JP5360191B2 - Imaging device - Google Patents

Description

  The present invention relates to an imaging apparatus.

  Analyzing the captured image data to detect areas with flesh-colored hues and obtaining the focal length of the imaging optical system to predict the maximum size of the face that will actually be photographed. There is known a face area detection method in which a large area is excluded and a face area is detected. For example, there are the following as prior art documents.

JP 2004-185555 A

  However, in the conventional face area detection method described above, the face size cannot be correctly predicted unless the focus of the photographing optical system matches the face of the person, and the face area cannot be accurately detected. There's a problem.

(1) An imaging apparatus according to a first aspect of the present invention includes an imaging unit that captures an image by an imaging optical system, a focus detection unit that detects a focus adjustment state of the imaging optical system, and an in-focus state by the focus detection unit. anda row cormorant image processing section the image processing of the captured image and determining in-focus determination section, by the imaging unit whether regarded as the image processing unit, focusing by the focusing determination unit when it is determined not regarded as performs determination processing of the photographic scene, said when it is determined that can be regarded as a focus by the focus determining unit, characterized in that intends line detection process of the face.
(2) An image pickup apparatus according to a second aspect of the invention includes an image pickup unit that picks up an image by an image forming optical system, a focus detection unit that detects a focus adjustment state of the image forming optical system, and an in-focus state by the focus detection unit. and determining focus determination section whether regarded as comprising a row cormorant image processing section the image processing of the image captured by the imaging unit, and a control unit for controlling the focusing state, wherein the image processing Department performs detection processing of the background when it is determined not to be regarded as focused by the focusing determination unit, have rows detection process of the face when it is determined that can be regarded as a focus by the focusing determination unit, When the focus determination unit determines that the focus cannot be regarded as in-focus, the control unit controls a focus adjustment state using a focus detection area corresponding to a region other than the background, and the focus determination unit When it is determined that the focus can be considered, the area of the face And performing control of the focus adjustment state using focus detection area for response.
(3) An image pickup apparatus according to a third aspect of the present invention is focused by an image pickup unit that picks up an image by an image forming optical system, a focus detection unit that detects a focus adjustment state of the image forming optical system, and the focus detection unit. and determining focus determination section whether regarded as the includes a row cormorant image processing section the image processing of the image captured by the imaging unit, and a control unit for controlling the exposure, the image processing unit performs detection processing of the background when it is determined not to be regarded as focused by the focusing determination unit, have rows detection process of the face when it is determined that can be regarded as a focus by the focusing determination unit, the control When the focus determination unit determines that the focus cannot be considered, the unit performs exposure control using a focus detection area corresponding to a region other than the background, and the focus determination unit Focus detection corresponding to the face area when it is determined that And performing exposure control with the rear.
(4) An imaging apparatus according to a fourth aspect of the present invention is the imaging apparatus according to the first aspect, wherein the focus corresponding to the face region is determined when the focus determination unit determines that the focus can be considered. It has a control part which controls a focus adjustment state using a detection area, It is characterized by the above-mentioned.
(5) The imaging device according to the invention of claim 5 is the imaging device according to claim 1, wherein the focus corresponding to the face region when the focus determination unit determines that the focus can be considered. It has a control part which controls exposure using a detection area .
(6) An imaging apparatus according to a sixth aspect of the present invention is the imaging apparatus according to the fifth aspect, wherein the focal point corresponding to the face region is determined when the in-focus determining unit determines that the in-focus state can be considered. It has a control part which controls a focus adjustment state using a detection area, It is characterized by the above-mentioned.

According to the present invention, it is possible to accurately detect a human face area from a captured image.

The figure which shows the structure of the imaging device of one embodiment The figure which shows the detailed structure of the body drive control apparatus of one embodiment. The figure which shows the example of a to-be-photographed object of a subject by a 2nd image sensor. The figure which shows the detailed structure of a 2nd image pick-up element. The figure which shows the extraction result of the background area | region of one Embodiment The figure which shows the extraction result of the face area | region of one Embodiment The flowchart which shows the imaging operation of one embodiment Flowchart showing the shooting operation of the modification

  The focus adjustment state of the photographic lens (in this embodiment, the defocus amount) is detected in a plurality of focus detection areas set in the photographic screen, and the photographic lens is focused based on the defocus amount in one of the areas. The automatic focus adjustment (AF) function to be driven and the image of the subject to be tracked in the photographed image are stored as a template image (reference image). An imaging device (single-lens reflex digital still camera) that has an image tracking function that tracks a subject to be tracked while searching for a position (template matching) and tracks the target while driving a photographing lens with an AF function and an image tracking function An embodiment will be described.

