JP2011217229A - Imaging apparatus and display method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an imaging apparatus capable of presenting such an image or a video image as not to give a sense of incompatibility to a user.SOLUTION: An imaging apparatus includes: a face detector 14 for detecting the face of a person included in a subject from an input image; a distance measuring unit 15 for measuring a distance between the face detected by the face detector and the imaging apparatus; a face index-adding unit 16 for making an index for the face detected by the face detector different in accordance with the distance measured by the distance measuring unit and for adding that index at a position of the face in the image; and an image display unit 18 for displaying an image of the face to which the index has been added by the face index-adding unit.

Description

  The present invention relates to an imaging apparatus and a display method for detecting a human face from an image obtained by imaging and displaying an image with an index on the detected face.

  In recent years, in an imaging apparatus such as a digital camera or a digital video camera that images a subject using a CCD or MOS type solid-state imaging device, a person's face included in the subject is automatically captured when a still image or a moving image is captured. An increasing number have face detection functions. In an imaging apparatus having the face detection function, focus control and exposure control are generally performed based on image information in a detected face area (face area).

  In general, an imaging device is often provided with a liquid crystal display device in its body, and an image captured by the imaging element is displayed on the liquid crystal display device. In a digital video camera or digital camera having a face detection function, a face detection frame (see, for example, Patent Document 1) or a face detection mark (see, for example, Patent Document 2) is superimposed on an image displayed on the liquid crystal display device. Is displayed.

JP 2005-286940 A JP 2007-201839 A

  However, when there are a plurality of persons having a difference in distance from the imaging apparatus and the face detection frames of the persons overlap, the face detection frame of the person far from the imaging apparatus (rear) is separated from the imaging apparatus. It is displayed so as to overlap the face detection frame of the person at the near position (front). For example, as shown in FIG. 12, since the face detection frame 73 of the person 71 at a position close to the imaging device and the face detection frame 74 of the person 72 at a position far from the imaging device are displayed independently, There is a portion 75 where the face detection frame 74 at a distant position overlaps the person 71 at a position close to the imaging device. Therefore, the front-rear relationship of the overlapping portion 75 is different from that of the other portions, and the user may feel uncomfortable with the image displayed on the liquid crystal display device of the imaging device.

  In recent years, there has been an increasing interest in still images (three-dimensional images) that can be viewed three-dimensionally by users and moving images (three-dimensional images) that can be viewed three-dimensionally by users. The number of three-dimensional imaging devices capable of photographing the image has increased. In this three-dimensional imaging device, a right-eye image and a left-eye image in consideration of parallax are obtained to obtain a three-dimensional image. The three-dimensional imaging device uses a parallax barrier method. A liquid crystal display device that enables stereoscopic viewing with the naked eye is provided.

  In the case of a three-dimensional image or a three-dimensional image, as shown in FIG. 12, when the object that should be far from the imaging device is displayed so as to overlap the object that is closer to the imaging device, the context of the part is displayed. As a result, the stereoscopic effect is lost, and the user who is viewing the image or video feels uncomfortable, which may cause a great feeling of fatigue.

  The problem to be solved by the present invention is to provide an imaging apparatus and a display method that can present images and videos that do not give the user a sense of incongruity.

  In order to solve the above problems, the present invention measures a face detection unit that detects a human face included in a subject from an input image, and a distance between the face detected by the face detection unit and the imaging device. A face measuring unit, a face index adding unit for changing an index for the face detected by the face detecting unit according to the distance measured by the distance measuring unit, and adding the index to the face position of the image; And an image display unit that displays a face image to which an index is added by the index adding unit.

  The present invention can present an image or video that does not give the user a sense of incongruity by displaying an index on the face by a method according to the distance from the imaging device to the person's face.

