JP2007336126A - Imaging device and its controlling method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To prevent the failure of detection of a face image from an image which constitutes a motion picture. <P>SOLUTION: First of all, a threshold value is calculated for detecting the face image (step 31). Then, an object is imaged (step 32), and a face score is obtained indicating the similarity of the face image of the object (steps 33 and 34). When the face score exceeds the threshold value (YES in step 35), the detection result is stored (step 36). Thereafter, the threshold value is re-calculated in a constant timing interval (YES in step 38, and step 31), and then face image detection processing is performed again. Since the threshold value is not fixed but can be changed, it can be prevented that the face image which has been detected until a certain frame of the object image is no longer detected after that frame. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an imaging apparatus and a control method thereof.

There is a device that detects a person image or a face image from subject images obtained by imaging a subject. As such a device, when a plurality of human images are included in a subject image, adjacent human images can be distinguished, and even if the shape of the same human image changes greatly in a moving image, the human image can be detected. There is a thing (patent document 1).
JP 2001-175868

  However, when a target image such as a person image or a face image is detected from each frame image in a moving image in which a subject is imaged at a constant cycle, the target image is detected in a certain frame image. May not be detected.

  An object of the present invention is to prevent a target image from being detected from images constituting a moving image.

  An image pickup apparatus according to the present invention is a solid-state electronic image pickup apparatus that picks up an image of a subject and outputs image data representing the image of the object. An object image represented by image data output from the solid-state electronic image pickup apparatus The solid-state electronic imaging device and the target image detection unit are configured to repeat target image detection means for detecting a target image portion having a target image quality, imaging by the solid-state electronic imaging device, and detection processing by the target image detection means, respectively. First control means for controlling, and threshold value changing means for changing a threshold value used for detection processing in the target image detection means during repetition of imaging based on the control of the first control means. It is characterized by that.

  The present invention also provides a control method suitable for the imaging apparatus. That is, in this method, the solid-state electronic imaging device images a subject and outputs image data representing the subject image, and the target image detection unit displays the subject image represented by the image data output from the solid-state electronic imaging device. The solid-state electronic imaging device detects a target image portion having a target image-likeness equal to or greater than a threshold value, and the control unit repeats imaging by the solid-state electronic imaging device and detection processing by the target image detection unit, respectively. The target image detecting means is controlled, and the threshold value changing means changes the threshold value used for the detection processing in the target image detecting means during the repetition of imaging based on the control of the control means.

  According to the present invention, a subject is imaged by the solid-state electronic imaging device, and image data representing the subject image is output. A target image portion having a target image quality equal to or higher than a threshold value is detected from a subject image represented by the output image data. Such imaging processing and target image portion detection processing are repeated. While the imaging is repeated, the threshold used for the target image detection process is changed. For example, since the probability that the target image portion is detected increases as the threshold value decreases, undetection of the target image portion is prevented in advance. As the threshold value increases, the target image portion of the detected target image portion becomes higher, so that erroneous detection can be prevented.

  The threshold value changing means changes the threshold value, for example, so as to become lower in response to detection of the target image portion by the target image detecting means.

  The threshold value changing means may reset the threshold value to an initial value when the target image portion is not detected by the target image detecting means.

  It is preferable to further include reset means for resetting the threshold value changed by the threshold value changing means to an initial value at a constant period.

  Second control means for controlling the target image detection means so as to detect the target image from a region around the detected target image part in response to detection of the target image part by the target image detection means; Further, it may be provided.

  FIG. 1 shows an embodiment of the present invention and is a block diagram showing an electrical configuration of a digital still camera.

  The entire operation of the digital still camera is controlled by the CPU 10.

  The digital still camera includes an operation device 16 including various buttons such as a shutter release button and a mode setting switch. The operation signal output from the operation device 16 is input to the CPU 10. Connected to the CPU 10 are a ROM 14 in which an operation program for the digital still camera and other necessary data are stored, and a RAM 15 in which data is temporarily stored.

  The digital still camera is provided with a strobe light emitting device 12 for strobe photography. Light emission of the strobe light emitting device 12 is controlled by a strobe control circuit 11 controlled by the CPU 10.

  An imaging lens 1 and a diaphragm 3 are provided in front of the CCD 5. The position of the imaging lens 1 is controlled by the lens driving circuit 2 controlled by the CPU 10 so that the subject image is formed on the light receiving surface of the CCD 5. The aperture value of the aperture 3 is controlled by an aperture driving circuit 4 controlled by the CPU 10 so that an appropriate exposure amount is obtained.

