JP2001338296A - Face image recognizing device and passing through controller - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a face image recognition device, with which lowering of a recognition rate due to the illumination fluctuation of an illumination on the ceiling or the like can be reduced, and facial image can be recognized with high accuracy. SOLUTION: A camera 101 picks up and inputs the facial image of a recognition target person 100. The face of the recognition target person 100 is irradiated by a first illumination part 102 with the light of fixed luminosity from the upper right or upper left side of the camera 101 and a second illuminance part 103 irradiates the face of the recognition target person with the light of fixed luminosity from the lower part of the camera 101. An image processing part 104 extracts the feature amount of the face of the recognition target person 100 from the face image inputted by the camera 101 and recognizes the facial image of the recognition target person 100, by collating this extracted feature amount with the reference feature amount registered previously.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a face image recognition device for recognizing a face image of a person in security management, for example, and a traffic control device for controlling the passage of a pedestrian using the face image recognition device. .

[0002]

2. Description of the Related Art In a conventional face image recognition apparatus, for example, the recognition rate has been lowered due to illumination fluctuations such as ceiling illumination or external light such as sunlight at the upper front of the apparatus. In order to reduce the decrease in the recognition rate, for example, as disclosed in Japanese Patent Application Laid-Open No. H11-316836, a lighting fixture is mounted on the upper part of the apparatus, and the amount of light and the direction of irradiation are controlled to control the amount of light at the time of imaging. In order to keep lighting conditions constant or to suppress changes in lighting conditions (aging or aging) as disclosed in JP-A-11-175718, information registered in advance when lighting conditions change is used. As described in Japanese Patent Application Laid-Open No. H11-167632, re-registration is performed when the recognition rate decreases.

Further, as disclosed in Japanese Patent Application Laid-Open No. H11-316836, when the direction of the person to be recognized at the time of recognition is different from the direction of a person registered in advance, the direction of the imaging camera is changed. JP-A-11-191856
As disclosed in Japanese Unexamined Patent Publication, a method of providing a gaze guidance device for guiding a gaze on the device has been adopted.

[0004]

SUMMARY OF THE INVENTION Japanese Patent Application Laid-Open No. H11-3168
As disclosed in Japanese Patent No. 36, in the method of controlling the amount of light by attaching a lighting fixture, it is necessary to control all lighting conditions, and in the method of controlling the irradiation angle of the lighting in several steps, It is necessary to newly provide a drive circuit for driving the device.

[0005] As disclosed in Japanese Patent Application Laid-Open No. H11-175718, updating the registration information when the lighting conditions change increases the burden on the user. As disclosed in Japanese Patent No. 167632, re-registration when the recognition rate decreases becomes
For example, a recognition target person who changes his hairstyle every day needs to update the registration information every time he or she recognizes it, and the user's convenience deteriorates.

Further, as disclosed in Japanese Patent Application Laid-Open No. H11-31636, if the orientation of the person to be recognized at the time of recognition is different from the orientation of a person registered in advance, the orientation of the imaging camera can be changed, As disclosed in Japanese Unexamined Patent Publication No. Hei 11-191856, in a method of providing a gaze guidance device for guiding a gaze on a device, it is necessary to newly provide a control circuit for controlling the direction of the imaging camera and a gaze guidance device. There is.

SUMMARY OF THE INVENTION Accordingly, the present invention provides a face image recognition apparatus and a traffic control apparatus capable of reducing a decrease in recognition rate due to illumination fluctuations such as ceiling illumination and enabling highly accurate face image recognition. With the goal.

Further, the present invention can reduce a decrease in the recognition rate due to a difference in the angle of the illuminating means for irradiating light to the face of the person to be recognized and the size of the face image, and realize highly accurate face image recognition. It is an object of the present invention to provide a face image recognition device and a traffic control device that can perform the operation.

[0009]

According to the present invention, there is provided a face image recognizing apparatus, comprising: image input means for inputting a face image of a person to be recognized; and obliquely above or to the left of the image input means as viewed from the person to be recognized. A first illuminator installed above and irradiating light toward the face of the recognition target; and a second illuminator installed below the image input unit and irradiating light toward the face of the recognition target. The illumination means, the feature quantity extraction means for extracting the feature quantity of the face of the recognition target person from the face image input by the image input means, and the feature quantity extracted by the feature quantity extraction means are registered in advance. A recognition unit for recognizing the face image of the recognition target person by collating with a reference feature amount.

A face image recognition apparatus according to the present invention is provided with image input means for inputting a face image of a person to be recognized, and installed diagonally above or to the left of the image input means as viewed from the person to be recognized. A first illuminating unit that irradiates light toward the face of the recognition target; and a second illumination unit that is installed below the image input unit and irradiates light toward the face of the recognition target.
Lighting means, display means for visually displaying the face image input by the image input means together with information indicating an appropriate size of the face image to the person to be recognized, and input by the image input means. A feature amount extracting unit that extracts a feature amount of the face of the recognition target person from a face image; and a feature amount extracted by the feature amount extraction unit is compared with a reference feature amount registered in advance to obtain the recognition target person. Recognizing means for recognizing the face image.

Further, the face image recognition apparatus of the present invention has a plurality of illuminating means for irradiating the face of the person to be recognized with light, and sequentially operates the plurality of illuminating means in a predetermined order and time interval. Lighting control means, image input means for sequentially inputting a face image of the recognition target person in synchronization with the sequential operation of the plurality of lighting means by the lighting control means, and sequentially input by the image input means Feature amount extracting means for respectively extracting feature amounts of the face of the recognition target person from the plurality of face images, and comparing the plurality of feature amounts extracted by the feature amount extracting means with reference feature amounts registered in advance. And a recognition unit for recognizing the face image of the recognition target person.

The traffic control device according to the present invention is a traffic control device for recognizing a face image of a passer and controlling the pass of the passer, wherein the image input means for inputting the face image of the passer; A first illumination unit that is installed diagonally above or to the left of the image input unit as viewed from a passerby and irradiates light toward the face of the passerby, and is installed below the image input unit; Second illuminating means for irradiating the face of the passerby with light, feature quantity extracting means for extracting the feature quantity of the passerby's face from the face image input by the image input means, and this feature quantity Recognition means for recognizing the passer's face image by comparing the feature quantity extracted by the extraction means with a pre-registered reference feature quantity, and recognizing the passer's traffic according to the recognition result of the recognition means. Traffic control means to control It is equipped with.

The traffic control device of the present invention is a traffic control device for recognizing a face image of a passer and controlling the pass of the passer, wherein the image input means for inputting the face image of the passer; A first illumination unit that is installed diagonally above or to the left of the image input unit as viewed from a passerby and irradiates light toward the face of the passerby, and is installed below the image input unit; Second illuminating means for irradiating light toward the face of the passerby, and a face image input by the image input means is visually displayed to the passerby together with information indicating an appropriate size of the face image. Display means for extracting, a feature amount extracting means for extracting the feature amount of the passerby's face from the face image input by the image input means, and a feature amount extracted by the feature amount extracting means as a reference registered in advance. Features and matching And comprising recognizing means for recognizing a face image of the passer, and a passage control means for controlling the passage of the passer in accordance with the recognition result of the recognition means by Rukoto.

According to the present invention, for example, the illumination means for irradiating light to the person to be recognized is provided diagonally above the image input means or diagonally above the left, and further, the recognition means is provided below the image input means. By providing illumination means for irradiating light to the target person, features of the face of the recognition target person are emphasized, and a reduction in the recognition rate due to illumination fluctuations such as ceiling illumination can be reduced. Can be recognized.

