JP2010041504A - Camera - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To detect the face of a person from an image. <P>SOLUTION: When photographing an image, a control device 104 increases an exposure priority for a center portion of a screen and carries out face recognition processing through pattern matching. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a camera.

  The following cameras are known. This camera detects a human face from within an image using a pattern matching technique (for example, Patent Document 1).

JP-A-6-259534

  However, in the conventional camera, when the shooting environment is a low illumination environment or a backlight environment, the contrast of the person's face in the image and its surroundings is small, so the outline of the person's face is cut out from the image. It is impossible to detect a human face by pattern matching.

The camera according to the present invention has an imaging unit that captures a subject image to acquire an image, a face detection unit that detects a human face from the image acquired by the imaging unit, and a human face detection accuracy by the face detection unit. And a process execution means for executing a process for increasing the speed.
In the present invention, the processing execution means may increase the exposure priority at the center of the screen when taking an image.
The processing execution means may correct the exposure in the plus direction with respect to the appropriate exposure when the image is captured.
The processing execution means may correct the dark part of the image brightly.
The processing execution means may correct the central portion of the image brightly.
The camera according to the present invention further includes a determination unit that determines whether or not the current shooting environment is a low illumination environment or a backlight environment, and the processing execution unit determines whether the current shooting environment is a low illumination environment or a backlight environment by the determination unit. The process may be executed when it is determined that.
The process execution means may execute the process when the shooting mode of the camera is set to a mode for shooting a person.

  According to the present invention, it is possible to detect a person's face even when the shooting environment is a low illumination environment or a backlight environment.

-First embodiment-
FIG. 1 is a block diagram illustrating a configuration of an embodiment of a camera according to the first embodiment. The camera 100 includes an operation member 101, a lens 102, an image sensor 103, a control device 104, a memory card slot 105, and a monitor 106. The operation member 101 includes various operation buttons operated by the user. For example, the operation member 101 includes a power button, a release button, a zoom button, a cross button, an enter button, a play button, a delete button, and the like.

  The lens 102 is composed of a plurality of optical lenses, but is representatively represented by one lens in FIG. The image sensor 103 is an image sensor such as a CCD or a CMOS, for example, and captures a subject image formed by the lens 102. Then, an image signal obtained by imaging is output to the control device 104.

  The control device 104 generates image data in a predetermined image format, for example, JPEG format (hereinafter referred to as “main image data”) based on the image signal input from the image sensor 103. Further, the control device 104 generates display image data, for example, thumbnail image data, based on the generated image data. The control device 104 generates an image file that includes the generated main image data and thumbnail image data, and further includes header information, and outputs the image file to the memory card slot 105. In the present embodiment, image file generation processing by the control device and recording processing of the generated image file on a memory card are referred to as photographing processing.

  The memory card slot 105 is a slot for inserting a memory card as a storage medium, and the image file output from the control device 104 is written and recorded on the memory card. The memory card slot 105 reads an image file stored in the memory card based on an instruction from the control device 104.

  The monitor 106 is a liquid crystal monitor (rear monitor) mounted on the back surface of the camera 100, and the monitor 106 displays an image stored in a memory card, a setting menu for setting the camera 100, and the like. . Further, when the user sets the mode of the camera 100 to the shooting mode, the control device 104 outputs image data for display of images acquired from the image sensor 103 in time series to the monitor 106. As a result, a through image is displayed on the monitor 106.

  The control device 104 includes a CPU, a memory, and other peripheral circuits, and controls the camera 100. Note that the memory constituting the control device 104 includes SDRAM and flash memory. The SDRAM is a volatile memory, and is used as a work memory for the CPU to develop a program when the program is executed or as a buffer memory for temporarily recording data. The flash memory is a non-volatile memory in which data of a program executed by the control device 104, various parameters read during program execution, and the like are recorded.

