JP2008242694A - Image processing apparatus and program thereof - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing apparatus and its program capable of easily and appropriately setting the faces of a plurality of persons as the subjects of face recognition. <P>SOLUTION: The image processing apparatus has a correlation data table that records the face images of a plurality of persons and stores affinity values between the plurality of persons. Based on user-designated affinity values and affinity range, an affinity is set (S6 to 12). The face image of the person who has the set affinity to a central person is set as the subject of face recognition (S13), and a face recognition process is executed (S15), whereby a determination is made as to whether or not the face image specified is included in image data (S16). <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an image processing apparatus and a program thereof, and more particularly to an image processing apparatus and a program thereof that can recognize a face of a subject.

  2. Description of the Related Art In recent years, an image processing apparatus that performs image search or the like can search by selecting a plurality of face images and recognizing image data including the selected face images, for example, by calculating facial feature amounts. Technology has appeared (Patent Document 1).

JP Patent Publication No. 2006-163527

  However, according to the conventional technique, when a plurality of face images are to be set as search targets and face recognition targets, it is necessary to manually select the face images one by one. It is difficult, and it is necessary to select a face image while considering which face image should be selected.

  Therefore, the present invention has been made in view of such conventional problems, and provides an image processing apparatus and a program thereof capable of easily and appropriately setting a plurality of human faces as face recognition targets. Objective.

To achieve the above object, the image processing apparatus according to the first aspect of the present invention includes a storage unit that stores a closeness table in which a closeness with a reference person is set for each person,
Setting means for setting intimacy with the reference person;
Using a closeness table stored in the storage means, a face recognition target specifying means for specifying a face of a person having a closeness set by the reference person and the setting means as a face recognition target;
Image acquisition means for acquiring image data;
Face recognition control means for performing face recognition processing on the image data acquired by the image acquisition means based on the face of the person specified as the face recognition target by the face recognition target specifying means;
It is provided with.

Also, for example, as described in claim 2, the closeness table is:
Each person ’s face image is set,
The face recognition control means includes
The face recognition process may be performed on the image data acquired by the image acquisition unit based on the face image data corresponding to the person specified as the face recognition target by the face recognition target specifying unit.

Further, for example, as described in claim 3, a user is provided with a closeness specifying means for specifying closeness,
The setting means includes
The closeness may be set based on the closeness specified by the closeness specifying means.

For example, as described in claim 4, the setting unit includes:
You may make it set the familiarity more than the familiarity designated by the familiarity designation | designated means, the designated familiarity, or the familiarity below the designated familiarity.

Further, for example, as described in claim 5, the apparatus includes a group specifying unit for the user to specify an arbitrary group,
The storage means
The intimacy table is stored for each group,
The face recognition target specifying means includes
The reference person and the face of the person having the closeness set by the setting means may be specified as a face recognition target using the closeness table of the group specified by the group specifying means.

Further, for example, as described in claim 6, a user specifying means for the user to specify a central person is provided,
The intimacy table is
Further, each person is set as a reference person, and the closeness between the persons is set to each other.
The face recognition target specifying means includes
The central person specified by the person specifying means may be a reference person, and the face of the reference person and the person having the familiarity set by the setting means may be specified as a face recognition target.

  Further, for example, as described in claim 7, when a face specified as a face recognition target by the face recognition target specifying unit is recognized by the face recognition processing by the face recognition control unit, the recognition is performed. Control means for performing at least one control among trimming control of the subject, display control indicating the subject position, enlargement display control of the subject image, and image processing control of the subject based on the face position may be provided. Good.

  For example, as described in claim 8, when a face identified as a face recognition target by the face recognition target identification unit is recognized by the face recognition processing by the face recognition control unit, the recognition is performed. You may make it provide the setting means to set the number of printed sheets according to the number of faces.

Further, for example, as described in claim 9, a recording unit for recording and holding image data or an image sensor that photoelectrically converts light of a subject,
The image acquisition means includes
You may make it acquire the image data currently recorded on the said recording means, or the image data photoelectrically converted by the said image pick-up element.