Further, according to the present invention, for example, a face image which is guided to keep the size of the face image of the person to be recognized at the time of registration and the size of the face image of the person to be recognized at the time of recognition within a certain range. Display means for displaying the face image, it is possible to reduce the reduction of the recognition rate due to the difference in the angle of the illuminating means and the size of the face image that irradiates the face of the recognition target person with light, and to achieve a highly accurate face image Recognition becomes possible.

[0016]

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

First, a first embodiment will be described.

FIG. 1 schematically shows a configuration of a face image recognition apparatus according to a first embodiment of the present invention. The face image recognition apparatus includes a camera 101 as an image input unit that captures and inputs a face image of the recognition target person 100, and a fixed illuminance toward the face of the recognition target person 100 from the upper right or upper left of the camera 101. A first illuminating unit 102 as a first illuminating unit for irradiating light, and a second illuminating unit as a second illuminating unit for irradiating light with a constant illuminance from below the camera 101 toward the face of the recognition target 100 Lighting unit 103, and
The image processing unit 104 includes an image processing unit 104 that processes a face image input from the camera 101 and performs recognition processing and the like.

The camera 101 captures and inputs a face image of the person to be recognized 100, and is composed of, for example, a television camera using an image sensor such as a CCD sensor.

The first illuminating unit 102 is an illuminating device such as a fluorescent lamp that irradiates light with a fixed illuminance toward the face of the person to be recognized 100 from the upper right or upper left of the camera 101. As shown in FIGS. 2A and 2B, the first illumination unit 10
Although the angle between the optical axis 2 and the optical axis of the camera 101 is set at 45 degrees, the angle may be set, for example, at 30 degrees or less.

That is, by directly irradiating the face of the person to be recognized 100 with light, as shown in FIG. 3, a shadow due to the face part (nose, eyes, etc.) is shaded on one side of the face (shaded lines in the figure). Made in part 100a). Even if the light is not direct light but diffuse light or indirect light, the effect remains the same if a shadow is formed on one half of the face.

The second lighting unit 103 is a lighting device such as a fluorescent lamp that irradiates light with a constant illuminance from below the camera 101 toward the face of the person 100 to be recognized. As shown in FIG. 4, the angle between the optical axis of the first illumination unit 102 and the optical axis of the camera 101 is set at 45 degrees.
It may be installed under conditions such as 0 degrees or more and 60 degrees or less.

That is, it is sufficient that the face of the person to be recognized 100 is directly irradiated with light. Further, instead of direct light, diffused light or indirect light may be used.
02 and the second illumination unit 103 must be the same type of light. Further, the relationship between the illuminance 1A of the first illumination unit 102 and the illuminance 2A of the second illumination unit 103 must satisfy the following expression (1).

1A ≧ 2A (1) One side half of the face image of the person 100 to be recognized by these two illuminating units (the first illuminating unit 102 and the second illuminating unit 103), especially by the first illuminating unit 102. However, the shadow expresses the unevenness information for each individual face, which emphasizes the individual difference and improves the recognition rate.

Further, the first illumination unit 103
Illuminating unit 102 reduces the influence of the lighting unit 102 so as not to create too much shadow on the face of the person 100 to be recognized. That is, the first
The illumination unit 102 alone has a different way of creating a shadow of a face due to a difference in the distance between the recognition target person 100 and the camera 101 at the time of recognition and registration. However, by using the second illumination unit 103, Reduction of the recognition rate due to subtle differences is reduced.

Further, the total value of the illuminance 1A of the first illuminator 102 and the illuminance 2A of the second illuminator 103 for irradiating the face of the person to be recognized 100 is B (lx), and the first illuminator 102
Person 100 to be recognized when the second illumination unit 103 is used.
Assuming that the illuminance of external light or the like irradiating the face of the subject is C (lx), if the relationship of 1A + 2A = B> C (2) is established, for example, the ceiling of a fluorescent lamp or the like above the rear of the person 100 to be recognized The effects of lighting can be reduced.

The total illuminance B (lx) of the first illuminator 102 and the second illuminator 103 is defined within a range where the input face image does not become saturated.

In this embodiment, the first lighting unit 1
02 and the second illuminating unit 103 are assumed to be constantly lit, but sense whether or not the person to be recognized 100 is approaching the present apparatus, and only when they are approaching, the first illuminating unit 102 and The second lighting unit 103 may be turned on.

In this case, for example, it can be realized by separately providing a human sensor such as an infrared sensor, or can be realized by using an input image from the camera 101.

Next, the image processing section 104 will be described. The image processing unit 104 can be realized by, for example, a computer, and stores a program for realizing this function in a storage medium such as a hard disk, a CD-ROM, an MD, or an FD in order to operate the function. Keep it.

In the following description, image input data,
The extracted feature amount, subspace, eigenvectors for constituting the subspace, correlation matrix, status information such as registration time, date and time, location, etc., and personal information such as a personal identification number and an ID code come out. Then, the term "recognition data" includes a subspace or an eigenvector for constituting the subspace, and the term "registration information" refers to image input data, an extracted feature, a subspace, and a subspace. Eigenvectors, correlation matrices, status information, and personal information. Therefore, the recognition data is included in the registration information.

Hereinafter, a specific configuration example of the image processing unit 104 will be described in detail with reference to FIG. In the image processing unit 104, an image input unit 105 as an image input unit, a feature amount extraction unit 106 as a feature amount extraction unit, a recognition unit 107 as a recognition unit, and a reference feature amount are registered (stored) in advance. And a registration information storage unit 108 as a storage means.

The image input unit 105 inputs a face image from the camera 101, A / D converts and digitizes the image, and sends it to the feature amount extraction unit 106.

The feature amount extraction unit 106 includes an image input unit 105
A feature amount such as light and shade information or partial space information is extracted using the face image of the person to be recognized 100 obtained from the image data. For example, as shown in FIG.
A, face part detection unit 106B, and feature amount generation unit 10
6C, which will be described in detail below.

The face area detection unit 106A detects a face area from the face image input by the camera 101. The face area detection method in the face area detection unit 106A determines a location having the highest correlation value as a face area, for example, by calculating a correlation value while moving in a template and a prepared template. In addition, a face area detection unit such as a face area extraction method using an eigenspace method or a subspace method may be used.

The face part detection unit 106B detects the positions of the eyes and nose from the detected face area. The detection method is described in, for example, literatures (Kazuhiro Fukui, Osamu Yamaguchi: "Face feature point extraction by combination of shape extraction and pattern matching", IEICE Transactions (D), vol. J80-D-II,
No. 8, pp. 2170-2177 (1997)).

The feature amount generation unit 106C cuts out the face area into a certain size and shape based on the detected position of the face part, and generates a feature amount. Here, for example, the grayscale value of an area of m pixels × n pixels is used as it is as information, and m × n-dimensional information is used as a feature vector.

When the recognizing unit 107 uses the mutual subspace method, a feature is generated according to the following procedure. The mutual subspace method is described in, for example, literatures (Kenichi Maeda, Seiichi Watanabe: “Pattern matching method with local structure introduced”, IEICE Transactions (D), vol. J68.
-D, No. 3, pp 345-352 (1985)).

When the mutual subspace method is used as a recognition method, the above-mentioned m × n-dimensional information is calculated as a feature vector, and then a correlation matrix (or covariance matrix) of the feature vectors is obtained. A subspace is calculated by obtaining an orthonormal vector (eigenvector) by expansion. The subspace contains the eigenvectors corresponding to the eigenvalues,
The k eigenvalues are selected in descending order, and are expressed using the eigenvector set.

