JP2008017169A - Electronic camera - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an electronic camera which performs controlling to raise a next authentication success rate at the time of the failure of photographic subject authentication. <P>SOLUTION: The electron camera is provided with an image pick-up, a zoom adjustment, a recorder, a photographic subject authentication, and a control unit. The image pick-up picturizes a photographic subject image by a photography optical system. The zoom adjustment adjusts the magnification of a photographic subject image. The recorder has recorded beforehand registration data indicating the characteristic details for attestation. The photographic subject authentication judges whether a photographic subject picturized by the image pick-up is coincident with a candidate for attestation, based on the registration data. When the photographic subject authentication judges that the photographic subject is not coincident with the candidate for attestation, the control unit makes the photographic subject authentication execute again the judgment, while expanding the magnification of the photographic subject image. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an electronic camera having a subject authentication function.

2. Description of the Related Art Conventionally, an electronic camera that authenticates a subject such as a person at the time of shooting based on dictionary data recorded in the camera is known. For example, Patent Document 1 discloses an electronic camera that photographs a face of an authenticated subject with a preferred size by performing zooming when the subject is authenticated.
JP 2004-320286 A

  By the way, in a general electronic camera equipped with a subject authentication function, for example, in a scene where the subject is located far away, authentication may fail because information about the characteristic part of the subject cannot be acquired by the first imaging operation. is there. In such a case, there has been a demand for an electronic camera that can easily detect the characteristic part of the subject and can increase the next authentication success rate.

  An object of the present invention is to provide an electronic camera that performs control to increase the next authentication success rate when subject authentication fails.

  An electronic camera according to a first aspect includes an imaging unit, a zoom adjustment unit, a recording unit, a subject authentication unit, and a control unit. The imaging unit captures a subject image by the imaging optical system. The zoom adjustment unit adjusts the magnification of the subject image. The recording unit records in advance registration data indicating feature points to be authenticated. The subject authentication unit determines whether the subject imaged by the imaging unit matches the authentication target based on the registration data. When the subject authentication unit determines that the subject does not match the authentication target, the control unit enlarges the magnification of the subject image and causes the subject authentication unit to re-execute the determination.

The second invention is characterized in that, in the first invention, the authentication target is a human face.
In the third invention, the electronic camera of the second invention further includes a face detection unit. The face detection unit detects a person's face from the shooting screen and extracts feature points of the detected person's face to generate determination data. In addition, the subject authentication unit acquires a reference distance connecting two specific feature points, and executes a normalization process for obtaining a ratio between the relative distance of the feature points and the reference distance for the registration data and the determination data. . The subject authentication unit performs determination based on the data after the normalization process.

In the fourth invention, the electronic camera of the second invention further includes a face detection unit, a monitor, and an operation unit. The face detection unit detects a person's face from the shooting screen. The monitor presents the face detected by the face detection unit. The operation unit receives a designation operation for designating a face to be determined from the user. Then, the subject authentication unit performs determination on the face specified by the specifying operation.
In the fifth invention, the electronic camera of the first invention further includes a first notification unit. The first notification unit alerts the subject when the subject authentication unit determines that the subject does not match the authentication target.

In the sixth invention, the electronic camera of the first invention further includes a second notification unit. The second notification unit alerts the user when the subject to be determined is out of the shooting angle of view due to the enlargement of the magnification of the subject image.
In a seventh aspect based on the first aspect, the recording unit records profile data that describes an authentication target in association with registration data. In addition, when the subject authentication unit determines that the subject matches the authentication target, the control unit adds additional data based on the profile data to the image file including the recording image in which the authentication target is captured.

  In the electronic camera of the present invention, when the subject authentication fails, the magnification of the subject image can be enlarged by zooming to increase the next authentication success rate.

(Description of the first embodiment)
FIG. 1 is a block diagram showing the configuration of the electronic camera of the first embodiment.
The electronic camera includes a zoom lens 11, a first lens driving unit 12, a focusing lens 13, a second lens driving unit 14, an image sensor 15, an analog processing unit 16, an A / D conversion unit 17, and a timing. Generator (TG) 18, first memory 19, image processing unit 20, recording I / F 21, display I / F 22, monitor 23, release button 24, operation unit 25, speaker 26, flash The light emitting unit 27, the CPU 28, the second memory 29, and the system bus 30 are included. The first memory 19, the image processing unit 20, the recording I / F 21, the display I / F 22 and the CPU 28 are connected via a system bus 30.