  FIG. 1 shows a configuration of an imaging apparatus (single-lens reflex digital still camera) 1 according to an embodiment. In FIG. 1, illustration and description of camera devices and circuits not directly related to the present invention are omitted. In a camera 1 according to an embodiment, an interchangeable lens 3 is attached to a camera body 2 in a replaceable manner. The camera body 2 is provided with a first image sensor 4 for capturing a subject image and recording the image. The first image sensor 4 can be constituted by a CCD, a CMOS, or the like. At the time of photographing, the quick return mirror 5 and the sub mirror 6 are retracted to a position outside the photographing optical path indicated by a solid line, the shutter 7 is opened, and a subject image is formed on the light receiving surface of the first image sensor 4 by the photographing lens 8.

  At the bottom of the camera body 2, a focus detection optical system 9 and a distance measuring element 10 for detecting the focus adjustment state of the photographing lens 8 are provided. In this embodiment, an example in which a focus detection method based on a pupil division phase difference detection method is adopted is shown. The focus detection optical system 9 guides the pair of focus detection light fluxes that have passed through the photographing lens 8 to the light receiving surface of the distance measuring element 10 and forms a pair of optical images. The distance measuring element 10 includes, for example, a pair of CCD line sensors, and outputs a focus detection signal corresponding to the pair of optical images. Before shooting, the quick return mirror 5 and the sub mirror 6 are set at positions in the shooting optical path as indicated by broken lines, and the pair of focus detection light beams from the shooting lens 8 are transmitted through the half mirror portion of the quick return mirror 5. Then, the light is reflected by the sub mirror 6 and guided to the focus detection optical system 9 and the distance measuring element 10.

  A finder optical system is provided on the upper part of the camera body 2. Before shooting, the quick return mirror 5 and the sub mirror 6 are in positions indicated by broken lines, and subject light from the shooting lens 8 is reflected by the quick return mirror 5 and guided to the finder screen 11, and a subject image is displayed on the finder screen 11. Form an image. The organic EL display element 12 superimposes and displays information such as a focus detection area mark on the subject image formed on the finder screen 11 and displays various shooting information such as an exposure value at a position outside the subject image. The subject image on the finder screen 11 is guided to the finder eyepiece window 15 via the penta roof prism 13 and the eyepiece lens 14 so that the photographer can visually recognize the subject image.

  The finder optical system at the top of the camera body 2 is provided with a second image sensor 16 that captures a subject image for subject tracking and photometry. Details of the second image sensor 16 will be described later. The subject image formed on the finder screen 11 is re-imaged on the light receiving surface of the second image sensor 16 via the penta roof prism 13, the prism 17 and the imaging lens 18. The second image sensor 16 outputs an image signal corresponding to the subject image. The subject image formed on the finder screen 11 before photographing is guided to the second image sensor 16 via the penta roof prism 13, the prism 17 and the imaging lens 18, and the subject image is formed on the light receiving surface of the second image sensor 16. Is re-imaged. As will be described in detail later, tracking control and exposure calculation are performed based on the subject image captured by the second image sensor 16.

  The camera body 2 is also provided with a body drive control device 19 and an operation member 20. The body drive control device 19 is constituted by peripheral components such as a microcomputer, a memory, and an A / D converter, the details of which will be described later, and performs various controls and calculations of the camera 1. The operation member 20 includes a switch and a selector for operating the camera 1 such as a shutter button, a focus detection area selection switch, and a shooting mode selection switch.

  The interchangeable lens 3 is provided with a zooming lens 8a, a focusing lens 8b, a diaphragm 21, a lens drive control device 22, and the like. In this embodiment, the photographic lens 8 is represented by a zoom lens 8a, a focusing lens 8b, and a diaphragm 21, but the configuration of the photographic lens 8 is not limited to the configuration shown in FIG. The lens drive control device 22 includes a microcomputer (not shown) and peripheral components such as a memory, a drive circuit, and an actuator, and performs drive control of the lenses 8a and 8b and the diaphragm 21 and detection of their positions. Information such as a focal length and an open aperture value of the interchangeable lens 3 is stored in a memory built in the lens drive control device 22.