Further, for example, as described in claim 10, an image sensor that photoelectrically converts light of a subject;
When a face identified as a face recognition target by the face recognition target specifying means is recognized by the face recognition processing by the face recognition control means, autofocus control and / or exposure control is performed based on the position of the recognized face. Control means to perform;
With
The image acquisition means includes
You may make it acquire the image data photoelectrically converted by the said image pick-up element.

Further, for example, as described in claim 11, a recording unit for recording and holding image data is provided,
The image acquisition means includes
Sequentially obtaining the image data recorded by the recording means,
The face recognition control means includes
Retrieval means for retrieving image data including a face specified as a face recognition target by the face recognition target specifying means by performing face recognition processing on the image data sequentially acquired by the image acquisition means. It may be included.

In order to achieve the above object, a program according to claim 12 is stored in a computer.
A setting process for setting intimacy with the reference person;
Using a familiarity table that stores the familiarity with the reference person for each person, the face recognition target specification that identifies the face of the reference person and the person having the familiarity set by the setting process as a face recognition target Processing,
Image acquisition processing for acquiring image data;
A face recognition control process for performing a face recognition process on the image data acquired by the acquisition process based on the face of the person specified as a face recognition target by the face recognition target specifying process;
Is executed.

  According to the present invention, it is possible to easily and appropriately specify the face of a person whose face is to be recognized.

Hereinafter, the present embodiment will be described in detail with reference to the drawings as an example in which the image processing apparatus of the present invention is applied to a digital camera.
[Embodiment]
A. Configuration of Digital Camera FIG. 1 is a block diagram showing a schematic electrical configuration of a digital camera 1 that implements the image processing apparatus of the present invention.
The digital camera 1 includes a photographing lens 2, a lens driving block 3, an aperture 4, a CCD 5, a driver 6, a TG (timing generator) 7, a unit circuit 8, an image generation unit 9, a CPU 10, a key input unit 11, a memory 12, a DRAM 13, A flash memory 14, an image display unit 15, and a bus 16 are provided.

  The photographing lens 2 includes a focus lens, a zoom lens, and the like that are constituted by a plurality of lens groups (not shown). A lens driving block 3 is connected to the photographing lens 2. The lens driving block 3 includes a focus motor and a zoom motor that drive the focus lens and the zoom lens along the optical axis direction, respectively, and a focus motor driver that drives the focus motor and the zoom motor according to a control signal sent from the CPU 10. And a zoom motor driver (not shown).

The diaphragm 4 includes a drive circuit (not shown), and the drive circuit operates the diaphragm 4 in accordance with a control signal sent from the CPU 10.
The diaphragm 4 is a mechanism that controls the amount of light that enters from the photographing lens 2.

  The CCD 5 is driven by the driver 6 and photoelectrically converts the intensity of light of each color of the RGB value of the subject image for every fixed period and outputs it to the unit circuit 8 as an imaging signal. The operation timing of the driver 6 and the unit circuit 8 is controlled by the CPU 10 via the TG 7. The CCD 5 has a Bayer color filter and also functions as an electronic shutter. The shutter speed of the electronic shutter is controlled by the CPU 10 via the driver 6 and TG7.

  A TG 7 is connected to the unit circuit 8, a CDS (Correlated Double Sampling) circuit that holds the imaged signal output from the CCD 5 by correlated double sampling, and an AGC that performs automatic gain adjustment of the imaged signal after the sampling. An (Automatic Gain Control) circuit and an A / D converter that converts an analog image pickup signal after the automatic gain adjustment into a digital signal, the image pickup signal output from the CCD 5 passes through the unit circuit 8 as a digital signal. It is sent to the image generator 9.

  The image generation unit 9 performs processing such as γ correction processing and white balance processing on the image data sent from the unit circuit 8, generates a luminance color difference signal (YUV data), and generates the generated luminance color difference. The image data of the signal is stored in the DRAM 13 (buffer memory). That is, the image generation unit 9 performs image processing on the image data output from the CCD 5.

