JP2011076457A - Face image correction device, face image correction method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To correct face image data with easy operation, and to apply even a non-full-faced image to face detection. <P>SOLUTION: An imaging device 100 includes: an image retrieval part 3a retrieving face image data similar to specific face image data specified based on predetermined operation of an operation input part from a plurality of image data stored in a storage medium; a designation decision part 3h deciding whether the face image data obtained as a result of the retrieval by the image retrieval part are specified as data to be used for correction; and a face-recognition data generation part 4a correcting the face image data to be stored in a memory for face recognition data, based on the face image data and the specific face image data, when the designation decision part decides that the face image data are specified as the data to be used for correction. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a face image correction apparatus, a face image correction method, and a program.

  Conventionally, in a technique related to a face verification apparatus using a database automatic update method and its system, when face image data of a person whose face is to be verified is registered in the verification system, a coordinate pair of both eyes of the face image data is detected, and the coordinate pair is detected. Normalization of the registered face image by calculating the center point of the face, moving the coordinate pair in the vertical and horizontal directions and diagonal directions based on the coordinate pair, and creating a feature classifier through a predetermined calculation process An invention of a face verification method and system for improving accuracy is known (see, for example, Patent Document 1).

JP 2003-317101 A

  However, the face verification method and system of the above-mentioned Patent Document 1 is intended for aging of only the front face, and is not suitable for verification when the individual face is viewed from all angles. For this reason, there is a problem that it is difficult to apply to the face detection technology of an individual's face used in recent digital cameras and the like.

  Accordingly, the present invention has been made in view of such problems. Face image data can be corrected with a simple operation, and face detection of an individual's face can be performed even with an image in an angle or direction other than the front. A face image correction apparatus, a face image correction method, and a program that can be applied to the above.

In order to solve the above-described problem, a face image correction apparatus according to the invention described in claim 1
Storage means for storing at least one face image data, designation means for designating specific face image data among at least one face image data stored in the storage means, and storage medium for storing a plurality of image data A search means for searching for face image data similar to the specific face image data specified by the specifying means from among a plurality of image data stored in the storage medium, and as a result of the search by the search means Determination means for determining whether or not the obtained face image data is designated as data used for the correction processing, and the determination means determines that the face image data is designated as data used for the correction processing. Then, based on the face image data and the specific face image data designated by the designation means, the face image data to be stored in the storage means It is characterized by and a correcting means for correcting.

The invention according to claim 2 is the face image correction apparatus according to claim 1,
The correction means includes generation means for generating new face image data using face image data specified as data used for the correction processing and specific face image data specified by the specification means. It is characterized by that.

The invention according to claim 3 is the face image correction device according to claim 1 or 2,
As a result of the search by the search means, a first determination means for determining whether or not similar face image data has been obtained, and if it is determined by the first determination means that similar face image data has not been obtained. And first notification means for notifying that new face image data is acquired by imaging.

According to a fourth aspect of the present invention, in the face image correcting device according to the third aspect,
An imaging means, a first detection judging means for judging whether or not an instruction to newly acquire face image data by imaging is detected based on the notification by the first notifying means, and the first detection judging means; When it is determined by the detection determination means that the instruction is detected, the apparatus further includes activation control means for controlling to activate the imaging means.

The invention according to claim 5 is the face image correction apparatus according to any one of claims 1 to 4,
The retrieval unit retrieves, as candidate face image data, image data having a similarity with the specific face image data designated by the designation unit from a plurality of image data stored in the storage medium. The candidate face image data can be specified as data used for the correction process.

The invention according to claim 6 is the face image correction apparatus according to any one of claims 3 to 5,
The storage medium is configured to be detachable from the apparatus main body. When the first determination unit determines that similar face image data has not been obtained, a new storage medium different from the storage medium is used. It is characterized by further comprising a second notifying means for notifying that it is to be worn.

The invention according to claim 7 is the face image correction apparatus according to claim 6,
After notifying by the second notifying means, the apparatus further comprises second determining means for determining whether or not a new storage medium is mounted, and the search means further includes a new storage medium by the second determining means. When it is determined that it has been mounted, the face image data similar to the specific face image data specified by the specifying means is searched from this new storage medium.

The invention according to claim 8 is the face image correction apparatus according to any one of claims 3 to 7,
When it is determined by the first determination means that similar face image data has not been obtained, a third notification means for notifying that the face image data stored in the storage means outside the apparatus is searched is further provided. It is characterized by that.

The invention according to claim 9 is the face image correction apparatus according to claim 8,
Second detection for determining whether or not an instruction to search for storage means outside the apparatus has been detected based on the communication means communicating with the communication apparatus outside the apparatus and the notification by the third notification means When it is determined that the instruction is detected by the determination unit and the second detection determination unit, the communication unit is activated, and the specific face image data specified by the specification unit with respect to the storage unit outside the apparatus Search instruction means for instructing search for face image data similar to the above.

The invention according to claim 10 is the face image correction apparatus according to any one of claims 1 to 9,
The image processing apparatus further includes display means for displaying the face image data searched by the search means.

The face image correction method of the invention according to claim 11
A face image correction method using a face image correction device comprising a storage means for storing at least one face image data, wherein specific face image data is stored in at least one face image data stored in the storage means. A process for specifying, a process for searching for face image data similar to the specific face image data from among a plurality of image data stored in a storage medium, and face image data obtained as a result of the search are subjected to correction processing. When it is determined that the face image data is specified as the data used for the correction process, the face image data and the specific face image data are determined. And a process of correcting the face image data to be stored in the storage means.