  The body drive control device 19 and the lens drive control device 22 communicate via the contact 23 of the lens mount, and transmit information such as a lens drive amount and an aperture value from the body drive control device 19 to the lens drive control device 22. Lens information and aperture information are transmitted from the lens drive control device 22 to the body drive control device 19.

  FIG. 2 shows a detailed configuration of the body drive control device 19. Note that illustration and description of control functions not directly related to the present invention are omitted. The body drive control device 19 includes an element control circuit 19a, an A / D converter 19b, a microcomputer 19c, a memory 19d, and the like. The element control circuit 19 a controls charge accumulation and reading of the second image sensor 16. The A / D converter 19b converts the analog image signal output from the second image sensor 16 into a digital image signal. The microcomputer 19c constitutes a background area / face area extraction unit 19e, an exposure control unit 19f, a focus detection calculation unit 19g, and a lens drive amount calculation unit 19h according to a software form. The memory 19d stores information such as a template image for image tracking and a defocus amount, or lens information such as a focal length, an open F value, an aperture value, and a conversion coefficient from an image shift amount to a defocus amount. To do.

  The background area / face area extraction unit 19 e extracts a background area or a face area from the subject image captured by the second image sensor 16. Details of the background area and face area extraction processing will be described later. The exposure calculation unit 19f calculates an exposure value (shutter speed and aperture value) based on the image signal captured by the second image sensor 16.

  The focus detection calculation unit 19g detects the focus adjustment state of the photographing lens 8, here the defocus amount, based on the focus detection signal corresponding to the pair of optical images output from the distance measuring element 10. Although details will be described later, a plurality of focus detection areas are set in the shooting screen of the shooting lens 8, and the distance measuring element 10 outputs a focus detection signal corresponding to a pair of optical images for each focus detection area. Then, the focus detection calculation unit 19g detects the defocus amount based on the focus detection signal corresponding to the pair of optical images for each focus detection area. The lens driving amount calculation unit 19h converts the detected defocus amount into a lens driving amount.

  FIG. 3 shows an example of imaging of a subject by the second image sensor 16. The second imaging element 16 includes a plurality of pixels 26 (photoelectric conversion elements; 22 horizontal elements × 15 vertical elements = 330 pixels in this example) arranged in a matrix. In this embodiment, the coordinate of the pixel 26 in the horizontal direction of the second image sensor 16 is represented by i (= 1 to 22), and the coordinate of the pixel 26 in the vertical direction is represented by j (= 1 to 15). The coordinate of the pixel 26 at the upper left corner is defined as the origin (1, 1).

  As shown in FIG. 4, each pixel 26 is divided into three portions 26a, 26b, and 26c, and primary color filters of red R, green G, and blue B are provided in these portions 26a, 26b, and 26c, respectively. . Thereby, the RGB signal of the subject image can be output for each pixel 26. When a subject as shown in FIG. 3A is imaged by the second image sensor 16, an image signal as shown in FIG. 3B is output from each pixel 26 of the second image sensor 16.

  In this embodiment, basically, a face area is extracted from a photographed image, and the focus of the person's face is correctly focused, and exposure control is performed so that the face of the person has appropriate brightness. . However, as described above, if the photographing lens 8 is not in focus with the face of the person, the face size cannot be correctly predicted, and the face area cannot be accurately extracted.

  Therefore, in this embodiment, when the photographing lens 8 is out of focus, face area extraction processing is not performed, but background region extraction processing is performed instead. Then, it is determined that the portion other than the extracted background region is the main subject region, and the main subject portion is correctly focused, and exposure control is performed so that the main subject portion has appropriate brightness.

Here, a background area extraction method and a face area extraction method executed by the body drive control device 19 will be described. First, in the extraction of the background region, the hue Hue [i, j] is calculated for the image signals of all the pixels 26 of the second image sensor 16, and the following conditional expressions (1) and (2) are used. To determine the subject area.
ABS (Hue [i, j] −Hue [i, 1]) <ThHue (1),
M1 [i, j-1] ≠ 0 (2)
In the conditional expression (1), ABS () is a function that returns the absolute value of the input hue difference, and ThHue is a determination threshold value determined by experiments or the like. M1 [i, satisfying j ≠ 1
The initial value of j] is 0, and the initial value of M1 [i, 1] is 1.

