit 4 performs various image signal processes on the analog value signal of the frame image I transferred from the electronic imaging unit 3b. Specifically, for example, the signal processing unit 4 adjusts the gain for each RGB color component with respect to the analog value signal of the frame image I, performs sample holding by a sample hold circuit (not shown), and performs A / D conversion. The digital data is converted by a device (not shown), and color processing including pixel interpolation processing and γ correction processing is performed by a color process circuit (not shown) to obtain a luminance signal Y and color difference signals Cb, Cr (YUV) of digital values. Data). The signal processing unit 4 outputs the generated luminance signal Y and color difference signals Cb and Cr to the memory 2 used as a buffer memory.

The signal processing unit 4 includes an image acquisition unit 4a, a face detection unit 4b, a first image quality adjustment unit 4c, and a first determination unit 4d.
Note that each unit of the signal processing unit 4 is configured by, for example, a predetermined logic circuit, but the configuration is an example and is not limited thereto.

The image acquisition unit 4 a acquires frame images (captured images) I that are sequentially captured by the imaging unit 3. Specifically, the image acquisition unit 4a sequentially acquires frame images I related to live view images sequentially transferred from the electronic imaging unit 3b when the imaging unit 3 captures a subject.
The frame image Ia in FIG. 4A, the frame image Ib in FIG. 4B, and the frame image Ic in FIG. 4C each show an example of the frame image I as described later.

The face detection unit (detection means) 4b detects a human face from the frame image I.
That is, for example, the face detection unit 4b performs a predetermined face detection process on each of the plurality of frame images I (Ia to Ic) sequentially acquired by the image acquisition unit 4a to include a human face as a subject. To detect the face area. FIG. 4A shows a state in which the frame image Ia is displayed as a live view image when a human face as a subject is detected on the display panel 6b, and includes the detected human face. A rectangular frame W represented by a broken line is schematically superimposed on the face area.
Further, since the face detection process is a known technique, detailed description thereof is omitted here.

The first image quality adjustment unit (adjustment unit) 4c automatically adjusts the image quality of the frame image I.
That is, the first image quality adjustment unit 4c automatically adjusts the white balance, brightness, and the like of the plurality of frame images I (Ia to Ic) related to the live view image sequentially acquired by the image acquisition unit 4a. Specifically, for example, the first image quality adjustment unit 4c is detected by the face detection unit 4b in an auto white balance (AWB) mode in which white balance is automatically adjusted during imaging. The white balance of the frame image I is automatically adjusted based on the human face and other conditions other than the human face. In addition, for example, the first image quality adjustment unit 4c detects the human face detected by the face detection unit 4b in a state in which an auto exposure (AE) mode for automatically adjusting the exposure condition is set at the time of shooting. The brightness of the frame image I is automatically adjusted based on other conditions other than the human face.

In the white balance adjustment using the human face as a reference, the first image quality adjustment unit 4c first, for each of the plurality of frame images I (Ia to Ic) sequentially acquired by the image acquisition unit 4a, based on the image data. A light source (for example, a room: a white light) is estimated, and a pixel corresponding to the skin color is specified under the estimated light source in the face area detected by the face detection unit 4b. Next, the first image quality adjustment unit 4c calculates a gain amount for each color component of RGB with reference to a pixel value (for example, RGB value) of a pixel corresponding to the specified skin color, and calculates each color of RGB The white balance of the frame image I is adjusted by amplifying the image data based on the gain amount for each component.
Moreover, as other conditions other than the human face, for example, the pixel value of a pixel corresponding to gray under a predetermined light source specified from the entire frame image I can be cited.
In this white balance adjustment, the first image quality adjustment unit 4c firstly uses a light source (for example, indoor: for each of the plurality of frame images I (Ia to Ic) sequentially acquired by the image acquisition unit 4a) based on the image data. White pixels, etc.) are estimated, and pixels corresponding to gray are identified under the estimated light source in the frame image I. Next, the first image quality adjustment unit 4c calculates a gain amount for each color component of RGB with reference to the pixel value (for example, RGB value) of the pixel corresponding to the specified gray, and calculates each color of RGB The white balance of the frame image I is adjusted by amplifying the image data based on the gain amount for each component.

  The above-described process for estimating the light source is a known technique and will not be described in detail. For example, using the image data corresponding to the HSV color space of the frame image I, the frame image I The light source may be estimated from the hue and the hue position of the gray component. Further, when specifying a skin color pixel in the face area, for example, an area having a size equal to or smaller than the size of the face area in the face area may be designated as the detection area.

In the brightness adjustment based on the human face, the first image quality adjustment unit 4c first determines, based on the image data, each of the plurality of frame images I (Ia to Ic) sequentially acquired by the image acquisition unit 4a. The luminance distribution (luminance histogram) in the face area detected by the face detection unit 4b is specified. Next, the first image quality adjustment unit 4c uses the signal distribution of the luminance signal Y so that the face area has a predetermined brightness based on a predetermined program diagram with reference to the luminance distribution in the specified face area. The brightness of the frame image I is adjusted by adjusting (ISO sensitivity) and amplifying the luminance signal Y.
Further, as other conditions other than the human face, for example, the luminance distribution of the entire frame image I (Ia to Ic) or a predetermined photometric area (for example, the central area) may be mentioned. In this brightness adjustment, the first image quality adjustment unit 4c, first, based on the image data of each of the plurality of frame images I (Ia to Ic) sequentially acquired by the image acquisition unit 4a, The luminance distribution of the photometric area is specified. Next, the first image quality adjustment unit 4c determines the luminance signal Y so that the entire frame image I and the predetermined photometric area have a predetermined brightness based on a predetermined program diagram based on the specified luminance distribution. The brightness of the frame image I is adjusted by adjusting the signal amplification factor and amplifying the luminance signal Y.

  Note that the first image quality adjustment unit 4c may adjust the brightness of the frame image I by adjusting the shutter speed and aperture value of the electronic imaging unit 1b, for example. Further, when specifying the luminance distribution of the face area, for example, an area having a size equal to or smaller than the size of the face area in the face area may be designated as the detection area.