The program of the invention described in claim 12 is:
A designation unit for designating specific face image data among at least one face image data stored in the storage unit, a storage medium comprising a computer of a face image correction apparatus comprising storage unit for storing at least one face image data Search means for searching for face image data similar to the specific face image data designated by the designation means from among a plurality of image data stored in the image data, and face image data obtained as a result of the search by the search means Determining means for determining whether the face image data has been designated as data used for the correction processing; And the face image data to be stored in the storage means based on the specific face image data designated by the designation means. Means, is characterized in that to function as a.

  According to the present invention, face image data can be corrected with a simple operation, and an image of an angle or direction other than the front can be applied to face detection of an individual's face.

It is a block diagram which shows schematic structure of the imaging device of one Embodiment to which this invention is applied. It is a figure which shows typically an example of the data for simple face recognition and the data for detailed face recognition. 4 is a flowchart illustrating an example of an operation related to face recognition image correction processing by the imaging apparatus of FIG. 1. It is a flowchart which shows the continuation of the face recognition image correction process of FIG.

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. However, the scope of the invention is not limited to the illustrated examples.
FIG. 1 is a block diagram illustrating a schematic configuration of an imaging apparatus 100 according to an embodiment to which the present invention is applied.

The imaging apparatus 100 according to the present embodiment is for simple face recognition corresponding to specific image data designated based on a predetermined operation of the operation input unit 11 by the user from among a plurality of image data stored in the storage medium 9. When similar image data similar to the data d1 (see FIG. 2) is searched and it is determined that the similar image data obtained as a result of the search is designated as data used for the correction process, the similar image data and a specific image data are specified. Based on the image data, the face image data to be stored in the face recognition data memory 5 is corrected to generate detailed face recognition data d2 (see FIG. 2).
Specifically, as illustrated in FIG. 1, the imaging apparatus 100 includes an imaging unit 1, an image data generation unit 2, a face detection processing unit 3, an image processing unit 4, a face recognition data memory 5, A display control unit 6, a display unit 7, a storage medium control unit 8, a storage medium 9, a communication control unit 10, an operation input unit 11, and a central control unit 12 are provided. The imaging apparatus 100 is configured to be able to communicate with an external database DB connected to the communication network N.

The imaging unit 1 captures a subject and generates an image frame. Specifically, although not shown, the imaging unit 1 includes a lens unit including a plurality of lenses such as a zoom lens and a focus lens, a diaphragm that adjusts the amount of light passing through the lens unit, and a CCD ( The image sensor includes an electronic image pickup unit that includes an image sensor such as a charge coupled device (CMOS) or a complementary metal-oxide semiconductor (CMOS), and converts an optical image that has passed through various lenses of the lens unit into a two-dimensional image signal.
Although not shown, the imaging unit 1 includes an imaging control unit including a timing generator, a driver, and the like. Then, the imaging control unit scans and drives the electronic imaging unit with a timing generator and a driver, converts the optical image into a two-dimensional image signal with the electronic imaging unit every predetermined cycle, and starts from the imaging region of the electronic imaging unit. Image frames are read out for each screen and output to the image data generation unit 2.
The imaging control unit performs AE (automatic exposure processing), AF (automatic focusing processing), AWB (automatic white balance), and the like as adjustment control of imaging conditions.

The image data generation unit 2 appropriately adjusts the gain for each of the RGB color components with respect to the analog value signal of the image data transferred from the electronic imaging unit, and then samples and holds the A / The digital data is converted into digital data by a D converter (not shown), and color processing including pixel interpolation processing and γ correction processing is performed by a color process circuit (not shown), and then a luminance signal Y and a color difference signal Cb, Cr (image data in YUV color space) is generated.
The luminance signal Y and the color difference signals Cb and Cr output from the color process circuit are DMA-transferred to a memory used as a buffer memory via a DMA controller (not shown).

  The face detection processing unit 3 includes an image search unit 3a, a search determination unit 3b, a notification control unit 3c, an instruction detection determination unit 3d, an attachment determination unit 3e, an activation control unit 3f, a search instruction unit 3g, And a designation determination unit 3h.

The image search unit 3a searches for image data similar to the simple face recognition data d1 using the simple face recognition data d1 (described later) related to the person to be registered in the face recognition process.
Specifically, the image search unit 3a uses the simple face recognition data d1 generated by the face recognition data generation unit 4a (described later) of the image processing unit 4 in the face recognition image correction process to store the storage medium. 9 is searched for image data similar to the simple face recognition data d1. The image search unit 3a then selects image data whose similarity with the simple face recognition data d1 is a predetermined value or more among the plurality of image data stored in the storage medium 9, and is similar image data (candidate face image data). As specified. In other words, the image search unit 3a selects the image data of the person to be registered in the face recognition process specified based on a predetermined operation of the operation input unit 11 by the user from the plurality of image data stored in the storage medium 9. Image data whose similarity with the simple face recognition data d1 generated corresponding to (face image data) is a predetermined value or more is searched as candidate face image data.
Further, when a new storage medium different from the mounted storage medium 9 is loaded, the image search unit 3a searches the new storage medium for image data similar to the simple face recognition data d1.
Note that any recognition algorithm may be used as a method of image search by the image search unit 3a, and this algorithm may have a learning function. For example, a method using principal component analysis may be mentioned. .
Here, the image search unit 3a selects the image of the person to be registered for the face recognition process designated based on a predetermined operation of the operation input unit 11 by the user from the plurality of image data stored in the storage medium 9. Search means for searching for image data (face image data) similar to the data (face image data) is configured.