  The zoom lens 11 is a lens for enlarging and reducing a subject image formed on the image sensor 15. The first lens driving unit 12 includes a motor for adjusting the position of the zoom lens 11 in the optical axis direction, a driver for driving the motor, and an encoder for detecting the position of the zoom lens 11. The input / output of the first lens driving unit 12 is connected to the CPU 28.

  The focusing lens 13 is a lens for adjusting the focus state of the subject image. The second lens driving unit 14 includes a motor for adjusting the position of the focusing lens 13 in the optical axis direction, a driver for driving the motor, and an encoder for detecting the position of the focusing lens 13. The input / output of the second lens driving unit 14 is connected to the CPU 28.

  The image sensor 15 photoelectrically converts the light beam that has passed through the zoom lens 11 and the focusing lens 13 to generate an analog image signal of the subject image. In the shooting mode for shooting a subject, the image sensor 15 captures a recording image (main image) at the time of release, and outputs a through image by thinning out at predetermined intervals even during standby for shooting. The through image data is used for various arithmetic processes by the CPU 28 and display on the monitor 23.

  The analog processing unit 16 is an analog front end circuit that performs analog signal processing on the output of the image sensor 15. The analog processing unit 16 has a CDS circuit and a gain circuit inside. The CDS circuit of the analog processing unit 16 reduces the noise component of the output of the image sensor 15 by correlated double sampling. The gain circuit of the analog processing unit 16 amplifies the gain of the input signal based on an instruction from the CPU 28. In the gain circuit described above, the imaging sensitivity corresponding to the ISO sensitivity can be adjusted.

The A / D conversion unit 17 performs A / D conversion on the analog image signal output from the analog processing unit 16. The output of the A / D converter 17 is connected to the first memory 19.
The TG 18 supplies timing pulses to the image sensor 15, the analog processing unit 16, and the A / D conversion unit 17 based on instructions from the CPU 28. The drive timing of the image sensor 15, the analog processing unit 16, and the A / D conversion unit 17 is controlled by the timing pulse of the TG 18.

The first memory 19 is a buffer memory for temporarily recording image data in the pre-process and post-process of image processing described later.
The image processing unit 20 performs various types of image processing on the main image data in the above-described shooting mode. Furthermore, the image processing unit 20 generates a display image (view image) from the image signal of the through image in accordance with an instruction from the CPU 28 in the shooting mode. The image processing unit 20 also executes processing for compressing the main image data in the JPEG format or the like, and processing for decompressing and restoring the compressed main image data during reproduction.

  A connector for connecting the recording medium 31 is formed in the recording I / F 21. Then, the recording I / F 21 executes writing / reading of the data of the main image with respect to the recording medium 31 connected to the connector. The recording medium 31 is composed of a hard disk, a memory card incorporating a semiconductor memory, or the like. In FIG. 1, a memory card is illustrated as an example of the recording medium 31.

  The display I / F 22 controls the display on the monitor 23 based on an instruction from the CPU 28. The monitor 23 displays various images in accordance with instructions from the CPU 28 and the display I / F 22. The monitor 23 of this embodiment is a liquid crystal monitor. The monitor 23 displays a moving image of the view image during shooting standby in the shooting mode. The monitor 23 displays various information necessary for shooting (for example, the number of frames that can be shot, the position of the focus detection area, the frame display of the face area detected by the face detection process described later, etc.) by the on-screen function. ) Can be superimposed on the view image. Further, the monitor 23 can display a reproduction image based on the data of the main image, a menu screen that can be input in a GUI (Graphical User Interface) format, etc. (the illustration of the reproduction image and the menu screen on the monitor 23 is omitted). To do).