The first determination unit (determination unit) 4d determines whether or not the content of the image quality adjustment based on the human face by the first image quality adjustment unit 4c should be maintained.
That is, when the detection state of the human face by the face detection unit 4b changes from the face detection state in which the human face is detected to the non-detection state in which the first detection unit 4d is not detecting the human face, It is determined whether or not the content of image quality adjustment (for example, white balance and brightness adjustment) based on the face should be maintained.
Here, maintaining the content of the image quality adjustment based on the human face means that the frame image I in a non-face detection state where the human face is not detected (for example, the frame image Ib etc.) The image quality adjustment of the same content as the image quality adjustment based on the human face performed on the frame image (for example, the immediately preceding frame image Ia) in which the human face is detected is performed. That is, even in the non-face detection state, image quality adjustment such as white balance and brightness of the frame image I is performed using a previously detected human face.

Specifically, the first determination unit 4d captures a plurality of frame images I () captured by the image capturing unit 3 and acquired by the image acquiring unit 4a before and after the detection state of the human face by the face detecting unit 4b is changed. It is determined whether or not the content of the image quality adjustment based on the human face by the first image quality adjustment unit 4c should be maintained based on the change state of the imaging environment determined from Ia to Ic).
Here, the change of the imaging environment is, for example, when the image quality of the frame image I is adjusted by the first image quality adjustment unit 4c on the basis of other conditions other than the human face. Judgment is made based on a change in the image feature information measured from Ic).

For example, in the white balance adjustment, the first determination unit 4d is a predetermined measurement measured from frame images (for example, frame images Ia, Ib, etc.) before and after the human face detection state is changed by the first image quality adjustment unit 4c. A change amount of the number of pixels (image feature information) corresponding to a predetermined color under a light source is used. That is, the first image quality adjustment unit 4c, for example, has a plurality of light sources (for example, sunlight, indoor: white light, indoor: fluorescent light) for each of the frame images I before and after the human face detection state has changed. Below, the number of pixels is calculated by identifying the pixels corresponding to gray. The specification of the pixel corresponding to gray may be performed by, for example, a process of estimating a light source.
And the 1st determination part 4d calculates the variation | change_quantity of the pixel count of the pixel applicable to gray before and after the detection state of a human face changed about each of several light sources, and the change of the calculated pixel count The amounts (absolute values) are summed, and it is determined whether or not the sum is less than a predetermined threshold.
Here, if it is determined that the total value is less than the predetermined threshold, it is considered that the imaging environment has not changed (see FIG. 4B). For example, as shown in FIGS. 4 (a) and 4 (b), when a human face as a subject whose face was previously detected faces sideways, the face cannot be detected. The imaging environment itself does not change simply because the face of the subject cannot be detected. In this case, the first determination unit 4d should maintain the content of the white balance adjustment based on the human face even for the frame image Ib in the non-face detection state in which no human face is detected. judge. Then, the first image quality adjustment unit 4c uses the frame area Ib based on the face area including the previously detected human face with respect to the frame image Ib in the non-face detection state in which no human face is detected. Automatically adjusts the white balance.
On the other hand, if it is determined that the total value is not less than the predetermined threshold, it is considered that the imaging environment has changed. (See FIG. 4 (c)). For example, as shown in FIG. 4A and FIG. 4C, the composition changes greatly when the user touches the imaging apparatus 100 to the right and the human face as the subject is detected. If not, the human face that is the subject does not exist within the angle of view, and the imaging environment changes. In this case, the first determination unit 4d determines that the content of the white balance adjustment based on the human face should not be maintained. Then, the first image quality adjustment unit 4c applies the white balance of the frame image Ic to the frame image Ic in a non-face detection state in which no human face is detected based on other conditions other than the human face. Adjust automatically.
Note that the predetermined threshold value used for the determination is a value for determining whether the human being who is the subject cannot simply detect the face by changing the direction or the imaging environment has changed. It is not a value that can be set uniquely due to differences in detection accuracy, but is determined empirically.For example, a predetermined value set for each shooting scene may be used. A uniform value may be used.

For example, in the brightness adjustment, the first determination unit 4d is measured from the frame images before and after the human face detection state is changed by the first image quality adjustment unit 4c (for example, the frame images Ia and Ib). The amount of change in luminance distribution (image feature information) is used. That is, for example, the first image quality adjustment unit 4c specifies the luminance distribution of the entire frame image I for each of the frame images I before and after the detection state of the human face has changed, and represents a representative luminance value (for example, an average value) Value).
Then, the first determination unit 4d calculates a change amount of the representative value of luminance before and after the detection state of the human face changes, and determines whether or not the calculated change amount is less than a predetermined threshold value. .
Here, if it is determined that the amount of change is less than the predetermined threshold, it is considered that the imaging environment has not changed (see FIGS. 4A and 4B), and the first determination unit 4d It is determined that the content of the brightness adjustment based on the human face should be maintained for the frame image Ib in a non-face detection state in which no human face is detected. Then, the first image quality adjustment unit 4c uses the frame area Ib based on the face area including the previously detected human face with respect to the frame image Ib in the non-face detection state in which no human face is detected. Automatically adjust the brightness.
On the other hand, if it is determined that the amount of change is not less than the predetermined threshold, it is considered that the imaging environment has changed (see FIGS. 4A and 4C), and the first determination unit 4d detects the human face. It is determined that the content of the standard brightness adjustment should not be maintained. Then, the first image quality adjustment unit 4c determines the brightness of the frame image Ic with respect to a frame image Ic in a non-face detection state in which no human face is detected based on other conditions other than the human face. Adjust automatically.
Note that the predetermined threshold value used for the determination is a value for determining whether the human being who is the subject can not detect the face simply by changing his orientation, or whether the imaging environment has changed. When the light level of the entire frame image I is greatly different, such as outdoors and at night, it is not a value that can be set uniquely, but is determined empirically. For example, a predetermined value set for each shooting scene However, a uniform value may be used regardless of the shooting scene.

The image processing unit 5 encodes still image or moving image image data generated by the signal processing unit 4 in a predetermined compression format (for example, JPEG format, MPEG format, etc.) and records still images and moving images. Generate image data.
Further, the image processing unit 5 decodes still image or moving image image data relating to the display target read from the memory 2 or the image recording unit 7 in accordance with a corresponding predetermined encoding method and outputs the decoded data to the display unit 6. . At this time, the image processing unit 5 may be transformed into a predetermined size (for example, VGA or full HD size) and output to the display unit 6 based on, for example, a display resolution of the display panel 6b described later.