  The camera 100 according to the present embodiment recognizes a person's face using a pattern matching technique on a through image, and performs AF (Auto Focus / Auto Focus Adjustment) or AE (Auto Exposure) on the person's face during shooting. / Face recognition AF / AE function that optimizes automatic exposure adjustment). In the present embodiment, since the face recognition process, the AF process, and the AE process using the pattern matching method are known processes, detailed description of the processes is omitted.

  As described above, in the camera 100 having the face recognition AF / AE function, in a low illumination environment or in a backlit state, since the contrast difference between the person's face and its surroundings in the through image is small, the contour of the face is reduced. It cannot be cut out. Therefore, in such an environment, pattern matching cannot be performed and a human face cannot be detected.

  In the first embodiment, in order to solve such a problem, the control device 104, when the shooting environment is a low-light environment or a backlight environment, has a high possibility that the main subject is present. By increasing the exposure priority of the part and increasing the contrast difference between the person's face and the surrounding area in the through image, the detection accuracy of the person's face from the through image is increased. Specifically, the control device 104 performs processing as follows.

  The control device 104 determines whether the current shooting environment is a low illumination environment or a backlight environment. For example, the control device 104 determines whether the current shooting environment is a low illuminance environment or a backlight environment based on the exposure evaluation value of the through image. Specifically, the control device 104 determines that the current shooting environment is a low illuminance environment when the average value of the exposure evaluation values in the through image is equal to or less than a predetermined threshold. For example, when the exposure evaluation value of a black pixel is 0 and the exposure evaluation value of a white pixel is 255, 60 is set as the threshold value.

  Further, the control device 104 determines that the current shooting environment is a backlight environment when the exposure evaluation value varies in the through image. For example, when the exposure evaluation value of a black pixel is 0 and the exposure evaluation value of a white pixel is 255, the difference between the highest exposure evaluation value and the lowest exposure evaluation value in the through image is 60 or more. At some time, it is considered that the exposure evaluation value varies, and it is determined that the current photographing environment is a backlight environment.

  When it is determined that the current shooting environment is a low illumination environment or a backlight environment, the control device 104 increases the exposure priority at the center of the screen by changing the photometry method. For example, in the present embodiment, the “multi-pattern metering mode” in which the camera 100 is optimized as the metering mode so that the exposure is appropriate over the entire screen, and the exposure is optimized with an emphasis on the center of the screen. It is assumed that a “center-weighted metering mode” and a “spot metering mode” that optimizes exposure with emphasis on a part of the screen are provided.

  When the current metering mode is the “multi-pattern metering mode”, the entire screen is properly exposed. Therefore, in a low illumination environment or a backlight environment, the face of the main subject existing in the center of the screen is often dark. For this reason, the control device 104 increases the exposure priority at the center of the screen by increasing the importance of the center of the screen in multi-pattern metering. Thereby, it is possible to increase the contrast between the face of the person and the surrounding area in the through image and perform face detection by pattern matching.

  Alternatively, when the current metering mode is “multi-pattern metering mode”, the control device 104 changes the metering mode to “center-weighted metering mode” or “spot metering mode” to emphasize the center of the screen. Control may be performed so as to optimize exposure. Also by this method, it is possible to increase the contrast between the face of the person existing in the center of the screen in the through image and the surrounding area, and to perform face detection by pattern matching.

  In the camera 100 according to the present embodiment, the control device 104 executes AF processing and AE processing when detecting that the release button included in the operation member 101 is half-pressed by the user. At this time, the control device 104 performs the AF process and the AE process so that the face of the person recognized by pattern matching is in focus and the person's face has optimum brightness. Thereafter, when the control device 104 detects that the release button has been fully pressed by the user, the control device 104 performs the above-described photographing process.

  FIG. 2 is a flowchart showing processing of the camera 100 according to the first embodiment. The processing shown in FIG. 2 is executed by the control device 104 as a program that starts when input of an image signal from the image sensor 103 is started and display of a through image on the monitor 106 is started.