Since the area of the coordinates [i, 1] in the top row of the image is highly likely to be the background, the hue of this area is set as the reference hue of the background, and the reference hue of this background area and other adjacent to the background area The hue of the area is sequentially compared. If the difference between the reference hue of the background area and the hue of another area adjacent to the background area is smaller than the determination threshold ThHue, the other area adjacent to the background area is set as the background area, and M1 [i, j ] Is 1. It should be noted that the background region extraction calculation according to the conditional expressions (1) and (2) is executed in order from the smallest j to the largest in each column. By this background region extraction calculation, the pixel 26 in which M1 [i, j] is 1 is the region extracted as the background.

  When the subject as shown in FIG. 3A is imaged by the second image sensor 16, an image signal as shown in FIG. 3B is output from each pixel 26 of the second image sensor 16, and these When the background region extraction calculation described above is performed based on the image signal, a background region extraction result as shown in FIG. 5 is obtained. In FIG. 5, the area of the pixel 26 indicated by hatching is the extracted background area.

Next, a method for extracting a face area will be described. The hue Hue [i, j] is calculated for the image signals of all the pixels 26 of the second image sensor 16, and the pixels 26 that satisfy the following conditional expression (3) are extracted as face candidate regions.
HueLoConst <Hue [i, j] <HueHiConst (3)
In conditional expression (3), HueLoConst and HueHiConst are the lower and upper limits of the hue of human skin, for example, 0 ° and 30 °.

When the subject as shown in FIG. 3A is imaged by the second image sensor 16, an image signal as shown in FIG. 3B is output from each pixel 26 of the second image sensor 16, and these When the above-described face candidate region extraction calculation is performed based on the image signal, a face candidate region extraction result as shown in FIG. 6A is obtained. In FIG. 6A, the area of the pixel 26 indicated by hatching is the extracted face candidate area.

Further, the number of pixels FaceWidth (estimated face pixel number) of the second image sensor 16 corresponding to the face width of the person.
Is calculated by the following equation (4).
FaceWidth = FwTyp · f / (Distance · SensorPitch) (4)
In Formula (4), FwTyp is a constant (for example, 160 mm) for setting the estimated length of the person's face, and Distance is the photographing lens 8 acquired from the lens drive control device 22.
The imaging distance, SensorPitch is the pitch of the pixels 26 of the second image sensor 16. In this embodiment, the image magnification is not changed in the optical path from the quick return mirror 5 to the imaging lens 18.

The estimated face pixel number FaceWidth (pixel unit) calculated by the expression (4) is compared with the face candidate area (pixel unit) calculated by the conditional expression (3). It is determined as an area. Now, assuming that the estimated face pixel number FaceWidth calculated by the equation (4) is 5 pixels, the right side in the figure in which the estimated face pixel number FaceWidth is not 5 pixels among the two face candidate regions shown in FIG. This 2 × 3 pixel area is determined not to be a face even if the hue is similar to human skin. On the other hand, the 5 × 5 pixel area on the left side in the figure has a hue similar to that of human skin, and the estimated face pixel count FaceWidth is equal to the face candidate area pixel count, that is, the width of the face candidate area And the estimated face width are equal to each other. FIG. 6B shows a face area as a result of extraction.

  FIG. 7 is a flowchart showing the shooting operation of the embodiment. The operation of the embodiment will be described with reference to FIG. When the half-pressing operation of the shutter button is detected by the release half-pressing switch of the operation member 20, the body drive control device 19 starts this photographing operation. In step 1, an image is picked up by the second image sensor 16, and the image signal of each pixel 26 is stored in the memory 19d. In the subsequent step 2, the defocus amount of the taking lens 8 is detected based on the focus detection signal output from the distance measuring element 10.

  In step 3, it is determined whether the defocus amount of the focus detection result is within the focus determination threshold value and the photographing lens 8 is in focus. If not in focus, the process proceeds to step 4 to perform the background area extraction process described above. If in focus, the process proceeds to step 5 to perform the face area extraction process described above. Here, when the background region is extracted, it is assumed that the main subject exists in a region other than the background, and the region other than the background is set as the main subject region. On the other hand, when the face area is extracted, the face area is set as the main subject area.