  The display unit 6 includes a display control unit 6a and a display panel 6b.

  The display control unit 6a performs control to display a predetermined image in the display area of the display panel 6b based on image data of a predetermined size read from the memory 2 or the image recording unit 7 and decoded by the image processing unit 5. . Specifically, the display control unit 6a includes a VRAM (Video Random Access Memory), a VRAM controller, a digital video encoder, and the like. The digital video encoder reads out the luminance signal Y and the color difference signals Cb and Cr decoded by the image processing unit 5 and stored in the VRAM (not shown) from the VRAM through the VRAM controller at a predetermined reproduction frame rate. Based on these data, a video signal is generated and output to the display panel 6b.

The display panel 6b displays an image taken by the imaging unit 3 in the display area based on the video signal from the display control unit 6a. Specifically, the display panel 6b displays a plurality of frame images I (Ia to Ic) generated by photographing an object by the imaging unit 3 in a predetermined frame rate in a still image shooting mode or a moving image shooting mode. The live view image is displayed while updating sequentially. At this time, the display control unit 6a acquires the image data of the frame image I (Ia to Ic) in which the image quality such as white balance and brightness is adjusted from the first image quality adjustment unit 4c as a control unit, and the live view image Is output to the display panel 6b and displayed in the display area of the display panel 6b (see FIGS. 4A to 4C).
Examples of the display panel 6b include a liquid crystal display panel and an organic EL (Electro-Luminescence) display panel. However, the display panel 6b is an example and is not limited thereto.

The image recording unit 7 includes, for example, a non-volatile memory (flash memory) or the like, and records image data for recording still images and moving images encoded by the image processing unit 5 in a predetermined compression format.
Note that the image recording unit 7 may be configured such that, for example, a recording medium (not shown) is detachable, and data reading from the mounted recording medium and data writing to the recording medium are controlled.

  The operation input unit 8 is for performing a predetermined operation of the imaging apparatus 100. Specifically, the operation input unit 8 includes a shutter button according to an instruction to shoot a subject, a selection determination button according to an instruction to select a shooting mode or a function, a zoom button according to an instruction to adjust a zoom amount, and the like (all not shown). And a predetermined operation signal is output to the central control unit 1 in accordance with the operation of each button of the operation unit.

<Live view display processing>
Next, live view display processing by the imaging apparatus 100 will be described with reference to FIGS.
FIG. 2 is a flowchart illustrating an example of an operation related to the live view display process. FIG. 3 is a flowchart illustrating an example of an operation related to the non-face detection state process in the live view display process. FIGS. 4A to 4C are diagrams schematically showing live view images displayed on the display panel 6b.

  The live view display process is a process executed by each unit of the imaging apparatus 100 under the control of the central control unit 1 when the subject is imaged by the imaging unit 3. In the live view display process described below, an auto white balance (AWB) mode for automatically adjusting white balance and an auto exposure (AE) mode for automatically adjusting exposure conditions are set. Shall be.

As shown in FIG. 2, when the imaging of the subject by the imaging unit 3 is started (step S <b> 1), the image acquisition unit 4 a of the signal processing unit 4 performs the live view sequentially transferred from the electronic imaging unit 3 b of the imaging unit 3. The frame images I (Ia to Ic) relating to the images are sequentially acquired (step S2).
Subsequently, the face detection unit 4b performs a predetermined face detection process on the frame image I (for example, the frame image Ia) acquired by the image acquisition unit 4a (step S3), and the human face that is the subject is detected. It is determined whether or not the included face area is detected (step S4).

If it is determined in step S4 that a face area has been detected (step S4; YES), the first image quality adjustment unit 4c performs white balance adjustment and brightness adjustment of the frame image I acquired by the image acquisition unit 4a. The reference is set to a face area including the detected human face (step S5). Then, the first image quality adjustment unit 4c adjusts the white balance and brightness (image quality) of the frame image I according to the set standard (step S6).
Specifically, in the white balance adjustment, the first image quality adjustment unit 4c estimates, for example, a light source (for example, a room: a white light), and selects pixels corresponding to the skin color under the estimated light source in the face area. Identify. Then, the first image quality adjustment unit 4c calculates the gain amount for each color component of RGB with reference to the pixel value (for example, RGB value) of the pixel corresponding to the specified skin color, and amplifies the image data. Adjust the white balance of the frame image I. In the brightness adjustment, the first image quality adjustment unit 4c, for example, specifies the luminance distribution in the face area, and then determines the signal amplification factor of the luminance signal Y with reference to the luminance distribution in the specified face area. The brightness of the frame image I is adjusted by adjusting and amplifying the luminance signal Y.

Thereafter, the display control unit 6a acquires image data of the frame image I (for example, the frame image Ia) whose image quality has been adjusted from the first image quality adjustment unit 4c, and within the display area of the display panel 6b as a live view image. It is displayed (step S7; see FIG. 4A, etc.).
Next, the CPU of the central control unit 1 determines whether or not an instruction to end the live view display process has been input (step S8). Here, the live view display processing is, for example, instructed to take an image for recording an object based on a predetermined operation of the shutter button of the operation input unit 8 by the user, an operation of turning off the power, or playback. It ends when an operation to switch to the mode is performed.

When it is determined in step S8 that an instruction to end the live view display process has not been input (step S8; NO), the image acquisition unit 4a transfers the live view image transferred from the electronic imaging unit 3b of the imaging unit 3. Next frame image I (for example, frame image Ib etc.) concerning is acquired (step S9), and the process returns to step S3.
In the same manner as described above, the face detection unit 4b performs a predetermined face detection process on the next frame image I acquired by the image acquisition unit 4a (step S3), and the human face that is the subject is included. It is determined whether or not a face area has been detected (step S4).

On the other hand, if it is determined in step S4 that no face area has been detected (step S4; NO), the signal processing unit 4 performs non-face detection state processing (see FIG. 3) (step S10).
Hereinafter, the non-face detection state process will be described in detail with reference to FIG.

<Non-face detection state processing>
As shown in FIG. 3, the first image quality adjustment unit 4c determines whether or not the previous detection state of the human face by the face detection unit 4b is a face detection state in which the human face was detected (step). S21).