1 is a block diagram illustrating a configuration of an imaging apparatus according to Embodiment 1 of the present invention. 5 is a flowchart illustrating the operation of the imaging apparatus according to the first embodiment of the present invention, centering on face detection frame display processing. It is a figure which shows the example when a face detection frame has overlapped in the imaging device which concerns on Example 1 of this invention. It is a figure which shows the example which distinguishes front and back by the thickness of a face detection frame in the imaging device which concerns on Example 1 of this invention. It is a figure which shows the example which distinguishes front and back with the color of a face detection frame in the imaging device which concerns on Example 1 of this invention. It is a block diagram which shows the structure of the imaging device which concerns on Example 2 of this invention. It is a figure which shows the positional relationship of the person's left image and right image at the time of three-dimensional imaging | photography in the imaging device which concerns on Example 2 of this invention. In the imaging device which concerns on Example 2 of this invention, it is a figure which shows the positional relationship of the person and imaging device which were seen from right above drawn from the right image and the left image. In the imaging device according to Example 3 of the present invention, the arrangement of a person a, a person b, and a person c is viewed from above. It is a figure which shows the horizontal axis coordinate of the position of the person in the image image | photographed from the left lens and the right lens in the imaging device which concerns on Example 3 of this invention. 5 is a flowchart illustrating the operation of the imaging apparatus according to the first embodiment of the present invention, centering on face detection frame display processing. It is a figure which shows the example of a display of the face detection frame in the conventional imaging device.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  The imaging apparatus according to the first embodiment of the present invention displays a face detection frame based on a still image or a moving image (hereinafter simply referred to as “image”). Note that the face detection frame is an example of an index, and the “index” of the present invention is not limited to the face detection frame, and an arbitrarily shaped mark, arrow, or the like can be used.

  FIG. 1 is a block diagram illustrating the configuration of the imaging apparatus according to the first embodiment. The imaging apparatus includes a lens 11, an image input unit 12, a memory 13, a face detection unit 14, a distance measurement unit 15, a face frame addition unit 16, an image output unit 17, an image display unit 18, and an external terminal output unit 19. Yes.

  The lens 11 forms an image of a subject on an image sensor (not shown). The image sensor converts an image based on light from a subject formed by a lens into an electrical signal and outputs the electrical signal. The image input unit 12 generates image data for each frame based on the electrical signal output by the image sensor and outputs the image data to the memory 13.

  The memory 13 temporarily stores image data for each frame input from the image input unit 12. The image data stored in the memory 13 is read from the face detection unit 14 and the face frame addition unit 16 as necessary.

  The face detection unit 14 detects the face of a person included in the subject from the image indicated by the image data for each frame read from the memory 13, and calculates the coordinates of the position of the detected face. Note that the face detection unit 14 detects a human face by using a well-known face detection technique for detecting a human face by detecting a skin color portion of the image or by using a pattern recognition technique. The coordinates calculated by the face detection unit 14 are sent to the distance measurement unit 15 as face position coordinate values.

The distance measurement unit 15 calculates the distance from the imaging device to the face of the person indicated by the face position coordinate value sent from the face detection unit 14 using either of the following well-known techniques (1) or (2). Use to measure. In the case of (1), the distance measurement unit 15 acquires the position of the lens 11 when the face detected by the face detection unit 14 is in focus, and calculates the distance to the face based on the position of the lens 11. .
(1) Measured by focusing on a person's face using the autofocus function. (2) Measured using a measuring device such as a laser distance measuring device, GPS, or ultrasonic distance measuring device.

  Data indicating the distance to the person's face measured by the distance measuring unit 15 is sent to the face frame adding unit 16 together with the face position coordinate value sent from the face detecting unit 14.

  The face frame adding unit 16 corresponds to the face index adding unit of the present invention, and is based on the data sent from the distance measuring unit 15 to the portion corresponding to the face position of the image indicated by the image data read from the memory 13. A face detection frame corresponding to the indicated distance is generated and added (synthesized). Image data representing the image with the face detection frame added by the face frame adding unit 16 is sent to the image output unit 17.

  The image output unit 17 generates a display signal for displaying an image based on the image data based on the image data sent from the face frame adding unit 16, and the display signal is displayed on the image display unit 18 and the external terminal output unit 19. Send to. The image display unit 18 includes, for example, an LCD (Liquid Crystal Display) or an organic electroluminescence display, and displays an image on the screen according to a display signal sent from the image output unit 17. The external terminal output unit 19 outputs the display signal sent from the image output unit 17 to an external display device.

  Next, the operation of the imaging apparatus according to the first embodiment of the present invention configured as described above will be described with reference to the flowchart shown in FIG. 2 with a focus on face detection frame display processing.

