JP2001177740A - Portraiture photographing method and portraiture device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a portraiture pickup method and a portraiture photographing device that can detect the head position of a person to be photographed with high accuracy even when the person is not a black-haired person and arrange the face posion of the person in a photographed image in an ideal state. SOLUTION: The portraiture photographing device, that photographs the upper half of the body including at least the face of a person to be photographed for the purpose of forming a certificate photograph that is stuck to an identification card and various licenses or the like, photographs the upper half of the body including at least the face of the person on a blue background, detects the head position of the person on the basis of the luminance of B and R signals of the blue background from the photographed image, segments the upper half of the person from the photographed image on the basis of the detected head position of the person, and prints out the segmented upper half of the person as a photographed image.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a person image for photographing an upper body including at least the face of a person to be photographed, for the purpose of producing a photograph for identification to be attached to an identification card or various licenses. The present invention relates to a photographing method and a person image photographing device.

[0002]

2. Description of the Related Art In general, in this type of person image photographing apparatus, it is necessary to take care that the size and position of the face of a person to be photographed have a fixed ratio (ideal state) in a photographed image. . Conventionally, for example, blue (hereinafter, referred to as a blue background) is used as a background of a subject, and a large area is photographed in advance in consideration of variations in the height of the subject,
The head position is detected from the top position and the left and right temporal positions of the subject based on the blue component luminance of the blue background (hereinafter, referred to as B luminance), and the face of the subject is detected based on the detected head position. Arrange so that the position is ideal in the captured image,
A method of cutting out the upper body image of a subject from a captured image has been used.

[0003]

When the subject is assumed to be a Japanese with black hair, the B brightness at the head position (black hair portion) of the subject is lower than the B brightness of the blue background. It is possible to detect the head position with high accuracy.

[0004] However, due to the recent increase in the foreign population and the aging of the population in Japan, it is quite possible that the subject may not have black hair. For example, when the subject has white hair or headless hair, the B luminance at the head position becomes high, so that the head position cannot be detected with high accuracy based on the blue luminance B luminance reference.

Accordingly, the present invention can accurately detect the position of the head of a subject even when the subject does not have black hair, and the position of the face of the subject becomes an ideal state in a photographed image. It is an object of the present invention to provide a person image photographing method and a person image photographing device which can be arranged as described above.

[0006]

A person image photographing method according to the present invention includes a first step of photographing an image including at least a face of a person to be photographed with a background of a specific color, and photographing is performed by the first step. A second step of detecting a position of the subject's head based on a color component luminance indicating a high luminance and a color component luminance indicating a low luminance with respect to the specific color which is the background of the subject from the captured image And a third step of cutting out an image of a predetermined region of the subject from the image captured in the first step based on the head position of the subject detected in the second step. A fourth step of outputting, as a photographed image, the image of the predetermined region of the subject, which is cut out in the third step.

Further, in the person image photographing method of the present invention, the specific color of the background is blue, the color component luminance indicating high luminance with respect to the specific color is blue component luminance, and The color component luminance indicating low luminance is a red component luminance.

Further, the person image photographing apparatus of the present invention comprises a photographing means for photographing an image including at least a face of the photographed person with a specific color as a background, and an image photographed by the photographing means. Head position detecting means for detecting a head position of the subject based on a color component luminance indicating high luminance and a color component luminance indicating low luminance with respect to a specific color as a background of the subject; Image extracting means for extracting an image of a predetermined region of the subject from an image taken by the photographing means based on the head position of the subject detected by the means; Output means for outputting the output image of the subject in a predetermined area as a captured image.

Further, in the person image photographing apparatus of the present invention, the specific color of the background is blue, a color component luminance indicating high luminance with respect to the specific color is a blue component luminance, and The color component luminance indicating low luminance is a red component luminance.

According to the present invention, for example, blue (blue background) is used as the background of the subject, and the head position of the subject is detected based on the blue component luminance and the red component luminance of blue. The upper body image of the subject is cut out based on the head position of the subject so that the position of the face of the subject is in an ideal state. The position of the head of the subject can be detected with high accuracy, and the position of the face of the subject can be arranged so as to be in an ideal state in the captured image.

