JP2004152163A - Face collating device and face collating method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To reduce an influence by the reflection of illumination or outside light on a face image used for face collation even if there is a white area caused by the reflection of the illumination or the outside light within the area to be photographed, and stable face collation can be conducted even if there is a white area caused by the reflection of the illumination or the outside light within the shoot area. <P>SOLUTION: This system detects the white area which exists on the image to be photographed, stores the position of the white area, and instructs so as to photograph a face at a position with less influence of the white area when the face image of an objective is photographed for the face collation. <P>COPYRIGHT: (C)2004,JPO

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to, for example, a face matching apparatus and a face matching method for taking an image (face image) including at least a face by a camera for taking an image of a specific area and performing face matching with a previously registered face image.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, a face matching apparatus extracts a face feature amount each time a face image of a person is obtained from an image captured by a camera, and performs face matching by comparing with a feature amount of a person registered in a dictionary in advance. . In a traffic control device that performs traffic control using face matching, door control is performed based on the result of face matching with a person registered in a dictionary in advance.
In such a face collation device, depending on the installation environment, there may be a part (white area) that is illuminated white due to illumination or reflection by external light, etc., within the range photographed by the camera. When capturing an image including the face of a person for face matching with the camera, when a part of the white area overlaps with the face area or when the white area exists near the face area, In some cases, the face area cannot be detected accurately, or the feature amount of the face cannot be detected accurately. For this reason, in the conventional face matching device, there is a problem that if the white area exists at a position that affects the face image, the accuracy of the face matching may be deteriorated.
[0003]
[Patent Document 1]
JP 2002-92601 A [Patent Document 2]
JP-A-11-161790
[Problems to be solved by the invention]
As described above, the present invention provides a method for face matching when an image captured by an image capturing unit includes a white area due to reflection of light such as illumination or external light due to the light that causes the white area. This solves the problem that performance deteriorates, and even when a white area exists due to the reflection of light such as illumination or external light on an image captured by the image capturing unit, face matching can be performed. It is an object of the present invention to provide a face matching device and a face matching method capable of maintaining performance.
[0005]
[Means for Solving the Problems]
A face matching apparatus according to the present invention performs a matching process with a face image registered in a dictionary, and includes: a photographing unit that photographs an image of a specific region; and a white color existing in the specific region photographed by the photographing unit. A storage unit for storing the position of the region, and when capturing a face image including at least the face of the subject by the imaging unit, an appropriate image corresponding to the position of the white region stored in the storage unit Guiding means for guiding the photographing position of the photographed person to the photographed person; collating a face image including the face of the photographed person photographed by the photographing means with a face image registered in the dictionary; Collating means for performing processing.
[0006]
The face matching method according to the present invention is a method used in a face matching device that has a photographing unit that photographs an image of a specific area and performs a matching process with a face image registered in a dictionary. A storage step of storing a position of a white area existing in a specific area to be captured in a storage unit; and storing the face image including at least a face of a subject by the imaging unit in the storage unit. A guiding step of guiding the subject to an appropriate photographing position of the subject corresponding to the position of the white area, and a face image including the face of the subject photographed by the photographing means. And a matching step of performing a matching process with a face image registered in the dictionary.
[0007]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram schematically showing a face matching system (passage control system) for performing personal authentication using a face image according to an embodiment of the present invention.
As shown in FIG. 1, it comprises a user interface unit 11, a control unit 12, and a traffic control unit 13. The user interface unit 11 and the control unit 12 constitute a face matching device. Note that the user interface unit 11 and the control unit 12 may be integrally configured.
[0008]
The user interface unit 11 has a camera 21, a display unit 22, an operation unit 23, a speaker 24, and the like. The camera 21 is configured by a digital video camera or the like. The camera 21 captures an image of a specific area (photographing range) according to the installation position. At the time of a matching process using a face image or at the time of registration of a face image, at least a person's face present in the photographing range is detected. It is designed to shoot images that include The camera 21 may always capture an image, or may capture an image based on an instruction from the control unit 12. The camera 21 may be color or monochrome. The display unit 22 includes a liquid crystal display device or the like. The display unit 22 displays an image being captured by the camera 21, a guidance display, a result of face matching, and the like. The operation unit 23 includes a numeric keypad or the like. The operation unit 23 inputs an ID number, a password, and the like as personal identification information. The speaker 24 outputs sound such as voice guidance.
[0009]
The control unit 12 controls the entire face matching system. The control unit 12 performs a collation process based on a face image and controls the camera 21, the display unit 22, the operation unit 23, the speaker 24, the automatic door 31 (or the electric lock 33), and the like.