In this embodiment, the correlation matrix Cd is obtained from the feature vector, and the correlation matrix Cd is obtained.

(Equation 1)

Then, a matrix Φ of eigenvectors is obtained. For example, a subspace is calculated by obtaining a correlation matrix of a feature vector from time-series face image data obtained by processing an input image by the feature extraction unit 106 and obtaining an orthonormal vector by KL expansion. I do. This subspace is used as a recognition dictionary for identifying a person. For example, it may be registered in advance and registered as a dictionary.

As will be described later, input data for recognizing the subspace itself may be used. Therefore, a subspace calculation result, which is a feature amount when the mutual subspace method is used as a recognition method, is sent to the recognition unit 107 and the registration information storage unit 108.

The recognizing unit 107 stores the recognition data (subspace) stored in the registration information storage unit 108 and the feature amount extracting unit 10
By comparing (comparing) with the feature amount obtained in step 6,
The person to be recognized 100 recognized by the camera 101 is recognized, or the person to be recognized is identified. In order to recognize a person, it is sufficient to determine which person's data is most similar, and the person corresponding to the data having the highest similarity may be used as the recognition result.

In the case of performing authentication using a face image using a card, a registration number, a password, a key, and the like, the similarity between each person and recognition data corresponding to personal information such as a card or number is determined. Calculate, compare with the set threshold,
If the threshold is exceeded, the person is identified.

As a recognition method, as described above, the subspace method, the composite similarity method, the mutual subspace method, or the like is used.

Here, the mutual subspace method will be described. In this method, both the recognition data and the input data in the registration information stored in advance are expressed as subspaces, and an “angle” formed by two subspaces is defined as a similarity. The subspace input here is called an input subspace.

Similarly, a correlation matrix Ci is applied to the input data sequence.
n

(Equation 2)

To obtain the eigenvector Φin. The subspace similarity (0.0 to 1.0) of the subspace represented by the two Φin and Φd is obtained, and is set as the similarity for recognizing the subspace similarity.

The recognizing unit 107 operates as shown in the flowchart of FIG. First, the operation of the recognizing unit 107 differs depending on whether a recognition operation or an identification operation is performed (ST1). When performing the identification operation, first, the ID code of the target recognition target person is read (ST2). Next, the registration information (subspace) corresponding to the target ID code is read from the registration information storage unit 108 (ST3).

Next, as described above, in order to perform recognition by the subspace method or the like, the similarity between the subspace of each registered data and the input vector (eigenvector from the feature amount extraction unit 106) or the input subspace Calculate the degree (S
T4). Next, the similarity is compared with a preset threshold value (ST5, ST6), and an identification result is output (ST7).

When performing the recognition operation, all the data to be recognized are read from the registration information storage unit 108 (ST).
8). Then, the similarity with each registered data is calculated (ST9). Next, the largest one is selected from the calculated similarities (ST10), and is output as a recognition result (ST12).

Step ST1 surrounded by a broken line in FIG.
By determining the maximum similarity as a threshold value as shown in FIG.
It is also possible to verify whether the recognition result is correct (S
T13). For example, if the similarity is too low,
It can also be determined that it is not any recognition target.

The registration information storage unit 108 can store a partial space (or a correlation matrix or the like) used for identifying a recognition target person, status information such as time, date and time, and location at the time of registration. It should be noted that image input data or extracted feature amounts may be used.

In the present embodiment, a description will be given of a mode in which not only a subspace is held but also a correlation matrix in a previous stage for calculating the subspace is held.

The registration information storage unit 108 holds one or a plurality of pieces of recognition data corresponding to one person or a certain ID code. The subspace is stored together with incidental information such as the acquired time. The reason why a plurality of partial spaces are held is that a plurality of partial spaces corresponding to one person are simultaneously passed to the recognition unit 107 for recognition.

Next, a second embodiment will be described.

FIG. 7 schematically shows a configuration of a face image recognition apparatus according to a second embodiment of the present invention. This face image recognition apparatus includes a camera 101, a first illumination unit 10
2, the second lighting unit 103, the image processing unit 104, and
It comprises a light blocking unit 109 as an external light blocking unit that blocks light from the side such as sunlight.

The camera 101 and the first illumination unit 10
2, the second illumination unit 103, and the image processing unit 104
Has the same configuration as that of the above-described first embodiment, and has the same operation. Therefore, the description thereof is omitted, and the external light blocking unit 109 will be described below.

The external light blocking section 109 blocks external light such as sunlight from the side of the person to be recognized 100 or from above the face of the person to be recognized 100. For example, as shown in FIG. 101 and the illumination units 102 and 103 are surrounded by a total of three surfaces including two surfaces (109A and 109B) on both sides and an upper surface (109C).

The height of the external light blocking unit 109 is the height from the upper side of the first illuminating unit 102 to the lower side of the second illuminating unit 103. As shown in FIG. It suffices if the length of the face is not less than 100. Further, the lateral width of the external light blocking unit 109 may be equal to or greater than the lateral length of the face of the recognition target person 100.

Further, the depth of the external light blocking unit 109 is a distance calculated from the focal length of the lens of the camera 101 and the size of the image sensor, that is, as shown in FIG. It is sufficient if the depth is such that it is covered.

In the present embodiment, a rectangular enclosure is shown as an example of the external light blocking section 109, but the effect is not changed even if it is a circular enclosure.

By blocking external light in this way, a stable illumination environment can be realized, and highly accurate face image recognition with little change in recognition rate can be realized.

Next, a third embodiment will be described.

FIG. 10 schematically shows a configuration of a face image recognition apparatus according to the third embodiment of the present invention. This face image recognition apparatus includes a camera 101, a first illumination unit 10
2, the second lighting unit 103, the image processing unit 104, and
The display unit 110 includes a display unit 110 that displays a face image of the recognition target person 100 that has been imaged.

The camera 101 and the first illumination unit 10
2, the second illumination unit 103, and the image processing unit 104
Has the same configuration as that of the above-described first embodiment, and has the same operation. Therefore, description thereof will be omitted, and the display unit 110 will be described below.

As shown in FIG. 11, the display unit 110 displays a moving image of the face of the person being photographed, and allows the person to be recognized 100 to confirm whether or not the photographing is correctly performed. Things. Also, the registered recognition target person 100
By calculating the position from the camera 101 at the time of registration using the face image of, the size of the face image at the time of registration is displayed by, for example, a square frame 100b as shown in FIG. Thereby, it is possible to suppress a decrease in the recognition rate due to a secular change or a secular change of the standing position of the recognition target person 100. That is, the registration information holding unit 108 also holds the size information of the face image at the time of registration, and the registration can be performed by using the information.

Note that even if guidance is given by voice guidance, for example, "Please move your face a little closer to the camera" or "Please move your face a little closer to the camera", the effect remains the same.

Next, a fourth embodiment will be described.

In the fourth embodiment, the face image recognition device described so far is divided into a registration unit and a recognition unit, and the two are connected by a communication line such as a LAN.

FIG. 13 schematically shows a configuration of a face image recognition apparatus according to a fourth embodiment of the present invention. This face image recognition device comprises a face image registration unit 40 and a face image recognition unit 41, and a communication line 42 such as a LAN
Connected by

The face image registration unit 40 is a device for registering a face image of the person to be recognized 100, and includes a camera 101a, a first illumination unit 102a, a second illumination unit 103a, and an image processing unit 1.
04a, and a display unit 110a as display means for displaying a face image of the person to be recognized 100 being captured and for confirming registration of the face image.