[0011]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 schematically shows an external configuration of a person image photographing apparatus according to the present embodiment. This person image photographing apparatus includes an illuminator 2 for illuminating a person 1 to be photographed, a CCD video camera 3 as photographing means for photographing an upper body image including at least the face of the person 1 to be photographed, a photographing state and a photographer ( A display (monitor display) 5 for displaying operation information of the operator 4, processing of an input image from the camera 3 in accordance with an operation instruction by the photographer 4, processing of the display 5 and a built-in storage unit, etc. Control table (control unit)
6, a chair 7 on which the subject 1 is seated at the time of shooting, and
It is composed of a background plate 8 that becomes the background of the subject 1 during shooting. Here, it is assumed that the color of the background plate 8 is set to, for example, blue.

FIG. 2 is a block diagram showing the overall configuration of the person image photographing apparatus shown in FIG. That is, a video capture unit 11 that converts an analog signal (input image) from the camera 3 into a digital signal in real time and transfers the digital signal to a video memory, a main memory, or the like, performs image data of the video capture unit 11, and performs other drawing processing. And a CPU (Central Processing Unit) for performing various arithmetic processing and various controls on image data and others, and temporarily storing image data and arithmetic results. Main memory for storing, CPU unit 13 having an interface with various peripheral devices, external bus control unit 14 for controlling an external bus (for example, SCSI, etc.) for connecting various peripheral devices, various OSs and applications, control data, Hard disk device for storing image data, etc. A mass storage device 15, a reader / writer unit 17 for reading / writing data from / to a portable storage medium (for example, a magneto-optical disk) 16 for storing output data of the control console 6, and an operator (photographer) 4, a keyboard 18 and a mouse 19 as input devices, an image printing device 20 as an output unit that prints out a captured face image and the like, for example, and other various devices (image printing device and image Network adapter (L) for performing mutual communication with a filing device, etc.
22).

FIG. 3 is a conceptual diagram showing a head search method used when detecting the top position of the subject 1.

Hereinafter, the processing operation of the present apparatus will be described with reference to the flowcharts shown in FIGS. 4 and 5 and FIG. The processing described below is mainly performed by using the CP in the CPU unit 13.
It is executed under the control of U.

First, the detection of the crown position will be described.

In step S1, the video capture unit 1
An input image 31 from the camera 3 obtained through the
Reference, hereinafter also referred to as a photographed image).
3 is temporarily stored in the main memory. Then, based on the input image 31 in the main memory, a total of four points (for example, a,
b, c, d) indicating a high luminance of a color component, in this case a blue component luminance (hereinafter, referred to as B luminance), and a color component luminance indicating a low luminance, in this case, a red component luminance (hereinafter, referred to as R) Brightness) and the four points a, b,
The respective average values of the B luminance and the R luminance of c and d are calculated, and the calculated average values are used as reference values bstd1 and rstd1 for the blue background (blue which is the color of the background plate 8).
And Here, the processing in step S1 corresponds to the first luminance calculating means in the present invention.

Next, in steps S2 and S3, in the range from the upper end line of the photographed image 31 to a predetermined line YR (initial detection range), scanning is sequentially performed in the horizontal direction from the upper end to obtain the scanning line ( Search line)
The top position is detected based on the B luminance average value by the binary search method described below. Here, this step S2,
The processing in S3 corresponds to the first parietal position detecting means in the present invention.

1. In a certain range of the horizontal scanning line (for example, between the X start line and the X end line shown in FIG. 3), the B luminance is checked at predetermined pixels from the left end of the photographed image 31 to check in step S1. The number of pixels of B luminance not within the calculated B luminance average value bstd1 ± α (α is an error) is counted.

2. A scan line in which the count value in 1 exceeds a preset reference value bnmax1 is defined as a scan line having a head (third search line, n-th search line in the example of FIG. 3).