The traffic control unit 13 includes an automatic door 31 or a door on which an electric lock 33 controlled by an electric lock control panel 32 is installed. For example, when the traffic control unit 13 includes the automatic door 31, the control unit 12 is connected to a door opening / closing mechanism (not shown) that opens and closes the automatic door 31. When the traffic control unit 13 is configured by an electric lock 33 installed on a door, the control unit 12 is connected to an electric lock control panel 32 that controls the electric lock 33.
[0010]
Next, the configuration of the control unit 12 will be described in detail.
FIG. 2 is a block diagram schematically showing an internal configuration of the control unit 12.
As shown in FIG. 2, the control unit 12 includes a CPU board 50, a CPU 51, a memory 52, an image input unit 54, an image output unit 55, an audio output unit 56, an operation unit interface unit 57, a door control unit 59, a hard disk 60 , And a power supply unit 61.
[0011]
The CPU board 50 includes a CPU 51, a memory 52, an image input unit 54, an image output unit 55, an audio output unit 56, an operation unit interface unit 57, a door control unit 59, and the like. The CPU 51 controls the entire control unit 12. The memory 52 includes a ROM in which control programs and control data are stored, a RAM in which work data is temporarily stored, and a PROM in which system setting information and the like are stored.
The image input unit 54 is an interface for inputting an image captured by the camera 21. The image output unit 55 is an interface that outputs an image to be displayed on the display unit 22. The audio output unit 56 is an interface that outputs audio generated by the speaker 24. The operation unit interface unit 57 is an interface that takes in the information input by the operation unit 23 into the control unit 12. The door control section 59 controls opening and closing of the automatic door 31 or the electric lock 33 provided in the traffic control unit 13. For example, when the electric lock 33 is installed on the door, the door control unit 59 is connected to the electric lock control panel 32 that controls unlocking and locking of the electric lock 33.
The hard disk 60 is a device that stores various data. The hard disk 60 is provided with a dictionary 60a in which a registrant's face image or face feature amount is stored in advance in correspondence with personal identification information, a password, and the like. The power supply unit 61 supplies power to each unit in the control unit 12, such as the CPU board 50, the door control unit 59, and the hard disk 60.
[0012]
The face image matching system configured as described above is designed to maintain good matching accuracy, for example, when the following conditions are satisfied.
1. Blocks external light.
2. It is assumed that the subject's face is within the illuminance of 200 lux to 600 lux throughout the day and night and throughout the year, and the illuminance variation range is ± 100 lux.
3. The subject stands about 40 cm away from the camera.
4. The subject's face reflected at the camera elevation angle of 30 ° is collated.
However, even if the face matching system is installed in accordance with the above conditions, if the shooting environment changes, a white area due to illumination or reflection of external light may be reflected in an image shot by the camera. is there. In such a case, the effect of the white area (the effect of light that causes the white area) appears on the face image captured for matching, and good matching accuracy may not be obtained. For example, when the position of the face and a part of the white area overlap in an image captured by the camera (when the outline of the face and the white area overlap), the white area overlaps in the captured image. The outline of the face is shining, and the face area cannot be detected accurately, or the feature amount of the face cannot be detected accurately. In such a case, the matching accuracy of the captured face image is reduced, and a good matching result cannot be obtained. Therefore, in the present embodiment, guidance of the photographing position and the like is provided to the subject so that the performance of face collation is not affected by the reflection of the illumination or external light photographed in white.
[0013]
Next, an image captured by the camera 21 will be described.
FIGS. 3A and 3B are diagrams for explaining each pixel in an image (acquired image) input from the camera 21. FIG.
It is assumed that the camera 21 is capturing an image as shown in FIG. In this case, the image captured by the camera 21 is taken into the control unit 12 by the image input unit 54. As shown in FIG. 3B, the CPU 51 of the control unit 12 converts each pixel in the X direction to X0, X1, X2,..., Xn, and Y directions with respect to the acquired image captured by the image input unit 54. It is assumed that the image data is represented by a matrix data structure of Y0, Y1, Y2,..., Yn. Further, the luminance of the acquired image is obtained by dividing each pixel represented by a matrix-like data structure in the X direction (X0, X1, X2,..., Xn) and the Y direction (Y0, Y1, Y2,. Is generated as matrix data indicating the luminance value of each pixel.
[0014]
In FIG. 3A, there is a white area (white area) W due to illumination or reflection of external light. In the white area W, illumination, external light, and the like are reflected on the lens surface of the camera 21 and reflected in white. Further, the white area W always appears at a fixed position on an image photographed by the camera 21 as long as the photographing environment such as illumination and external light does not change.