The release button 24 receives an instruction input for starting an exposure operation from the user. The operation unit 25 has a plurality of input buttons such as a cross key and a determination button. The operation unit 25 receives various setting change inputs from the user.
The speaker 26 is provided for outputting sound to the outside of the electronic camera at the time of shooting. The speaker 26 is connected to the CPU 28.

The flash light emitting unit 27 includes, for example, a xenon arc tube, a main capacitor that stores light emission energy, a reflector or lens member for efficiently irradiating the subject with flash light, a light emission control circuit, and the like.
The CPU 28 controls the operation of each part of the electronic camera according to a sequence program stored in a ROM (not shown). Then, the CPU 28 executes various calculations such as auto focus (AF) calculation, automatic exposure (AE) calculation, and auto white balance (AWB) calculation. The CPU 28 of the first embodiment also functions as a face detection unit 28a and a face authentication unit 28b.

  The face detection unit 28a extracts feature points from the data of the through image or the main image, and detects the face area of the subject, the size of the face, and the like. For example, the face detection unit 28a extracts a face region by a feature point extraction process described in Japanese Patent Laid-Open No. 2001-16573. Moreover, as said feature point, each end point of an eyebrow, eyes, nose, lips, the intermediate point, etc. are mentioned, for example. In FIG. 2A and FIG. 2B, the positions of feature points are indicated by black dots as an example in the present embodiment. In the present specification, description of individual feature points is omitted.

  The face authentication unit 28b generates face authentication data based on the feature points detected by the face detection unit 28a. For example, the face authentication unit 28b generates face authentication data of a registered person to be authenticated from the position of the detected feature point of the face, the relative distance of each feature point, and the like. Further, the face authentication unit 28b performs face authentication processing for determining whether or not the person's face in the shooting screen is the face of the person in the face authentication data. The specific content of this face authentication process will be described later.

The second memory 29 is connected to the CPU 28. In the second memory 29, face authentication data (registration data) generated by the face authentication unit 28b is recorded. In the second memory 29, a group folder is generated for each registered person. Therefore, a plurality of face authentication data related to the same registered person are grouped by the group folder.
Further, the profile data of the registered person is recorded in each group folder of the second memory 29 in association with each other. In this profile data, for example, the names of registered persons (for example, name, nickname, etc.) and attribute information (gender, age, address, telephone number, email address, organization to which they belong, other notes, etc.) It is recorded. It should be noted that various settings of the electronic camera (for example, exposure correction at the time of shooting, image processing settings, etc.) applied when authenticating the registered person may be included in the profile data.

Next, a photographing operation with the electronic camera of the first embodiment will be described with reference to the flowchart of FIG. In the following description, it is assumed that the face authentication function is turned on on the menu screen or the like.
Step 101: The CPU 28 drives the image sensor 15 to start obtaining a through image. The imaging element 15 acquires an image signal of a through image by thinning out reading at predetermined intervals. The image processing unit 20 sequentially generates view images based on through-image data. The view image is displayed as a moving image on the monitor 23 at the time of shooting standby. Therefore, the user can perform framing for determining the shooting composition based on the view image on the monitor 23.

Step 102: The face detection unit 28a of the CPU 28 performs a face detection process on the through image data to detect a face area in the shooting screen.
Step 103: The CPU 28 displays the result of the face detection in S102 on the monitor 23 and accepts an input for selecting a person to perform face authentication processing from the user.
For example, when a face of a person is detected on the shooting screen, the CPU 28 superimposes a rectangular frame on the position of the face area on the view image and displays it on the monitor 23 (see FIG. 4). Thereby, the user can confirm the result of face detection with the view image.

  Further, the user can select a face to be subjected to face authentication processing from the detected faces by operating the operation unit 25. Then, the CPU 28 designates a face area to be subjected to face authentication processing among the detected faces according to an input from the operation unit 25. If there is no user designation input operation at the time of face detection, the CPU 28 designates all detected face areas as targets for face authentication processing.

Step 104: The CPU 28 determines whether or not the release button 24 is half-pressed. When the release button 24 is half-pressed (YES side), the process proceeds to S105. On the other hand, when the release button 24 is not half-pressed (NO side), the CPU 28 returns to S102 and repeats the above operation.
Step 105: The CPU 28 determines whether or not a face area to be subjected to face authentication processing is designated. If the target for face authentication processing is designated (YES side), the process proceeds to S106. On the other hand, when the face authentication processing target is not designated (NO side), the process proceeds to S115.