  In step S10, as described above, the control device 104 determines whether or not the current shooting environment is a low illumination environment or a backlight environment based on the exposure evaluation value of the through image. If a negative determination is made in step S10, the process proceeds to step S30 described later. On the other hand, if a positive determination is made in step S10, the process proceeds to step S20. In step S20, as described above, the control device 104 increases the importance of the center of the screen in multi-pattern metering, or changes the metering mode from “multi-pattern metering mode” to “center-weighted metering mode” or “spot metering mode”. To increase the exposure priority at the center of the screen. Then, it progresses to step S30.

  In step S30, the control device 104 recognizes a person's face by performing pattern matching processing on the through image. Thereafter, the process proceeds to step S40, and the control device 104 determines whether or not the release button included in the operation member 101 is half-pressed by the user. If a negative determination is made in step S40, the process returns to step S10. On the other hand, if a positive determination is made in step S40, the process proceeds to step S50. In step S50, the control device 104 focuses on the face of the person recognized in step S30, and further performs AF processing and AE processing so that the face of the person has optimum brightness. Thereafter, the process proceeds to step S60.

  In step S60, the control device 104 determines whether or not the release button included in the operation member 101 has been fully pressed by the user. If a negative determination is made in step S60, the process proceeds to step S61, and the control device 104 determines whether or not the half-press of the release button by the user is released. If a positive determination is made in step S61, the process returns to step S10. On the other hand, if a negative determination is made in step S61, the process returns to step S60.

  On the other hand, if a positive determination is made in step S60, the process proceeds to step S70. In step S70, the control device 104 executes the above-described shooting process and proceeds to step S80. In step S <b> 80, the control device 104 determines whether or not the display of the through image on the monitor 106 is terminated due to the stop of the input of the image signal from the image sensor 103. If a negative determination is made in step S80, the process returns to step S10 and is repeated. On the other hand, if an affirmative determination is made in step S80, the process ends.

According to the first embodiment described above, the following operational effects can be obtained.
(1) The control device 104 increases the exposure priority at the center of the screen when taking an image. This increases the contrast between the human face and the surrounding area in the through image so that the face can be detected by pattern matching, and the detection accuracy of the human face from the through image can be increased.

(2) The control device 104 increases the exposure priority at the center of the screen when the current shooting environment is a low illumination environment or a backlight environment. As a result, when the current shooting environment is a low-light environment or backlight environment, the contour of the face cannot be cut out because there is little contrast difference between the human face and its surroundings in the through image, and pattern matching Although it is difficult to perform face detection by the above, it is possible to avoid this and perform face detection.

-Second embodiment-
In the first embodiment described above, the control device 104 increases the exposure priority at the center of the screen by changing the photometry method when the current shooting environment is a low-light environment or a backlight environment. explained. On the other hand, in the second embodiment, when the current shooting environment is a low-light environment or a backlight environment, the control device 104 corrects the exposure in the positive direction with respect to the appropriate exposure, thereby making the entire through image. Brighten up. Accordingly, it is possible to increase the contrast between the face of the person existing in the through image and the surrounding area and to perform face detection by pattern matching. Note that the block diagram shown in FIG. 1 is the same as that of the first embodiment, and a description thereof will be omitted.

  FIG. 3 is a flowchart showing processing of the camera 100 according to the second embodiment. The processing shown in FIG. 3 is executed by the control device 104 as a program that starts when input of an image signal from the image sensor 103 is started and display of a through image on the monitor 106 is started. In FIG. 3, the same step number is assigned to the same process as the process of FIG. 2 described in the first embodiment, and the difference from FIG. 2 will be mainly described here.

  In step S <b> 21, the control device 104 corrects the exposure in the through image in the positive direction with respect to the appropriate exposure. For example, the entire through image is brightened by setting the exposure in the through image to +0.7 from the appropriate exposure. In this case, in the photographing process of step S70, the control device 104 cancels the exposure correction for the through image and performs exposure control so that the exposure becomes appropriate. In the present embodiment, the control device 104 sets the exposure in the through image to +0.7 from the appropriate exposure. However, the present invention is not limited to this, and may be +1.0, for example.