[0015]
For example, when an image is taken in a state where a person's face or the like overlaps a part of the white area W, the area of the face adjacent to the white area W becomes white as shown in FIG. Therefore, the face image may not be normally captured. In this case, the feature amount of the face cannot be accurately acquired from the face image in some cases, so that the performance of face matching is reduced. However, when the face of a person is photographed by the camera 21, it is possible to block the light that causes the white region W depending on the standing position of the person. The influence on the face image can be avoided. Further, the white region W appears at a specific position if the shooting environment does not change. Therefore, if a face image is taken at a position distant from the white region W, the influence of the white region W on the face image is reduced. It is also possible to prevent it.
[0016]
Next, a white region extraction process for extracting the white region (reference white region) W will be described.
FIG. 4 is a flowchart illustrating a process of detecting a white region W from a background image. Here, the white area W is an image area of a white area detected from an image of only a reference background captured by the camera 21 (an image captured without a person or the like). . Even when a person or the like exists, a white region can be detected by extracting a background region from a captured image and performing the same processing as that described below on the background region. Things.
[0017]
That is, as shown in FIG. 4, first, an image of only the background (reference background image) is captured by the camera 21 (step S11). The reference background image captured by the camera 21 is taken into the control unit 12 by the image input unit 54 of the control unit 12. The CPU 51 of the control unit 12 generates luminance data indicating the luminance value of each pixel in the entire acquired image by converting each pixel of the reference background image (acquired image) photographed by the camera 21 into a luminance value ( Step S12). When the luminance data indicating the luminance value of each pixel in the entire acquired image is obtained, the CPU 51 performs a white point determination process of determining a white point (white point pixel) based on the luminance value of each pixel of the acquired image (step S13). In this white point determination process, a pixel having a luminance value equal to or greater than a predetermined white point determination threshold Y in the acquired image is extracted as a white point pixel. Here, the white point determination threshold value Y is a threshold value for a luminance value of a pixel determined as a white point.
[0018]
When the white point pixels in the acquired image are extracted by the white point determination processing, the CPU 51 performs a white area extraction processing for extracting a white area W including the white point pixels (Step S14). In this white area extraction processing, a set of adjacent white point pixels in the acquired image is extracted as a white area W. That is, the CPU 51 counts white point pixels adjacent to each white point pixel, and extracts a set of adjacent white point pixels on the acquired image as a white area W. When the reference white area W as the white area of the reference background image is extracted by such white point extraction processing, the CPU 51 stores information indicating the position of the reference white area W in a storage unit such as the memory 52 (step S1). S15). The information indicating the white area (reference white area) W is stored in the memory 52 by the white area extraction processing as described above.
[0019]
In the above operation example, the white area is detected from the reference background image. However, the white area may be updated at a specific timing. For example, the white area extraction processing from the background image as described above may be performed at predetermined intervals to update the position information of the white area. Further, the white area may be updated according to the timing at which the environment such as illumination or external light at the shooting position changes. Further, the white area may be detected by performing the above-described white area extraction processing on the background area when performing face matching. As described above, by performing the white area extraction processing at a specific timing, the white area can be appropriately updated. It is possible to provide highly accurate guidance.
[0020]
Next, the face matching process in the face matching system will be described.
FIG. 5 is a flowchart for explaining an operation of performing face matching while guiding the shooting position based on the white area W.
First, in the face matching system, it is assumed that the camera 21 is capturing an image in a standby state of face matching (step S21). In the standby state for face matching, the CPU 51 of the control unit 12 detects the presence of a person by determining the presence or absence of a moving object in the image captured by the camera 21 (step S22). Note that the presence or absence of a person may be detected by a human detection sensor or the like. When a person is detected from the image captured by the camera 21 (step S22, YES), the CPU 51 starts face matching processing. When the face matching process is started, the CPU 51 acquires an image photographed by the camera 21 by the image input unit 54, and performs a face detection process of detecting a face area from the acquired image (Step S23).
[0021]
When the face area is detected by the face area detection processing (step S23, YES), the CPU 51 reads information indicating the position of the reference white area W from the memory 52 (step S24). When these pieces of information are read, the CPU 51 determines whether or not a part of the reference white area W overlaps with the face area detected in step S23 (step S25). When the CPU 51 determines that the face area overlaps a part of the reference white area W (step S25, YES), the CPU 51 determines the appropriate face position as the face photographing position. A determination process is performed (Step S26). In this face position determination processing, a position at which the influence of the reference white region W on the face to be captured is reduced is determined as an appropriate face position.