  First, the imaging device is set to a shooting mode by the user (step S11). As a result, the lens 11 forms an image of the subject on the image sensor, and the image input unit 12 converts the image imaged on the image sensor by the lens 11 into an electrical signal, and image data for one frame. Is sent to the memory 13. The memory 13 temporarily stores image data for one frame sent from the image input unit 12. In this state, the face detection frame display process is started.

  In the face detection frame display process, first, it is checked whether or not a face has been detected (step S12). That is, the face detection unit 14 reads one frame of image data from the memory 13 and determines whether all human faces have been detected from the images indicated by the read image data. At this time, when the face detection unit 14 determines that there is a face of a person that has not been detected yet, the face detection unit 14 detects the face of one person among the faces that have not been detected and calculates the coordinates of the face part. The face position coordinate value, which is data indicating the coordinates, is sent to the distance measuring unit 15. If it is determined that all human faces have been detected in the initial state where no human faces have been detected (when no person is included in the image), the process proceeds to step S12. stand by.

  Next, in step S12, distance measurement (calculation) is performed (step S13). That is, the distance measuring unit 15 calculates the distance from the imaging device indicated by the face position coordinate value sent from the face detecting unit 14 to the human face.

  Next, the face position coordinates and the distance to the face are stored (step S14). That is, the distance measurement unit 15 stores the face position coordinate value sent from the face detection unit 14 in step S12 and data indicating the distance to the human face calculated in step S13. Data indicating the face position coordinate value and the distance stored in the distance measuring unit 15 is read by the face frame adding unit 16. Then, it returns to step S12 and the process mentioned above is repeated.

  In step S12, when it is determined that all faces have been detected by the face detection unit 14, it is recognized that processing has been completed for all faces in the image of one frame, and then a face detection frame is created ( Step S15). That is, the face frame adding unit 16 reads out the image data for one frame from the memory 13, and the face position read out from the distance measuring unit 15 is the face detection frame to be added to the face included in the image indicated by the read image data. It is created based on the coordinate value and data indicating the distance to the person's face. At this time, the face frame adding unit 16 determines the thickness, size, or size of the face detection frame according to the distance from the imaging device to the face, that is, according to the data indicating the distance sent from the distance measuring unit 15. The color may be changed. By changing in such a manner, it is possible to obtain an image or video that does not make the user feel more uncomfortable.

  Next, it is checked whether or not there are overlapping face detection frames (step S16). That is, the face frame adding unit 16 checks whether there is a portion where two or more face detection frames overlap as shown in FIG. 12, for example, from the face position coordinate values read from the distance measuring unit 15.

  If it is determined in step S16 that the face detection frames overlap, the overlapping portion of the rear face detection frames is erased (step S17). That is, the face frame adding unit 16 erases the overlapping portion of the rear face detection frames, for example, as shown in FIG. On the other hand, if it is determined in step S16 that the face frame adding unit 16 has no overlapping face detection frames, the process in step S17 is skipped.

  Next, the face detection frame is synthesized (step S18). That is, the face frame adding unit 16 synthesizes the face detection frame created by the above-described process with the image indicated by the image data for one frame read from the memory 13. Image data representing the image with the face detection frame synthesized by the face frame adding unit 16 is sent to the image output unit 17.

  Next, an image is displayed (step S19). That is, the image output unit 17 generates a display signal based on the image data sent from the face frame adding unit 16 and sends it to the image display unit 18. The image display unit 18 displays an image to which a face detection frame is added as shown in FIG. 3 on the screen in accordance with the display signal sent from the image output unit 17.

  As described above, according to the imaging apparatus according to the first embodiment of the present invention, the distance to all detected faces existing in the image is measured (calculated). It is possible to know the front-rear relationship between the face detection frame 73 of the person 71 and the face detection frame 74 of the person 72 at a position farther from the imaging device (backward) than the person 81. Therefore, as shown in FIG. 3, the face detection frame 73 starts from the intersection point 76 between the front face detection frame 73 and the face detection frame 74 of the rear person 72 located farther from the imaging device than the front person. By generating a face detection frame 74a in which a part of 74 is deleted and adding it to the image, it is possible to display an image or video that does not make the user feel uncomfortable.