The CPU 10 is a one-chip microcomputer that has functions of performing imaging control on the CCD 5, recording processing on the flash memory 14, and display processing of image data, and controls each part of the digital camera 1. Further, the CPU 10 includes a clock circuit and has a function as a timer.
In particular, the CPU 10 has a function of specifying one or more face images as face recognition targets, and a function of performing face recognition processing on image data based on the specified face images.

The key input unit 11 includes a plurality of operation keys such as a shutter button, a mode switching key, a cross key, and a SET key, and outputs an operation signal corresponding to the user's key operation to the CPU 10.
The memory 12 stores a control program and necessary data (correlation data table) necessary for the CPU 10 to control each unit, and the CPU 10 operates according to the program. The memory 12 is a rewritable nonvolatile memory.

The DRAM 13 is used as a buffer memory for temporarily storing image data sent to the CPU 10 after being imaged by the CCD 5 and also as a working memory for the CPU 10.
The flash memory 14 is a recording medium that stores compressed image data.

  The image display unit 15 includes a color LCD and its drive circuit, and displays the subject imaged by the CCD 5 as a through image when in a shooting standby state, and is read out from the flash memory 14 and decompressed when a recorded image is reproduced. Display the recorded image.

B. Operation of Digital Camera 1 The operation of the digital camera 1 in the embodiment will be described with reference to the flowchart of FIG.
When the face recognition mode is set by the user's operation of the key input unit 11, the CPU 10 causes the image display unit 15 to display a list of registered face photos in step S1.
The registered face photo is recorded in the correlation data table of the memory 12, and the registered face photo recorded in the correlation data table is read and displayed as a list.

Here, FIG. 3A is a diagram showing an example of the contents of the correlation data table 21 recorded in the memory 12.
The correlation data table 21 includes records (R1, R2, R3,..., Rn) for each person, and each record includes a person name field 21a, a face photo field 21b, and a linked person name field group 21c. Including. The linked person name field group 21c includes individual person name fields 21c-1, 21c-2, 21c-3,..., 21c-n corresponding to all persons.

  The name of the person is stored in the person name field 21a, and the face picture corresponding to the person is stored in the face picture field 21b. The face photo stored in the face photo field 21b is the registered face photo. In addition, in the individual person name fields 21c-1, 21c-2, 21c-3,..., 21c-n of the link destination person name field group 21c, all person names, that is, the person name field 21a are displayed. Stored person name is stored.

  Of the intersections of the person name field 21a and the individual person name fields 21c-1, 21c-2,... 21c-n of the linked person name field group 21c, the intersections of the same person names (with hatched lines) Each intersection (intersection) except for (intersection) is an area for storing a “correlation value” representing intimacy. That is, at these intersections, “correlation values (intimacy values)” representing the closeness (intimacy) between the intersecting persons are stored. The lower the correlation value, the higher the closeness between the intersecting persons, and the higher the correlation value, the lower the closeness between the intersecting persons (becomes unfriendly).

For example, since the correlation value between the person A and the person B and between the person A and the person C is “1”, the person A and the person B, and the person A and the person C are in a very close relationship. Further, since the correlation value between the person A and the person F is “4”, it can be seen that the person A and the person F are not so close.
The user can freely create this correlation data table 21, and the user records the person's name in the person name field 21a, the face photo in the person name field 21a in the face photo field 21b, and the linked person name field. In the individual person name fields 21c-1, 21c-2,... Of the group 21c, the person names recorded in the person name field 21a are automatically recorded. In each record, the user inputs a correlation value between the person in the person name field 21a and the person in each individual person field of the linked person name field group 21c. That is, the user inputs a correlation value between each person.

  In a certain record, for example, in the record of the person A, the individual person name field 21c-n of the person name field 21a and the linked person name field group 21c, for example, the individual person name field 21c-2 of the person B, When the correlation value “1” is recorded at the intersection, the recorded correlation value is a record corresponding to the person in each individual person name field 21c-n of the linked person name field 21c, that is, each individual person name. The record of the person B in the field 21c-2 is automatically recorded at the intersection with each individual person name field 21c-1 corresponding to the person A.