[0022]
As an appropriate face position determined by such face position determination processing, for example, a face position (the above-described reference There is a position where the subject himself / herself overlaps the white area W), or a position of the face that is away from the reference white area W. The appropriate face position determined by the face position determination process is determined based on the position and size of the reference white region W on an image (photographing region) photographed by the camera 21. .
[0023]
For example, as shown in FIG. 6, when the reference white area W is located near the center of the shooting area of the camera 21 in the shooting area of the camera 21, the CPU 51 determines that the subject himself / herself has the reference white area W Is determined as an appropriate face position (the area of M2 shown in FIG. 6). As shown in FIG. 7, when the reference white area W is located near the end of the shooting area of the camera 21 (position distant from the center of the shooting area) in the shooting area of the camera 21, the CPU 51 Then, the position of the face in which the face of the subject is photographed at a position away from the reference white area W is determined as an appropriate face position (the area M2 shown in FIG. 7).
[0024]
When the appropriate face position is determined by the face position determination process, the CPU 51 performs face position guidance for guiding an area determined to be appropriate as the face position on the display unit 22 (step S27). In the guidance of the face position, for example, a guidance screen as shown in FIGS. 6 and 7 is displayed. In the guidance screens shown in FIGS. 6 and 7, a mark M <b> 1 indicating a face area detected from an image captured by the camera 21 and an appropriate position on the image being captured by the camera 21 are displayed. A mark M2 indicating the position of the face determined to be is displayed. In such a display screen, the subject moves the face or the standing position so that the face of the subject is photographed in the mark M2 indicating the appropriate face position by displaying the mark M2. It is guided to. In other words, on the display screen, the subject is guided to move so that the mark M1 indicating the detected face area matches the mark M2 indicating the appropriate face position.
[0025]
The CPU 51 displays a face position guide screen as described above and performs a face detection process of detecting a face area from an image captured by the camera 21 (step S28). When a face area is detected by such face detection processing, the CPU 51 performs processing to determine whether or not the face area is at an appropriate position (step S29). In this determination processing, for example, it is determined whether or not the face has been photographed at an appropriate position based on whether or not the detected face area is close to the appropriate face position determined in step S26.
If it is determined in the determination processing that the face is not at the appropriate position (step S29, NO), the CPU 51 returns to step S28 and executes the face detection processing again. Further, when the number of times that the face is determined not to be at the appropriate position in the determination processing has reached a predetermined number of times, that is, even if the face detection processing of step S28 is performed a predetermined number of times, the face can be determined to be at the appropriate position. If not, the CPU 51 returns to step S21, and executes the processing from step S21 again by capturing the image captured by the camera 21.
[0026]
When it is determined in the above determination process that a face is detected at an appropriate position (step S29, YES), the CPU 51 performs a face matching process using an image in which a face is detected at an appropriate position as an acquired image (steps S30 to S34). ). In the face matching process, first, the CPU 51 performs a face feature amount detection process of detecting a face feature amount from an acquired image (step S30). When the face feature amount is detected by the face feature amount detection process, the CPU 51 calculates the degree of matching between the face feature amount detected from the acquired image and the face feature amount registered in the dictionary 60a ( Step S31), it is determined whether the calculated degree of collation is equal to or greater than a predetermined collation threshold value (step S32). If the matching degree calculated by this determination is equal to or greater than a predetermined matching threshold, it is determined that the face matching has succeeded, and if the matching degree is equal to or less than the predetermined matching threshold, it is determined that the face matching has failed.
[0027]
For example, when it is determined that the face matching is successful (step S32, YES), the CPU 51 displays a guide indicating that the matching is possible on the display unit 22 and opens the automatic door 31 by the door control unit 59 or the like. Then, the person is allowed to pass by unlocking the electric lock 33 (step S33). If it is determined that the face matching has failed (step S32, NO), the CPU 51 displays a guide indicating that the matching is not possible on the display unit 22, and keeps the automatic door 31 closed or the electric lock 33. By keeping the lock, the passage of the person is disabled (step S34).
[0028]
As described above, when a white area existing in an image to be captured is detected and the position of the white area is stored, and when a face image of a subject is captured for face matching, the influence of the white area is determined. Is provided so that the face is photographed at a position where the number is small. This makes it possible to reduce the influence of illumination and reflection of external light on a face image used for face matching even when a white area due to illumination and reflection of external light exists in the area to be captured. Even when a white area exists due to illumination or reflection of external light in the area, stable face matching can be performed.