  Even when the face detection frames do not overlap with each other, as shown in FIG. 4, the face frame addition unit 16 has the face detection frame 83 of the person 81 at a position close to the imaging apparatus and a position farther from the imaging apparatus than the person 81. The face detection frame 84 of the person 82 may be displayed with a different frame thickness. In this case, the thickness of the face detection frame can be changed in inverse proportion to the distance to the human face. For example, the face frame adding unit 16 adds a face frame using a perspective method in which the face detection frame of a person close to the imaging device is thicker and the face detection frame of a person farther from the imaging device is thinner, so Visually understandable images or videos can be displayed. Furthermore, if it is configured to display the distances 85 and 86 to the person, it is possible to support the determination of the composition of shooting by the user.

  Also, as shown in FIG. 5, the face frame adding unit 16 adds a brighter face frame to a face detection frame corresponding to a person closer to the imaging device, and a face detection frame corresponding to a person farther from the imaging device. A dark face frame may be added. As described above, by adjusting and displaying the brightness of the color of the frame according to the distance to the face of the person, there is an effect that the front-rear relationship of the person can be visually understood as in the perspective method.

  As described above, the face frame adding unit 16 changes the face detection frame (index) for the face detected by the face detecting unit according to the distance from the imaging device measured by the distance measuring unit 15 to the human face. Therefore, even if a face detection frame is added, it is possible to present an image or video that does not give the user a sense of incongruity.

  FIG. 6 is a block diagram illustrating a configuration of the imaging apparatus according to the second embodiment of the present invention. This imaging device includes a right lens 21, a left lens 22, a first image input unit 23, a second image input unit 24, a first memory 25, a second memory 26, a first face detection unit 27, and a second face detection unit 28. , A distance calculation unit 29, a first face frame addition unit 30, a second face frame addition unit 31, an image output unit 32, an image display unit 33, and an external terminal output unit 34.

  The right lens 21 forms an image of a subject on a first image sensor (not shown). The first image sensor converts an image based on the light from the subject imaged by the right lens 21 into an electrical signal and inputs it to the first image input unit 23. The first image input unit 23 performs the first imaging. Based on the electrical signal input from the element, image data for each frame is generated and sent to the first memory 25.

  The left lens 22 forms an image of the subject on a second image sensor (not shown). The second image sensor converts an image based on the light from the subject imaged by the left lens 22 into an electrical signal and inputs it to the second image input unit 24. The second image input unit 24 performs the second imaging. Based on the electrical signal input from the element, image data for each frame is generated and sent to the second memory 26.

  The right lens 21 and the left lens 22 are arranged with a predetermined interval, and it is desirable that the interval is approximately the same as the interval between the right eye and the left eye of a general person. In addition, it is desirable that the directions of the center line of the right lens 21 and the center line of the left lens 22 can be changed. The center line and the left lens 22 are positioned so that the center line substantially intersects.

  The first memory 25 temporarily stores image data for each frame sent from the first image input unit 23. The image data stored in the first memory 25 is read from the first face detection unit 27 and the first face frame addition unit 30 as necessary.

  The second memory 26 temporarily stores image data for each frame sent from the second image input unit 24. The image data stored in the second memory 26 is read from the second face detection unit 28 and the second face frame addition unit 31 as necessary.

  The first face detection unit 27 detects the face of a person from the image indicated by the image data for each frame read from the first memory 25, and calculates the coordinates of the position of the detected face. The coordinates calculated by the first face detection unit 27 are sent to the distance calculation unit 29 as face position coordinate values, which are data indicating the coordinates of the detected face position.

  The second face detection unit 28 detects the face of a person from the image indicated by the image data for each frame read from the second memory 26, and calculates the coordinates of the position of the detected face. The second face detection unit 28 sends a face position coordinate value, which is data indicating the coordinates of the detected face position, to the distance calculation unit 29.

  The distance calculation unit 29 uses the face position coordinate value sent from the first face detection unit 27 and the face position coordinate value sent from the second face detection unit 28, to the person's face from the imaging device. The distance is obtained by calculation based on trigonometry (details will be described later). The data indicating the distance calculated by the distance calculation unit 29 is sent to the first face frame adding unit 30 together with the face position coordinate value sent from the first face detection unit 27 and the second face detection unit 28. Is sent to the second face frame adding unit 31 together with the face position coordinate value sent from.