If it is determined in step S21 that the previous detection state is not the face detection state (step S21; NO), the first image quality adjustment unit 4c uses the white balance adjustment and the brightness adjustment reference of the frame image I as human standards. Other conditions other than the face are set (step S22).
Returning to FIG. 2, in step S6, the first image quality adjustment unit 4c adjusts the white balance and brightness (image quality) of the frame image I according to the set reference (step S6).
Specifically, in the white balance adjustment, the first image quality adjustment unit 4c estimates, for example, a light source (for example, a room: a white light) and corresponds to gray under the estimated light source in the frame image I. Identify the pixel. Then, the first image quality adjustment unit 4c calculates the gain amount for each color component of RGB with reference to the pixel value (for example, RGB value) of the pixel corresponding to the specified gray, and amplifies the image data. Adjust the white balance of the frame image I. In the brightness adjustment, the first image quality adjustment unit 4c, for example, specifies the luminance distribution of the entire frame image I or a predetermined photometry area, and then amplifies the luminance signal Y with reference to the specified luminance distribution. The brightness of the frame image I is adjusted by adjusting the rate and amplifying the luminance signal Y.
Each process after step S7 is the same as described above, and a detailed description thereof will be omitted.

  On the other hand, if it is determined in step S21 that the previous detection state is the face detection state (step S21; YES), the human face detection state is detected from the face detection state in which the human face was detected. The first determination unit 4d determines whether or not the content of the image quality adjustment based on the human face by the first image quality adjustment unit 4c should be maintained. (Steps S23 to S30).

Specifically, first, the first image quality adjustment unit 4c corresponds to gray under a plurality of light sources for each of the frame images before and after the human face detection state has changed (for example, the frame images Ia and Ib). The number of pixels to be calculated is calculated (step S23). Then, the first determination unit 4d determines, for each of the plurality of light sources, the total value of the amount of change (absolute value) of the number of pixels corresponding to gray before and after the detection state of the human face changes. It is determined whether it is less than (step S24).
Here, if it is determined that the total value is less than the predetermined threshold (step S24; YES), the first image quality adjustment unit 4c uses the white balance adjustment reference of the frame image I (for example, the frame image Ib) as a reference. A face area including a human face detected from the previous frame image I (for example, the frame image Ia) is set (step S25; see FIG. 4B, etc.). On the other hand, when it is determined that the total value is not less than the predetermined threshold value (step S24; NO), the first image quality adjustment unit 4c sets the reference for white balance adjustment of the frame image I (for example, the frame image Ic). Other conditions other than the human face are set (step S26; see FIG. 4C, etc.).

Subsequently, the first image quality adjustment unit 4c specifies the luminance distribution of the entire frame image I for each of the frame images before and after the human face detection state has changed (for example, the frame images Ia and Ib). A representative value of luminance is calculated (step S27). Then, the first determination unit 4d determines whether or not the amount of change in the representative value of luminance before and after the change in the human face detection state is less than a predetermined threshold (step S28).
Here, if it is determined that the amount of change is less than the predetermined threshold (step S28; YES), the first image quality adjustment unit 4c uses the brightness adjustment reference of the frame image I (for example, the frame image Ib) as a reference. A face region including a human face detected from the previous frame image I (for example, the frame image Ia) is set (step S29; see FIG. 4B, etc.). On the other hand, if it is determined that the amount of change is not less than the predetermined threshold (step S28; NO), the first image quality adjustment unit 4c uses the brightness adjustment reference of the frame image I (for example, the frame image Ic) as a reference. Other conditions other than the human face are set (step S30; see FIG. 4B, etc.).

Returning to FIG. 2, in step S6, the first image quality adjustment unit 4c adjusts the white balance and brightness (image quality) of the frame image I according to the set reference (step S6).
That is, the first image quality adjustment unit 4c performs white balance adjustment and brightness adjustment based on the previously detected human face, or performs white balance adjustment based on the previously detected human face and The brightness is adjusted based on other conditions other than, the white balance is adjusted based on other conditions other than the human face, and the brightness is adjusted based on the previously detected human face. White balance adjustment and brightness adjustment based on other conditions other than the face.
Each process after step S7 is the same as described above, and a detailed description thereof will be omitted.

  As described above, according to the imaging apparatus 100 of the first embodiment, when automatically adjusting the image quality such as the white balance and brightness of the frame image I with the human face as a reference, the human face detection state Determines whether or not to maintain the image quality adjustment contents based on the human face when the face detection state changes from the face detection state that detected the human face to the non-detection state that does not detect the human face. Therefore, if it is determined that the content of the image quality adjustment based on the human face should be maintained, the frame using the previously detected human face is used even in the non-face detection state. Image quality such as white balance and brightness of the image I can be adjusted. As a result, for example, when the human being who is the subject simply faces sideways and the face cannot be detected and the imaging environment itself has not changed, white reference is made based on other conditions other than the human face. Adjustment of image quality such as balance and brightness can be suppressed, and image quality adjustment based on the human face of the output live view image can be more stably performed.

Specifically, based on the change state of the imaging environment determined from a plurality of frame images (for example, frame images Ia, Ib, etc.) captured before and after the detection state of the human face changes, the human face It is determined whether or not the content of the image quality adjustment based on the image should be maintained. Therefore, in the non-face detection state, the image quality adjustment of the frame image I can be performed in consideration of the change in the imaging environment. it can. In other words, the image quality of the frame image I is not adjusted using only the detection result of the human face, but the change in the imaging environment is taken into consideration, so that even if it was in the non-face detection state, it was detected before The human face can be used to adjust the image quality such as white balance and brightness of the frame image I.
In addition, image feature information (under a predetermined light source) measured from a plurality of frame images I when the image quality of the frame image I is adjusted with reference to other conditions other than the human face for determining the change in the imaging environment. Changes in the number of pixels corresponding to a predetermined color, luminance distribution, etc.), and appropriately determines whether or not the content of image quality adjustment based on the human face should be maintained. be able to.