FIG. 4A is a diagram illustrating an example of a registered face photograph displayed as a list.
4A shows that the face image stored in the face photo field 21b of FIG. 3A is displayed. When displaying a list, the CPU 10 selects a predetermined face photo and identifies and displays the selected registered face photo. Here, it can be seen that the face photo of the person name A is selected, and the selected face photo of the person name A is displayed in a thick frame so as to be discriminated.

When the list of registered face photos is displayed, in step S2, the CPU 10 determines whether or not the cross key has been operated by the user. This determination is made based on whether or not an operation signal corresponding to the operation of the cross key is sent from the key input unit 11.
If it is determined in step S2 that an operation signal corresponding to the operation of the cross key is sent from the key input unit 11, the CPU 10 newly selects a registered face photo according to the operation (step S3), and then proceeds to step S4. . That is, the selected registered face photo is changed. At this time, the registered face photo selected after the change is discriminated and displayed.

For example, when the “→” key of the cross key is operated in the state as shown in FIG. 4A, the selected registered face photo changes from the person name A to the person name B. When the “↓” key of the cross key is operated in the state as shown in FIG. 4A, the registered face photo to be selected changes from the person name A to the person name E.
On the other hand, if it is determined in step S2 that an operation signal corresponding to the operation of the cross key is not sent from the key input unit 11, the process proceeds to step S4 as it is.

In step S4, the CPU 10 determines whether or not the user has operated the SET key. This determination is made based on whether or not an operation signal corresponding to the operation of the SET key is sent from the key input unit 11.
At this time, when the user wants to determine the person of the currently selected facial photograph as the central person, the user operates the SET key. The central person refers to a person serving as a reference in obtaining the familiarity of each person, and the familiarity of each person is determined based on the central person. This is because the intimacy of each person changes if the reference person is different.

FIG. 3B is a diagram showing the intimacy with each person using the correlation data table 21 when the person A is the central person. Of these circles, the circle at the center represents the central person, and it can be seen that the circles are stacked over several layers around this circle. Each of these circles represents the familiarity (correlation value) with the central person A, and the further away from the central circle, the lower the familiarity.
Here, there are persons A to L (G to L are not shown in FIG. 3A), and the familiarity between the central person A and each person (B to L) is known. As described above, by using the correlation data table 21 as shown in FIG. 3A, the familiarity with each person can be easily derived.

  If it is determined in step S4 that an operation signal corresponding to the operation of the SET key has not been sent, the process returns to step S2, and if it is determined in step S4 that an operation signal corresponding to the operation of the SET key has been sent, step S5 is performed. The CPU 10 sets the person selected when the operation signal corresponding to the operation of the SET key is sent as the central person.

Next, in step S6, the CPU 10 causes the image display unit 15 to display a closeness information setting screen.
FIG. 4B is a diagram illustrating an example of the displayed familiarity information setting screen.
Looking at FIG. 4 (b), it can be seen that the text “Recognize faces up to intimacy value 3” is displayed.

  Next, in step S <b> 7, the CPU 10 determines whether or not an operation for specifying the familiarity value (correlation value) has been performed. This determination is made as to whether or not the column “3” (intimacy value designation column) is selected by the user's operation of the cross key or the like. At this time, the user can change the intimacy value designated by selecting the column “3” and operating the cross key. For example, when the “↑” key of the cross key is operated, the familiarity value increases from “3” to “4” and “5”, and when the “↓” key of the cross key is operated, the familiarity value is , “3”, “2”, “1”, the numbers become smaller.

If it is determined in step S7 that a closeness value designation operation has been performed, the process proceeds to step S8, and the CPU 10 changes the familiarity value in accordance with the designation operation, and then proceeds to step S9.
On the other hand, if it is determined in step S7 that the intimacy value designation operation has not been performed, the process proceeds directly to step S9.

  In step S9, the CPU 10 determines whether or not a closeness range has been designated. This determination is made as to whether or not the “until” column (intimacy range designation column) has been selected by the user's operation of the cross key or the like. At this time, when the user selects the “until” column, a small screen for designating a range of “until”, “from” or “no” as shown in FIG. The user can specify an arbitrary range by operating the cross key while looking at the small screen.