  The first face frame addition unit 30 corresponds to the face index addition unit of the present invention, and a distance calculation unit is provided in a portion corresponding to the face position of the image indicated by the image data for one frame read from the first memory 25. A face detection frame corresponding to the distance indicated by the data sent from 29 is generated and added (synthesized). Image data representing the image with the face detection frame added by the first face frame adding unit 30 is sent to the image output unit 32.

  The second face frame addition unit 31 corresponds to the face index addition unit of the present invention, and a distance calculation unit is provided in a portion corresponding to the face position of the image indicated by the image data for one frame read from the second memory 26. A face frame corresponding to the distance indicated by the data sent from 29 is generated and added (synthesized). Image data representing the image with the face frame added by the second face frame adding unit 31 is sent to the image output unit 32.

  The image output unit 17 generates a display signal based on at least one of the image data sent from the first face frame adding unit 30 and the image data sent from the second face frame adding unit 31 to display an image. To the unit 33 and the external terminal output unit 34. The image display unit 33 displays an image on the screen according to a display signal sent from the image output unit 32. The external terminal signal unit 34 outputs a display signal sent from the image output unit 32 to an external display device.

  Next, a method for calculating the distance from the imaging device to the face by calculation based on the trigonometry performed by the distance calculation unit 29 of the present embodiment will be described with reference to FIGS. 7 and 8.

  FIG. 7A shows a right image obtained from the right lens 21, and FIG. 7B shows a left image obtained from the left lens 22, where A is the center point of the detected human face area. To do. Let the vertical center line of the right image be line C, the vertical center line of the left image be line E, the right end of the right image be line D, and the right end of the left image be line F. The intersection of a line drawn from the point A of the right image and the line C is K, the intersection of the line D is M, and the intersection of the line drawn from the point A of the left image and the line E is N Let P be the intersection with line F.

  The distance calculation unit 29 calculates the ratio between the length of the line segment AK and the length of the line segment AM in the right-right image based on the coordinates of the line C and the face position coordinate value sent from the first face detection unit 27. “R1: R2” is obtained, and based on the coordinates of the line E and the face position coordinate value sent from the second face detection unit 28, the length of the line segment AN and the length of the line segment AP in the left image are calculated. The ratio “R3: R4” is determined.

  Next, a description of FIG. FIG. 8 shows the relationship between the person and the imaging device viewed from directly above based on the right image shown in FIG. 7A and the left image shown in FIG. 7B. In FIG. 8, among the symbols attached to the lines and points, those having the same meaning as the symbols used in FIG. 7 are the same as those used in FIG. In FIG. 8, the point I represents the center point of the right lens 21 of the imaging device G, and the point H represents the center point of the left lens 22. In the imaging apparatus of the present embodiment, a three-dimensional image is created by adjusting the angle (convergence angle) formed by the right lens 21 and the left lens 22. Let the convergence angle be α, and let B be the point (convergence point) where the center line of the right lens 21 and the center line of the left lens 22 intersect. Further, the interval L1 between the right lens 21 and the left lens 22 is generally set to be equal to the interval between the left and right eyes of a human, and is set to about 60 mm, for example. The angle (right photographing limit angle) β from the center line of the right lens 21 and the center line of the left lens 22 to the right end is determined by the performance of the lens. Also, let Q be the intersection of a line J passing through the points I and H and a line orthogonal to the line J and passing through the point A. Furthermore, the length of the line segment IQ is L2, and the length of the line segment AQ is L3. The distance measuring unit 29 according to the present embodiment obtains the distance from the imaging device to the person's face by obtaining the length of L3.

  Next, a method for obtaining L3 will be described in detail.

From the ratio of the length R1 from the center of the right image to A and the length R2 from the right end of the right image to A shown in FIG. 7 and the relationship between the right triangle IKM and the right triangle IKA, R1: R1 + R2 = tan (δ) : Tan (β)
From the relationship between the length R3 from the center of the left image to A and the length R4 from the right end of the left image to A, and the relationship between the right triangle HNF and the right triangle HNA, R3: R3 + R4 = tan (ε): tan (Β)
Thus, the angle δ of I of the right triangle ANI and the angle ε of H of the right triangle AKH can be obtained.