In addition, a predetermined color (for example, gray) is obtained under a plurality of light sources measured from a plurality of frame images (for example, frame images Ia, Ib, etc.) captured before and after the detection state of the human face is changed. When the total change amount of the corresponding number of pixels is less than a predetermined threshold value, it is determined that the content of white balance adjustment based on the human face should be maintained. Whether the content of white balance adjustment based on the human face should be maintained using the number of pixels corresponding to a predetermined color under a plurality of light sources as image feature information in the case of automatic adjustment This determination can be made more appropriately.
In addition, when the amount of change in luminance distribution measured from a plurality of frame images I captured before and after the detection state of the human face changes is less than a predetermined threshold, the brightness with respect to the human face is used as a reference. Therefore, when the brightness of the frame image I is automatically adjusted, the brightness based on the human face is used as the image feature information when the brightness of the frame image I is automatically adjusted. It is possible to more appropriately determine whether or not the content of the adjustment should be maintained.

  If it is determined that the content of the image quality adjustment based on the human face should not be maintained, the imaging environment has changed. Therefore, the white balance of the frame image I is determined based on other conditions other than the human face. And image quality such as brightness can be adjusted automatically.

[Embodiment 2]
Below, the imaging device 200 of Embodiment 2 is demonstrated with reference to FIGS.
The imaging apparatus 200 according to the second embodiment has substantially the same configuration as that of the imaging apparatus 100 according to the first embodiment except for the details described below, and detailed description thereof is omitted.

FIG. 5 is a block diagram illustrating a schematic configuration of the imaging apparatus 200 according to the second embodiment to which the present invention is applied.
As illustrated in FIG. 5, the signal processing unit 4 of the imaging apparatus 200 according to the present embodiment includes an image acquisition unit 4 a, a face detection unit 4 b, a second image quality adjustment unit 204 c, and a second determination unit 204 d. ing.

The second image quality adjustment unit (adjustment unit) 204c automatically adjusts the white balance of the plurality of frame images I (Ia to Ic) related to the live view image sequentially acquired by the image acquisition unit 4a. Specifically, in substantially the same manner as the first image quality adjustment unit 4c of the first embodiment, for example, in the state in which the auto white balance (AWB) mode for automatically adjusting the white balance is set at the time of imaging. The second image quality adjustment unit 204c automatically adjusts the white balance of the frame image I based on the human face detected by the face detection unit 4b and other conditions other than the human face.
Note that the second image quality adjustment unit 204c may automatically adjust the brightness of the plurality of frame images I (Ia to Ic) in substantially the same manner as the first image quality adjustment unit 4c of the first embodiment.

The second determination unit (determination unit) 204d determines whether or not the content of white balance adjustment based on the human face by the second image quality adjustment unit 204c should be maintained.
That is, the second determination unit 204d detects the human face detection state detected by the face detection unit 4b from the face detection state in which the human face was detected, in substantially the same manner as the first determination unit 4d of the first embodiment. When it is changed to a non-face detection state that is not performed, it is determined whether or not the content of white balance adjustment based on the human face should be maintained.

Specifically, the second determination unit 204d detects a change in the light source estimated from the frame images before and after the human face detection state is changed by the second image quality adjustment unit 204c (for example, the frame images Ia and Ib). Use. That is, for example, the second image quality adjustment unit 204c estimates a light source (for example, a room: a white light, etc.) based on the image data for each of the frame images I before and after the human face detection state has changed.
Then, the second determination unit 204d compares the estimated light sources of the previous and next frame images I to determine whether the light source has changed.
Here, if it is determined that the light source has not changed, it is considered that the imaging environment has not changed (see FIG. 4A and FIG. 4B), and the second determination unit 204d detects the human face. It is determined that the content of the white balance adjustment based on the human face should be maintained even for the frame image Ib in the non-face detection state in which no is detected. Then, the second image quality adjustment unit 204c performs the frame image Ic on the basis of the face area including the previously detected human face with respect to the frame image Ib in the non-face detection state in which no human face is detected. Automatically adjusts the white balance.
On the other hand, if it is determined that the light source has changed, it is considered that the imaging environment has changed (see FIGS. 4A and 4C), and the second determination unit 204d performs white based on the human face. It is determined that the balance adjustment content should not be maintained. Then, the second image quality adjustment unit 204c applies the white balance of the frame image Ic to the non-face-detected frame image Ic in which no human face is detected based on other conditions other than the human face. Adjust automatically.

  The other configurations of the signal processing unit 4, that is, the image acquisition unit 4a and the face detection unit 4b are substantially the same in configuration and function as those in the first embodiment, and thus detailed description thereof is omitted.

<Live view display processing>
Next, live view display processing by the imaging apparatus 200 will be described with reference to FIGS. 6 and 7.
FIG. 6 is a flowchart illustrating an example of an operation related to the live view display process. FIG. 7 is a flowchart illustrating an example of an operation related to the non-face detection state process in the live view display process.

The live view display process performed by the imaging apparatus 200 according to the second embodiment is substantially the same as the live view display process performed by the imaging apparatus 100 according to the first embodiment described above, except for the details described below. Description is omitted.
In the live view display process described below, it is assumed that the auto white balance (AWB) mode for automatically adjusting the white balance is set.

As shown in FIG. 6, when the imaging of the subject by the imaging unit 3 is started (step S201), the image acquisition unit 4a of the signal processing unit 4 performs the live view sequentially transferred from the electronic imaging unit 3b of the imaging unit 3. The frame images I (Ia to Ic) relating to the images are sequentially acquired (step S202).
Subsequently, the face detection unit 4b performs a predetermined face detection process on the frame image I (for example, the frame image Ia) acquired by the image acquisition unit 4a (step S203), and the human face that is the subject is detected. It is determined whether an included face area has been detected (step S204).

If it is determined in step S204 that a face area has been detected (step S204; YES), the second image quality adjustment unit 204c is detected with a white balance adjustment reference for the frame image I acquired by the image acquisition unit 4a. A face area including a human face is set (step S205). Then, the second image quality adjustment unit 204c adjusts the white balance of the frame image I according to the set standard (step S206). Specifically, the second image quality adjustment unit 204c estimates, for example, a light source (for example, a room: a white light) and the like in the face area, in substantially the same manner as the first image quality adjustment unit 4c of the first embodiment. The pixel corresponding to the skin color is specified under the light source. Then, the second image quality adjustment unit 204c calculates the gain amount for each color component of RGB with reference to the pixel value (for example, RGB value) of the pixel corresponding to the specified skin color, and amplifies the image data. Adjust the white balance of the frame image I.
At this time, for example, after specifying the luminance distribution in the face area, the second image quality adjustment unit 204c adjusts the signal amplification factor of the luminance signal Y with reference to the luminance distribution in the specified face area, The brightness of the frame image I may be adjusted by amplifying the signal Y.