Here, “until” refers to the specified intimacy or higher (refers to the specified intimacy and the intimacy higher than the specified intimacy, that is, the specified intimacy value) For example, when 3 is specified as the intimacy value (correlation value), the intimacy value (correlation degree) ranges from “3”, “2”, and “1”. Point to.
“From” refers to the specified intimacy or lower (refers to the specified intimacy and the intimacy lower than the specified intimacy, that is, the specified intimacy value or more. For example, when 3 is specified as the familiarity value, it indicates a range of familiarity values “3”, “4”, “5”.
“No” refers to the designated familiarity value. For example, when “3” is designated as the familiarity value, only the familiarity value “3” is indicated.

If it is determined in step S9 that the familiarity range has been designated, the process proceeds to step S10, and the CPU 10 changes the familiarity range in accordance with the designation and proceeds to step S11.
On the other hand, if it is determined in step S9 that the closeness range is not designated, the process proceeds directly to step S11.

In step S11, the CPU 10 determines whether or not the SET key has been operated. At this time, if the user thinks that the specified familiarity value and familiarity range are acceptable, the user operates the SET key.
If it is determined in step S11 that the SET key has not been operated, the process returns to step S7 to repeat the above operation. Thereby, the intimacy value and the intimacy range can be freely changed until the SET key is operated.

On the other hand, if it is determined in step S11 that the SET key has been operated, the process proceeds to step S12, and the CPU 10 sets the familiarity based on the currently designated familiarity value and familiarity range. For example, when the set intimacy value is “2” and the set intimacy range is “up to”, the set intimacy is the intimacy values “1” and “2”. When the density value is “3” and the set familiarity value is “from”, the set familiarity is the familiarity value “3”, “4”, “5”,... .
Thereby, it is possible to set the intimacy desired by the user.

Next, the process proceeds to step S13, and the CPU 10 specifies a face image of a person who is a face recognition target from the persons recorded in the correlation data table 21 based on the set central person and familiarity. That is, the set central person and the face image of the person having the set closeness are specified.
For example, when the set central person is the person A, the set intimacy value is “2”, and the intimacy range is “to”, the face image of the specified person has the person A and the intimacy value “ The face images of the persons who become “1” and “2”, that is, person B, person C, person D, person E, and person K (see FIG. 3) are specified.

  Next, in step S14, the CPU 10 starts imaging by the CCD 5 at a predetermined frame rate (for example, 30 fps), and sequentially buffers the image data of the luminance color difference signals sequentially captured by the CCD 5 and sequentially generated by the image generating unit 9. A so-called through image display is started in which the image data is stored in the memory (DRAM 13) and the stored image data is displayed on the image display unit 15.

  Next, in step S15, the CPU 10 performs face recognition processing for each frame image data sequentially captured by the CCD 5. This face recognition not only recognizes whether or not there is a face in the image, but also performs a process of specifically recognizing who the subject's face is. For example, it recognizes skin color, hair color, eye position, nose position, mouth position, etc., and their positional relationship, and numerically calculates them to calculate numerical data (facial feature numerical data) To do. Since there are a plurality of other well-known methods for face recognition processing, they will not be described in detail here.

(Please explain in more detail. The image data (numerical data) of the person specified in step S13 stored in the correlation data table 21 is collated with the numerical data calculated in step S15.)
Next, in step S16, the CPU 10 determines whether any face of the person (specific person) specified in step S13 has been recognized based on the specified face image. More specifically, based on the face image data specified in step S13, the face feature data of the person of the specified face image is calculated. This facial feature data is calculated by recognizing skin color, hair color, eye position, nose position, mouth position, etc., and their positional relationship, etc. calculate. Then, the calculated face feature data and the numerical data calculated in step S15 are collated to determine whether there is matching face feature data.

Here, since the person B, the person C, the person D, the person E, and the person K are specified, the facial feature data of the specified person is calculated, and the person B, the person C, the person D, the person E, and the person K are calculated. By comparing the face feature data with the numerical data calculated by the image recognition processing in step S15, it is determined whether or not the facial feature data of any person matches the numerical data calculated in the face recognition processing. To do.
In addition to the human face image data, the human face image feature data may be stored in the correlation data table 21 in advance. In this storage, when face image data of a person is stored in the correlation data table, face feature data is automatically calculated based on the face image data, and the calculated face feature data is used as the face image data of the person. Relate to remember.