  The search determination unit 3b determines whether similar image data (face image data) similar to the simple face recognition data d1 is obtained as a result of the image search by the image search unit 3a. That is, the search determination unit 3b determines whether face image data similar to the face image data of the person to be registered in the face recognition process is obtained as the first determination unit.

When the search determination unit 3b determines that similar image data similar to the simple face recognition data d1 has not been obtained, the notification control unit 3c controls notification of a similar image search instruction using another method.
Specifically, the notification control unit 3c controls the display control unit 6 to give a message for instructing acquisition of new image data (face image data) by imaging or a new storage medium 9 that is different from the mounted storage medium 9. A message for instructing the mounting of the storage medium, a message for instructing to search for image data (face image data) stored in an external database (storage means external to the apparatus) DB outside the imaging apparatus 100, and the like are displayed on the display unit 7. A notification is displayed.
Here, the notification control unit 3c, the display control unit 6 and the display unit 7 are mounted with a new storage medium different from the first notification unit and the storage medium 9 for notifying that new face image data is acquired by imaging. A second notifying unit for informing the user, and a third notifying unit for informing the user to search for face image data stored in a storage unit outside the imaging apparatus 100.

The instruction detection determination unit 3d acquires a similar image by another method based on a predetermined operation of the operation input unit 11 by the user after notification of a similar image search instruction by another method under the control of the notification control unit 3c. It is determined whether an instruction to that effect has been detected.
Specifically, under the control of the notification control unit 3c, a message instructing acquisition by capturing new image data is displayed on the display unit 7, and then based on a predetermined operation of the operation input unit 11 by the user. Depending on whether or not a signal related to the acquisition of the output new image data is input, the instruction detection determination unit (first detection determination unit) 3d newly acquires the image data (face image data) by the imaging. ) Is detected.
Further, under the control of the notification control unit 3c, a message instructing the search of the image data stored in the external database (storage unit) DB outside the imaging apparatus 100 is displayed on the display unit 7, and then by the user. Depending on whether or not a signal related to the search of image data outside the imaging apparatus 100 output based on a predetermined operation of the operation input unit 11 is input, an instruction detection determination unit (second detection determination unit) 3d. Determines whether an instruction to search the external database DB outside the imaging apparatus 100 is detected.

The attachment determination unit 3e determines whether or not a new storage medium has been attached based on a predetermined operation by the user after notification of a similar image search instruction by another method under the control of the notification control unit 3c.
That is, under the control of the notification control unit 3c, after a message for instructing the mounting of a new storage medium different from the mounted storage medium 9 is displayed on the display unit 7, the mounting determination unit 3e As the determination means, it is determined whether or not a new storage medium has been loaded, depending on whether or not a signal output from the storage medium control unit 8 has been input based on the user's attachment / detachment operation of the storage medium 9.

The activation control unit 3f controls the imaging unit 1 to be activated when it is determined by the instruction detection determination unit 3d that an instruction to newly acquire image data is detected by imaging.
Specifically, the activation control unit 3 f outputs a signal instructing activation of the imaging mode as the operation mode of the imaging device 100 to the imaging unit 1 to activate the imaging unit 1, and the imaging unit 1 selects the subject. Let's take an image. At this time, the image search unit 3a searches for image data (face image data) similar to the simple face recognition data d1 from the live view image generated by imaging by the imaging unit 1.
Here, the activation control unit 3f includes an activation control unit that controls to activate the imaging unit 1 when the instruction detection determination unit 3d determines that an instruction to newly acquire face image data is detected by imaging. It is composed.

When it is determined by the instruction detection determination unit 3d that the instruction to search the storage unit outside the imaging apparatus 100 is detected, the search instruction unit 3g activates the communication control unit 10 and then starts the communication control unit 10 The storage unit outside the imaging apparatus 100 is instructed to search for image data similar to the simple face recognition data d1.
Specifically, the search instruction unit 3g outputs a signal instructing the activation to the communication control unit 10 to activate the communication control unit 10, and then externally transmits the communication control unit 10 via the communication network N. The database DB is accessed, and a search instruction for image data (face image data) similar to the simple face recognition data d1 is transmitted.
Here, when it is determined by the instruction detection determination unit 3d that the instruction to search the storage unit outside the imaging apparatus 100 is detected, the search instruction unit 3g activates the communication control unit 10 and externals the imaging apparatus 100. Search instruction means for instructing the external database (storage means) DB to search for face image data similar to the face image data of a person to be registered for face recognition processing.

The designation determination unit 3h determines whether the similar image data (face image data) obtained as a result of the search is designated as data used for the generation process (correction process) of the detailed face recognition data d2.
Specifically, at least one of the similar images displayed on the display unit 7 as a result of the search by the image search unit 3a or the external database DB is output based on a predetermined operation of the operation input unit 11 by the user. In accordance with whether or not a signal related to the designation of the similar image is input, the designation determination unit 3h determines whether or not it has been designated as data used for the generation processing of the detailed face recognition data d2.
Here, the designation determination unit 3h constitutes a determination unit that determines whether or not face image data obtained as a result of the search by the search unit is specified as data used for the correction process.