Step 106: The CPU 28 executes face authentication processing on the face area designated as the target of face authentication processing. In this face authentication process, the zoom lens 11 is zoomed up as necessary to increase the success rate of face authentication. Details of the face authentication process in S106 will be described later.
Step 107: The CPU 28 displays the result of the face authentication process in S106 on the monitor 23. As an example, FIG. 5 shows a display example of the face authentication result. In FIG. 5, the face area that the CPU 28 has authenticated as a registered person is shown on the monitor 23 by means such as changing the thickness and color of the rectangular frame of the view image shown in FIG. Thereby, the user can confirm the result of the face authentication process in S106 with the view image.

Step 108: If the zoom lens 11 has been moved in the face authentication process of S105 described above, the CPU 28 drives the first lens drive unit 12 to return the zoom lens 11 to the half-pressed state. Of course, this step is omitted when zooming is not performed in the face authentication process.
Step 109: The CPU 28 executes AF by a contrast detection method or the like, and also executes AE calculation and AWB calculation to adjust shooting conditions (aperture value, exposure time, imaging sensitivity).

Here, if a registered person is detected in the face authentication process of S106, the CPU 28 may execute AF based on the face of the registered person. When a registered person is detected in the face authentication process in S106, the CPU 28 may read profile data corresponding to the registered person and adjust the shooting conditions according to the registered person.
Step 110: The CPU 28 determines whether or not the release button 24 is fully pressed. When the release button 24 is fully pressed (YES side), the process proceeds to S105. On the other hand, when the release button 24 is not fully pressed (NO side), the CPU 28 waits for the release button 24 to be fully pressed.

Step 111: The CPU 28 drives the image sensor 15 to capture the main image. Thereafter, the image processing unit 20 generates image data of the main image. The CPU 28 records the image data on the recording medium 31 in a file format that conforms to the Exif (Exchangeable image file format for digital still cameras) standard.
Step 112: The CPU 28 determines whether or not the registered person has been authenticated in the face authentication process of S106. When the registered person is authenticated (YES side), the process proceeds to S113. On the other hand, if the registered person is not authenticated (NO side), the process proceeds to S114.

Step 113: The CPU 28 executes processing for adding additional data to the image data file based on the profile data of the authenticated registered person. The additional data adding process in S113 is performed by one of the following methods, for example.
First, the CPU 28 adds part or all of the profile data to the image data file as additional data. In this case, based on the additional data of the image file, the viewer of the image file can acquire various information (name etc.) of the registered person who has been photographed.

  Here, in the profile data, items to be added by the CPU 28 are previously input to the CPU 28 by the user on a menu screen or the like. The CPU 28 may add the additional data to the image file by using, for example, an Exif MakerNote tag. Alternatively, the CPU 28 may embed the additional data in the image data by means such as a digital watermark.

Second, the CPU 28 sets the file name of the image data based on the profile data. For example, the CPU 28 assigns a file name including a part of the name of the authenticated registered person to the image file. In this case, the registered person photographed in the main image can be easily searched by referring to the file name.
Step 114: The CPU 28 generates face authentication data (registered data) from the feature points of the photographed person used in the face authentication process of S106. Then, the CPU 28 records this registration data in the second memory 29. It should be noted that this step is omitted when the user turns off the registration of face authentication data to the CPU 28 on the menu screen.

Here, the CPU 28 records the face authentication data of the registered person who has been face-authenticated in the group folder of the registered person. Thereby, since the number of samples of face authentication data increases, the authentication precision of the face authentication from the next time can be improved.
On the other hand, for face authentication data of an unregistered person, the CPU 28 generates a new group folder and records the face authentication data in the group folder. This makes it possible to easily register a person who is a target for face authentication. For a new group folder, the user can register profile data again later on the menu screen. Then, the CPU 28 ends a series of shooting operations.