  According to the second embodiment described above, the following operational effects can be obtained. That is, the control device 104 corrects the exposure in the plus direction when taking an image. Thus, the contrast between the human face existing in the through image and its surroundings can be increased so that face detection can be performed by pattern matching, and the detection accuracy of the human face from within the through image can be increased.

-Third embodiment-
In the first and second embodiments described above, when the current shooting environment is a low illumination environment or a backlight environment, the control device 104 calculates the contrast between the human face existing in the through image and the surrounding area. The example which performs the process for raising was demonstrated. On the other hand, in the third embodiment, the control device 104 determines whether the current photographing environment is a low-light environment or a backlight environment, A case of performing processing for increasing the contrast of the image will be described. Note that the block diagram shown in FIG. 1 is the same as that of the first embodiment, and a description thereof will be omitted.

  In the third embodiment, the control device 104 brightly corrects a dark portion in the through image by performing gradation conversion on the through image. For example, a gradation conversion characteristic (gamma curve) 4a for lifting a dark part of an image as shown in FIG. 4 is set in advance, and the control device 104 uses this gradation conversion characteristic 4a to apply a through image. Tone conversion is performed. This makes it possible to detect faces by pattern matching even when a dark face in a live view contains a person's face by brightening that part and increasing the contrast between the person's face and its surroundings. Be able to.

  FIG. 5 is a flowchart illustrating processing of the camera 100 according to the third embodiment. The processing shown in FIG. 5 is executed by the control device 104 as a program that starts when input of an image signal from the image sensor 103 is started and display of a through image on the monitor 106 is started. In FIG. 5, the same step number is assigned to the same process as the process of FIG. 2 described in the first embodiment, and the difference from FIG. 2 will be mainly described here.

  In step S22, as described above, the control device 104 performs gradation conversion on the through image using the gradation conversion characteristic 4a for lifting the dark portion of the image as shown in FIG. Thereafter, the process proceeds to step S30, and the control device 104 recognizes the face of the person by performing pattern matching processing on the through image after gradation conversion.

  According to the third embodiment described above, the following operational effects can be obtained. In other words, the control device 104 performs gradation conversion on the live view image to brightly correct dark portions in the live view image. This makes it possible to detect faces by pattern matching even when a dark face in a live view contains a person's face by brightening that part and increasing the contrast between the person's face and its surroundings. It is possible to improve the accuracy of detecting a human face from the through image.

-Fourth embodiment-
In the fourth embodiment, the control device 104 detects an area where the brightness difference in the exposure evaluation value is small, for example, an area within 0.5 EV, as the target area with respect to the image center portion of the through image. Then, the control device 104 brightens the target area by increasing the gain of only the detected target area. For example, the control device 104 increases the gain of the target area by multiplying the target area by a gain twice that of the other areas. As a result, it is possible to increase the contrast between the face of the person existing near the center of the through image and its surroundings and perform face detection by pattern matching. Note that the block diagram shown in FIG. 1 is the same as that of the first embodiment, and a description thereof will be omitted.

  FIG. 6 is a flowchart illustrating processing of the camera 100 according to the fourth embodiment. The processing shown in FIG. 6 is executed by the control device 104 as a program that starts when input of an image signal from the image sensor 103 is started and display of a through image on the monitor 106 is started. In FIG. 6, the same step number is assigned to the same process as the process of FIG. 2 described in the first embodiment, and here, differences from FIG. 2 will be mainly described.

  In step S23, the control device 104 determines whether or not there is a region with a small luminance difference in the exposure evaluation value, for example, a region within 0.5 EV, in the center portion of the through image. If a negative determination is made in step S23, the process proceeds to step S30. On the other hand, if a positive determination is made in step S23, the process proceeds to step S24.

  In step S24, the control device 104 brightens the target area by increasing the gain of the detected target area, for example, twice that of the other areas, and proceeds to step S30. In step S30, the control device 104 recognizes a human face by performing a pattern matching process on the through image after gaining up the target region.