The image processing unit 104a includes an image input unit 105
a, feature amount extraction unit 106a, and registration information storage unit 1
08. Registration information storage unit 108
Saves (stores) the feature amount extracted by the feature amount extraction unit 106a as a reference feature amount.

The camera 101a and the first illumination unit 10
2a, second illumination unit 103a, image input unit 105a, feature amount extraction unit 106a, and registration information storage unit 108
Are the camera 101 in the first embodiment described above,
The configuration is the same as that of the first illumination unit 102, the second illumination unit 103, the image input unit 105, the feature amount extraction unit 106, and the registration information storage unit 108, and the operation is the same. .

The face image recognizing unit 41 is a device for recognizing a face image of the person to be recognized 100, and includes a camera 101b, a third illuminating unit 102b as a third illuminating unit, and a fourth illuminating unit as a fourth illuminating unit. Illuminating section 103b and image processing section 104b.

The image processing unit 104b includes an image input unit 105
b, a feature amount extraction unit 106b, and a recognition unit 107. The recognizing unit 107 includes the feature amount extracting unit 1
By comparing (comparing) the feature amount extracted in step 06b with the feature amount stored in the registration information storage unit 108 of the face image registration unit 40, the recognition target person 1 captured in the camera 101 is compared.
Recognize who 00 is, or identify if it is the person in question.

The camera 101b and the third illumination unit 10
2b, the fourth illumination unit 103b, the image input unit 105b, the feature amount extraction unit 106b, and the recognition unit 107 are the camera 101, the first illumination unit 102, and the second illumination in the above-described first embodiment. The configuration is the same as that of the unit 103, the image input unit 105, the feature amount extracting unit 106, and the recognizing unit 107, and the operation is the same.

Although the face image registration unit 40 is shown to be registered in a state where the person to be recognized 100 is sitting on a chair or the like, the registration may be performed with the person to be recognized 100 standing.

Further, the face image recognizing section 41 does not show a display section for displaying a face image as in the first embodiment, but if the face image registering section 40 is to be registered in a sitting state,
As in the third embodiment, a display unit may be provided to display the size of the face image at the time of registration.

As described above, by dividing the image into the face image registration unit 40 and the face image recognition unit 41, the face image registration unit 40 and the face image recognition unit 41 can be installed in different places.

As another application example of the fourth embodiment, for example, as shown in FIG. 14, a plurality of face image recognition sections 41,... Configurations are possible.

As in the first embodiment, in order to use a face image recognition apparatus, it was necessary to register a reference face image in the face image recognition apparatus. According to this, when the face image recognition units 41 are installed at a plurality of locations, a reference face image is registered by only one face image registration unit 40, and the other plurality of face image recognition units 41,. In this case, it is possible to use without registration, and the burden on the number of registrations of the user is reduced.

Next, a fifth embodiment will be described.

FIG. 15 schematically shows a configuration of a face image recognition apparatus according to the fifth embodiment. The difference between the fifth embodiment and the first embodiment is that the camera 101
Is installed below the face of the person to be recognized 100 to capture a face image from a diagonally downward direction, and the first illumination unit 102 is installed diagonally to the right or diagonally to the left. Are the same as those in the first embodiment, and the description is omitted.

The first and second illumination units 102, 1
03 may be a point light source or a linear light source, or a combination thereof.

With such an arrangement, two nostrils and two pupils of a normal person can be picked up with good contrast, having a shadow reflecting the unevenness characteristic of the face characteristic of an individual.

Next, a sixth embodiment will be described.

In the sixth embodiment, a plurality of illumination light sources are arranged in front of the person to be recognized, and the plurality of illumination light sources are sequentially turned on in a predetermined order and at a time interval. Capture a face image. Then, registration and collation of the face images are performed using the plurality of face images taken in.

FIG. 16 schematically shows an arrangement example of the illumination light source according to the sixth embodiment. In FIG. 16, for example, an illumination light source L1 as eight illumination means
Reference numerals L8 to L8 denote point light sources, which are arranged at equal intervals vertically and horizontally (so-called matrix) on the left, right, and upper portions of the camera 101 arranged in the same manner as in the fifth embodiment. The lighting light sources L1 to L8 are sequentially turned on as described later.

Further, an illumination light source L0 as another illumination means is arranged below the camera 101. The illumination light source L0 is, for example, a linear light source such as a fluorescent lamp, and illuminates the face of the person to be recognized from an obliquely downward direction.

FIG. 17 shows the configuration of a face image recognition apparatus in which a plurality of illumination light sources are arranged as shown in FIG. 17, an output (video signal) of the camera 101 is connected to an input of a capture board 122 in the image processing unit 121. Capture board 12
2 is an A / D conversion circuit 122a and an image memory 122
b. That is, a video signal (analog data) from the camera 101 is transmitted to the A / D conversion circuit 12.
After being converted into digital image data by 2a, it is temporarily stored in the image memory 122b.

In the image processing section 121, the capture board 122, the processing processor 123, the work memory 1
24, the display board 125, and the communication board 126 are communicably connected via a system bus 127.

The system bus 127 is connected to a dictionary 128 as storage means for registering (storing) a plurality of dictionary data (reference feature amounts). The display 129 is connected to the display board 125. An illumination control unit 130 is connected to the communication board 126, and illumination light sources L0, L1 to L8 are connected to the illumination control unit 130.

The processor 123 captures digital image data relating to the face image captured by the camera 101 obtained from the capture board 122, and registers the face image with the image data using the work memory 124 and the dictionary 128. And a collation process, and controls the lighting of the illumination light sources L0, L1 to L8.

Next, the operation of the main part in such a configuration will be described.

First, FIG. 18 and FIG.
This will be described with reference to FIG. When capturing a face image to be registered, the illumination light source L0 is always turned on and the illumination light sources L1 to L
8 are sequentially turned on in a predetermined order and at a predetermined time interval, and face images from the camera 101 are sequentially captured while synchronizing with the sequential lighting operation of the illumination light sources L1 to L8.

As a result, assuming that the illumination light source L1 is illuminated at illumination 1 and the illumination light source L2 is illuminated at illumination 2,..., And the illumination light source L8 is illuminated at illumination 8, as shown in FIG. , K time-series images are obtained for each of the illuminations 1 to 8.
The lighting order of the illumination light sources L1 to L8 may be from the illumination light source L1 or from the illumination light source L8, and the order is arbitrary.

For the time-series images obtained in this way, dictionary data (reference feature amounts) is created for each face image of the same illumination. That is, the dictionary data 1 corresponding to the lighting 1, the dictionary data 2 corresponding to the lighting 2,..., The dictionary data 8 corresponding to the lighting 8 are respectively created, and the created eight dictionary data 1 to 8 are stored in the dictionary 128. Is registered (stored).

FIG. 18 and FIG.
0 will be described. The acquisition of the face image to be collated is performed in the same manner as at the time of registration, as shown in FIG. Then, the obtained time-series images are sequentially collated with dictionary data 1 to 8 in the dictionary 128 for each face image of the same illumination.
That is, the input face image at the time of lighting 1 is compared with the dictionary data 1, the input face image at the time of lighting 2 is compared with the dictionary data 2,... As a result of the collation, for example, if the collation succeeds at any of the lighting points (if the collations match), it is determined that the user is the user.

As a modified example of the collation processing, if the collation results, for example, all collations (eight collations) are successful (if all collations match), it is determined that the user is the principal. You may do so. According to this collation processing, more accurate identity verification can be performed, and for example, it is also effective in preventing impersonation using a photograph.