Next, the low angle γ of the isosceles triangle BHI, the angle θ of H of the right triangle AQH, and the angle λ of I of the right triangle AIQ are γ = (180−α) / 2.
λ = 180− (γ + δ)
θ = γ−ε
It is calculated by. Therefore, from the sides and angles of the right triangle AQH and the right triangle AIQ, tan (θ) = L3 / (L1 + L2)
tan (λ) = L3 / L2
From these two formulas, the distance L3 from the three-dimensional imaging device to the human face can be obtained by the following formula.
L3 = tan (λ) × tan (θ) × L1 / (tan (λ) −tan (θ))

  The distance calculation unit 29 obtains L3 as described above based on the coordinates of each point and the face position coordinate values sent from the first face detection unit 27 and the second face detection unit 28. The distance from the imaging device to the person's face is obtained. Since the imaging apparatus of the present embodiment obtains the distance from the imaging apparatus to the person's face as described above, the imaging apparatus to the person's face can be obtained without using an autofocus function or using various distance measuring devices. Can be obtained.

  Even in an imaging device that can capture a 3D image or a 3D image, the distance from the imaging device to a person's face is measured using an autofocus function, or various distance measuring devices such as a laser distance meter are used. The distance from the imaging device to the person's face may be measured.

  In an imaging apparatus capable of capturing a 3D image or a 3D image, the front-rear relationship of a person can be recognized from the parallax between the right image and the left image without measuring the distance to the person's face. The imaging apparatus according to Embodiment 3 of the present invention displays a face detection frame based on the parallax between the right image and the left image.

  The configuration of the imaging apparatus according to the third embodiment is substantially the same as the configuration of the imaging apparatus according to the second embodiment illustrated in FIG. However, the distance calculation unit 29 of this embodiment functions as a parallax calculation unit. In the following, the operation of the distance calculation unit 29 that is different from the second embodiment will be mainly described.

  FIG. 9 is a view of the arrangement of the persons a, b, and c when the center line of the right lens 21 and the center line of the left lens 22 intersect at a predetermined convergence angle as viewed from above. The person a exists at a position where the ratio of the distance from the left end d of the region included in the left image photographed by the left lens 22 to the center line e passing through the center of the left image is 13: 7. When the person a is photographed with the right lens 21, the ratio of the distance from the left end j of the region included in the left image to the center line k is 6:14. Similarly, the positional relationship between the person b and the person c can be expressed by the following ratio together with the person a. Note that these ratios change according to the point (convergence point) where the center line of the right lens 21 and the center line of the left lens 22 intersect, so that if the orientation of the right lens 21 and the left lens 22 can be changed, It is desirable that the distance calculation unit 29 of the embodiment obtains information on the lens orientation from a lens control unit (not shown) and calculates the following ratio according to the lens orientation.

Person a Left image da: ae = 13: 7
Right image j−a: a−k = 6: 14
Person b Left image fb: bg = 8: 12
Right image lb: bm = 11: 9
Person c Left image hc: ci = 6: 14
Right image nc: co = 12: 8

  FIG. 10A is an image (left image) taken with the left lens 22, FIG. 10A is an image (right image) taken with the right lens 21, and the person a, person b, and person c are: The image is taken at the position shown in FIG. When the horizontal axis coordinate at the left end of the image is 0, the horizontal axis coordinate at the center is 100, and the horizontal axis coordinate at the right end is 200, each horizontal axis is calculated from the ratio of the image positions of the person a, person b, and person c. The coordinates are obtained as follows.

Person a Left image 65
Right image 30
Person b Left image 140
Right image 155
Person c Left image 130
Right image 160

Here, in each of the persons a to c, when the difference between the coordinates of the right image from the coordinates of the left image is obtained,
Person a 65-30 = + 25
Person b 140-155 = -15
Person c 130-160 = -30
Thus, it can be seen that the larger difference value is ahead. Further, the difference value of the coordinates of the person in front of the point (convergence point) where the center line of the right lens 21 and the center line of the left lens 22 intersect is positive, and the difference value of the rear is negative.

  By using this principle, the distance calculation unit 29 of the present embodiment obtains the front-rear relationship of each person from the horizontal axis coordinates of the person in the left and right images in the case of a three-dimensional image or a three-dimensional image. As a result, the thickness, size, or color of the person's face detection frame can be changed according to the context of each person.