  When the imaging mode is set by the mode setting switch, the subject is imaged by the CCD 5. When the CCD 5 is driven by the CCD driver 6, a video signal representing a subject image is output from the CCD 5. The video signal is converted into digital image data in the analog / digital conversion circuit 7 which operates based on the clock pulse supplied from the timing generator 13.

  The image data converted in the analog / digital conversion circuit 7 is input to the signal processing circuit 22. In the signal processing circuit 22, corrections such as offset correction, gain correction, and gamma correction are performed. The image data output from the signal processing circuit 22 is input to the display control circuit 27. When the liquid crystal display device 29 is controlled by the display control circuit 27, the subject image is displayed on the display screen of the liquid crystal display device 29. A signal output from the on-screen device signal generation circuit 28 is also given to the liquid crystal display device 29. Characters and the like appearing by the signal output from the on-screen device signal generation circuit 28 are displayed so as to be superimposed on the subject image displayed on the display screen of the liquid crystal display device 29.

  In the digital still camera of this embodiment, the face image portion can be detected from the subject image. The subject image is scanned by a predetermined detection frame, and the face image likelihood of the image in the detection frame is calculated as the face score. If the calculated face score is equal to or greater than the threshold value, the image portion that is given a face score equal to or greater than the threshold value is determined as the face image portion. In this embodiment, the threshold value used for detecting the face image portion is not fixed but can be changed. The digital still camera is provided with a threshold value calculation circuit 23 for calculating the threshold value.

  The image data output from the analog / digital conversion circuit 6 is also input to the face score calculation circuit 8. In this face score calculation circuit 8, as described above, the subject image represented by the input image data is scanned by a predetermined detection frame, and a face score indicating the face image likeness of the image in the detection frame is displayed in the detection frame. Calculated for each scanning position. Data representing the calculated score is given to the threshold value judgment circuit 9. Data representing the threshold value calculated by the threshold value calculation circuit 23 is also input to the threshold value determination circuit 9. Data indicating whether or not the calculated face score is greater than the threshold value is input to the CPU 10. If the face score is larger than the threshold value, it is determined that the image portion giving the face score is the face image portion. The diaphragm 3 is driven so that the face image portion has an appropriate brightness, and the lens 1 is positioned so that the face image portion is in focus.

  When the shutter release button is pressed, the digital image data converted in the analog / digital conversion circuit 6 as described above is input to the face score calculation circuit 8, and the face score in each part of the subject image is calculated. The Data representing the calculated score is input to the threshold discrimination circuit 9 to determine whether the face score is equal to or greater than the threshold. If the face score is equal to or greater than the threshold value, data indicating the position of the image portion (portion determined to be the face image portion) giving the face score is input to the CPU 10.

  Further, the image data converted in the analog / digital conversion circuit as described above is also input to the signal processing circuit 22. In the signal processing circuit 22, offset correction and gain correction are performed. When these corrections are performed in the signal processing circuit 22, the image data is given to the memory 21 and temporarily stored. The image data stored in the memory 21 is read out under the control of the CPU 10, and interpolation processing is performed while being read out. The interpolated image data is again given to the memory 21 and stored.

  The interpolated image data is read from the memory 21 and input to the compression / decompression circuit 24. The interpolated image data is compressed in the compression / decompression circuit 24. The compressed image data is given to the memory card 26 via the card interface 25 and recorded.

  When the playback mode is set by the mode setting switch, the compressed image data recorded on the memory card 26 is read via the card interface 25. The read image data is decompressed by the compression / decompression circuit 24. When the decompressed image data is given to the display control circuit 27, an image represented by the image data recorded in the memory card 26 is displayed on the display screen of the display device 29.

  FIG. 2 is a flowchart showing a processing procedure for moving image capturing.

  Moving image capturing is a method for determining the angle of a subject by setting an image capturing mode in a digital still camera when a subject is repeatedly imaged for moving image recording in a digital camera capable of recording moving images. This is the case where the subject is repeatedly imaged (so-called through image capturing).

  A threshold value is calculated as described above (step 31). The calculation of this threshold will be set to an appropriate value based on past experience. The subject is imaged and image data representing the subject image is obtained (step 32). As described above, the subject image represented by the image data is scanned by the detection frame (step 33), and the face score at each position of the detection frame is calculated (step 34).

  If the calculated face score is equal to or greater than the threshold value (YES in step 35), the image part to which the face score is given is considered to be a face image part, so that the detection result (face score, face image part is determined). Are stored (step 36). Based on the detection result, for example, a frame representing the face image portion is displayed on the subject image.