  According to the fourth embodiment described above, the following operational effects can be obtained. That is, the control device 104 brightens the target area by increasing the gain of the target area having a small luminance difference in the exposure evaluation value of the center portion of the through image. This increases the contrast between the face of the person existing near the center of the live view and the surrounding area so that face detection can be performed by pattern matching, and the detection accuracy of the human face from within the live view is increased. be able to.

-Modification-
The camera according to the above-described embodiment can be modified as follows.
(1) In the first and second embodiments described above, the control device 104 determines whether the current shooting environment is a low illumination environment or a backlight environment based on the exposure evaluation value of the through image. An example of performing was described. However, when the control device 104 has an auto scene discrimination function for automatically discriminating a shooting scene, it may be determined whether the environment is a low illumination environment or a backlight environment based on the discrimination result. For example, the control device 104 determines that the current shooting environment is a low illuminance environment when the current shooting scene is determined to be “night scene” by auto scene determination. In addition, when it is determined that the current shooting scene is “backlight” by the automatic scene determination, the control device 104 determines that the current shooting environment is a backlight environment. Alternatively, the control device 104 may determine whether the environment is a low-light environment or a backlight environment based on the setting state of the scene mode by the user. Further, the control device 104 may determine that the current shooting environment is a low illumination environment when the shutter speed during shooting is 1/8 or less.

(2) In the first and second embodiments described above, the control device 104 can detect the face of a person from the image when the current shooting environment is a low-light environment or a backlight environment. In the third and fourth embodiments described above, the control device 104 determines whether the current shooting environment is a low-light environment or a backlight environment from within the image. An example in which processing for enabling detection of a human face has been described. However, in the third and fourth embodiments, the control device 104 can detect a person's face from the image when the current shooting environment is a low illumination environment or a backlight environment. You may make it perform the process for doing.

(3) In the first embodiment described above, the control device 104 increases the exposure priority at the center of the screen by changing the photometry method when the current shooting environment is a low illumination environment or a backlight environment. In the live view, the contrast between the human face and its surroundings is increased so that face detection can be performed by pattern matching. However, when the current shooting environment is a low illumination environment or a backlight environment, the control device 104 first performs face recognition processing without changing the photometry method. Then, as a result, if the face cannot be recognized, the control device 104 may change the photometry method to increase the exposure priority at the center of the screen, and then perform the face recognition process again.

(4) In the second embodiment described above, the control device 104 corrects the exposure in the positive direction with respect to the proper exposure when the current shooting environment is a low illumination environment or a backlight environment. By increasing the contrast, the contrast between the person's face and its surroundings in the through image is increased, and face detection can be performed by pattern matching. However, when the current shooting environment is a low illumination environment or a backlight environment, the control device 104 first performs face recognition processing on a through image shot with appropriate exposure without performing exposure correction. Then, as a result, when the face cannot be recognized, the control device 104 may correct the exposure in the positive direction from the appropriate exposure to brighten the entire through image, and then perform the face recognition process again. .

(5) In the second embodiment described above, for example, when the current shooting environment is a low illumination environment or a backlight environment, the control device 104 increases the exposure to +0.7 or +1.0 from the appropriate exposure. An example was described. However, when the current shooting environment is a low illumination environment or a backlight environment, the control device 104 first performs a face recognition process after setting the exposure to +0.7 from the appropriate exposure. As a result, when the human face cannot be recognized from the through image, the control device 104 may perform the face recognition process by setting the exposure to +1.0 from the appropriate exposure.

(6) In the first to fourth embodiments described above, when the control device 104 starts to input an image signal from the image sensor 103 and starts displaying a through image on the monitor 106, FIGS. The example of executing the processing of the flowcharts shown in FIGS. However, the control device 104 may execute the above processing when the shooting mode of the camera 100 is set to a mode for shooting a person, for example, a portrait mode or a night view portrait mode. As a result, the above process is performed only when there is a high possibility that a person's face appears in the through image. Is no longer necessary.