  In step 6, focus adjustment is performed in the focus detection area corresponding to the main subject area, and exposure control is performed in the main subject area. When the background area is extracted, the focus of the photographic lens 8 is adjusted based on the focus detection result of the focus detection area corresponding to the main subject area other than the background area. When the face area is extracted, the focus of the photographing lens 8 is adjusted based on the focus detection result of the focus detection area corresponding to the main subject area, that is, the face area. If there are a plurality of focus detection areas corresponding to the main subject region, focus adjustment is performed based on the closest focus detection result among the plurality of focus detection results, for example.

  When the background area is extracted, the exposure calculation is performed based on the image signal of the pixel 26 corresponding to the main subject area other than the background area in the image signal of each pixel 26 of the second image sensor 16. Calculate the shutter speed and aperture value. On the other hand, when the face area is extracted, the exposure calculation is performed based on the image signal of the pixel 26 corresponding to the main subject area, that is, the face area, among the image signals of each pixel 26 of the second image sensor 16, Calculate the shutter speed and aperture value.

In step 7, it is determined whether the defocus amount detected in the focus detection area corresponding to the main subject area is within the focus determination threshold value and the photographing lens 8 is in focus. If not, the process proceeds to step 9, and it is determined whether or not the shutter button is pressed halfway. If the shutter button is pressed halfway, the process returns to step 1 and the above-described processing is repeated. On the other hand, when the shutter button is released, the shooting operation is terminated.

  If the subject in the main subject area is in focus in step 7, the process proceeds to step 8, and it is determined whether or not the shutter release operation has been performed by the release switch of the operation member 20. If there is no shutter release operation, the process proceeds to step 9, and the above-described processing is performed depending on whether or not the shutter button is half-pressed. On the other hand, when the shutter release operation is performed, the process proceeds to step 10 to perform a photographing operation. That is, the aperture 21 is set to the aperture value of the exposure calculation result, the shutter 7 is opened only for the seconds of the exposure calculation result, the first image sensor 4 is exposed, and the first image sensor 4 performs imaging.

  In step 11 after imaging, the image signal output from the first image sensor 4 is subjected to known image processing, recorded on a recording medium (not shown) such as a memory card, and displayed on a monitor (not shown). To do.

  As described above, according to the embodiment, after the focus detection result of the photographic lens 8 is determined to be in focus, the human face region, that is, the image corresponding to the human face is detected from the captured image. Since this is performed, it is possible to accurately detect the face area of the person from the captured image.

  A face candidate area detection process for detecting a human skin color area as a face candidate area from the captured image and a face width estimation process for estimating the face width of the person based on the shooting distance are performed. In the face area detection process in which the face candidate area whose horizontal width matches the face width is the face area, the face candidate area detection process is performed until the focus detection result is determined to be in focus, and the focus detection result matches. The face width estimation process may be performed after the focus is determined. Normally, it is desirable that the second imaging element 4 is exposed immediately after the photographing lens 8 is focused, and photographing is performed, and the face candidate area detection process is performed until it is determined to be in focus and then after focusing. , You can shoot quickly and take a picture in focus.

  Further, in the above-described embodiment, until the focus detection result is determined to be in focus, the background region detection process, that is, the image corresponding to the background is detected, and the focus detection result is determined to be in focus. Although an example of performing the face area detection process has been shown, the process executed until it is determined to be in focus is not limited to the background area detection process, and an image discrimination process different from the face area detection process, for example, a captured image Based on the shooting scene determination process, it may be performed.

<< Modification of Embodiment of Invention >>
In the above-described embodiment, an example in which the face area extraction process is performed immediately when the photographic lens 8 is in focus has been described. In general, the face area extraction process requires a longer calculation time than the background area extraction process. If the face area extraction process is performed for a long time and from the entire range of the photographed image, an area similar to the human skin hue in the background may be mistaken for the face area.

  Therefore, in this modification, as shown in FIG. 8, even if it is determined in step 3 that the taking lens 8 is in focus, the background region is extracted once in step 5A, and then in step 5B. Perform face area extraction processing. Here, in the face area extraction process in step 5B, the background area extracted by the background area extraction process is excluded from the images captured by the second image sensor 16, and the face area is extracted only from the main subject area. Perform the extraction process.