After that, the display control unit 6a acquires the image data of the frame image I (for example, the frame image Ia) whose white balance has been adjusted from the second image quality adjustment unit 204c, and within the display area of the display panel 6b as a live view image. (Step S207; see FIG. 4A, etc.).
Next, the CPU of the central control unit 1 determines whether or not an instruction to end the live view display process has been input, similarly to step S8 in the live view display process of the first embodiment (step S208).

If it is determined in step S208 that an instruction to end the live view display process has not been input (step S208; NO), the image acquisition unit 4a transfers the live view image transferred from the electronic imaging unit 3b of the imaging unit 3. Next frame image I (for example, frame image Ib etc.) concerning is acquired (step S209), and the process returns to step S203.
Similarly to the above, the face detection unit 4b performs a predetermined face detection process on the next frame image I acquired by the image acquisition unit 4a (step S203), and includes the human face that is the subject. It is determined whether or not a face area has been detected (step S204).

On the other hand, if it is determined in step S204 that no face area has been detected (step S4; NO), the signal processing unit 4 performs non-face detection state processing (see FIG. 7) (step S210).
Hereinafter, the non-face detection state process will be described in detail with reference to FIG.

<Non-face detection state processing>
As shown in FIG. 7, the second image quality adjustment unit 204c determines whether or not the previous detection state of the human face by the face detection unit 4b is the face detection state in which the human face was detected (step). S221).

If it is determined in step S221 that the previous detection state is not the face detection state (step S221; NO), the second image quality adjustment unit 204c sets the reference for white balance adjustment of the frame image I to other than the human face. (Step S222).
Returning to FIG. 6, in step S206, the second image quality adjustment unit 204c adjusts the white balance of the frame image I according to the set reference (step S206). Specifically, the second image quality adjustment unit 204c estimates, for example, a light source (for example, a room: white light, etc.) in the frame image I in substantially the same manner as the first image quality adjustment unit 4c of the first embodiment. A pixel corresponding to gray under the estimated light source is identified. Then, the second image quality adjustment unit 204c calculates the gain amount for each color component of RGB with reference to the pixel value (for example, RGB value) of the pixel corresponding to the specified gray, and amplifies the image data. Adjust the white balance of the frame image I.
At this time, for example, after specifying the luminance distribution of the entire frame image I or a predetermined photometric area, the second image quality adjustment unit 204c adjusts the signal amplification factor of the luminance signal Y with reference to the specified luminance distribution. The brightness of the frame image I (Ia to Ic) may be adjusted by amplifying the luminance signal Y.
Each processing after step S207 is the same as described above, and detailed description thereof is omitted.

  On the other hand, if it is determined in step S221 that the previous detection state is the face detection state (step S221; YES), the human face detection state is detected from the face detection state in which the human face was detected. The second determination unit 204d determines whether or not the content of white balance adjustment based on the human face by the second image quality adjustment unit 204c should be maintained. Determination is made (steps S223 to S226).

Specifically, first, the second image quality adjustment unit 204c determines the light source (for example, the frame image Ia, Ib, etc.) before and after the human face detection state has changed based on the image data. , Indoor: white light, etc.) is estimated (step S223). Then, the second determination unit 204d determines whether or not the light source has changed in the frame images I before and after the human face detection state has changed (step S224).
Here, if it is determined that the light source has not changed (step S224; NO), the second image quality adjustment unit 204c sets the reference for white balance adjustment of the frame image I (for example, the frame image Ib) as the previous frame. A face area including a human face detected from the image I (for example, the frame image Ia) is set (step S225; see FIG. 4B, etc.). On the other hand, if it is determined that the light source has changed (step S224; YES), the second image quality adjustment unit 204c sets the reference for white balance adjustment of the frame image I (for example, the frame image Ic) other than the human face. The other conditions are set (step S226; see FIG. 4C, etc.).

Returning to FIG. 6, in step S206, the second image quality adjustment unit 204c adjusts the white balance of the frame image I according to the set reference (step S206).
That is, the second image quality adjustment unit 204c performs white balance adjustment based on the previously detected human face, or performs white balance adjustment based on other conditions other than the human face.
At this time, the second image quality adjustment unit 204c may adjust the brightness of the frame image I based on other conditions other than the human face, for example.
Each processing after step S207 is the same as described above, and detailed description thereof is omitted.

As described above, according to the imaging apparatus 200 of the second embodiment, it is determined that the content of white balance adjustment based on the human face should be maintained, as in the imaging apparatus 100 of the first embodiment. In this case, the white balance of the frame image I can be adjusted using the previously detected human face even in the non-face detection state, and the human face in the output live view image can be adjusted. The white balance adjustment based on can be performed more stably.
In particular, white based on a human face based on a change in a light source estimated from a plurality of frame images (for example, frame images Ia, Ib, etc.) taken before and after the detection state of the human face is changed. Since it is determined whether or not the content of the balance adjustment should be maintained, the change in the light source estimated from the plurality of frame images I can be used to determine the change in the imaging environment. Specifically, since it is determined that the content of the white balance adjustment based on the human face should be maintained until the light source estimated from the plurality of frame images I changes, the white balance of the frame image I is determined. When automatically adjusting the image, use the change in the light source as the image feature information, and more appropriately determine whether or not the content of white balance adjustment based on the human face should be maintained Can do.