  If an imaging end command is not given (NO in step 37), it is determined whether or not it is time to recalculate the threshold (step 38). If it is not time to recalculate the threshold value, the threshold value is not recalculated (NO in step 38), and the processing from steps 32 to 37 is repeated again. When it is time to recalculate the threshold (YES in step 38), the threshold is calculated again (step 31). Face image portion detection processing is performed using the calculated new threshold value.

  The threshold value can be changed in accordance with the imaged situation.

  3 to 9 show another embodiment.

  In this embodiment, when an image portion having a face score larger than the threshold is found from the subject image of the frame in which the subject is repeatedly imaged, the threshold is lowered. Since the threshold value is lowered, it is possible to prevent the face image portion from being undetected in other frames.

  First, the case where the threshold value is fixed as in the prior art will be described.

  FIG. 3 shows the relationship between each frame (horizontal axis) of the subject image repeatedly captured and the face score (vertical axis) calculated in each frame. It is assumed that only one face image is included in the subject image.

  The threshold value Th0 is fixed, and the face score exceeds the threshold value Th0 up to n frames.

  FIG. 4 is an example of a subject image captured in the nth frame.

  The subject image in the nth frame includes a person image 41, and the face score of the face image portion i51 of the person image 41 exceeds the above-described threshold value. For this reason, a frame F51 surrounding the face image portion i51 is displayed.

  Returning to FIG. 3, when the (n + 1) frame is reached, the face score becomes less than the threshold value Th0.

  FIG. 5 is an example of a subject image captured in the (n + 1) th frame.

  The subject image includes the human image 41, but for some reason, a face score exceeding the threshold Th0 cannot be obtained, and the face image portion is not detected.

  Returning to FIG. 3 again, since the face image portion is not detected in the subject image of the (n + 1) th frame, the automatic exposure control and the face image portion are focused so that the brightness of the face image portion is appropriate. If the automatic focusing control is performed, a malfunction occurs. After that, when the face score exceeds the threshold Th0, it is assumed that the shutter button is pressed at the timing when the p frame is imaged, and the face score obtained in the subject image of the p frame exceeds the threshold Th0. Otherwise, automatic exposure control and automatic focusing control in accordance with the face image portion included in the subject image obtained at the timing when the shutter button is pressed cannot be realized.

  FIG. 6 shows the relationship between the frame and the face score in this embodiment.

  When a face score exceeding the threshold value (initial value) Th1 is obtained in the subject image of the 0th frame, the threshold value is lowered in the next first frame (threshold value Th2).

  FIG. 7 is an example of the subject image of the nth frame.

  Since the subject image 41 is included in the subject image of the nth frame and the face image detection processing is performed using the lowered threshold value, the face image i51 is detected. A face image i51 is surrounded by a frame F51.

  Returning to FIG. 6, even when the (n + 1) th frame is imaged, the face image is detected using the lowered threshold value, so that the face image is detected from the subject image.

  FIG. 7 shows an example of the subject image of the (n + 1) th frame.

  A subject image 41 is included in the subject image. Since the threshold value is lowered as described above, the face image portion i61 of the person image 41 is detected, and a frame F61 surrounding the face image portion i61 is displayed.

  Returning to FIG. 6 again, the threshold value Th1 is returned to the threshold value Th2, which is the initial value, at the timing when the m-th frame is imaged. By detecting a face image also in the subject image of the mth frame, the threshold value is returned from the threshold value Th2 to the initial value Th1.

  Since the threshold value is lowered even when the shutter button is pressed at the timing when the p frame is imaged, the face image portion is detected, and automatic exposure control and automatic focus control adapted to the face image portion can be realized. become.

  FIG. 9 is a flowchart showing the moving image imaging processing procedure.

  In this figure, the same processes as those shown in FIG.

  First, the threshold value of the face score is set to the initial value Th1 (step 71). Thereafter, the subject is imaged and a face score is calculated (steps 32-35).

  If there is a face score exceeding the threshold (YES in step 35), the detection result is stored (step 36). The threshold value is set lower than the initial value (step 72). If the imaging end command is not given (NO in step 37), the subject is imaged again, and the face score is compared with the lowered threshold value. As described above, since the threshold value is low, it is possible to prevent the face image portion that should exist from being undetected. If a face score larger than the lowered threshold is detected after the threshold is lowered, the threshold is set again lower than the initial value, but it is not always necessary to set it again. Needless to say. Once the threshold value has been lowered, the processing in step 72 may be skipped. Needless to say, the lowered threshold value may be further lowered.

  If there is no face score exceeding the threshold value (NO in step 35), the threshold value is returned to the initial value (step 73).