As a result, the calculation time until the face area is finally extracted can be shortened, and the face area is extracted only for the main subject area, so that the area similar to the hue of the human skin in the background can be obtained. The face area can be extracted more accurately without being mistaken for the face area.

  In the above-described embodiment, the example in which the focus detection by the phase difference detection method is performed by the focus detection optical system 9 and the distance measuring element 10 has been described. However, the method for detecting the focus adjustment state of the photographing lens 8 has been described above. The method is not limited to the method of one embodiment, and for example, focus detection by a contrast detection method may be performed based on an image captured by the first image sensor 4 or the second image sensor 16.

  In the above-described embodiment, the example in which the detection process of the face area and the background area is performed based on the image captured by the second image sensor 16 is described. However, based on the image captured by the first image sensor 4. These detection processes may be executed.

  Furthermore, the method for detecting the face region and the background region from the image is not limited to the method of the above-described embodiment.

  In the above-described one embodiment, one embodiment in which the present invention is applied to a single-lens reflex digital still camera and a modification example thereof have been described. Can be applied. Moreover, although the example applied to the camera provided with the image tracking function was described in the above-described embodiment, the present invention can also be applied to a camera without the image tracking function.

DESCRIPTION OF SYMBOLS 8 Shooting lens 9 Focus detection optical system 10 Distance measuring element 16 2nd image pick-up element 19 Body drive control apparatus

Claims (6)

An imaging unit for imaging an image by the imaging optical system;
A focus detection unit for detecting a focus adjustment state of the imaging optical system;
A focus determination unit that determines whether the focus detection unit can be regarded as in-focus;
Anda row Cormorant image processing section the image processing of the image captured by the imaging unit,
The image processing unit performs a shooting scene determination process when it is determined that the in-focus determination unit cannot be regarded as in-focus, and when the in-focus determination unit determines that it can be regarded as in-focus , imaging device, characterized in that intends line detection processing. An imaging unit for imaging an image by the imaging optical system;
A focus detection unit for detecting a focus adjustment state of the imaging optical system;
A focus determination unit that determines whether the focus detection unit can be regarded as in-focus;
And line Cormorant image processing section the image processing of the image captured by the imaging unit,
A control unit for controlling the focus adjustment state ,
The image processing unit performs a background detection process when it is determined by the focus determination unit that it cannot be regarded as in focus, and performs a face detection process when the focus determination unit determines that it can be regarded as a focus. There line,
The control unit, when it is determined by the focus determination unit that it can not be regarded as in-focus, performs a focus adjustment state control using a focus detection area corresponding to a region other than the background,
An imaging apparatus that controls a focus adjustment state using a focus detection area corresponding to the face area when the focus determination unit determines that the focus can be considered . An imaging unit for imaging an image by the imaging optical system;
A focus detection unit for detecting a focus adjustment state of the imaging optical system;
A focus determination unit that determines whether the focus detection unit can be regarded as in-focus;
And line Cormorant image processing section the image processing of the image captured by the imaging unit,
A control unit for controlling exposure ,
The image processing unit performs a background detection process when it is determined by the focus determination unit that it cannot be regarded as in focus, and performs a face detection process when the focus determination unit determines that it can be regarded as a focus. There line,
The control unit performs exposure control using a focus detection area corresponding to a region other than the background when the focus determination unit determines that the focus cannot be considered, and the focus determination unit performs focus control. An image pickup apparatus that controls exposure using a focus detection area corresponding to the face area when it is determined that it can be regarded as a focus . The imaging apparatus according to claim 1,
An imaging apparatus comprising: a control unit that controls a focus adjustment state using a focus detection area corresponding to the face area when the focus determination unit determines that the focus can be considered . The imaging apparatus according to claim 1,
An imaging apparatus comprising: a control unit that controls exposure using a focus detection area corresponding to the face area when the focus determination unit determines that the focus can be considered . An imaging apparatus according to claim 5, wherein
An imaging apparatus comprising: a control unit that controls a focus adjustment state using a focus detection area corresponding to the face area when the focus determination unit determines that the focus can be considered .

Images