  Next, the operation of the imaging apparatus according to the third embodiment of the present invention configured as described above will be described with reference to the flowchart shown in FIG. 11 focusing on the face detection frame display processing. In the flowchart shown in FIG. 11, the same reference numerals used in FIG. 2 are used to execute the same or equivalent processing as the face detection frame display processing of the imaging apparatus according to the first embodiment shown in the flowchart of FIG. The description will be simplified with reference numerals.

  First, the imaging device is set to a shooting mode by the user (step S11). Thereby, the face detection frame display process is started. In the face detection frame display process, first, it is determined whether all human faces included in the right image have been detected (step S21). That is, the first face detection unit 27 reads image data for one frame from the first memory 25 and checks whether all human faces have been detected from the right image indicated by the read image data.

  If it is determined in step S21 that there is a human face that has not yet been detected, then the face coordinates of the right image are calculated (step S22). That is, the first face detection unit 27 detects one person out of the undetected faces, calculates the horizontal coordinate of the face, and sends it to the distance calculation unit 29. If it is determined that all human faces have been detected in the initial state in which no human faces have been detected (if no right person is included in the right image), the process proceeds to step S21. And wait.

  Next, it is determined whether or not all human faces included in the left image have been detected (step S23). That is, the second face detection unit 28 reads one frame of image data from the second memory 26 and checks whether all human faces have been detected from the left image indicated by the read image data.

  If it is determined in step S23 that there is a human face that has not yet been detected, then the face coordinates of the left image are calculated (step S24). That is, the second face detection unit 28 selects the most recently detected face of the person detected by the first face detection unit 27 (at this time, the face of the person detected last by the first face detection unit 27). The face of the person in the corresponding left image is detected, the horizontal axis coordinate of the face is calculated, and sent to the distance calculation unit 29.

  The second face detection unit determines whether or not the face recently detected by the first face detection unit 27 and the face of each person in the left image are the same by using a well-known pattern matching technique. It is desirable to calculate the horizontal coordinate of the face determined to be and send the data indicating the horizontal coordinate value to the distance calculation unit 29. However, the second face detection unit detects the face recently detected by the first face detection unit 27. The coordinate value of the face corresponding to the coordinate value closest to the coordinate value may be sent to the distance calculation unit 29.

  If the face of the person in the left image corresponding to the face recently detected by the first face detection unit 27 cannot be detected, the face may not be included in the left image due to the influence of parallax. It is desirable not to display the face detection frame for the face.

  Returning to the description of FIG. 11, the difference between the left and right coordinates is then stored (step S25). That is, the distance calculation unit 29 corresponds to the horizontal axis coordinate of the person's face sent from the first face detection unit 27 in step S22 and the second face detection unit 28 in step S24 corresponding to the person's face. The difference from the horizontal axis coordinate of the person's face that has been obtained is calculated and stored. The difference between the horizontal axis coordinate of the person's face in the right image and the horizontal axis coordinate of the left image of the person's face is a value corresponding to the parallax. Then, it returns to step S21 and the process mentioned above is repeated.

  When it is determined in step S21 that no face has been detected from the right image or in step S23 that no face has been detected from the left image, the processing for all the faces in the image of one frame has been completed. Then, a face detection frame is created (step S26). That is, the first face frame adding unit 30 reads image data for one frame from the first memory 25 and creates a face detection frame to be added to the face included in the image indicated by the read image data. At this time, the first face frame adding unit 30 changes the thickness, size, or color of the face detection frame according to the parallax, that is, according to the data indicating the parallax sent from the distance calculation unit 29.

  In step S26, the second face frame adding unit 31 reads image data for one frame from the second memory 26, and creates a face detection frame to be added to the face included in the image indicated by the read image data. You may make it do. At this time, the second face frame adding unit 31 changes the thickness, size, or color of the face detection frame according to the parallax, that is, according to the data indicating the parallax sent from the distance calculation unit 29.

  Next, it is checked whether or not there are overlapping face detection frames (step S16). That is, the first face frame adding unit 30 checks whether two or more face detection frames are overlapped from the face position coordinate values sent from the distance calculation unit 29. In addition, the process of step S16 can also be configured to be performed by the second face frame adding unit 31.