In the second embodiment, in the determination of whether or not the content of white balance adjustment based on the human face should be maintained, the detection state of the human face is the same as in the first embodiment. The amount of change in the number of pixels corresponding to a predetermined color under a predetermined light source measured from frame images before and after the change of (for example, frame images Ia, Ib, etc.) may be used together.
That is, for the frame images before and after the human face detection state has changed (for example, the frame images Ia, Ib, etc.), the determination result of whether the estimated light source has changed, and the gray in each of the plurality of light sources Whether or not the imaging environment has changed based on the determination result of whether or not the total value of the amount of change in the number of pixels corresponding to is less than a predetermined threshold (the content of white balance adjustment based on the human face) Whether or not it should be maintained).
At this time, it may be possible to set one of the two determination methods described above that should be prioritized. In addition, for example, when one of the two determination methods described above (for example, the determination method of the first embodiment) specifies that the imaging environment has not changed, the human face is used as a reference. By maintaining the content of white balance adjustment, the human face can be used for white balance adjustment with higher priority. Also, white balance adjustment is performed by maintaining the content of white balance adjustment based on the human face only when it is determined that the imaging environment has not changed by both of the above two determination methods. Accuracy can be further improved.
In this way, by using the two determination methods described above, it is possible to set a plurality of determination levels as to whether or not the content of white balance adjustment based on the human face should be maintained. Usability can be further improved.

The present invention is not limited to the first and second embodiments, and various improvements and design changes may be made without departing from the spirit of the present invention.
For example, frame images before and after the change of the human face detection state (for example, frame images Ia, Ib, etc.) are used to determine whether or not the content of white balance adjustment based on the human face should be maintained. When using the amount of change in the number of pixels corresponding to a predetermined color under a predetermined light source measured from the total of the amount of change in the number of pixels corresponding to gray in each of the plurality of light sources is less than a predetermined threshold However, this is only an example, and the present invention is not limited to this, and can be arbitrarily changed as appropriate.
That is, for example, for each of a plurality of colors with a single light source, the amount of change in the number of pixels before and after the human face detection state changes is calculated, and the amount of change in the number of pixels (absolute value) for the calculated plurality of colors ) May be summed, and it may be determined whether the sum is less than a predetermined threshold.

  Further, in determining whether or not the content of white balance adjustment based on the human face should be maintained, frame images before and after the detection state of the human face is changed (for example, frame images Ia and Ib). For example, a change rate of the number of pixels corresponding to a predetermined color under a predetermined light source may be used instead of the change amount of the number of pixels corresponding to a predetermined color under a predetermined light source.

  In addition, the configurations of the imaging devices 100 and 200 illustrated in the first and second embodiments are examples, and are not limited thereto. Furthermore, although the imaging devices 100 and 200 have been illustrated as output control devices, the present invention is not limited to this, and whether or not an imaging function is provided can be arbitrarily changed as appropriate.

In addition, in the first and second embodiments, the functions as the detection unit, the adjustment unit, the control unit, and the determination unit are controlled under the control of the central control unit 1, and the face detection unit 4b and the first image quality adjustment unit. 4c (second image quality adjustment unit 204c), first determination unit 4d (second determination unit 204d), and display control unit 6a are configured to be driven. However, the present invention is not limited to this, and the central control is performed. The configuration may be realized by executing a predetermined program or the like by the unit 1.
That is, a program including a detection processing routine, an adjustment processing routine, a control processing routine, and a determination processing routine is recorded in a program memory (not shown). Then, the CPU of the central control unit 1 may function as means for detecting a human face from the frame images I sequentially captured by the imaging unit 3 by the detection processing routine. Further, the CPU of the central control unit 1 may function as a means for automatically adjusting the image quality of the frame image I with the detected human face as a reference by an adjustment processing routine. Further, the CPU of the central control unit 1 may function as a means for outputting an image whose image quality is adjusted by a control processing routine. Further, when the CPU of the central control unit 1 is changed from the state in which the human face is detected to the state in which the human face is not detected by the determination processing routine, the human face is used as a reference. You may make it function as a means to determine whether the content of image quality adjustment should be maintained.

  Furthermore, as a computer-readable medium storing a program for executing each of the above processes, a non-volatile memory such as a flash memory or a portable recording medium such as a CD-ROM is applied in addition to a ROM or a hard disk. Is also possible. A carrier wave is also used as a medium for providing program data via a predetermined communication line.

Although several embodiments of the present invention have been described, the scope of the present invention is not limited to the above-described embodiments, but includes the scope of the invention described in the claims and equivalents thereof.
The invention described in the scope of claims attached to the application of this application will be added below. The item numbers of the claims described in the appendix are as set forth in the claims attached to the application of this application.
[Appendix]
<Claim 1>
Detecting means for detecting a human face from captured images sequentially imaged by the imaging means;
An adjustment unit that automatically adjusts the image quality of the captured image based on the human face detected by the detection unit;
Control means for outputting an image whose image quality has been adjusted by the adjusting means;
When the detection state of the human face by the detection unit changes from a state in which the human face is detected to a state in which the human face is not detected, the content of image quality adjustment based on the human face by the adjustment unit is Determining means for determining whether or not to maintain;
An output control device comprising:
<Claim 2>
The determining means is based on a change state of an imaging environment determined from a plurality of captured images respectively captured by the imaging means before and after the detection state of the human face by the detecting means is changed, and the adjusting means by the adjusting means. 2. The output control apparatus according to claim 1, wherein it is determined whether or not the content of image quality adjustment based on a human face should be maintained.
<Claim 3>
The determination unit is based on a change in image feature information measured from the plurality of captured images when the adjustment unit adjusts the image quality of the captured image based on other conditions other than the human face. The output control apparatus according to claim 2, wherein it is determined whether or not the content of the image quality adjustment based on the human face by the adjustment unit should be maintained.
<Claim 4>
The adjusting means automatically adjusts the white balance of the captured image,
The determination unit is based on the human face by the adjustment unit based on a change amount of the number of pixels corresponding to a predetermined color under a predetermined light source measured from the plurality of captured images by the adjustment unit. 4. The output control apparatus according to claim 3, wherein it is determined whether or not the content of white balance adjustment should be maintained.
<Claim 5>
The determination unit is configured to adjust the adjustment unit when a total value of changes in the number of pixels corresponding to a predetermined color under a plurality of light sources measured from the plurality of captured images by the adjustment unit is less than a predetermined threshold. The output control apparatus according to claim 4, wherein it is determined that the content of white balance adjustment based on the human face according to the above should be maintained.
<Claim 6>
The adjusting means automatically adjusts the brightness of the captured image,
The determination unit is configured to adjust brightness based on the human face by the adjustment unit when a change amount of a luminance distribution measured from the plurality of captured images by the adjustment unit is less than a predetermined threshold. 4. The output control apparatus according to claim 3, wherein it is determined that the content should be maintained.
<Claim 7>
The adjusting means automatically adjusts the white balance of the captured image,
Whether the determination unit should maintain the content of white balance adjustment based on the human face by the adjustment unit based on a change in light source estimated from the plurality of captured images by the adjustment unit. The output control apparatus according to claim 3, wherein the output control apparatus determines whether or not.
<Claim 8>
The determination unit determines that the content of white balance adjustment based on the human face by the adjustment unit should be maintained until the light source estimated from the plurality of captured images is changed by the adjustment unit. The output control device according to claim 7, wherein:
<Claim 9>
The determination unit is further configured to reference the human face by the adjustment unit based on an amount of change in the number of pixels corresponding to a predetermined color under a predetermined light source measured from the plurality of captured images by the adjustment unit. The output control apparatus according to claim 7, wherein it is determined whether or not the content of white balance adjustment to be maintained should be maintained.
<Claim 10>
When the determination unit determines that the content of the image quality adjustment based on the human face should not be maintained by the determination unit, the image quality of the captured image is based on other conditions other than the human face. The output control device according to claim 1, wherein the output control device is automatically adjusted.
<Claim 11>
An output control method using an output control device,
Processing for detecting a human face from captured images sequentially captured by the imaging means;
A process of automatically adjusting the image quality of the captured image based on the detected human face;
Processing to output an image with adjusted image quality;
Whether or not the content of the image quality adjustment based on the human face should be maintained when the detection state of the human face changes from a state where the human face is detected to a state where the human face is not detected A process of determining
The output control method characterized by including.
<Claim 12>
In the computer of the output control device,
A function of detecting a human face from captured images sequentially captured by the imaging means;
A function of automatically adjusting the image quality of the captured image based on the detected human face;
A function to output an image with adjusted image quality,
Whether or not the content of the image quality adjustment based on the human face should be maintained when the detection state of the human face changes from a state where the human face is detected to a state where the human face is not detected A function for determining
A program characterized by realizing.