It is also possible to perform illumination with a plurality of illumination light sources only for registration, and to perform illumination with a smaller number of illumination light sources (for simplicity of the apparatus) for collation. In such a case, it is assumed that registration is performed at a designated place where the lighting environment can be controlled, and matching is performed at a plurality of entrances and exits in a wide area (the lighting environment varies slightly depending on the installation location) ( Case where registration place and collation place are different).

Next, a seventh embodiment will be described.

In the seventh embodiment, for example, the face image recognition device described in the first embodiment is applied to a traffic control device for recognizing a face image of a passer and controlling the pass of the passer. This is an example of the case. Here, as the representative, the first
The case where the face image recognition device described in the embodiment is applied will be described, but it is needless to say that the face image recognition device described in the second to sixth embodiments can be similarly applied. That is not.

FIG. 21 schematically shows a configuration of a traffic control device according to the seventh embodiment. This traffic control device performs, for example, entry / exit management to an important facility, recognizes a face image of a user (passer), and opens / closes an entry / exit door for an important facility based on the recognition result. And a camera 101, a first lighting unit 102, a second lighting unit 103, an image processing unit 104, and a recognizing unit 10.
7 includes a door control unit 111 as a traffic control unit that controls opening and closing of an entrance / exit door 202 of an important facility (a room with an emphasis on security) 201 in accordance with the recognition result.

In FIG. 21, the door control unit 111
Except for this point, the configuration is the same as that of the face image recognition apparatus of FIG.

For example, when the similarity obtained in step ST6 of FIG. 6 is larger than the threshold value, or when the similarity obtained in step ST11 is larger than the threshold value, 111
And outputs a “door closed” signal to the door control unit 111 when the obtained similarity is smaller than the threshold value.

When the door control unit 111 receives the "door open" signal from the recognizing unit 107, the door control unit 111 controls the entrance / exit door 202 to the open state, and the recognition target person (in this case, a passerby) 10
When the entrance of the door 0 is permitted and the signal of “door closed” is received, the entrance / exit door 202 is kept in the closed state, and the entrance of the pedestrian 100 is rejected.

As described above, according to the seventh embodiment,
It is possible to control the traffic of passers-by using the face image recognition device described in the first embodiment. Of course, as described above, the use of the face image recognition device described in the second to sixth embodiments can similarly control the passage of a pedestrian.

Next, an eighth embodiment will be described.

The eighth embodiment is an example in which the present invention is applied to a traffic control device that recognizes a face image of a passer and controls the pass of the passer, as in the seventh embodiment. In this example, a case will be described in which, for example, a wireless card reader is used as specific information input means for inputting specific information for specifying a passerby.

FIG. 22 schematically shows a configuration of a face image capturing section of a traffic control device according to the eighth embodiment. In FIG. 22, for example, a linear first illuminating unit 102 is provided vertically at an obliquely upper left portion of the camera 101 arranged in the same manner as in the fifth embodiment, and In the lower part, a linear second illumination unit 103 is provided in a horizontal state.

Note that the first and second illumination units 102, 1
03 may be a point light source, a linear light source, or a combination thereof. However, in this embodiment, a linear light source such as a fluorescent lamp is used in each of the embodiments. I have.

In the upper part of the camera 101, a wireless communication is performed with a wireless card (not shown) carried by the person to be recognized (in this case, a passerby) 100, and the data is stored in the wireless card. A wireless card reader 203 is provided for reading an ID code as identification information for identifying a passerby in a non-contact manner.

The camera 101, the first and second illumination units 102 and 103, and the wireless card reader 20
Reference numeral 3 denotes an entrance / exit door 202 of an important facility (a room where security is emphasized) 201 as a face image capturing unit 204.
It is installed near.

FIG. 23 shows the structure of a traffic control device when the face image capturing section shown in FIG. 22 is used. This traffic control device is basically similar to the traffic control device shown in FIG. 17 except that a communication board 131 for connecting the wireless card reader 203 is provided.
The difference is that a door control unit 132 is connected to the communication board 126 as a traffic control unit that controls opening and closing of the entrance door 202. The dictionary 128 stores (stores) dictionary data (reference feature amounts) corresponding to each ID code specifying a passerby.

Next, the operation of the main part in such a configuration will be described.

When the passerby 100 holding the wireless card is located in front of the face image capturing unit 204, the processor 123 sends the information to the passerby 1 via the wireless card reader 203.
00 communicates with a wireless card possessed by the camera 101 to read the ID code of the passerby 100 and
The face image of the passerby 100 is taken in through.

Next, by referring to the dictionary 128 based on the ID code read from the wireless card, the processor 123 searches the dictionary data managed by the corresponding ID code, Collation with the face image is performed on a one-to-one basis, and it is finally determined whether or not the person is the person. As a result of the determination, if the person is the person, the door control unit 132
And outputs a “door closed” signal to the door control unit 132 if the user is not the user.

When receiving the signal of "door open", the door control unit 132 controls the entrance / exit door 202 to the open state, permits the pedestrian 100 to enter the room, and receives the signal of "door closed". , The entrance / exit door 202 is held in the closed state,
Refuse entry to room 00.

[0120] The wireless card may communicate in a state where the wireless card is kept in the pocket of the passerby 100, or may be held over the wireless card reader 203 by hand. When holding the wireless card reader 203 over the wireless card reader 203, the passerby 100
Since looking at the direction of 03 is a natural movement, there is an advantage that the camera 101 can be arranged so as to capture a frontal image of the passerby 100 at that opportunity.

Also, it is not always necessary to use a card-like wireless medium, and various modifications such as a name tag form, a batch form, and a pendant form are possible as the wireless tag.

Furthermore, the method of acquiring the ID code of the passerby 100 is not limited to the wireless card reader, and the point is that it takes advantage of the remote (non-contact) capture of the face image, so that it can be remotely and non-contacted. The feature is that it is combined with the means for performing. Therefore, for example, a mobile phone or a mobile terminal with a wireless function may be used.

Next, a ninth embodiment will be described.

In the ninth embodiment, for example, in the eighth embodiment, a camera for face image collation is also used for recording an image (video), and the camera detects the face image of a passerby or succeeds in collation. / The unsuccessful information as additional information
This is recorded together with the image captured by the camera.

FIG. 24 schematically shows a configuration of a traffic control device according to the ninth embodiment. This traffic control device is basically the same as the traffic control device shown in FIG. 23 except that the signal branch circuit 133 for branching the video signal from the camera 101 and the signal branch circuit 1
The difference is that a delay circuit 134 for delaying the video signal branched at 33 for a predetermined time and an image recording unit 135 as an image recording means for recording the video signal delayed for a predetermined time by the delay circuit 134 are added.

The image recording unit 135 includes
3 controls ON / OFF of the recording operation. That is, when the processing processor 123 detects the face image of the passerby 100 from the image from the camera 101, it sends a recording start signal to the image recording unit 135, and when the face image collation is completed (successful or unsuccessful), A recording stop signal is sent to the image recording unit 135. Upon receiving the recording start signal, the image recording unit 135 sets a predetermined time (delay circuit 1
The recording is started from the image (video) before (delay time of 34), and when the recording stop signal is received, the recording is stopped. As a result, the image recording unit 135 records the time from the detection of the passer's face image to the end of the verification as a continuous image.
Further, the image recording unit 135 records the collation result (success / failure) for the input image at this time together with the corresponding image.

The image recording section 135 may use any image recording means such as a magnetic tape recording device, a magnetic disk recording device, and an optical disk recording device.

Next, a tenth embodiment will be described.