If it is determined in step S16 that no face of the specific person is recognized, the process stays in step S16 until it is recognized. If it is determined in step S16 that any face of the specific person is recognized, the process proceeds to step S17. Contrast detection type autofocus processing is performed on the recognized faces of one or more specific persons. In other words, the focus lens is driven through the lens driving block 3 and the focus lens is moved to the lens position where the AF evaluation value is highest based on the recognized face image data of the specific person. Thereby, it is possible to easily perform autofocus on a person photographed by the user.
Note that autofocus may be performed by a method other than the contrast detection method.
Next, in step S18, the CPU 10 performs still image shooting processing, compresses still image data obtained by the shooting processing and records it in the flash memory 14, and returns to step S1.

C. As described above, in the embodiment, the closeness is set based on the closeness value and closeness range specified by the user, and the face image of the central person and the person having the set closeness is the face recognition target. Therefore, it is possible to easily and appropriately specify the face of a person whose face is to be recognized.
In addition, the correlation data table stores the face images of a plurality of persons and the closeness value between the plurality of persons, and the user can set the face image of any person as the central person, so that the user can The reference person who wants to be the face image to be recognized can be freely changed, and the accuracy and the degree of freedom of the face image to be recognized are improved.

[Modification]
H. The above embodiment may be the following modes.

  (01) In the above embodiment, as shown in FIG. 3A, the closeness value (link destination person name) between persons is recorded for each person (A, B, C˜). In other words, R1 and R2 and a plurality of records are provided, but mutual closeness values between persons based on one person (for example, oneself) may be recorded. That is, referring to the correlation data table 21 in FIG. 3A, one record may be used.

(02) In the above embodiment, only one correlation data table 21 is provided. However, the correlation data table is classified by user (group) (for example, by father, mother, son, daughter, etc.). A plurality of 21 may be provided. In this case, first, after selecting the user, the central person and the familiarity value are set.
Thereby, the face of the person corresponding to each user can be specified, and even when there are a plurality of users, it is possible to cope with it.

(03) In the above embodiment, only one correlation data table 21 is provided. However, a plurality of correlation data tables 21 are provided for each group (for example, for each group such as a workplace, a friend, and a club). It may be. In this case, first, after selecting a group, the central person and the familiarity value are set.
Thereby, the user can select the group to which the person to be photographed belongs, and the face of the person in the desired group can be specified.

(04) In the above embodiment, the correlation value with the person is recorded by the table as shown in FIG. 3A. However, the correlation value may be recorded as in the correlation diagram. good.
FIG. 5 is a diagram showing an example of the contents of the correlation diagram.
Looking at the figure, there are person A to person L (this person is the same person as the person shown in FIG. 3B), and the human relationship of each person can be understood. Here, the couple and the direct line have a correlation value “1”, a friend “2”, and a lover “1”.

For example, considering wife A as the center (reference), the correlation value between the husband B and the child C is “1”, and the relationship between the child C and the lover E is “1”. ”, Child C, and lover E have a correlation value of“ 1 ”, so that the correlation value is 1 + 1 and the correlation value is“ 2 ”.
In addition, the correlation value is “2” in the relationship between the friend D and the friend K, and the correlation value between the friend D and the husband J is “1” in the relationship with the friend D. The value is “3”, and the correlation value with each person is a correlation value as shown in FIG.

In this way, by recording the correlation values as in the correlation system diagram, the human relationship between the individual persons becomes clear at a glance, and it is not necessary to record the correlation values between the individual persons.
Here, for example, the correlation value of friends is uniformly “2”. However, since the intimacy changes among the same friends, the correlation value does not need to be uniform, and the correlation value is changed for each person. It may be.

  (05) In the above embodiment, when a face image specified as a face recognition target is recognized, AF processing is performed on the recognized face. An AE process may be performed based on this.