  Step 115: In this case, the CPU 28 performs AF calculation and AE calculation with the same algorithm as in the normal shooting mode in which face authentication is not performed. Then, the CPU 28 captures the main image in response to the release button 24 being fully pressed. Thereafter, the image processing unit 20 generates image data of the main image. The image data is finally recorded on the recording medium 31. In this case, various processes based on profile data and generation of face authentication data are not performed. Above, description of the flowchart of FIG. 3 is complete | finished.

Next, the face authentication process will be described in more detail. FIG. 6 is a flowchart showing the control executed by the CPU 28 in the face authentication process of S106 described above.
Step 201: The CPU 28 starts a time count for measuring the allowable time for the face authentication process.
Step 202: The CPU 28 sets the priority for performing the face authentication process on the face area to be subjected to the face authentication process.

  For example, the CPU 28 sets the priority order of the face authentication processing in the order in which the user specified the face area in S103. Alternatively, the CPU 28 sets the priority order based on the face size and the face position in the shooting screen. As a specific example, the CPU 28 regards the face of a person located at the center of the shooting screen as the main subject and raises the priority. Further, the CPU 28 sets a higher priority for a person who has a large face and is on the near side. In this case, a person with high priority is more likely to be able to perform face authentication without zooming, so a series of face authentication can be performed efficiently. Alternatively, the CPU 28 may increase the priority of the face area in the focused state over the face area in the out-of-focus state.

Step 203: Based on the priority order of S202, the CPU 28 determines a face area (determination target face area) for which face authentication is determined on the shooting screen.
Step 204: The CPU 28 executes a registration data normalization process for each registered person in the second memory 29. Note that this step is omitted when the registration data is registered in a normalized state in advance.

Specifically, the normalization process in S204 is performed by the following method.
First, the CPU 28 obtains the relative distance between each feature point at each of the feature points indicated by the registration data in the second memory 29 at a plurality of locations. The position that takes the relative distance between the feature points can be arbitrarily determined. Here, as an example, among the feature points shown in FIG. 2A, the distance between both ends of the mouth (first distance), the distance between the eyes of both eyes (second distance), the distance from the bottom of the nose to the lips The distance (third distance), the distance from the eyebrows to the bottom of the nose (fourth distance), and the like are obtained.

  Second, the CPU 28 determines a reference distance from the relative distances obtained in the first step. Although the position of the reference distance can be arbitrarily determined, it is necessary to set the position of the reference distance to be the same for comparison. Therefore, when normalizing the face authentication data of each registered person, it is desirable to make the position of the reference distance common. Here, as an example, the following description will be given using the length of the straight line connecting the pupils of both eyes (second distance) as a reference distance.

Thirdly, the CPU 28 calculates the ratio between each relative distance obtained in the first step and the reference distance obtained in the second step. Then, the CPU 28 treats the calculated ratio value as normalized authentication data. That is, in the above example, the value obtained by dividing the first distance by the second distance, the value obtained by dividing the third distance by the second distance, and the like constitute normalized registration data.
In this embodiment, as will be described later, zooming is performed during face authentication. The ratio value obtained in the third step is substantially the same before and after zooming for the same face. Therefore, according to the normalization process, authentication can be performed even for a zoomed face.

  Here, the distance between the above feature points may change depending on the orientation of the face. For example, when the face is sideways with respect to the camera, the relative distance (the first distance and the second distance described above) of the feature points in the horizontal direction of the face changes on the shooting screen. Further, when the face is facing upward or downward with respect to the camera, the relative distances (the above-described third distance and fourth distance) of the feature points in the vertical direction of the face change on the shooting screen. Therefore, when performing the above normalization processing, a plurality of reference distances are set in different directions of the face, and registration data corresponding to a plurality of directions is generated by obtaining the value of the above ratio for each reference distance. It is preferable to do. In this case, the possibility of performing face authentication is improved regardless of the face orientation of the photographed person.

Step 205: The CPU 28 acquires feature point data (determination data) of the face area to be determined from the through image of the image sensor 15. Note that as for the feature point data of the face area, the CPU 28 may apply the data acquired in the face detection process of S102 as it is.
Step 206: The CPU 28 normalizes the determination data acquired from the through image in S205. Since the specific method of the normalization process in S206 is performed in the same manner as in S204, redundant description is omitted. In this normalization process, the position at which the relative distance is taken between the feature points and the position at which the reference distance is taken are set in common with the case of S204.