[0029]
【The invention's effect】
As described in detail above, according to the present invention, even when a white region exists due to reflection of light such as illumination or external light on an image captured by the capturing unit, the performance of face matching can be improved. A face matching device and a face matching method that can be maintained can be provided.
[Brief description of the drawings]
FIG. 1 is a diagram showing a schematic configuration of a face matching system according to an embodiment of the present invention.
FIG. 2 is a diagram schematically showing a configuration of a control system of the face matching system.
FIG. 3 is a diagram illustrating an example of an image captured by a camera and a configuration of pixels on the image.
FIG. 4 is a flowchart illustrating a white region extraction process for extracting a white region.
FIG. 5 is a flowchart for explaining face matching processing in the present face matching system.
FIG. 6 is a view showing an example of a guidance screen displayed on a display unit.
FIG. 7 is a diagram showing an example of a guidance screen displayed on a display unit.
[Explanation of symbols]
21: Camera, 22: Display Unit, 23: Operation Unit, 31: Automatic Door, 33: Electric Lock, 51: CPU, 52: Memory, 54: Image Input Unit, 55: Image Output Unit, 59: Door Control Unit, 60: Hard disk, 60a: Dictionary

Claims (8)

In a face matching device that performs a matching process with a face image registered in a dictionary,
Photographing means for photographing an image of a specific area;
Storage means for storing a position of a white area existing in a specific area photographed by the photographing means;
When photographing a face image including at least the face of the subject by the photographing unit, an appropriate photographing position of the subject corresponding to the position of the white region stored in the storage unit is provided to the subject. Guidance means for guiding
Collation means for performing a collation process between a face image including the face of the subject photographed by the imaging means and a face image registered in the dictionary;
A face matching device comprising: 2. The face matching apparatus according to claim 1, wherein the guidance unit guides the photographing position of the subject such that the subject hides the white area stored in the storage unit. apparatus. The said guidance means guides the said imaging | photography position to the imaging | photography subject so that the position of the to-be-photographed person's face may leave | separate from the said white area memorize | stored in the said memory | storage means. 2. The face matching device according to claim 1. In a face matching device that performs a matching process with a face image registered in a dictionary,
Photographing means for photographing an image of a specific area;
Storage means for storing a position of a white area existing in a specific area photographed by the photographing means;
When capturing a face image including at least the face of the subject by the photographing unit, the position of the face of the subject to be photographed by the photographing unit based on the position of the white region stored in the storage unit Determining means for determining an appropriate position as
Guide means for guiding the photographing position of the photographed person determined to be appropriate as the position of the face of the photographed person to the photographed person,
Collation means for performing a collation process between a face image including the face of the subject photographed by the imaging means and a face image registered in the dictionary;
A face matching device comprising: The determining means determines the position of the face such that the position of the face of the subject hides the white area stored in the storage means,
5. The photographing device according to claim 4, wherein the guiding unit guides the photographing position of the subject such that the photographing person hides the white area determined by the determining unit. 2. The face matching device according to claim 1. The determining means determines the position of the face such that the position of the face of the subject is away from the white area stored in the storage means,
The method according to claim 4, wherein the guiding means guides the photographing position to the subject such that the position of the face of the subject to be determined determined by the determining means is separated from the white area. The face matching device described in the above. A face matching method used in a face matching device that has a shooting unit that shoots an image of a specific area and performs a matching process with a face image registered in a dictionary,
A storage step of storing a position of a white area existing in a specific area photographed by the photographing means in a storage means,
When photographing a face image including at least the face of the subject by the photographing unit, an appropriate photographing position of the subject corresponding to the position of the white region stored in the storage unit is provided to the subject. A guidance process for guiding
A collation step of performing a collation process between a face image including the face of the subject photographed by the photographing unit and a face image registered in the dictionary;
A face matching method characterized by having: A face matching method used in a face matching device that has a shooting unit that shoots an image of a specific area and performs a matching process with a face image registered in a dictionary,
A storage step of storing a position of a white area existing in a specific area photographed by the photographing means in a storage means,
When capturing a face image including at least the face of the subject by the photographing unit, the position of the face of the subject to be photographed by the photographing unit based on the position of the white region stored in the storage unit A determining step of determining an appropriate position as
A guiding step of guiding the photographing position of the photographed person determined to be appropriate as the position of the face of the photographed person to the photographed person by the determining step;
A collation step of performing a collation process between a face image including the face of the subject photographed by the photographing unit and a face image registered in the dictionary;
A face matching method characterized by having:

Images