  If it is determined in step S16 that the face detection frames overlap, the overlapping portion of the rear face detection frames is erased (step S17). That is, the first face frame adding unit 30 deletes the overlapping portion of the rear face detection frame. In addition, the process of step S17 can also be configured to be performed by the second face frame adding unit 31. On the other hand, if it is determined in step S16 that the face detection frames do not overlap, the process of step S17 is skipped.

  Next, the face detection frame is synthesized (step S18). That is, the first face frame adding unit 30 combines all the face detection frames created by the above-described process with the image indicated by the image data for one frame read from the first memory 25, and combines the face detection frames. Image data representing the processed image is sent to the image output unit 32. In step S18, the second face frame adding unit 31 synthesizes all the face detection frames created by the above-described process with the image indicated by the image data for one frame read from the second memory 26, Image data representing an image obtained by combining the face detection frames may be sent to the image output unit 32.

  Next, an image is displayed (step S19). As a result, an image with a face detection frame added as shown in FIG. 3 is displayed on the screen of the image display unit 33.

  As described above, the face frame adding unit according to the present exemplary embodiment has a face detection frame (index) for the face detected by the face detecting unit according to the parallax between the right image and the left image measured by the distance calculating unit 29. Therefore, even if a face detection frame is added, an image or video that does not give the user a sense of incongruity can be presented.

  The present invention is not limited to the embodiments described above, and various modifications can be made without departing from the scope of the present invention.

  For example, in the second and third embodiments, the configuration has two memories, but one memory may have the functions of both the first memory 25 and the second memory 26. Further, in the second and third embodiments, the configuration includes two image input units. However, one image input unit has functions of both the first image input unit 23 and the second image input unit 24. Also good. In the second and third embodiments, the configuration includes two face detection units. However, one face detection unit has functions of both the first face detection unit 27 and the second face detection unit 28. Also good. Furthermore, in Example 2 and Example 3, it was set as the structure which has two face frame addition parts, but one face frame addition part has the function of both the 1st face frame addition part 30 and the 2nd face frame addition part 31. You may make it have. In each embodiment, the face position coordinates are, for example, the coordinates of the center of the area where the face is detected.

  The present invention can be used for a digital camera, a digital video camera, and the like.

DESCRIPTION OF SYMBOLS 11 Lens 12 Image input part 13 Memory 14 Face detection part 15 Distance measurement part 16 Face frame addition part 17 Image output part 18 Image display part 19 External terminal output part

Claims (6)

In the imaging device,
A face detection unit for detecting the face of a person included in the subject from the input image;
A distance measuring unit that measures a distance between the face detected by the face detecting unit and the imaging device;
A face index adding unit that varies an index for the face detected by the face detecting unit according to the distance measured by the distance measuring unit, and adds the index to the position of the face of the image;
An image display unit for displaying an image of the face to which an index is added by the face index adding unit;
An imaging apparatus comprising:   The face index adding unit changes the thickness of the index frame corresponding to the face, the size of the index, or the color of the index according to the distance to the face measured by the distance measuring unit. The imaging apparatus according to claim 1.   The face index adding unit, when a plurality of faces is detected by the face detection unit, based on the distance to the plurality of faces measured by the distance measurement unit, the index corresponding to a predetermined face, The imaging apparatus according to claim 1, wherein a portion overlapping an index corresponding to a face closer to the imaging apparatus than the predetermined face is erased.   The imaging apparatus according to claim 1, wherein the distance measurement unit measures the distance to the face by focusing on the face detected by the face detection unit. In a display method for displaying an image on an image display unit of an imaging apparatus,
Detect human faces from input images,
Measure the distance between the detected face and the imaging device,
According to the measured distance, the index for the detected face is changed, the index is added to the position of the face of the image,
A display method comprising displaying an image of a face to which the index is added. In an imaging device that captures a stereoscopically visible still image or a stereoscopically visible moving image,
A first face detecting unit for detecting a human face from the input first image;
A second face detection unit for detecting the face of the person from the input second image;
A parallax calculation unit that calculates parallax between the face image detected by the first face detection unit and the face image detected by the second face detection unit;
A face that changes an index for the face according to the parallax calculated by the parallax calculation unit, and adds the index to the position of the face of at least one of the first image and the second image. An index adding unit;
An image display unit for displaying an image of the face to which an index is added by the face index adding unit;
An imaging apparatus comprising:

Images