3. If there is a head in the scan line checked in the above 2, check the scan line located at half the distance of the detection range above the scan line, and if there is no head in the scan line, The scanning line located at a distance half the detection range below the scanning line is determined. In this manner, the head position is narrowed down (detected) by repeatedly performing the line survey with the detection range being halved.

When the head position is determined based on the B luminance as described above, the process proceeds to step S4, and as a noise detection process, a scan in which the head is present below the scan line in which the head position is determined is performed. It is confirmed that the number of lines is equal to or more than a predetermined number of lines YN.

In steps S2 and S3, if the top position cannot be detected based on the B luminance,
Proceeding to S6, in the range (initial detection range) from the upper end line of the photographed image 31 to the predetermined line YR, by sequentially scanning in the horizontal direction from the upper end, the scan line (search line) is moved to step S2. 2 similar to S3
The top position is detected by the minute search method based on the R luminance average value. However, the reference value of R luminance is rstd1 ± β
(Β is an error), and the maximum count is rnmax1. Here, the processing of steps S5 and S6 corresponds to the second parietal position detecting means in the present invention.

When the top position is determined based on the R luminance as described above, the process proceeds to step S4, and a noise detection process is performed. When the crown position is not determined based on the R luminance,
Proceeding to step S22, error processing is performed, and the photographing processing ends. Here, the processing in step S22 corresponds to the error processing means in the present invention.

The error processing in step S22 means, for example, that the contents of the error are stored in a main memory in the CPU unit 13 so that they can be referred to later, and the details of the error are displayed on the display unit 5. To the photographer 4.

Next, detection of the left and right head positions will be described.

First, the left head position is detected.

In step S7, based on the photographed image 31 stored in the main memory in the CPU section 13, each of the two left and right ends of the background image portion near the top of the head of the image detected as described above. A total of four color component luminances indicating high luminance, in this case, blue component luminance (hereinafter, referred to as B luminance) and color component luminance indicating low luminance, in this case, red component luminance (hereinafter, R luminance) ) And calculate the average values of the B luminance and the R luminance of the four points, respectively, and calculate the calculated average value as a reference value bstd for a blue background (blue which is the color of the background plate 8).
2, rstd2. Here, the processing in step S7 corresponds to the second luminance calculating means in the present invention.

Next, in steps S8 and S9, in the range from the left end line of the photographed image 31 to a predetermined line XR1 (initial detection range), scanning is sequentially performed in the vertical direction from the left end to obtain the scanning line ( For the search line), the left head side position is detected based on the B luminance average value by the binary search method described below. Here, the processing of steps S8 and S9 corresponds to the first head side position detecting means in the present invention.

1. In a certain range of the vertical scanning line (for example, between the top line and the Y end line shown in FIG. 3), the B luminance is determined at predetermined pixels from the upper end of the photographed image 31 to be obtained in step S7. B which is not within the B luminance average value bstd2 ± α (α is an error)
The number of pixels of luminance is counted.

2. A scan line in which the count value in 1 exceeds a preset reference value bnmax2 is defined as a scan line having a head.

3. If there is a head in the scan line examined in the above 2, check the scan line located at a distance of half the detection range in the left direction from that scan line, and if there is no head in that scan line, The scanning line located half the distance in the rightward detection range from the scanning line is searched. In this manner, the left head side position is narrowed down (detected) by repeatedly performing the line inspection with the detection range being halved.

When the left head position is determined on the basis of the B luminance in this way, the process proceeds to step S10, and the noise detection processing is performed in the right direction with respect to the scan line whose left head position is determined. It is confirmed that the number of scan lines in which there is a number is equal to or more than a predetermined number of lines XN1.

In steps S8 and S9, if the left head position cannot be detected on the basis of the B luminance, step S1
1, the process proceeds to S12, in a range from the left end line of the captured image 31 to a predetermined line XR1 (initial detection range),
By sequentially scanning in the vertical direction from the left end, the left head position is detected for the scan line (search line) by the binary search method similar to steps S8 and S9 based on the R luminance average value. . However, the reference value of R luminance is rstd
2 ± β (β is the error), the maximum count number is rnMax2
And Here, the processing of steps S11 and S12 corresponds to the second head-side position detecting means in the present invention.