  Here, when some of the facial feature points cannot be detected from the through image, the CPU 28 may perform the normalization process using only the feature points detected from the through image. For example, when half of the face is hidden, the CPU 28 performs normalization processing with the feature points acquired from the half face data. In the above, when the position of the reference distance cannot be detected, the CPU 28 needs to re-acquire the position of the reference distance and normalize the registered data again.

Step 207: The CPU 28 compares the registration data normalized in S204 with the determination data normalized in S206. And CPU28 calculates the likelihood which shows the probability that the person of the face area | region used as determination object corresponds to a registered person for every registered person.
Step 208: The CPU 28 determines whether or not the person in the face area to be determined corresponds to any registered person. Specifically, if there is a person with the highest likelihood calculated in S207 and the likelihood is equal to or greater than the threshold, the CPU 28 determines that the person in the face area to be determined corresponds to the registered person. . When it corresponds to a registered person (YES side), the process proceeds to S209. On the other hand, if it is not a registered person (NO side), the process proceeds to S211.

  Step 209: The CPU 28 determines whether there is a face area that has not been subjected to face authentication processing among the face areas specified in S103 (that is, there is a face area set with a lower priority than the face area to be determined). Determine whether or not. If the above requirement is satisfied (YES side), the process proceeds to S210. On the other hand, the case where the above requirement is not satisfied (NO side) corresponds to the case where all the face authentication processing for the face designated in S103 is completed. In this case, the processing of the subroutine shown in FIG. 6 is terminated and the process returns to S107.

Step 210: The CPU 28 changes the face area to be determined from the currently processed face area to the face area of the next priority. Thereafter, the CPU 28 returns to S205.
Step 211: The CPU 28 determines whether or not the count of allowable time for face authentication processing (S201) is within a threshold value. If it is within the threshold (YES side), the process proceeds to S212. On the other hand, if the threshold value is exceeded (NO side), the CPU 28 terminates the processing of the subroutine shown in FIG. 6 due to timeout and returns to S107. In this case, the CPU 28 treats the face area that is the current determination target and the face area that has not undergone the face authentication process as face areas that cannot be authenticated.

Step 212: The CPU 28 determines whether or not the zoom lens 11 can be zoomed to the telephoto side. If zooming to the telephoto side is possible (YES side), the process proceeds to S213. On the other hand, when zooming to the telephoto side cannot be performed (NO side), the CPU 28 treats the current determination target face area as a face area that cannot be authenticated. Then, the CPU 28 proceeds to S209.
Step 213: The CPU 28 performs control to move the zoom lens 11 to the telephoto side by a predetermined step width. Then, the CPU 28 returns to S205 and determines the next face authentication. Above, description of the flowchart of FIG. 6 is complete | finished.

Hereinafter, effects of the first embodiment will be described.
In the first embodiment, when face authentication cannot be performed, the CPU 28 drives the zoom lens 11 to execute zoom up (S208, S213). Therefore, in the next face authentication determination, the success rate of face authentication can be increased as compared to the previous determination.
Further, at the time of photographing the main image, the zoom lens 11 is returned to the half-pressed position and photographing is performed (S108). Therefore, even in a scene where a person is photographed together with a group photo or a landscape, it is possible to acquire a main image according to the user's intention while ensuring high accuracy of face authentication.

Furthermore, in the first embodiment, the registration data and the determination data are normalized based on the reference distance between feature points common to each face (S204 to S206). Therefore, even when comparing faces with different magnifications by zooming, face authentication can be performed with high accuracy.
(Description of Second Embodiment)
Hereinafter, the electronic camera of the second embodiment will be described. The following embodiment is a modification of the first embodiment, and the configuration of the electronic camera is the same as that of the first embodiment. Also, the flow of the shooting operation is the same as that shown in FIG. 3, but only the operation of the face authentication process described in FIG. 6 is partially different. Therefore, in the following embodiments, only differences from the first embodiment will be described, and redundant descriptions with the first embodiment will be omitted.