(7) In the first to fourth embodiments described above, the processes of the flowcharts shown in FIGS. 2, 3, 5, and 6 are executed so that a human face can be detected from the through image. The picture was brightened. In this case, since the through image may have different brightness for each frame, the through image may flicker. Therefore, the control device 104 may lower the display frame rate of the through image than usual while executing the processing of the flowcharts shown in FIGS. For example, when the normal display frame rate is 1/30 fps, the control device 104 may reduce the display frame rate to 1/60 fps during the above processing. As a result, the time interval during which the brightness of the image changes during live view display can be lengthened, and flickering of the screen can be suppressed.

(8) In the third and fourth embodiments described above, the control device 104 can detect the face of a person from the through image by performing image processing on the through image. For this reason, it is not always necessary to perform image processing on the through image itself displayed on the monitor 106. A copy of the through image is created for face detection, and image processing is performed on the copy image to perform face recognition processing. It may be. In this way, since the through image displayed on the monitor 106 is not subjected to image processing, it is possible to suppress the brightness change for each frame of the through image, while the copy image is subjected to image processing to be brighter. By doing so, it is possible to detect a human face by pattern matching processing.

(9) In the above-described first to fourth embodiments, the control device 104 has described an example in which a face of a person is detected from a through image by executing a face recognition process on the through image. However, the detection target is not limited to a human face. For example, the present invention can be applied to a case where an animal face or the like is a detection target. Further, the present invention is not limited to the face of a person or an animal, and the present invention can also be applied to a case where various objects are photographed as subjects and the objects are detected by pattern matching.

(10) In the first to fourth embodiments described above, the control device 104 has described an example in which AF or AE is optimized for a human face after detecting the human face. However, when the control device 104 detects the face of a person by the processing described in the first to fourth embodiments, the control device 104 tracks the face between through-image frames, thereby tracking the subject. It is possible to apply to this technology. In addition, when the control device 104 detects a person's face by the processing described in the first to fourth embodiments, the control mode of the camera 100 is changed to a mode for shooting a person, for example, a portrait mode. The present invention may be applied to auto scene discrimination by shifting.

  Note that the present invention is not limited to the configurations in the above-described embodiments as long as the characteristic functions of the present invention are not impaired. Moreover, it is good also as a structure which combined the above-mentioned embodiment and a some modification.

1 is a block diagram illustrating a configuration of an embodiment of a camera 100. FIG. It is a flowchart figure which shows the process of the camera 100 in 1st Embodiment. It is a flowchart figure which shows the process of the camera 100 in 2nd Embodiment. It is a figure which shows the specific example of the gradation conversion characteristic used by the gradation conversion process in 2nd Embodiment. It is a flowchart figure which shows the process of the camera 100 in 3rd Embodiment. It is a flowchart figure which shows the process of the camera 100 in 4th Embodiment.

Explanation of symbols

100 Camera, 101 Operation member, 102 Lens, 103 Image sensor, 104 Control device, 105 Memory card slot, 106 Monitor

Claims (7)

Imaging means for capturing a subject image and acquiring the image;
Face detecting means for detecting a human face from within the image acquired by the imaging means;
A camera comprising: a process execution unit that executes a process for increasing the accuracy of detection of a human face by the face detection unit. The camera of claim 1,
The camera according to claim 1, wherein the processing execution unit increases the exposure priority at the center of the screen when the image is captured. The camera of claim 1,
The camera according to claim 1, wherein the processing execution unit corrects the exposure in a plus direction with respect to the appropriate exposure when the image is captured. The camera of claim 1,
The camera according to claim 1, wherein the processing execution unit corrects a dark part of the image brightly. The camera of claim 1,
The camera according to claim 1, wherein the processing execution unit corrects a central portion of the image brightly. In the camera according to any one of claims 1 to 5,
A determination means for determining whether the current shooting environment is a low-light environment or a backlight environment;
The camera according to claim 1, wherein the processing execution unit executes the processing when the determination unit determines that the current shooting environment is a low illumination environment or a backlight environment. In the camera according to any one of claims 1 to 6,
The process execution means executes the process when the shooting mode of the camera is set to a mode for shooting a person.

Images