When the left head position is determined on the basis of the R luminance as described above, the process proceeds to step S10, and a noise detection process is performed. If the left temporal position is not determined based on the R luminance, the process proceeds to step S22, where error processing is performed, and
The photographing process ends.

Next, the right head position is detected.

At steps S13 and S14, the photographed image 3
1 in the range from the right end line to the predetermined line XR2 (initial detection range), by sequentially scanning vertically from the right end, the scan line (search line)
The right head position is detected based on the B luminance average value by the binary search method described below. Here, this step S1
Steps S3 and S14 correspond to the first head-side position detecting means in the present invention.

1. In a certain range of the vertical scanning line (for example, between the top line and the Y end line shown in FIG. 3), the B luminance is determined at predetermined pixels from the upper end of the photographed image 31 to be obtained in step S7. B which is not within the B luminance average value bstd2 ± α (α is an error)
The number of pixels of luminance is counted.

2. A scan line in which the count value in 1 exceeds a preset reference value bnmax2 is defined as a scan line having a head.

3. If there is a head in the scan line examined in the above 2, check the scan line located at a distance of half the detection range in the right direction from the scan line. If no head exists in the scan line, The scanning line located at a half distance of the detection range in the left direction from the scanning line is searched. In this manner, the right head side position is narrowed down (detected) by repeatedly performing the line inspection with the detection range being halved.

When the right head position is determined on the basis of the B luminance in this way, the process proceeds to step S15, and the noise detection processing is performed in the left direction from the scan line in which the right head position is determined. It is confirmed that the number of scan lines in which there is a number is equal to or more than a predetermined number of lines XN1.

In steps S13 and S14, if the right position cannot be detected based on the B luminance,
The process proceeds to S17, and in the range from the right end line of the captured image 31 to the predetermined line XR2 (initial detection range), the scanning is sequentially performed in the vertical direction from the right end. S13, S
By the same binary search method as in 14, the right head position is detected based on the R luminance average value. Here, the reference value of R luminance is rstd2 ± β (β is an error), and the maximum count is rnd.
max2. Here, this step S16, S17
Corresponds to the second head-side position detecting means in the present invention.

When the right head position is determined on the basis of the R luminance as described above, the process proceeds to step S15, and a noise detection process is performed. If the right head position is not determined based on the R luminance, the process proceeds to step S22, where error processing is performed, and
The photographing process ends.

For convenience of explanation, it has been described that the top position is detected and then the left and right head positions are detected. However, the top position detection and the left and right head positions are actually performed in parallel. ing.

When the detection of the parietal position and the left and right head side positions is completed, the process proceeds to step S18, where the center position of the detected left and right head side positions is calculated and set as the face center position CC. Here, the processing in step S18 corresponds to the face center position calculating means in the present invention.

Next, in step S19, it is checked whether the head position and the face center position CC detected earlier are within a preset reference range. As a result of this check, if it is not within the reference range, step S22
Then, error processing is performed, and the photographing processing ends.
Here, the processing in step S19 corresponds to the determination means in the present invention.

As a result of the above check, if it is within the reference range, the process proceeds to step S20, where the photographing stored in the main memory in the CPU unit 13 is performed based on the top position and the left and right temporal positions detected earlier. An upper body image of the subject 1 is cut out from the image 31. An example of the extracted upper body image is indicated by reference numeral 32 in FIG. Here, the process of step S20 corresponds to the upper body extracting means in the present invention.

Next, in step S21, the cut-out upper body image 32 is converted for output, and together with other personal information of the subject 1 and the image printing apparatus connected to the CPU 13 according to the purpose. 20 or an image printing device (not shown) connected to the network 21 from the network adapter 22 for printing out on a recording medium (paper, card, etc.) or as an image storage unit connected to the network 21 To an image filing device (not shown), and further, by using a main memory or a large-capacity storage device 15 or a portable storage medium 16 in the CPU section 13 as an image storage means, It is stored (stored and output). Thus, all the photographing processes for one photographed person are completed.