FIG. 7 is a flowchart showing the control executed by the CPU 28 in the face authentication process of S106 in the electronic camera of the second embodiment. Note that S301 to S312 in FIG. 7 correspond to S201 to S212 in FIG.
Step 313: The CPU 28 performs control to move the zoom lens 11 to the telephoto side by a predetermined step width.

Step 314: The CPU 28 determines whether or not the processing time for the current determination target is equal to or greater than a threshold value. If it is equal to or greater than the threshold (YES side), the process proceeds to S315. On the other hand, if it is less than the threshold value (NO side), the CPU 28 returns to S305 and determines the next face authentication.
Step 315: The CPU 28 causes the flash light emitting unit 27 to emit light and outputs sound from the speaker 26 in order to direct the attention of the subject to the camera. Thereafter, the CPU 28 returns to S305 to determine the next face authentication. In S315, the CPU 28 may omit one of the light emission from the flash light emitting unit 27 and the sound output from the speaker 26. Above, description of the flowchart of FIG. 7 is complete | finished.

According to the second embodiment, substantially the same effect as that of the first embodiment can be obtained. Furthermore, in the second embodiment, the face authentication success rate can be increased by directing the face of the subject to the camera by voice or the like.
(Description of the third embodiment)
FIG. 8 is a flowchart showing the control executed by the CPU 28 in the face authentication process of S106 in the electronic camera of the first embodiment. Note that S401 to S412 in FIG. 7 correspond to S201 to S212 in FIG.

  Step 413: The CPU 28 determines whether or not the face area to be determined is out of the shooting angle of view (out of frame) when the zoom lens 11 is zoomed. For example, if the zoom is to be performed when the face area to be determined is at the outer edge of the shooting screen, the CPU 28 determines that the frame is out. When the frame is out (YES side), the process proceeds to S414. On the other hand, when the frame is not out (NO side), the process proceeds to S416.

Step 414: The CPU 28 superimposes and displays on the view image of the monitor 23 a warning display indicating that the face area to be determined is out of frame due to zooming. The warning display may be an iconized mark or a message display using characters.
If there is a warning display in S414, the user can also change the camera orientation or shooting position in order to perform face authentication on the determination target. In this case, the CPU 28 resumes the photographing operation when an operation for resuming face authentication is received from the operation unit 25. The CPU 28 may make the above warning by voice.

Step 415: The CPU 28 determines whether or not an operation for resuming face authentication by the user has been received from the operation unit 25. If there is an operation for resuming face authentication (YES side), the process proceeds to S416. On the other hand, when there is no operation for resuming face authentication (NO side), the CPU 28 returns to S411 and repeats the above operation.
Step 416: The CPU 28 performs control to move the zoom lens 11 to the telephoto side by a predetermined step width. Then, the CPU 28 returns to S405 and determines the next face authentication. Above, description of the flowchart of FIG. 8 is complete | finished. In the third embodiment, when the user changes the camera orientation or shooting position between S414 and S415, the user returns the camera orientation to the same state as when half-pressed and shoots the main image. .

According to the third embodiment, substantially the same effect as that of the first embodiment can be obtained. Furthermore, in the third embodiment, when the subject's face deviates from the shooting angle of view by zooming up, the success rate of face authentication can be increased by alerting the user and changing the shooting angle of view.
(Supplementary items of the embodiment)
(1) The example in which the electronic camera of the above embodiment performs authentication of a person's face has been described. However, the present invention is widely applicable to general pattern authentication including authentication of animal faces such as dogs, cats, and birds. Can be applied. Further, in the above embodiment, the CPU 28 does not need to perform authentication using all the feature points of the face, but performs authentication using only the feature points of a specific part of the human face (for example, eyes, nose, mouth, etc.). It may be.