  FIG. 10 is a flowchart showing the moving image imaging processing procedure. In this figure, the same processes as those shown in FIG.

  In this processing, the threshold value is reset to the initial value at a constant cycle.

  First, the reset variable N is set to 0 (step 81). In this embodiment, the threshold is reset to the initial value when the remainder when the reset variable N is divided by M (M is an integer of 2 or more excluding N) becomes zero. For this purpose, it is confirmed whether the remainder when the reset variable N is divided by M is 0 (step 82). When it becomes 0 (YES in step 82), the threshold value is returned to the initial value (step 83).

  Thereafter, the subject is imaged and a face image portion detection process is performed (steps 32-73). When the face image detection process ends, the reset variable N is incremented (step 84).

  Since the threshold value is reset to the initial value at a fixed period, even if it is misjudged that it is a face image part because the threshold value has been lowered, the misjudgment can be stopped halfway. it can.

  11 to 13 show still another embodiment.

  In this embodiment, when a face image portion is detected, a target image area in which the face image portion is to be detected is set near the detected face image portion.

  11 and 12 are examples of captured subject images.

  Referring to FIG. 11, the target image area 91 in which the face image portion is to be detected is substantially the entire subject image 90 in the initial area. A face image portion 92 present in the target image area 91 is detected.

  Referring to FIG. 12, when the face image portion is detected, the target image region where the face image portion is to be detected is not the almost entire region of the subject image 95, but the region in the vicinity of the detected face image portion 92. 96. Since the area where the face image part is not detected is excluded from the target image area, it is possible to prevent the part that is not the face image part from being determined as the face image. In addition, the time required for the detection process can be shortened.

  FIG. 13 is a flowchart of the moving image imaging processing procedure. In this figure, the same processes as those shown in FIG.

  If the remainder when the reset variable N is divided by M becomes 0, the threshold value is set to an initial value and the detection target area is set to an initial area corresponding to almost the entire subject image (step 83A). When face detection processing is performed and a face score exceeding the threshold value is obtained (YES in step 35), the threshold value is lowered from the initial value (step 72), and the detection target area is set to the peripheral area of the face image. It will be set (step 85).

It is a block diagram which shows the electric constitution of a digital still camera. It is a flowchart which shows the imaging processing procedure for moving images. The relationship between the frame of the captured subject image and the face score is shown. It is an example of a to-be-photographed image. It is an example of a to-be-photographed image. The relationship between the frame of the captured subject image and the face score is shown. It is an example of a to-be-photographed image. It is an example of a to-be-photographed image. It is a flowchart which shows the imaging processing procedure for moving images. It is a flowchart which shows the imaging processing procedure for moving images. The relationship between a subject image and a detection target area is shown. The relationship between a subject image and a detection target area is shown. It is a flowchart which shows the imaging processing procedure for moving images.

Explanation of symbols

5 CCD
8 Face score calculation circuit 9 Threshold discrimination processing circuit
10 CPU
23 Threshold calculation circuit

Claims (6)

A solid-state electronic imaging device for imaging a subject and outputting image data representing the subject image;
Target image detection means for detecting a target image portion having a target image quality equal to or higher than a threshold from a subject image represented by image data output from the solid-state electronic imaging device;
First control means for controlling the solid-state electronic image pickup device and the target image detection means so as to repeat imaging by the solid-state electronic image pickup device and detection processing by the target image detection means, and Threshold value changing means for changing a threshold value used for detection processing in the target image detecting means during repetition of imaging based on control;
An imaging apparatus comprising: The threshold changing means is
The threshold value is changed so as to decrease in response to the detection of the target image portion by the target image detection means.
The imaging device according to claim 1. The threshold changing means is
The threshold value is reset to the initial value in response to the target image portion not being detected by the target image detection means.
The imaging device according to claim 1.   The imaging apparatus according to claim 1, further comprising a reset unit that resets the threshold value changed by the threshold value changing unit to an initial value at a constant period.   Second control means for controlling the target image detection means so as to detect the target image from a region around the detected target image part in response to detection of the target image part by the target image detection means; The imaging device according to claim 1, further comprising: A solid-state electronic imaging device images the subject and outputs image data representing the subject image,
A target image detecting means detects a target image portion having a target image quality equal to or greater than a threshold value from a subject image represented by the image data output from the solid-state electronic imaging device;
The control means controls the solid-state electronic imaging device and the target image detection means so as to repeat imaging by the solid-state electronic imaging device and detection processing by the target image detection means, respectively.
A threshold value changing means for changing a threshold value used for detection processing in the target image detecting means during repetition of imaging based on the control of the control means;
Control method of imaging apparatus.

Images