In the tenth embodiment, for example, in the eighth embodiment, a camera for face image collation is also used for remote monitoring, and the camera detects a face image of a passerby or succeeds / fails in collation. This is transmitted to the remote monitoring monitor together with the image captured by the camera as additional information.

FIG. 25 schematically shows a configuration of a traffic control device according to the tenth embodiment. This traffic control device is basically similar to the traffic control device shown in FIG. 24, except that the image recording unit 135 is replaced with an image transmission unit 136.

The image transmission section 136 is provided for the processor 12.
3 controls on / off of the transmission operation. That is, when the processor 123 detects the face image of the passerby 100 from the image from the camera 101, the processor 123 sends a transmission start signal to the image transmission unit 135, and when the face image matching is completed (successful or unsuccessful), A transmission stop signal is sent to the image transmission unit 135. Upon receiving the transmission start signal, the image transmission unit 135 starts transmission from an image (video) that is a predetermined time before that point to a remote monitoring monitor (not shown). Stop.
As a result, the process from the detection of the passer's face image to the end of the collation is transmitted as a continuous image to the remote monitoring monitor.
Further, the image transmission unit 135 transmits the collation result (success / unsuccess) for the input image at this time to the remote monitoring monitor together with the corresponding image.

Next, an eleventh embodiment will be described.

The eleventh embodiment is a combination of the ninth and tenth embodiments described above, and uses digital transmission for image transmission.

FIG. 26 schematically shows a structure of a traffic control device according to the eleventh embodiment. This traffic control device is basically similar to the traffic control device shown in FIG.
In addition, a communication board 137 for connecting the system bus 127 to a digital line 138 such as a LAN or the Internet is provided, in addition to having a digital image transmission function for transmitting a digitized input image from the camera 101 to the outside. The added points are different.

When the processor 123 detects the face image of the passerby 100 from the image from the camera 101, the processor 123 starts the remote image connection via the digital line 138 such as a LAN or the Internet from the image a predetermined time before the time. Digital transmission to a monitoring monitor and an image recording device (both not shown) installed in the monitoring center of the place is started, and when the matching of the face image is completed (successful or unsuccessful), the transmission is stopped. As a result, from the detection of the face image of the passer-by to the end of the verification is transmitted as a continuous image to the monitoring center. The matching result (success / failure) for the input image at this time is also transmitted to the monitoring center together with the corresponding image.

When transferring a digital image to a monitoring center via a digital line, the image may be compressed. As the image compression, for example, motion JPEG or MPEG4, which is a world standard moving image system, can be used.

Note that the present invention is not limited to the above embodiment. For example, the above embodiments can be implemented in various combinations. Further, in the above-described embodiment, a case has been described in which a camera having sensitivity to a normal visible region wavelength is used. However, an infrared camera having sensitivity to an infrared region wavelength may be used, or distance information (depth information) may be used. May be used. Alternatively, different types of image input means can be mixed. In addition, various modifications can be made without departing from the spirit of the present invention.

[0138]

As described above in detail, according to the present invention, it is possible to reduce a decrease in the recognition rate due to a variation in illumination such as ceiling illumination, and a face image recognition apparatus capable of highly accurate face image recognition. And a traffic control device.

Further, according to the present invention, it is possible to reduce a decrease in the recognition rate due to a difference in the angle of the illuminating means for irradiating light to the face of the person to be recognized and the size of the face image, and to obtain a highly accurate face image. And a traffic control device capable of recognizing a car.

[Brief description of the drawings]

FIG. 1 is a configuration diagram schematically showing a configuration of a face image recognition device according to a first embodiment.

FIG. 2 shows a relationship between a first illumination unit and a camera;
(A) is a side view as viewed from the side, and (b) is a top view as viewed from above.

FIG. 3 is a diagram showing an example of a face image by a first lighting unit.

FIG. 4 is a side view showing a relationship between a second illumination unit and a camera.

FIG. 5 is a block diagram schematically showing a configuration of a feature amount extraction unit.

FIG. 6 is a flowchart illustrating a recognition process of a recognition unit.

FIG. 7 is a configuration diagram schematically showing a configuration of a face image recognition device according to a second embodiment.

FIG. 8 is a perspective view showing a relationship between an external light blocking unit, a first lighting unit, and a second lighting unit.

FIG. 9 is a side view showing a relationship between an external light blocking unit, a first lighting unit, and a second lighting unit.

FIG. 10 is a configuration diagram schematically showing a configuration of a face image recognition device according to a third embodiment.

11A and 11B show a display example of a face image according to a difference in the position of a recognition target person. FIG. 11A shows a case where a normal image is captured, and FIG. 11B shows a case where the face is tilted. Show the case.

12A and 12B show a display example of a face image according to a difference in the size of the face image. FIG. 12A shows a case where the size is the same as that at the time of registration, and FIG. Show,
(C) shows a case where the size is smaller than the time of registration.

FIG. 13 is a configuration diagram schematically showing a configuration of a face image recognition device according to a fourth embodiment.

FIG. 14 is a configuration diagram schematically showing a configuration of a face image recognition device according to another application example of the fourth embodiment;

FIG. 15 is a configuration diagram schematically showing a configuration of a face image recognition device according to a fifth embodiment.

FIG. 16 is a front view schematically showing an arrangement example of the illumination light source according to the sixth embodiment.

FIG. 17 is a configuration diagram schematically showing a configuration of a face image recognition device according to a sixth embodiment.

FIG. 18 is a view for explaining a face image capturing process according to the sixth embodiment;

FIG. 19 is a diagram illustrating a registration process according to the sixth embodiment.

FIG. 20 is a view for explaining a matching process according to the sixth embodiment;

FIG. 21 is a configuration diagram schematically showing a configuration of a traffic control device according to a seventh embodiment;

FIG. 22 schematically shows a configuration of a face image capturing unit of a traffic control device according to an eighth embodiment, where FIG. 22 (a) is a side view and FIG. 22 (b) is a front view.

FIG. 23 is a configuration diagram schematically showing a configuration of a traffic control device according to an eighth embodiment.

FIG. 24 is a configuration diagram schematically showing a configuration of a traffic control device according to a ninth embodiment;

FIG. 25 is a configuration diagram schematically showing a configuration of a traffic control device according to a tenth embodiment.

FIG. 26 is a configuration diagram schematically showing a configuration of a traffic control device according to an eleventh embodiment.

[Explanation of symbols]

101, 101a, 101b ... camera (image input means), 102, 102a ... first illuminator (first illuminator), 103, 103a ... second illuminator (second illuminator), 102b... Third lighting section (third lighting means), 103b... Fourth lighting section (fourth lighting means),
104, 104a, 104b, 121 ... image processing unit,
105, 105a, 105b ... image input unit (image input means), 106, 106a, 106b ... feature amount extraction unit (feature amount extraction unit), 107 ... recognition unit (recognition unit),
108 registration information storage unit (storage unit), 109 external light blocking unit (external light blocking unit), 110, 110a display unit (display unit), 111, 132 door control unit (passage control unit) ), 128 ... dictionary (storage means), 130 ...
Lighting control unit, 135 ... image recording unit (image recording means),
136 image transmission unit 203 wireless card reader (specific information input means), L0, L1 to L8 illumination light source (illumination means) 40 face image registration unit 41 face image recognition unit , 42... LAN (communication line).

Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat II (Reference) G07C 9/00 G07C 9/00 Z (72) Inventor Toshio Sato 70 Yanagicho, Sai-ku, Kawasaki-shi, Kanagawa Toshiba Yanagicho Business Co., Ltd. Office (72) Inventor Hiroshi Sukekawa 70 Yanagimachi, Saiwai-ku, Kawasaki-shi, Kanagawa Prefecture F-term (reference) 2E250 AA04 AA12 BB10 BB32 BB54 BB56 CC11 CC13 DD08 EE03 FF11 FF35 FF36 FF44 3E038 AA01 J023B10 JA04 FA10 AA04 AA09 BA04 DA05 FA07 GA02 GA04 GA11 GA18 HA02 5B047 AA23 BB01 BB06 BC04 BC12 CA19 DB01 5B057 AA20 BA02 BA11 BA19 BA29 CE09 DA08 DC34

Claims (18)

[Claims] 1. An image input means for inputting a face image of a recognition target person, a plurality of lighting means for irradiating light toward the face of the recognition target person, and a face image input by the image input means A feature amount extracting unit that extracts a feature amount of the face of the recognition target person; and a feature image extracted by the feature amount extracting unit is compared with a reference feature amount registered in advance to convert the face image of the recognition target person. A face image recognition device, comprising: recognition means for recognizing; 2. An image input means for inputting a face image of a recognition target person. The image input means is installed diagonally above or to the left of the image input means as viewed from the recognition target person, and faces the face of the recognition target person. A first illuminating unit that irradiates light to the recognition target; a second illuminating unit that is installed below the image input unit and irradiates light to the face of the recognition target person; A feature amount extraction unit for extracting a feature amount of the face of the recognition target person from a face image; and a feature amount extracted by the feature amount extraction unit is compared with a reference feature amount registered in advance to obtain the recognition target person. And a recognition means for recognizing the face image. 3. An image input means for inputting a face image of a recognition target person. The image input means is installed diagonally above and to the right or left of the image input means as viewed from the recognition target person, and faces the face of the recognition target person. A first illuminating unit that irradiates light to the recognition target person; a second illuminating unit that is installed below the image input unit and irradiates light toward the face of the recognition target person; External light blocking means for blocking external light to be irradiated; feature value extracting means for extracting a feature value of the face of the person to be recognized from the face image input by the image input means; A recognition unit that recognizes the face image of the recognition target person by comparing the registered feature amount with a reference feature amount registered in advance. 4. An image input means for inputting a face image of a recognition target person, wherein the image input means is installed diagonally above or to the left of the image input means as viewed from the recognition target person, and faces the recognition target person's face. A first illuminating unit that irradiates light to the recognition target; a second illuminating unit that is installed below the image input unit and irradiates light to the face of the recognition target person; Display means for visually displaying a face image together with information indicating an appropriate size of the face image to the recognition target person; and a feature amount of the recognition target person face from the face image input by the image input means. Feature amount extracting means to be extracted; and recognizing means for recognizing the face image of the recognition target person by comparing the feature amount extracted by the feature amount extracting means with a reference feature amount registered in advance. Features Face image recognition device. 5. A first image input means for inputting a face image of a person to be recognized, and a diagonally upper right or a diagonally upper left of the first image input means as viewed from the person to be recognized,
First illuminating means for irradiating light to the face of the recognition target; and second lighting provided below the first image input means and irradiating light to the face of the recognition target. Means, first feature amount extracting means for extracting feature amounts of the face of the person to be recognized from the face image input by the first image input means, and extracted by the first feature amount extracting means. A face image registration unit comprising storage means for storing a feature amount as a reference feature amount; a second image input unit connected to the face image registration unit for inputting a face image of a recognition target person; A third illumination unit that is installed obliquely above or to the left of the second image input unit as viewed from a user, and irradiates light toward the face of the recognition target person; and the second image input unit. Illuminates the face of the person to be recognized. Fourth illumination means, second feature quantity extraction means for extracting the feature quantity of the face of the person to be recognized from the face image input by the second image input means, and second feature quantity extraction means A face image recognition unit comprising recognition means for recognizing the face image of the person to be recognized by comparing the feature amount extracted by the above with the feature amount stored in the storage means of the face image registration unit. A face image recognition apparatus characterized in that: 6. A first image input means for inputting a face image of a person to be recognized, and a diagonally upper right or a diagonally upper left of the first image input means as viewed from the person to be recognized.
First illuminating means for irradiating light to the face of the recognition target; and second lighting provided below the first image input means and irradiating light to the face of the recognition target. Means, first display means for visually displaying the face image input by the image input means to the person to be recognized, and the face image of the person to be recognized from the face image input by the first image input means. A face image registration unit comprising: first feature amount extraction means for extracting a feature amount of the face; and storage means for storing the feature amount extracted by the first feature amount extraction means as a reference feature amount. A second image input unit that is connected to the face image registration unit and inputs a face image of the recognition target person; and a second image input unit that is installed diagonally above or to the left of the second image input unit when viewed from the recognition target person. Irradiating light toward the face of the recognition target person; Illuminating means, a fourth illuminating means installed below the second image inputting means for irradiating light toward the face of the recognition target person, and a face inputted by the second image inputting means. Second display means for visually displaying an image together with information indicating an appropriate size of the face image to the person to be recognized; and a face image input by the second image input means to identify the person to be recognized. A second feature amount extracting unit for extracting a feature amount of the face; and a feature amount extracted by the second feature amount extracting unit is compared with a feature amount stored in a storage unit of the face image registration unit. A face image recognition unit comprising: recognition means for recognizing the face image of the person to be recognized. 7. An image input means for inputting a face image of a person to be recognized, and a diagonally right front or diagonally left front near the image input means as viewed from the person to be recognized. A first illuminating unit that irradiates light toward the recognition unit; a second illuminating unit that is installed below the first illuminating unit and irradiates light from below toward the face of the recognition target person; A feature amount extracting unit that extracts a feature amount of the face of the recognition target person from the face image input by the input unit; and a feature amount extracted by the feature amount extracting unit is compared with a reference feature amount registered in advance. And a recognition unit for recognizing the face image of the recognition target person. 8. A plurality of illuminating means for irradiating light to the face of the person to be recognized, an illuminating control means for operating the plurality of illuminating means sequentially in a predetermined order and at a time interval, and the illuminating control means. Image input means for sequentially inputting the face image of the recognition target person in synchronization with the sequential operation of the plurality of lighting means, and the recognition target from the plurality of face images sequentially input by the image input means. Feature amount extracting means for respectively extracting feature amounts of the face of the person; and comparing the plurality of feature amounts extracted by the feature amount extracting means with reference feature amounts registered in advance to obtain the face of the recognition target person. A face image recognition device, comprising: recognition means for recognizing an image. 9. A plurality of illumination means for irradiating light toward the face of the recognition target person, an illumination control means for sequentially operating the plurality of illumination means in a predetermined order and at a time interval, and the illumination control means. Image input means for sequentially inputting the face image of the recognition target person in synchronization with the sequential operation of the plurality of lighting means, and the recognition target from the plurality of face images sequentially input by the image input means. Feature amount extracting means for respectively extracting feature amounts of a person's face; registering means for registering a plurality of feature amounts extracted by the feature amount extracting means as reference feature amounts when registering a face image; At the time of matching, the face image of the recognition target person is recognized by comparing the plurality of feature amounts extracted by the feature amount extraction unit with the plurality of reference feature amounts registered by the registration unit. Face image recognition apparatus characterized by comprising a recognition means. 