Whether the photographed face image is printed out or saved may be selected depending on the purpose, and the method of outputting the face image is arbitrary.

With the head position detection algorithm described above, even when the subject 1 does not have black hair,
The head position of the subject can be detected with high accuracy. As an example, the RGB values of the black hair, the white hair, the headless hair, and the head position of the subject are as shown in Table 1 below.

[0051]

[Table 1]

As is clear from Table 1, since the brightness of the black hair is much different from the brightness of the blue background, the head position can be accurately detected only by using the brightness B reference.
In addition, white hair, hairless hair, B brightness is blue background B
Since the luminance is almost the same, it cannot be detected on the basis of the B luminance. However, since the R luminance is far from the R luminance of the blue background, it can be seen that the head position can be accurately detected on the basis of the R luminance.

In the above embodiment, the case where the blue back is used as the background of the subject and the head position of the subject is detected based on the B luminance and the R luminance of the blue back has been described. The invention is not limited to this. For example, another specific color such as red or green may be used as the background of the subject. In this case, the head position of the subject is detected based on the color component luminance indicating high luminance and the color component luminance indicating low luminance with respect to the specific color which is the background of the subject.

[0054]

As described above in detail, according to the present invention, even if the subject is not black hair, the position of the head of the subject can be accurately detected, and the position of the face of the subject can be detected. It is possible to provide a person image photographing method and a person image photographing apparatus which can be arranged in an ideal state in a photographed image.

[Brief description of the drawings]

FIG. 1 is a configuration diagram schematically showing an external configuration of a person image photographing apparatus according to an embodiment of the present invention.

FIG. 2 is a block diagram showing an overall configuration of the person image photographing apparatus shown in FIG.

FIG. 3 is a conceptual diagram showing a head search method used when detecting a top position of a subject.

FIG. 4 is a flowchart illustrating a processing operation.

FIG. 5 is a flowchart illustrating a processing operation.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Subject 2 ... Illumination device 3 ... Video camera (photographing means) 4 ... Photographer (operator) 5 ... Display (monitor display) 6 ... Control stand (control part) 11 ... Video capture section 12 Video acceleration section 13 CPU section 15 Large-capacity storage medium 16 Storage medium 17 Reader / writer section 20 Image printing device (output means)

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G03B 17/53 G03B 17/53 G06T 7/60 G06F 15/70 350B

Claims (4)

[Claims] 1. A first step of photographing an image including at least a face of a subject with a specific color as a background, and identifying a background of the subject from an image photographed in the first step. A second step of detecting a head position of the subject based on a color component luminance indicating a high luminance and a color component luminance indicating a low luminance with respect to a color, and the object detected by the second step. A third step of cutting out an image of the predetermined region of the subject from the image taken in the first step based on the position of the head of the photographer; and the subject cut out by the third step. A fourth step of outputting an image of a predetermined region of the photographer as a photographed image, and a method of photographing a person image. 2. The specific color of the background is blue, the color component luminance indicating high luminance with respect to the specific color is blue component luminance, and the color component luminance indicating low luminance with respect to the specific color is red. 2. The method according to claim 1, wherein the brightness is a component luminance. 3. A photographing means for photographing an image including at least a face of a photographed person with a background of a specific color, and an image photographed by the photographing means is used for a specific color which is a background of the photographed person. Head position detecting means for detecting a head position of the subject based on color component luminance indicating high luminance and color component luminance indicating low luminance; and the subject detected by the head position detecting means. Image extracting means for extracting an image of the predetermined region of the subject from an image captured by the capturing means based on the head position of the subject; and a predetermined image of the subject extracted by the upper body extracting means. Output means for outputting an image of the region as a photographed image. 4. The specific color of the background is blue, the color component luminance indicating high luminance with respect to the specific color is blue component luminance, and the color component luminance indicating low luminance with respect to the specific color is red. 4. The apparatus according to claim 3, wherein the apparatus has component luminance.