(06) In the above embodiment, when a face image specified as a face recognition target is recognized, still image shooting is performed. However, the present invention is not limited to this, and face recognition is performed using the specified face image. It is sufficient that the recognition result is used. In this case, the image processing apparatus is not limited to an imaging apparatus such as a digital camera, and any apparatus that processes images may be used. Thereby, the recognition result of the face of the specified person by the image recognition process can be utilized over many limbs.
For example, the trimming process is performed based on the recognized face position, the enlargement process (zoom process) is performed based on the recognized face position, or the recognized face position (or based on the face position). You may make it display so that a user may visually recognize the position of a to-be-photographed object. This subject display is effective for images taken in a crowd.

Further, image processing may be performed on the recognized face or on a subject based on the position of the recognized face.
Further, the number of printed sheets may be set according to the number of recognized faces. In this case, there is also an advantage that the user does not have to count the number of people who distribute the photos.
Further, image data including the specified face image may be searched from a large amount of image data recorded on the recording medium. In this case, whether to search for image data including all of the specified face images or to search for image data including at least one of the specified face images or a predetermined number of face images is specified. You may be able to do that. Thereby, a plurality of persons to be searched can be easily selected, and an image including the person to be searched can be easily searched.

(07) In the above embodiment, a correlation data table including a reference person and a group up to a familiarity value 1, a group up to a familiarity value 2, and a group up to a familiarity value 3 may be provided.
In this case, for example, when a group up to the familiarity value 2 is selected, face images having the familiarity value “1” and the familiarity value “2” are specified.

  (08) In the above embodiment, the closeness is set based on the closeness value specified in step S12 and the specified closeness range. However, the user specifies two closeness values. The closeness may be set based on the two specified closeness values. For example, when the designated closeness values are “2” and “4”, the closeness values of the closeness values “2” to “4” may be set as closeness values, or the closeness value “2” ”And the familiarity value from the familiarity value“ 4 ”may be set as the familiarity.

(09) In the above embodiment, when the through image display is started in step S14, the image recognition process is started (step S15). After the through image display starts, the shutter button is half-pressed by the user. If it is done (when shooting preparation is instructed), the process may proceed to step S15.
If it is determined in step S16 that the identified face has been recognized, AF processing is performed on the recognized face (step S17), and still image shooting processing is performed. After AF processing in step S17, When the shutter button is fully pressed by the user (when shooting is instructed), the process proceeds to step S18, and still image shooting may be performed.

  (10) In the above embodiment, in step S16, if any face image specified in step S13 is recognized, the process proceeds to step S17. However, all the faces specified in step S13 When the image is recognized, the process may proceed to step S17.

(11) In the above embodiment, the face image of a person is recorded in the correlation data table 21, but the face feature data may be stored instead of the face image. In this case, the list display of registered face photos in step S1 of FIG. 2 does not display the registered face images but displays a list of person names.
Further, although the person name and the face image are stored in the correlation data table 21, the person name may not be stored. That is, the storage area of the person name field 21a may be eliminated. This is because the person can be identified by looking at the face image.

  (12) Moreover, the aspect which combines arbitrarily the said modification (01)-(11) within the range which does not produce contradiction may be sufficient.

(13) The above embodiments of the present invention are merely examples as the best embodiments, and are described in order to better understand the principle and structure of the present invention. And is not intended to limit the scope of the appended claims.
Therefore, it should be understood that all the various variations and modifications that can be made to the above-described embodiments of the present invention are included in the scope of the present invention and protected by the appended claims.

  Finally, in each of the above-described embodiments, the case where the image processing apparatus of the present invention is applied to the digital camera 1 has been described. However, the present invention is not limited to the above-described embodiment. Any device can be applied.

1 is a block diagram of a digital camera according to an embodiment of the present invention. It is a flowchart which shows operation | movement of the digital camera 1 of embodiment. FIG. 4 is a diagram showing an example of the contents of a correlation data table 21 recorded in the memory 12 and a diagram showing the familiarity with each person when the central person is a person A using the correlation data table 21. It is a figure which shows an example of the mode of the registered face photograph displayed as a list, and a figure which shows an example of the mode of the familiarity information setting screen displayed. It is a figure which shows the example of the content of a correlation system diagram.