The image processing unit 4 includes a face recognition data generation unit 4a that generates simple face recognition data d1 and detailed face recognition data d2.
In the face recognition image correction process, the face recognition data generation unit 4a determines the target of the face recognition process from a plurality of images displayed on the display unit 7 based on a predetermined operation of the operation input unit 11 by the user. When any one image is designated as a registered image of a person, a predetermined conversion process (for example, zoom, parallel movement, rotation, etc.) is performed on the image, and the face size and eye position are normalized. As a result, the simplified face recognition data (see FIG. 2) d1 is generated.
The normalization may be performed manually by the user, or automatically using face detection and part recognition.

Further, the face recognition data generation unit 4a, based on a predetermined operation of the operation input unit 11 by the user, image data selected and designated as a registered image of a person to be subjected to face recognition processing, and detailed face recognition data d2 Detailed face recognition data d2 is generated based on at least one similar image data designated as data used in the generation process (see FIG. 2).
Specifically, when it is determined by the designation determination unit 3h that any similar image data has been designated as data used for the generation processing of the detailed face recognition data d2, a face recognition data generation unit (generation unit) 4a generates detailed face recognition data d2 as new face image data stored in the face recognition data memory 5 using the image data selected and designated as the registered image of the person and the similar image data. The face recognition data generation unit 4a performs correction processing on the simple face recognition data d1 based on the image data selected and designated as the registered image of the person and the similar image data, thereby performing detailed face recognition. Data d2 may be generated.
Here, the face recognition data generation unit 4a determines that similar image data (face image data) is specified as data used for the generation processing (correction processing) of the detailed face recognition data d2 by the specification determination unit 3h. Then, the correction for correcting the face image data to be stored in the face recognition data memory (storage means) 5 based on the similar image data and the image data (face image data) selected and designated as the registered image of the person. Means.

The face recognition data memory 5 is composed of, for example, a non-volatile memory (flash memory) or the like, and stores simple face recognition data d1, detailed face recognition data d2 (see FIG. 2), and the like.
As shown in FIG. 2, the simple face recognition data d1 and the detailed face recognition data d2 are stored in association with the names of persons (for example, “Mr. A”, “Mr. B”, “Mr. C”, etc.). ing. The simple face recognition data d1 is data used for simple face recognition processing of a person, and is, for example, monochrome binary 1-bit color data. The detailed face recognition data d2 is data used for highly accurate face recognition processing of a person, for example, grayscale data representing the shading of a face, and various face angles of the person. Data, etc.
The simple face recognition data d1 and the detailed face recognition data d2 are only examples, and are not limited to these. Any data can be used as long as it is used for face recognition processing according to the characteristics of the face image. Also good.
Here, the face recognition data memory 5 constitutes storage means for storing the simple face recognition data d1 and the detailed face recognition data d2 as at least one face image data.

The display control unit 6 performs control to read display image data temporarily stored in the memory and display it on the display unit 7.
Specifically, the display control unit 6 includes a VRAM, a VRAM controller, a digital video encoder, and the like. The digital video encoder reads the luminance signal Y and the color difference signals Cb and Cr read from the memory under the control of the central control unit 12 and stored in the VRAM (not shown) from the VRAM via the VRAM controller. The data is read periodically, a video signal is generated based on these data, and is output to the display unit 7.

  The display unit 7 is, for example, a liquid crystal display device, and displays an image captured by the electronic imaging unit based on a video signal from the display control unit 6 on a display screen. Specifically, the display unit 7 updates the live view image while sequentially updating a plurality of image frames generated by imaging of the subject by the imaging unit 1 at a predetermined frame rate in the still image capturing mode and the moving image capturing mode. indicate. The display unit 7 displays an image (rec view image) recorded as a still image or an image being recorded as a moving image.

  Further, the display unit 7 displays the similar image data (face image data) searched by the image search unit 3a of the face detection processing unit 3 as display means. At this time, the display unit 7 displays a portion of the similar image determined to be similar to the simple face recognition data d1 in a state surrounded by a rectangular frame under the control of the display control unit 6.

  The storage medium control unit 8 controls the writing of data to the storage medium 9 and the reading of data from the storage medium 9 under the control of the central control unit 12.

  The storage medium 9 is a memory card configured to be detachable from the imaging apparatus 100 main body. The storage medium 9 stores still image data for recording and moving image data composed of a plurality of image frames encoded in a predetermined compression format by an encoding unit (not shown) of the image processing unit 4. ing.

The communication control unit 10 includes, for example, an external database DB that includes a communication antenna, a communication circuit (not shown), and the like and is connected via a communication network N according to a predetermined communication standard such as a wireless local area network (LAN). Control communication of information between.
Here, the communication control unit 10 constitutes a communication unit that communicates with an external database (communication device) DB outside the imaging device 100.