(2) In the above embodiment, the CPU 28 may set an upper limit on the number of persons to be determined. Further, the CPU 28 may set a limit on the number of determinations at the time of authentication. Further, the CPU 28 may exclude the face of the person at the outer edge of the shooting screen from the selection of the determination target in order to prevent the frame-out due to the zoom-up.
(3) Further, when a plurality of determination target face areas are set in the above embodiment, the CPU 28 may simultaneously perform the authentication process for a plurality of face areas in one face authentication process. In this case, the number of movements of the zoom lens 11 can be further reduced.

  (4) When the zoom lens 11 is moved as in the above embodiment, the amount of information of the image to be determined increases due to zooming in, and the luminance distribution characteristic in the shooting screen changes, so that the authentication accuracy of face authentication Will improve. However, there is a possibility that the authentication accuracy may be adversely affected by a decrease in luminance accompanying zooming of the zoom lens 11. For this reason, the CPU 28 may increase the gain in the analog processing unit 16 or the image processing unit 20 in accordance with the zoom-up amount of the zoom lens 11 to exclude an adverse effect on the authentication accuracy.

  (5) In the above embodiment, when the face authentication fails, the CPU 28 may set the resolution of the through image to be higher than the previous time. In this case, since the amount of information of the face area to be determined is larger than the previous determination, it is easy to improve the accuracy of face authentication. Further, when increasing the resolution of the through image, the CPU 28 may omit zooming by the zoom lens 11. Furthermore, the CPU 28 may perform electronic zoom as necessary in the above embodiment.

The block diagram which shows the structure of the electronic camera of 1st Embodiment. The figure which shows the example of arrangement | positioning of the feature point in 1st Embodiment. Flowchart explaining photographing operation with electronic camera of first embodiment The figure which shows the example of a display of the view image at the time of face detection The figure which shows the example of a display of the face authentication result in a view image Flow chart for explaining the contents of face authentication processing in the first embodiment Flow chart for explaining the contents of face authentication processing in the second embodiment Flow chart for explaining the contents of face authentication processing in the third embodiment

Explanation of symbols

DESCRIPTION OF SYMBOLS 11 ... Zoom lens, 12 ... 1st lens drive part, 15 ... Image sensor, 22 ... Display I / F, 23 ... Monitor, 25 ... Operation part, 26 ... Speaker, 27 ... Flash light emission part, 28 ... CPU, 28a ... Face detection unit, 28b ... face authentication unit, 29 ... second memory

Claims (7)

An imaging unit that captures a subject image by the imaging optical system;
A zoom adjustment unit for adjusting the magnification of the subject image;
A recording unit in which registration data indicating a feature point of an authentication target is recorded in advance;
A subject authentication unit that determines whether the subject imaged by the imaging unit matches the authentication target based on the registration data;
A control unit that enlarges the magnification of the subject image and causes the subject authentication unit to re-execute the determination when the subject authentication unit determines that the subject does not match the authentication target;
An electronic camera comprising: The electronic camera according to claim 1,
An electronic camera, wherein the authentication target is a human face. The electronic camera according to claim 2,
A face detection unit that detects the face of the person from the shooting screen, and extracts feature points of the detected face of the person to generate determination data;
The subject authentication unit acquires a reference distance connecting two specific feature points, and performs a normalization process for obtaining a ratio between a relative distance between the feature points and the reference distance on the registration data and the determination data. An electronic camera that executes the determination on the basis of the data after the normalization processing. The electronic camera according to claim 2,
A face detection unit for detecting a person's face from the shooting screen;
A monitor that presents the face detected by the face detection unit;
An operation unit for receiving a designation operation for designating a face to be determined from a user;
The subject authentication unit performs the determination on a face designated by the designation operation. The electronic camera according to claim 1,
The electronic camera further comprising: a first notification unit that calls attention to the subject when the subject authentication unit determines that the subject does not match the authentication target. The electronic camera according to claim 1,
An electronic camera, further comprising: a second notification unit that alerts a user when the subject subject to the determination deviates from a shooting angle of view due to enlargement of the magnification of the subject image. The electronic camera according to claim 1,
In the recording unit, profile data describing the authentication target is recorded in association with the registration data,
When the subject authentication unit determines that the subject matches the authentication target, the control unit adds additional data based on the profile data to an image file including a recording image in which the authentication target is captured. An electronic camera characterized by being added.

Images