Explanation of symbols

1 Digital Camera 2 Shooting Lens 3 Lens Drive Block 4 Aperture 5 CCD
6 Driver 7 TG
8 Unit circuit 9 Image generator 10 CPU
11 Key input section 12 Memory 13 DRAM
14 Flash memory 15 Image display unit 16 Bus

Claims (12)

Storage means for storing a familiarity table in which the familiarity with the reference person is set for each person;
Setting means for setting intimacy with the reference person;
Using a closeness table stored in the storage means, a face recognition target specifying means for specifying a face of a person having a closeness set by the reference person and the setting means as a face recognition target;
Image acquisition means for acquiring image data;
Face recognition control means for performing face recognition processing on the image data acquired by the image acquisition means based on the face of the person specified as the face recognition target by the face recognition target specifying means;
An image processing apparatus comprising: The intimacy table is
Each person ’s face image is set,
The face recognition control means includes
2. The face recognition process is performed on the image data acquired by the image acquisition unit based on a face image corresponding to a person specified as a face recognition target by the face recognition target specifying unit. The image processing apparatus described. A user has a closeness specifying means for specifying closeness,
The setting means includes
The image processing apparatus according to claim 1, wherein the intimacy is set based on the intimacy specified by the intimacy specifying means. The setting means includes
The intimacy greater than or equal to the intimacy specified by the intimacy specifying means, or the intimacy specified, or the intimacy less than or equal to the specified intimacy is set. Image processing apparatus. A group specifying means for the user to specify an arbitrary group is provided,
The storage means
The intimacy table is stored for each group,
The face recognition target specifying means includes
The face of the person having the familiarity set by the reference person and the setting means is specified as a face recognition target using the familiarity table of the group designated by the group designation means. 5. The image processing apparatus according to any one of 4. A user specifying means for the user to specify a central person,
The intimacy table is
Further, each person is set as a reference person, and the closeness between the persons is set to each other.
The face recognition target specifying means includes
6. The central person specified by the person specifying means is used as a reference person, and the face of the person having the familiarity set by the reference person and the setting means is specified as a face recognition target. An image processing apparatus according to any one of the above. When a face identified as a face recognition target by the face recognition target identification means is recognized by the face recognition processing by the face recognition control means, subject trimming control, subject position is determined based on the recognized face position. 7. The image processing according to claim 1, further comprising a control unit that performs at least one of display control, display enlargement display control of the subject image, and image processing control of the subject. apparatus. When a face identified as a face recognition target by the face recognition target identification unit is recognized by the face recognition process by the face recognition control unit, a setting unit that sets the number of prints according to the number of recognized faces The image processing apparatus according to claim 1, further comprising: an image processing apparatus according to claim 1. A recording means for recording and holding image data or an image sensor that photoelectrically converts light of a subject,
The image acquisition means includes
The image processing apparatus according to claim 1, wherein the image data recorded in the recording unit or image data photoelectrically converted by the imaging device is acquired. An image sensor that photoelectrically converts the light of the subject;
When a face identified as a face recognition target by the face recognition target specifying means is recognized by the face recognition processing by the face recognition control means, autofocus control and / or exposure control is performed based on the position of the recognized face. Control means to perform;
With
The image acquisition means includes
The image processing apparatus according to claim 1, wherein the image data photoelectrically converted by the imaging element is acquired. Comprising recording means for recording and holding image data;
The image acquisition means includes
Sequentially obtaining the image data recorded by the recording means,
The face recognition control means includes
Retrieval means for retrieving image data including a face specified as a face recognition target by the face recognition target specifying means by performing face recognition processing on the image data sequentially acquired by the image acquisition means. The image processing apparatus according to claim 1, further comprising: On the computer,
A setting process for setting intimacy with the reference person;
Using a familiarity table that stores the familiarity with the reference person for each person, the face recognition target specification that identifies the face of the reference person and the person having the familiarity set by the setting process as a face recognition target Processing,
Image acquisition processing for acquiring image data;
A face recognition control process for performing a face recognition process on the image data acquired by the acquisition process based on the face of the person specified as a face recognition target by the face recognition target specifying process;
A program characterized in that is executed.

Images