The communication network N is, for example, a communication network N constructed using a dedicated line or an existing general public line, and has various line forms such as a LAN (Local Area Network) and a WAN (Wide Area Network). It is possible to apply. The communication network N includes, for example, various communication line networks such as a telephone line network, an ISDN line network, a dedicated line, a mobile communication network, a communication satellite line, and a CATV line network, and an Internet service provider that connects them. included.
The external database DB is provided in, for example, a PC that can be used by a user, an image management server managed by a predetermined supplier, and a communication control unit and an image search unit (all not shown). Etc. The communication control unit of the external database DB has substantially the same configuration as the communication control unit 10 and controls communication of information with the imaging device 100 connected via the communication network N.
The image search unit of the external database DB has substantially the same configuration as the image search unit 3a, and uses the simple face recognition data d1 received by the communication control unit, and is similar to the simple face recognition data d1. And the image data whose similarity with the simple face recognition data d1 is a predetermined value or more is specified as the similar image data. Then, the communication control unit of the external database DB transmits the similar image data searched by the image search unit to the imaging device 100 via the communication network N.

  The operation input unit 11 is for performing a predetermined operation of the imaging apparatus 100. Specifically, the operation input unit 11 includes a shutter button related to an instruction to shoot a subject, a selection determination button related to an instruction to select an imaging mode or a function, a zoom button related to an instruction to adjust the zoom amount, and the like (all shown) Abbreviation), a predetermined operation signal is output to the central control unit 12 in accordance with the operation of these buttons.

The selection determination button of the operation input unit 11 is a plurality of images (faces) that are read from the storage medium 9 and displayed on the display unit 7 based on a predetermined operation of the menu button by the user in the face recognition image correction process. An instruction to specify any one image (specific face image) is input as a registered image of a person who is a target of face recognition processing. Then, the operation input unit 11 outputs a predetermined designation signal to the central control unit 12 in accordance with the operation of the selection determination button.
The central control unit 12 designates user-desired image data as face image data from at least one image data stored in the storage medium 9 according to the inputted designation signal.
Here, the operation input unit 11 and the central control unit 12 constitute designation means for designating specific face image data among at least one face image data stored in the storage medium (storage means) 9.

  The central control unit 12 controls each unit of the imaging apparatus 100. Specifically, the central control unit 12 includes a CPU, a RAM, a ROM (all not shown), and the like, and performs various control operations according to various processing programs (not shown) for the imaging apparatus 100.

Next, face recognition image correction processing will be described with reference to FIGS.
3 and 4 are flowcharts illustrating an example of operations related to the face recognition image correction process.
The face recognition image correction process is performed when an image registration mode for the face recognition process is selected from a plurality of imaging modes displayed on the menu screen based on a predetermined operation of the selection determination button of the operation input unit 11 by the user. It is a process to be executed.

  As shown in FIG. 3, the user wants to register as a face recognition processing target based on a predetermined operation of the operation input unit 11 by the user from among a plurality of images read from the storage medium 9 and displayed on the display unit 7. When any one image (face image) of a person is designated (step S1), the face recognition data generation unit 4a of the image processing unit 4 performs a predetermined conversion process on the face image, and the face Normal face recognition data d1 (see FIG. 2) is generated by normalizing the size and the eye position (step S2).

Next, the image search unit 3a of the face detection processing unit 3 uses the generated simple face recognition data d1 to select the simple face recognition data from the plurality of image data stored in the storage medium 9. Image data similar to d1 is searched, and image data whose similarity to the simple face recognition data d1 is a predetermined value or more is specified as similar image data (step S3).
Subsequently, the search determination unit 3b of the face detection processing unit 3 determines whether similar image data similar to the simple face recognition data d1 is obtained as a result of the image search by the image search unit 3a (step S4). .
Here, if it is determined that similar image data is obtained (step S4; YES), the display control unit 6 uses a rectangular frame to identify a portion that is determined to be similar to the simple face recognition data d1 in the similar image. The similar image is displayed on the display unit 7 in an enclosed state (step S5).

Next, the designation determination unit 3h of the face detection processing unit 3 receives an instruction to designate similar image data used for the generation processing of the detailed face recognition data d2 based on a predetermined operation of the operation input unit 11 by the user. It is determined whether or not it has been done (step S6).
If it is determined that an instruction for designating similar image data has been input (step S6; YES), the face recognition data generation unit 4a of the image processing unit 4 selects and designates image data selected and designated as a person registered image. The detailed face recognition data d2 is generated by applying a predetermined correction process to the simple face recognition data d1 based on the similar image data and the similar image data (step S7), and the face image correction process is terminated.

  On the other hand, if it is determined in step S4 that similar image data has not been obtained (step S4; NO), or if it is determined that an instruction to specify similar image data has not been input (step S6; NO). As shown in FIG. 4, the notification control unit 3c notifies a similar image search instruction by another method (step S8). Specifically, the notification control unit 3c controls the display control unit 6 to attach a message for instructing acquisition by capturing new image data, or mounting a new storage medium different from the mounted storage medium 9. A message for instructing, a message for instructing a search for image data stored in an external database DB external to the imaging apparatus 100, and the like are displayed on the display unit 7 as a notification.

Subsequently, the central control unit 12 branches the process in accordance with user operations such as acquisition by capturing new image data, searching for image data stored in the external database DB, and replacement of the storage medium 9 (steps). S9).
That is, in step S9, when acquisition by imaging of new image data is selected based on a predetermined operation such as a selection determination button of the operation input unit 11 by the user, the predetermined operation of the operation input unit 11 by the user is performed. The signal output based on this is input to the instruction detection determination unit 3d of the face detection processing unit 3. Then, the instruction detection determination unit 3d determines that it has detected an instruction to newly acquire image data by imaging, and the activation control unit 3f of the face detection processing unit 3 is a signal instructing activation of the imaging mode. Is output to the imaging unit 1 to activate the imaging unit 1 (step S91A).
Subsequently, the display control unit 6 displays a live view image on the display screen of the display unit 7 based on a plurality of image frames generated by imaging the subject by the imaging unit 1, and the image search unit 3a Using the recognition data d1, image data similar to the simple face recognition data d1 is sequentially searched from the live view image (step S91B).

Next, the central control unit 12 determines whether or not an imaging instruction has been input based on a predetermined operation of the shutter button of the operation input unit 11 by the user (step S91C). Here, if it is determined that an imaging instruction has been input (step S91C; YES), the central control unit 12 causes the imaging control unit of the imaging unit 1 to adjust the imaging conditions so that the optical image of the subject is obtained under predetermined conditions. An image is captured by the electronic imaging unit of the imaging unit 1 and the image data generation unit 2 generates YUV data of the captured image transferred from the electronic imaging unit (step S91D).
Subsequently, the image search unit 3a determines whether the similarity between the captured image data of the subject and the simple face recognition data d1 is equal to or greater than a predetermined value. Based on the determination result, the search determination unit 3b Then, it is determined whether or not similar image data similar to the simple face recognition data d1 is obtained (step S91E). That is, if the image search unit 3a determines that the similarity with the simple face recognition data d1 is equal to or greater than a predetermined value, the search determination unit 3b determines that captured image data as similar image data has been obtained. To do. On the other hand, when it is determined by the image search unit 3a that the similarity with the simple face recognition data d1 is less than a predetermined value, the search determination unit 3b has not obtained captured image data as similar image data. to decide.

If it is determined in step S91E that similar image data has been obtained (step S91E; YES), the central control unit 12 shifts the process to step S5 (see FIG. 3) and executes the subsequent processes. . That is, as shown in FIG. 3, the display control unit 6 surrounds a portion that is determined to be similar to the simple face recognition data d1 in the newly captured image (similar image) with a rectangular frame. Then, the similar image is displayed on the display unit 7 (step S5).
In addition, the process after step S6 is as substantially the same as the process content demonstrated above, The description is abbreviate | omitted.
On the other hand, if it is determined in step S91E that similar image data has not been obtained (step S91E; NO), the central control unit 12 shifts the process to step S8 and executes the subsequent processes.

In step S9, when search of image data stored in the external database DB is selected based on a predetermined operation such as a selection determination button of the operation input unit 11 by the user, the operation input unit 11 by the user is selected. A signal output based on the predetermined operation is input to the instruction detection determination unit 3d of the face detection processing unit 3. Then, the instruction detection determination unit 3d determines that an instruction to search image data stored in the external database DB has been detected, and the search instruction unit 3g of the face detection processing unit 3 After starting the communication control unit 10 by outputting a signal instructing activation to the mobile phone, the communication control unit 10 accesses the external database DB via the communication network N and is similar to the simple face recognition data d1. A search instruction for image data to be transmitted is transmitted (step S92A).
Thereafter, the central control unit 12 of the imaging apparatus 100 determines whether or not similar image data transmitted from the external database DB by the communication control unit 10 has been received (step S92B).
That is, when receiving the search instruction transmitted from the communication control unit 10 in step S92A, the external database DB searches for image data similar to the simple face recognition data d1. Then, when similar image data is specified by the search process, the similar image data is transmitted from the external database DB via the communication network N, and the similar image data is received by the communication control unit 10 of the imaging apparatus 100. Then, the central control unit 12 determines that the similar image data transmitted from the external database DB by the communication control unit 10 has been received (step S92B; YES). On the other hand, if similar image data is not specified even if image data similar to the simple face recognition data d1 is searched in the external database DB, similar image data is transmitted from the external database DB. Therefore, the similar image data is not received by the communication control unit 10 of the imaging apparatus 100, and the central control unit 12 determines that the similar image data transmitted from the external database DB by the communication control unit 10 cannot be received (step). S92B; NO).

If it is determined in step S92B that the similar image data transmitted from the external database DB has been received by the communication control unit 10 (step S92B; YES), the central control unit 12 performs the process in step S5 (see FIG. 3). And the subsequent processing is executed. That is, as shown in FIG. 3, the display control unit 6 acquires the similar image data received by the communication control unit 10, and the simple face recognition data d1 in the similar images searched in the external database DB. The similar image is displayed on the display unit 7 in a state where a portion determined to be similar is surrounded by a rectangular frame (step S5).
In addition, the process after step S6 is as substantially the same as the process content demonstrated above, The description is abbreviate | omitted.
On the other hand, if it is determined in step S92B that the similar image data transmitted from the external database DB cannot be received by the communication control unit 10 (step S92B; NO), the central control unit 12 moves the process to step S8. And execute the subsequent processing.

In step S9, when replacement of the storage medium 9 is selected based on a predetermined operation by the user, a signal output from the storage medium control unit 8 based on the attachment / detachment operation of the storage medium 9 by the user is detected by face detection. The information is input to the mounting determination unit 3e of the processing unit 3. Thereby, the attachment determination unit 3e determines that a new storage medium is attached.
Next, the central control unit 12 shifts the processing to step S3 (see FIG. 3), and executes the subsequent processing. That is, as shown in FIG. 3, the image retrieval unit 3a retrieves image data similar to the simple face recognition data d1 from the newly mounted storage medium, and obtains the simple face recognition data d1. Image data whose similarity is equal to or greater than a predetermined value is specified as similar image data (step S3).
In addition, the process after step S4 is substantially the same as the process content demonstrated above, The description is abbreviate | omitted.

  As described above, according to the imaging apparatus 100 of the present embodiment, specific image data specified based on a predetermined operation of the operation input unit 11 by the user from among a plurality of image data stored in the storage medium 9. The similar image data similar to the simple face recognition data d1 corresponding to is retrieved, and the face image data to be stored in the face recognition data memory 5 is corrected based on the similar image data and the specific image data. Thus, the detailed face recognition data d2 used for the highly accurate face recognition processing of the person can be generated, and the face image data can be corrected with a simple operation. Furthermore, the accuracy of the face recognition process can be improved by using the detailed face recognition data d2, and even if the image registered for the face recognition process is an image of an angle or direction other than the front, It can be applied to face detection.

Further, image data having a degree of similarity with the simple face recognition data d1 is specified as candidate face image data (similar image data), and the similar image data is used to generate detailed face recognition data d2. It can be specified as data. More specifically, the similar image data specified as the candidate face image data can be displayed on the display unit 7, and the user-desired similar image data can be selected and designated from the displayed similar image data. The user's intention can be reflected in the face image detected by the recognition process.
In addition, a plurality of similar image data can be designated, whereby the detailed face recognition data d2 with high accuracy can be generated using the plurality of similar image data, and the accuracy of the face recognition processing can be improved. be able to.

In addition, when similar image data is not obtained in the image search process, notification is made to acquire new image data by imaging, so that new image data can be acquired by imaging, and face recognition image correction processing Thus, since the similar image data similar to the simple face recognition data d1 is not stored in the storage medium 9, the face recognition image correction process is interrupted, and the detailed face recognition data d2 is generated. It is possible to prevent things that cannot be done.
In particular, when an instruction to newly acquire image data is detected by imaging, the imaging unit 1 is activated, so that new image data can be easily acquired by imaging, and the imaging apparatus 100 by the user can be obtained. It is possible to reduce the burden on the operation.

In addition, when similar image data is not obtained in the image search process, a notification is made to insert a new storage medium different from the mounted storage medium 9, so that new image data is acquired from the new storage medium. In the face recognition image correction process, since similar image data similar to the simple face recognition data d1 is not stored in the storage medium 9, the face recognition image correction process is interrupted. It is possible to prevent the detailed face recognition data d2 from being generated.
In particular, when it is determined that a new storage medium has been installed, image data similar to the simple face recognition data d1 is searched from this new storage medium, so that acquisition of new image data from the new storage medium is performed. This can be performed easily, and the burden on the operation of the imaging apparatus 100 by the user can be reduced.

In addition, when similar image data is not obtained in the image search process, a notification is made to search for face image data stored in the external database DB outside the imaging apparatus 100, so that a new search is performed by searching the external database DB. Since the similar image data similar to the simple face recognition data d1 is not stored in the storage medium 9 in the face recognition image correction process, the face recognition image correction process is performed. It can be prevented that the detailed face recognition data d2 cannot be generated due to interruption.
In particular, when an instruction to search the face image data stored in the external database DB is detected, the external database DB is instructed to search for face image data similar to the simple face recognition data d1, New image data can be easily acquired from the external database DB, and the burden on the operation of the imaging apparatus 100 by the user can be reduced.

The present invention is not limited to the above-described embodiment, and various improvements and design changes may be made without departing from the spirit of the present invention.
For example, when similar image data is not obtained in the image search process, in order to acquire similar image data similar to the simple face recognition data d1, acquisition by imaging of new image data is performed in the external database DB. Although notifications such as retrieval of stored image data and replacement of the storage medium 9 are performed, whether or not to perform these notifications can be arbitrarily changed as appropriate.
In addition, one of the above-described processes specified based on a predetermined operation by the user is performed. However, the present invention is not limited to this, and may be automatically performed in a predetermined order specified by the user. good. That is, when similar image data is not obtained in the image search process, a search for similar image data from an external database DB that does not limit the function related to the imaging of the subject by the imaging unit 1 is executed, and the search process also performs the search process. When similar image data is not obtained, new image data may be captured. Also, the similar image data retrieval process from the external database DB and the subject imaging process may be performed in parallel.

  In addition, a predetermined message is displayed on the display unit 7 in order to notify acquisition of new image data by imaging, retrieval of image data stored in the external database DB, replacement of the storage medium 9, and the like. The notification mode is not limited to this, and for example, a predetermined message may be output by voice.

  Further, the processing target image is captured by an imaging device different from the imaging device 100, and the face recognition image correction processing is performed by acquiring the image data of the processing target image transferred from the imaging device 100. It may be a correction device.

In addition, in the above embodiment, the functions of the designation unit, the search unit, the determination unit, and the correction unit are controlled by the central control unit 12 and the image search of the operation input unit 11 and the face detection processing unit 3 is performed. The configuration is realized by driving the face recognition data generation unit 4a of the unit 3a, the designation determination unit 3h, and the image processing unit 4. However, the configuration is not limited to this, and the CPU of the central control unit 12 performs predetermined processing. A configuration realized by executing a program or the like may be employed.
That is, a program memory (not shown) that stores a program stores a program including a designation processing routine, a search processing routine, a determination processing routine, and a correction processing routine. Then, the CPU of the central control unit 12 may function as a designation unit that designates specific face image data among at least one face image data stored in the storage unit by a designation processing routine. In addition, the CPU of the central control unit 12 searches the face image data similar to the specific face image data specified by the specifying means from the plurality of image data stored in the storage medium 9 by the search processing routine. You may make it function as a means. Further, the CPU of the central control unit 12 is caused to function as a determination unit that determines whether or not the face image data obtained as a result of the search by the search unit is designated as data used for the correction process by the determination process routine. Anyway. Further, if the CPU of the central control unit 12 determines that the face image data is designated as data used for the correction processing by the determination unit by the correction processing routine, the face image data and the specific unit specified by the specifying unit are specified. You may make it function as a correction means which correct | amends the face image data which should be memorize | stored in a memory | storage means based on face image data.

DESCRIPTION OF SYMBOLS 100 Image pick-up device 1 Image pick-up part 3 Face detection process part 3a Image search part 3b Search judgment part 3c Notification control part 3d Instruction detection judgment part 3e Installation judgment part 3f Startup control part 3g Search instruction part 3h Specification determination part 4 Image processing part 4a Face Recognition data generation unit 5 Face recognition data memory 7 Display unit 9 Storage medium 10 Communication control unit 12 Central control unit DB External database

Claims (12)

Storage means for storing at least one face image data;
Designation means for designating specific face image data among at least one face image data stored in the storage means;
A storage medium for storing a plurality of image data;
Search means for searching for face image data similar to the specific face image data designated by the designation means from among a plurality of image data stored in the storage medium;
Determination means for determining whether or not the face image data obtained as a result of the search by the search means is designated as data used for correction processing;
When it is determined by the determination means that the face image data is designated as data used for the correction processing, the storage is performed based on the face image data and the specific face image data designated by the designation means. Correction means for correcting face image data to be stored in the means;
A face image correction apparatus comprising: The correction means includes
It includes generation means for generating new face image data using face image data designated as data used for the correction processing and specific face image data designated by the designation means. The face image correction apparatus according to claim 1. First determination means for determining whether similar face image data is obtained as a result of the search by the search means;
A first notifying unit for notifying that new face image data is acquired by imaging when it is determined by the first determining unit that similar face image data is not obtained;
The face image correction apparatus according to claim 1, further comprising: Imaging means;
First detection determination means for determining whether or not an instruction to newly acquire face image data by imaging is detected based on the notification by the first notification means;
An activation control means for controlling to activate the imaging means when the first detection judgment means determines that the instruction is detected;
The face image correction apparatus according to claim 3, further comprising: The search means includes
Searching among the plurality of image data stored in the storage medium as candidate face image data for image data whose similarity with the specific face image data specified by the specifying means is a predetermined value or more,
The face image correction apparatus according to claim 1, wherein the candidate face image data can be designated as data used for the correction process. The storage medium is configured to be detachable from the apparatus main body,
When it is determined by the first determination means that similar face image data has not been obtained, the apparatus further comprises second notification means for notifying that a new storage medium different from the storage medium is to be mounted. The face image correction device according to any one of claims 3 to 5. And further comprising second determination means for determining whether or not a new storage medium is attached after the notification by the second notification means,
The search means further includes
When it is determined by the second determination means that a new storage medium is mounted, the face image data similar to the specific face image data specified by the specification means is searched from the new storage medium. The face image correction apparatus according to claim 6.   When it is determined by the first determination means that similar face image data has not been obtained, a third notification means for notifying that the face image data stored in the storage means outside the apparatus is searched is further provided. The face image correction apparatus according to any one of claims 3 to 7, wherein Communication means for communicating with a communication device outside the device;
Second detection determination means for determining whether or not an instruction to search for storage means outside the device is detected based on notification by the third notification means;
When it is determined that the instruction is detected by the second detection determination unit, the communication unit is activated, and a face similar to the specific face image data specified by the specification unit with respect to the storage unit outside the apparatus Search instruction means for instructing search of image data;
The face image correction apparatus according to claim 8, further comprising:   The face image correction apparatus according to claim 1, further comprising display means for displaying face image data searched by the search means. A face image correction method using a face image correction device comprising a storage means for storing at least one face image data,
A process of designating specific face image data among at least one face image data stored in the storage means;
A process of searching for face image data similar to the specific face image data from a plurality of image data stored in a storage medium;
A process of determining whether or not the face image data obtained as a result of the search is designated as data used for the correction process;
When it is determined that the face image data is designated as data used for the correction process, the face image data to be stored in the storage unit is corrected based on the face image data and the specific face image data. Processing to
The face image correction method characterized by performing. A computer of a face image correction device comprising storage means for storing at least one face image data,
Designation means for designating specific face image data among at least one face image data stored in the storage means;
Search means for searching for face image data similar to the specific face image data designated by the designation means from among a plurality of image data stored in a storage medium;
Determination means for determining whether or not the face image data obtained as a result of the search by the search means is designated as data used for correction processing;
When it is determined by the determination means that the face image data is designated as data used for the correction processing, the storage is performed based on the face image data and the specific face image data designated by the designation means. Correction means for correcting face image data to be stored in the means;
A program characterized by functioning as

Images