100, 200 Imaging device 1 Central control unit 2 Memory 3 Imaging unit 4 Signal processing unit 4a Image acquisition unit 4b Face detection unit 4c First image quality adjustment unit 4d First determination unit 204c Second image quality adjustment unit 204d Second determination unit 6 Display Part 6a Display control part 6b Display panel

Claims (12)

Detecting means for detecting a human face from captured images sequentially imaged by the imaging means;
An adjustment unit that automatically adjusts the image quality of the captured image based on the human face detected by the detection unit;
Control means for outputting an image whose image quality has been adjusted by the adjusting means;
When the detection state of the human face by the detection unit changes from a state in which the human face is detected to a state in which the human face is not detected, the content of image quality adjustment based on the human face by the adjustment unit is Determining means for determining whether or not to maintain;
An output control device comprising:   The determining means is based on a change state of an imaging environment determined from a plurality of captured images respectively captured by the imaging means before and after the detection state of the human face by the detecting means is changed, and the adjusting means by the adjusting means. 2. The output control apparatus according to claim 1, wherein it is determined whether or not the content of image quality adjustment based on a human face should be maintained.   The determination unit is based on a change in image feature information measured from the plurality of captured images when the adjustment unit adjusts the image quality of the captured image based on other conditions other than the human face. The output control apparatus according to claim 2, wherein it is determined whether or not the content of the image quality adjustment based on the human face by the adjustment unit should be maintained. The adjusting means automatically adjusts the white balance of the captured image,
The determination unit is based on the human face by the adjustment unit based on a change amount of the number of pixels corresponding to a predetermined color under a predetermined light source measured from the plurality of captured images by the adjustment unit. 4. The output control apparatus according to claim 3, wherein it is determined whether or not the content of white balance adjustment should be maintained.   The determination unit is configured to adjust the adjustment unit when a total value of changes in the number of pixels corresponding to a predetermined color under a plurality of light sources measured from the plurality of captured images by the adjustment unit is less than a predetermined threshold. The output control apparatus according to claim 4, wherein it is determined that the content of white balance adjustment based on the human face according to the above should be maintained. The adjusting means automatically adjusts the brightness of the captured image,
The determination unit is configured to adjust brightness based on the human face by the adjustment unit when a change amount of a luminance distribution measured from the plurality of captured images by the adjustment unit is less than a predetermined threshold. 4. The output control apparatus according to claim 3, wherein it is determined that the content should be maintained. The adjusting means automatically adjusts the white balance of the captured image,
Whether the determination unit should maintain the content of white balance adjustment based on the human face by the adjustment unit based on a change in light source estimated from the plurality of captured images by the adjustment unit. The output control apparatus according to claim 3, wherein the output control apparatus determines whether or not.   The determination unit determines that the content of white balance adjustment based on the human face by the adjustment unit should be maintained until the light source estimated from the plurality of captured images is changed by the adjustment unit. The output control device according to claim 7, wherein:   The determination unit is further configured to reference the human face by the adjustment unit based on an amount of change in the number of pixels corresponding to a predetermined color under a predetermined light source measured from the plurality of captured images by the adjustment unit. The output control apparatus according to claim 7, wherein it is determined whether or not the content of white balance adjustment to be maintained should be maintained.   When the determination unit determines that the content of the image quality adjustment based on the human face should not be maintained by the determination unit, the image quality of the captured image is based on other conditions other than the human face. The output control device according to claim 1, wherein the output control device is automatically adjusted. An output control method using an output control device,
Processing for detecting a human face from captured images sequentially captured by the imaging means;
A process of automatically adjusting the image quality of the captured image based on the detected human face;
Processing to output an image with adjusted image quality;
Whether or not the content of the image quality adjustment based on the human face should be maintained when the detection state of the human face changes from a state where the human face is detected to a state where the human face is not detected A process of determining
The output control method characterized by including. In the computer of the output control device,
A function of detecting a human face from captured images sequentially captured by the imaging means;
A function of automatically adjusting the image quality of the captured image based on the detected human face;
A function to output an image with adjusted image quality,
Whether or not the content of the image quality adjustment based on the human face should be maintained when the detection state of the human face changes from a state where the human face is detected to a state where the human face is not detected A function for determining
A program characterized by realizing.