10. A traffic control apparatus for recognizing a passer's face image and controlling the passer's traffic, comprising: image input means for inputting the passer's face image; and light directed toward the passer's face. A plurality of illumination means for irradiating the image, a feature quantity extraction means for extracting a feature quantity of the passer's face from the face image input by the image input means, and a feature quantity extracted by the feature quantity extraction means in advance. Recognition means for recognizing the passer's face image by collating with a registered reference feature amount, and traffic control means for controlling the traffic of the passer according to the recognition result of the recognition means. A traffic control device, characterized in that: 11. A traffic control device for recognizing a passer's face image and controlling the passer's traffic, comprising: an image input means for inputting the passer's face image; and the image input device as viewed from the passer's face. A first illuminating unit that is installed diagonally above or to the left of the unit and irradiates light toward the face of the passer; and a lower unit that is installed below the image input unit and faces the face of the passer. A second illumination unit for irradiating light; a feature amount extraction unit for extracting a feature amount of the passer's face from the face image input by the image input unit; a feature amount extracted by the feature amount extraction unit Recognizing means for recognizing the passer's face image by comparing with a reference feature amount registered in advance, and traffic control means for controlling the traffic of the passer according to the recognition result of the recognizing means. Specially Passage control apparatus according to. 12. A traffic control device for recognizing a passer's face image and controlling the passer's traffic, comprising: image input means for inputting the passer's face image; and the image input device as viewed from the passer's face. A first illuminating unit that is installed diagonally above or to the left of the unit and irradiates light toward the face of the passer; and a lower unit that is installed below the image input unit and faces the face of the passer. A second illumination unit that irradiates light; an external light blocking unit that blocks external light that is applied to a face portion of the passerby; and a characteristic of the face of the passerby from a face image input by the image input unit. A feature extracting means for extracting a quantity; a recognizing means for recognizing the passer's face image by comparing the feature extracted by the feature extracting with a reference feature registered in advance; Depending on the recognition result of the means Passage control device being characterized in that includes the passage control means for controlling the passage of serial passerby, the. 13. A traffic control device for recognizing a passer's face image and controlling the passer's traffic, comprising: an image input means for inputting the passer's face image; and the image input device as viewed from the passer's face. A first illuminating unit that is installed diagonally above or to the left of the unit and irradiates light toward the face of the passer; and a lower unit that is installed below the image input unit and faces the face of the passer. Second illuminating means for irradiating light; display means for visually displaying the face image input by the image input means together with information indicating an appropriate size of the face image to the passer-by; A feature amount extracting means for extracting a feature amount of the passer's face from the face image input by the means, and a feature amount extracted by the feature amount extracting means is compared with a reference feature amount registered in advance. The passer-by 1. A traffic control device comprising: a recognition unit that recognizes a face image of the above; and a traffic control unit that controls the traffic of the passer-by in accordance with a recognition result of the recognition unit. 14. A traffic control device for recognizing a face image of a passer and controlling the pass of the passer, a first image input means for inputting the face image of the passer,
First illuminating means which is installed diagonally above or to the left of the first image input means as viewed from the passerby and irradiates light toward the face of the passerby; and wherein the first image input means A second illuminating means installed below the means for irradiating light to the face of the passerby, and extracting a feature amount of the passer's face from the face image input by the first image input means A face image registration unit comprising: a first feature amount extraction unit for performing the operation; a storage unit for storing the feature amount extracted by the first feature amount extraction unit as a reference feature amount; A second image input means for inputting a face image of the passerby;
A third illuminating unit that is installed diagonally above or to the left of the image input unit, and irradiates light toward the face of the pedestrian; and a third illuminating unit that is installed below the second image input unit. Fourth lighting means for irradiating light toward the face of the person,
A second feature value extracting means for extracting a feature value of the passer's face from the face image input by the second image input means; and a feature value extracted by the second feature value extracting means. Recognition means for recognizing the passer's face image by collating with the feature amount stored in the storage means of the face image registration unit, and traffic control for controlling the traffic of the passer according to the recognition result of the recognition means. And a face image recognition unit comprising control means. 15. A traffic control device for recognizing a passer's face image and controlling the passer's traffic, wherein: first image input means for inputting the passer's face image;
First illuminating means which is installed diagonally above or to the left of the first image input means as viewed from the passerby and irradiates light toward the face of the passerby; and wherein the first image input means A second illuminating unit that is provided below the unit and irradiates light toward the face of the passerby; and a first illuminator that visually displays a face image input by the image input unit to the passerby.
Display means, first feature amount extraction means for extracting the feature amount of the passer's face from the face image input by the first image input means, and the first feature amount extraction means A face image registration unit including storage means for storing the feature amount as a reference feature amount, a second image input unit connected to the face image registration unit and inputting a passerby face image,
A third illumination unit that is installed diagonally above or to the left of the second image input unit as viewed from the passerby and irradiates light toward the face of the passerby; and the second image input unit. A fourth illuminating unit which is installed below the unit and irradiates light to the face of the passerby; and a face image input by the second image input unit, which indicates an appropriate face image size. Second display means for displaying the information to the passerby together with information, and second feature value extracting means for extracting the feature value of the passer's face from the face image input by the second image input means A recognition unit for recognizing the passer's face image by comparing the feature amount extracted by the second feature amount extraction unit with a feature amount stored in a storage unit of the face image registration unit; According to the recognition result of this recognition means, Passage control identification device comprising a facial image recognition unit consisting of the passage control means for controlling, characterized by comprising a make. 16. A traffic control apparatus for recognizing a passer's face image and controlling the passer's traffic, comprising: image input means for inputting the passer's facial image; and light directed toward the passer's face. A plurality of illuminating means for illuminating the pedestrian; a feature quantity extracting means for extracting a feature quantity of the passer's face from the face image input by the image input means; and specific information for inputting specific information for specifying the passer An input unit, and a reference feature amount corresponding to the specific information input by the specific information input unit is searched from a reference feature amount registered in advance in correspondence with the specific information specifying the passerby. A recognition unit for recognizing the passer's face image by comparing the reference feature amount with the feature amount extracted by the feature amount extraction unit; and To Passage control device comprising a passage control means Gosuru, by comprising a. 17. A traffic control device for recognizing a face image of a passer and controlling the pass of the passer, a plurality of lighting means for irradiating light to the face of the passer, and the plurality of lighting means. Lighting control means for sequentially operating at predetermined intervals and time intervals; and image input means for sequentially inputting the passer's face image in synchronization with the sequential operation of the plurality of lighting means by the lighting control means. A feature amount extracting unit that extracts a feature amount of the passer's face from a plurality of face images sequentially input by the image input unit; and a specific information input that inputs specific information for specifying the passer. Means, from the reference characteristic amount registered in advance in correspondence with the specific information specifying the passerby, to search for the reference characteristic amount corresponding to the specific information input by the specific information input means, Recognizing means for recognizing the passer's face image by comparing the retrieved reference feature quantity with the feature quantity extracted by the feature quantity extracting means, and the passer-by according to the recognition result of the recognizing means. A traffic control device, comprising: traffic control means for controlling the traffic of the vehicle. 18. A traffic control device for recognizing a passer's face image and controlling the passer's traffic, comprising: image input means for inputting the passer's face image; and light directed toward the passer's face. A plurality of illumination means for irradiating the image, a feature quantity extraction means for extracting a feature quantity of the passer's face from the face image input by the image input means, and a feature quantity extracted by the feature quantity extraction means in advance. Recognition means for recognizing the passer's face image by comparing with a registered reference feature amount; traffic control means for controlling the passer's traffic according to the recognition result of the recognition means; Image recording for recording at least the image input by the image input means as a continuous image from when the face image is detected by the extraction means to when the recognition processing of the face image is completed by the recognition means. Means, and a traffic control device, characterized by comprising: