JP5128880B2 - Image handling device - Google Patents

Description

The present invention, a person image photographed relates to image handling equipment to identify using other image, particularly, by determining person or the like taken are taken together with someone , by analogy to human and human relations such relates to image handling equipment possible to identify the person from the relationships of the subject.

In recent years, the memory capacity that a digital camera can handle tends to increase, and images for several years can be stored in the camera. In addition, the digitized image can be output to the outside via the Internet or the like, and conversely, the image can be acquired from the outside and used for various purposes.

Under these circumstances, since there are countless images that can be handled, it is difficult to collect and enjoy only related images. Also, when sending a photographed image to another person, it is important to identify the parties involved in the photographed image. In other words, a person who has been in a photo together is considered to be acquainted with the person and can be a candidate for a destination.

In addition, if you look at old albums at a relative's house, you may not know who is who, so you may want to identify your relatives. In this case, you may not know if the photo is a young face, and you often do not know the relationship with yourself and you are not familiar. However, when I find out that it was actually my grandfather's sister, I often feel close. In addition, when taking a picture, there is a case where the friendship of the subject is not known, and it is not known who can show it.

In this way, there are many cases where the person who appears in the photograph is not known, or even if the person concerned wants to show an image, the person concerned is not known. Therefore, it is conceivable to identify a related image from among countless images and make an analogy from the related image. As a technique for determining a related image, for example, Patent Document 1 proposes an electronic camera that determines the degree of coincidence with a registered person based on facial feature points from an image signal.
JP 2007-150604 A

In the case of the electronic camera disclosed in Patent Document 1, it is possible to search for a character that matches the captured image. However, it is impossible to infer who the characters in the photo are from the people photographed together.

This onset Ming, has been made in view of such circumstances, using the photograph that is reflected in together, person or the like is by analogy to someone, it is possible to prominence thoughts on the relationship between the people and the people an object of the present invention is to provide an image handling equipment.

In order to achieve the above object, an image handling apparatus according to a first invention includes an image recording unit that records an image, an image designation unit that designates a first image including a first person, and the first image. An age processing unit that performs age processing on the image, a first person specified by the image specifying unit, and an image similar to the first image age-processed by the age processing unit , and the first image An image search unit that searches the image recorded in the image recording unit for a second image in which a person other than the person is present, and a display unit that displays the first image and the second image.

In the image handling apparatus according to a second aspect of the present invention, in the first aspect, the age processing unit performs an age process on the eyes and mouth of the first person.
In the image handling apparatus according to a third aspect, in the second aspect, the age processing unit performs a process of eliminating an aging sign as the age process for the first person.

According to the present invention, it is possible to use a photo that is reflected in together, person or the like is by analogy to someone, to provide an image handling equipment that can wins thoughts on the relationship between people and people.

Hereinafter, a preferred embodiment and a technology related thereto will be described using a digital camera to which the present invention is applied according to the drawings. A digital camera according to an embodiment of the present invention can record image data of a subject image acquired by an image sensor on a recording medium, roughly in response to an operation of a release button. Further, the digital camera has a function of detecting the face of the subject image, and further has a function of generating an image of an early age. And it has the function to search the image similar to the detected face (image rejuvenated by the case) from many image data currently recorded on the recording part. In addition to the recorded images, it is also possible to search from images stored in an external server through the Internet network.

Prior to describing an embodiment of the present invention, a digital camera according to a first technique related to the present invention will be described in detail. FIG. 1A is a block diagram of a digital camera 10 according to the first technique related to the present invention. Inside the camera 10, there are a control unit 1, an imaging unit 2, a lens determination unit 3, a recording unit 4, an image database 4b, a face detection unit 5, an operation determination unit 6, an age processing unit 7, a display unit 8, and a clock unit 9. A similarity detection unit 11 and a communication unit 14 are provided.

The control unit 1 is configured by an MPU (Micro Processing Unit) or the like, and is connected to each unit such as the imaging unit 2 to the communication unit 14 described above. The control unit 1 inputs a signal from each unit and outputs a control signal. Control the whole. The imaging unit 2 includes a photographing lens for forming a subject image, photoelectrically converts the subject image formed by the photographing lens, and outputs an image signal.

The lens determination unit 3 can determine the zoom position (focal length, zoom magnification) and focus position (subject distance) of the photographic lens, and information on the determined zoom position and focus position records photographic image data. Can be recorded at the same time. Also, the focus state for focusing the photographic lens is determined. The clock unit 9 is a clock that measures the date and time, and can record this date and time information (time information) when recording the captured image data in the recording unit 4.

The recording unit 4 compresses the image data based on the image signal output by the imaging unit 2 and records it on a recording medium. The image database 4b in the recording unit 4 is a database in which recorded person names and face information are associated with each other. In the image database 4b, for example, as shown in FIG. 1B, who's face is in which photograph is manually input. In the example of Fig. 1B, Mr. X indicates the position of the A part (for example, upper left or lower right) of the photograph M (which is an identification number of the photograph and may be represented by a number). The position may be shown), and it is shown in the B part of the photo N.

Further, the face detection unit 5 extracts shadows peculiar to the human face in the image, and determines whether the captured image includes a face and, if included, in which part of the image. The similarity detection unit 11 in the control unit 1 compares the face pattern detected by the face detection unit 5 with the face pattern recorded in the image database 4b in the recording unit 4 to determine who the face is. It is determined who the subject is, that is, the subject.

The operation determination unit 6 detects the state of operation members such as operation switches and operation dials provided in the camera 10 to determine the operation state. When the user operates the camera, the operation determination unit 6 detects the operation state, and the control unit 1 controls shooting and reproduction according to the result. In addition, the age processing unit 7 performs age processing on the eyes, the mouth, and the like so that a person appearing in the image has a facial expression when the age is young.

The display unit 8 is provided on the back surface of the camera 10 and can display a subject image as a moving image based on the image data output from the imaging unit 2 and use it as a viewfinder at the time of shooting. Further, the image data recorded on the recording medium of the recording unit 4 is read in accordance with the operation of the playback button and the like, and after being expanded, displayed on the display unit 8. Further, the display unit 8 displays the relationship between the persons shown in the captured image, as will be described later. The communication unit 14 transmits and receives facial feature signals 20 and image data to and from the external server 22, another user 23, and the external recording 21 via the Internet 15 at a hot spot or the like.

The above-described control unit 1 can classify images by effectively using the above-described output. Here, classification and is a classification that Who is reflected in the photographic image, because not go to not to have a face data of all of the people in the image database 4b, in this technology, any person with any person However, the person of the subject is determined by checking whether or not they are in a friendship relationship.

That is, when an image in which a person to be searched is shown (for example, the image 51 in FIG. 1), the control unit 1 (including the similarity detection unit 11) determines with whom the person is shown. The images 52, 53, and 54 in which Mr. A is reflected in the designated image 51 of A but other people are also sequentially retrieved and displayed.

From this display, you can see at a glance what kind of friendship Mr. A has. From this display, the user can remember various people and think about it. The designated person (Mr. A in FIG. 1 (A)) may be seen by another person depending on the expression and the angle of the face. Therefore, it is better to designate a plurality of images like the image 51 in FIG. 1 (A). , Detection accuracy goes up.

In a case where a similar image is not searched for in an image recorded in the recording unit 4 in the camera, an image recorded in the external recording unit 21 outside the camera may be searched. Further, the face feature signal 20 may be output to the external server 22 to help part or all of the search. Of course, the search result as shown on the display unit 8 may be viewed by the external user 23 and enjoyed among the users. By using the image that can be searched in this way, it is possible to determine a friend who enjoys this image.

Next, the display of the party search performed by the control unit 1 will be described with reference to the flowchart of FIG. First, an image of a person (for example, Mr. A) who wants to perform a related person search is designated (S1). From this step, the user is prepared to perform a search for searching for a friendship relationship between the person (Mr. A). In this specification, one image may be used, but the search accuracy can be improved by selecting a plurality of images as shown in the image 51 in FIG. Subsequently, a face search is started (S2). That is, an image similar to the face image specified in step S1 is searched from the image data recorded in the recording unit 4 or, in some cases, the image data recorded in the external recording unit 21. .

Next, with respect to all face images recorded in the recording unit 4 and the external recording unit 2, it is determined whether or not the search has been completed as to whether there is an image similar to the face of a person (for example, Mr. A) ( S3). As a result of the determination, if the search has not been completed for all the image data, the search is continued and it is determined whether there is an image having the same face (S11). As a result of the determination, if there is no image with the same face, the process returns to step S3 to continue searching for an image with Mr. A, for example.

If the result of determination in step S11 is that there is an image with the same face (for example, Mr. A), it is subsequently determined whether or not a plurality of persons are shown in the image (S12). As a result of the determination, if only the person (for example, Mr. A) is captured, the process jumps to step S14. On the other hand, if the image includes a plurality of persons, the person to be searched (for example, Mr. A) ) Is temporarily stored (S13).

If the face of the next person is temporarily stored, next, an image showing the next person (if jumped from step S12, that image) is temporarily stored (S14). When temporary storage ends, the process returns to step S3 and the above steps are repeated. By repeating these steps, it is possible to search for an image in which the face of the person specified in step S1 is shown, temporarily store the image, and temporarily store the face shown next to the person. It should be noted that the next face in step S13 is not limited to the next person, but the face shown in the image may be temporarily stored.

As a result of the determination in step S3, when the search for the face is completed, that is, when searching for an image in which the person to be searched (for example, Mr. A) is reflected and other persons are also reflected, Preparations for selecting a representative image from the images are started (S4). For the representative image, the face data in step S13 is used from the image data temporarily stored in step S14, and if the adjacent person is the same person, the representative image is selected from them.

When the representative image determination is started (S4), first, for each image temporarily stored in step S14, the face size is weighted (an appropriate size is a high score) (S5), and then for each image. Weighting is performed by facial expression (smile is higher score) (S6), and weighting is performed so that the closer the target face is to the center of the screen, the higher score is obtained (S7). Thereafter, steps S5 to S7 are repeatedly performed, and a representative image is selected from the same person on the basis of the total score given in these steps (S8). The representative image selected here is displayed as a representative image 52 (see FIG. 1) in step S10 described later.

When a representative image is selected in step S8, it is subsequently determined whether selection of all representative images has been completed (S9). That is, in step S13, when there is another same face among the temporarily stored faces, a representative image is selected for the next face by repeating steps S4 to S8 for the next face. The selected representative image is displayed as a representative image 53 (see FIG. 1) in step S10 described later. In the example shown in FIG. 1, there are three persons related to the person to be searched (displayed by the image 51), and these are displayed as representative images 52, 53, and 54.

If it is determined in step S9 that all representative images have been selected, the representative images 52, 53, and 54 are displayed side by side on the display unit 8. Of course, every time a search is performed, a display method may be used in which the image is displayed unsorted, but in the example shown in FIG. 1, the friendship is organized and displayed. However, since the display does not start until all searches are completed, there are some users who cannot wait, so the display may be performed each time the search is performed.

As described above, in the first technique related to the present invention , the representative images 52, 53, and 54 of the person shown together with the person to be searched (representative image 51 in FIG. 1) are displayed side by side. . For this reason, the friendship relationship etc. of the person who became the search object can be understood at a glance. Further, even if the person to be searched is a person who is not acquainted (the person in the image 51), if there is an acquaintance with the person displayed in the representative images 52, 53, 54, the person to be retrieved from these relationships Can be specified.

Next, a second technique related to the present invention will be described with reference to FIGS. The second technique uses the friendship relationship with the search target person obtained by the first technique to transmit image data to a destination suitable for viewing a photographed image. Since the digital camera 10 according to the second technique is the same as that of the first technique , the description thereof is omitted, and the operation and the display method in the display unit 8 will be mainly described.

When the digital camera 10 is reset to power-on, a normal shooting operation is performed (S31). In this shooting operation, the subject is framed by the live view display on the display unit 8, the operation state of the release button is determined by the operation determination unit 6, and is acquired by the imaging unit 2 when the release button is fully pressed. The recorded image data is recorded in the recording unit 4.

Subsequently, an image similar to the face of a person (for example, Mr. A) in the image data recorded in the recording unit 4 is searched (S32). That is, an image in which Mr. A is shown is searched. Next, it is determined whether or not the retrieved image is a photograph showing a plurality of human faces (S33). As a result of the determination, if the photograph does not show a plurality of faces, the process returns to step S31.

Steps S32 and S33 described above may apply the related party search flow (FIG. 2) in the first technique . However, in the flow shown in FIG. 2, the representative image is displayed, but this step is not necessary. If the result of determination in step S33 is that there are a plurality of faces in an image having a face similar to Mr. A, another face image is extracted (S34).

Next, it is determined whether or not the extracted face is registered in the image database 4b (S35). That is, another face other than Mr. A is detected, and it is determined whether or not the person's face image is registered in the database (corresponding to the image database 4b) shown in FIG. If it is registered as a result of the determination, it is recorded as a candidate for image transmission in the registered person (Mr. X and Mr. Y in FIG. 1B) (S36).

After this, although not shown in the figure, if the image of Mr. A is sent to the other party listed as a destination candidate by the user's selection, the other party enjoys the recent situation of Mr. A together with the sender. be able to. At this time, if the e-mail address is also described in the image database 4b, it is possible to form a community and enjoy it in the circle without thinking about who and who the destination is. Become.

For example, when an image of the subject 12 (Mr. A) is taken, a person who knows Mr. A can view and enjoy the image, but a person who does not know Mr. A cannot understand and enjoy anyone's photo. Therefore, in the second technique , the friendship of Mr. A is determined from a photographed image (recorded in the recording unit 4) or a publicly available image database (recorded in the external recording unit 21), and this is displayed on the display unit 8. It is trying to display.

In other words, Mr. X (see image 56 and image 58) and Mr. Y (see image 57 and image 59) who have been photographed with Mr. A (see image 55) should know Mr. A. In the present embodiment, it is possible to transmit Mr. A's image to those people, thinking that the present condition of Mr. A will be appreciated.

Next, an embodiment of the present invention will be described with reference to FIGS. In the first and second techniques related to the present invention , a search is performed for a person or the like that is shown together with a person to be searched. However, in one embodiment of the present invention, a search is performed together with a person to be searched. The related parties are searched in a chained manner, such as a person who is shown with a person who is shown in the picture, as well as a person who is shown in the picture. In one embodiment of the present invention, age processing is performed on a face image so that a search beyond generations can be performed. Since the digital camera 10 according to the present embodiment is the same as that of the first technique , a detailed description thereof is omitted, and the operation and the display method in the display unit 8 will be mainly described. The flowchart shown in FIG. 5 is executed by the control unit 1 (see FIG. 1).

First, as in step S1, an image 51 (see FIG. 6) such as a person (for example, Mr. A) who wants to perform a related person search is designated (S51). The designated image may be a single image, but the search accuracy can be improved by selecting a plurality of images. Subsequently, as in step S2, a face in the designated image is detected, and an image similar to the designated image is detected from the image data recorded in the recording unit 4 or the external recording unit 21 with the same face image. Is searched (S52).

Subsequently, it is determined whether or not the image data of the similar image has a plurality of face images (S53). As a result of the determination, if there are a plurality of face images, the image 52 is displayed adjacent to the designated image 51 (S54). Subsequently, it is determined whether or not the user has changed the candidate (S55). That is, when an image 52 having a plurality of faces is searched, the image 52 is displayed adjacent to the original designated image 51 in step S54. If the friendship relationship is known from the image 52 and the user is interested in the person appearing in the image 52, the operation member instructs to change the candidate.

If the result of determination in step S55 is that the candidate has been changed, the search face is changed to the image 52 from the original designated image 51 (S56). Subsequently, a new candidate image 53 is searched from the image 52 and displayed below the image 52 (S57). Then, the process returns to step S52, and the same step as above is processed for this new candidate (designated image 53) to search whether a similar face exists, and as shown in FIG. Etc. are displayed.

In this way, by repeating steps S52 to S57, it is possible to search and display related parties sequentially in a chain starting from the designated image 51. During this time, if a photograph with a plurality of faces cannot be found in step S53, or if the candidate is not changed in step S55, all images recorded in the recording unit 4 and the external recording unit 21 are displayed. It is determined whether or not the search has been completed for the data (S61).

As a result of the determination in step S61, if the search is completed for all the image data, this routine is ended. If the search is not completed, the search is continued. When continuing the search, it is determined whether or not there are no candidates (S62). As a result of the determination, if there is a candidate, the process jumps to step S64, but if there is no candidate, age processing is performed (S63). Here, the age processing is performed because the currently searched face image is actually old, and there may be candidates if it is a young photograph. Age processing is applied to the images. This age process will be described later with reference to FIGS.

Subsequently, display during search is performed (S64). In this routine, the search-in-progress display takes many time-consuming steps such as searching for similar images and age processing, and it may take time to display, and may appear to appear as if processing is not performed. Because there is. When the processing speed is high and it does not take time to display, the display during search can be omitted.

When the first image 51 is displayed on the display unit 8 by executing the flow shown in FIG. 5, an image (photograph) 52 in which a person (Mr. A) shown in the image 51 and another person are shown together is displayed. The user may be interested in a person (Mr. B) located next to Mr. A by viewing the displayed image 52 displayed. In this case, when a predetermined operation is performed with an operation member or the like, another image of Mr. B as shown in the image 53 is displayed, and as with Mr. A, what kind of friendship relationship is present with Mr. B. The image 54 is retrieved and displayed. Furthermore, if the interest shifts to a person (C) who is located next to B, it is possible to search for other images of C.

In this way, even if the image of Mr. A is not known, it is possible to grasp who it is and the clues of the relationship with him while looking at Mr. B and Mr. C. Furthermore, it is possible to proceed with image appreciation with interest, and while enjoying the story of A, B and C, it is possible to enjoy the image while feeling the story.

Next, the age process in step S63 will be described with reference to FIGS. FIG. 8A shows an example of an aging sign (shade feature) appearing on a human face. Particularly conspicuous are the slack of the eyelid 61 of the outer corner of the eye, the line 62 of the side of the lips, the slack of the cheek 63, and the like. By correcting (thinning) this sign from FIG. 8 (b) to FIG. 8 (c), the face becomes younger. That is, when performing a search retrospectively, the search may be performed while eliminating such an aging sign in consideration of changes in the face with age.

When entering the flow of face correction shown in FIG. 7 for search with face correction, first, face detection is performed (S71). In this face detection, the brightness around 65 in the circle is made uniform, that is, a circle. The brightness is made uniform in accordance with the brightness of the brightest portion of the inner 65 or the portion having a larger area. Subsequently, the eyes, mouth, and cheeks are detected from the detected face (S72).

The aging sign is determined using the detected part such as the eye, but before that, it is determined whether or not glasses are being worn (S73). This is because, when this operation is performed on a person wearing glasses, the edges of the glasses become unnatural. Therefore, in this embodiment, face detection (S71) and face part detection (S72) are performed. At this time, if there is a high contrast portion around the eye, it is determined that the user is wearing glasses.

If the result of determination in step S <b> 73 is that the user is wearing glasses, the routine returns to the original routine, and the series of processing is not performed. This is because the portion where the aging sign appears is hidden by wearing glasses, so it is considered that an error due to age is unlikely to occur without performing such processing. However, a person who wears or does not wear glasses may not be able to search. This is a limiting condition here.

If the result of determination in step S73 is that no glasses are being worn, aging sign determination is subsequently performed (S74). Here, in step S72, it is determined whether or not there is an aging sign in the detected face portion (sag of eyelid 61, horizontal line 62 of lips, sagging of cheek 63). If the result of determination in this step is that there is an aging sign (S75 → Yes), how much rejuvenation is determined from the relationship between the search year obtained from the photograph and the original data is determined (S76).

Subsequently, the brightness of the area including the eyes, the edge of the lips, and the cheek outline is equalized (S77). That is, the brightness is adjusted according to the difference in the year so that the area including the corners of the corners of the eyes, the edges of the mouth, and the cheek outlines is continuously and uniformly so as not to become unnatural from around. By brightening this area as much as the surroundings, it is possible to correct the appearance of a young face as shown in FIG. However, if the old image is not searched, the face image is slightly brightened. The face image obtained in this way is reflected in the face image at the time of search (S78).

If the result of determination in step S75 is that there is no aging sign, the process returns to the original routine without correcting the face image. In this embodiment, since this process is performed only when there is an aging sign, an age process is performed on a person of a predetermined age or older. However, the present invention is not limited to this. For example, age information may also be recorded in the database 4b, and such age processing may not be performed for people in their 20s and 30s.

As described above, in the age processing according to the embodiment of the present invention, the friendship relationship can be understood from the old photos in addition to the search candidates up to the old age photos. By performing face image correction with age processing, it is possible to search beyond generations, and for example, from the image of Mr. A who was initially designated, it is possible to enjoy image appreciation that is even more thoughtful to other people .

Further , in one embodiment of the present invention, it is not a way of enjoying that the image is simply beautiful or the expression is wonderful, but the characters are searched one after another from the image in which a certain person is reflected, and how Cameras and photo appreciation systems that allow people to know how people are connected and enjoy intelligent ways are possible.

Next, a third technique related to the present invention will be described with reference to FIGS. A person image search using a face image is effective for a revised commemorative photo or the like, but a familiar photo such as a snapshot may cause a false detection depending on the facial expression of the person. Therefore, in order to obtain face data of a list of what kind of face a person shows, in the third technique , a face database is created in consideration of the clothes of the person. That is, in images taken within a predetermined time, such as a party or a meeting, it is considered that the same person was wearing the same clothes, so a face database is created focusing on clothes. Since the third technique is constituted by the same digital camera 10 as that of the first technique , the difference will be mainly described.

When entering the flow of creating the same person face database (DB) shown in FIG. 10, first, a certain person image is selected, and images taken in the same time zone are collected from the recording unit 4 (S81). Subsequently, an image showing a plurality of persons is selected therefrom (S82). Then, it is determined whether or not there is a person with the same color and pattern (clothes) under each face (S83). As a result of the determination, if there is no color or pattern of the same clothes, it is assumed that individuals can be specified by clothes, and persons with the same clothes are classified into the same person (S84). That is, as shown in FIG. 9, it is determined whether clothes are the same A or not, and data is collected on what kind of face Mr. A changes.

As a result of the determination in step S83, if the bottom of the face has the same clothes color and the same pattern (S83 → Yes), the person appearing in the image taken during this time zone is wearing a uniform. Since it is conceivable, the user sequentially determines whether or not the images are the same person, and manually selects the same person image (S89).

Even if the same clothes are worn in the same time zone, it is necessary to search for other opportunities (time zones) using facial images. Therefore, it is possible to perform a more accurate and reliable search by storing various patterns as facial images as a database. In the third technique , as shown in FIG. 9, an image extracted from the recording unit 4 in the digital camera 10 is used to have a plurality of face patterns of the same person in the image database 4b.

When the classification is completed in step S84 or step S89, next, a list of the images of the same person is displayed on the display unit 8 with respect to the portion indicated by reference numeral 4b in FIG. 9 (S85). The user checks the list display of the images, and if there is no mistake, the user performs an approval operation, so it is determined whether or not the approval has been made (S86). As a result of the determination, if approval is not made, the process proceeds to step S89 and an image is manually selected. On the other hand, if approved by the user in step S86, a face list is created and recorded in the image database 4b (S87).

In this way, in the third technique , it is possible to more accurately determine whether or not the person is the same person even if the face of the person changes by also using clothes information worn by the person. A high database can be created. By using this database, it is possible to search for a similar image of a face with more certainty. Further, in step S83, by determining whether the clothes under the face are the same color and the same pattern, even when the member is wearing the same clothes as in a uniform, it can be recognized correctly and accurately. Can create a database of various faces.

Next, a digital camera 10 that can search for and display an image similar to a person's face in a designated image using the database 4b of a plurality of face data in the third technique related to the present invention will be described with reference to FIG. Will be described. As described above, the digital camera 10 has the same configuration as the digital camera 10 shown in FIG.

First, the control unit 1 of the digital camera 10 designates an image of the specified person (here, Mr. A). In the flow shown in FIG. 11B, the face of the designated image is determined by the user in consideration of the deformation of the person's face (S91). Then, a similar face pattern is searched from the image database 4b (S92). It is specified which person's face the face image is (S93), and a search is performed using the variation pattern of the person's face (S94).

In performing the search, first, using the representative face image, an image in which the face of the pattern is photographed is searched (S95). That is, a similar image is searched using a representative image among a plurality of face images. It is determined whether or not a similar image can be searched based on the representative image (S96). If the search is successful, the image is displayed on the display unit 8 as a search result.

On the other hand, if the search cannot be performed using the representative image, it is determined whether there is a modification (S97). That is, if there are a plurality of face image data for the same person (there are three types in the example of FIG. 11A), it is determined whether there is an unsearched face image (S97). If there is no modification of the face image, the process returns to the original routine. If there is, the search is performed using the modification of the face image (S98). When the search is completed, the process returns to step S96. Perform the above operations.

As described above, in the third technique related to the present invention , a plurality of face images corresponding to the same person are collected, and the face images are stored in a database. Since the face image database is used to search for an image in which the designated person is shown, as in the first technique, the second technique, and the embodiment of the present invention, Relationships can be displayed. In the third technique , unlike the second technique , the function of transmitting an image to a friend is not provided, but it is of course possible to add this function. Further, in the third technique , the friendship relationship is not displayed in a chain manner as in the embodiment of the present invention, but of course, it may be displayed in the same manner as in the embodiment. Furthermore, it is good also as a search which considered the age like one Embodiment.

In the embodiment and the related art of the present invention, the detected similar image, which had be displayed adjacent, this display method can be variously modified, also originally specified In addition to displaying the searched image and the searched image at the same time, only the searched image may be displayed. If there are a large number of searched images, the images may be displayed divided into a plurality of pages. In one embodiment of the present invention and related technology , a face of an image to be designated first is detected as a feature part, and a similar image is searched based on this face. However, the present invention may be the whole person or a conspicuous part such as the eyes and nose.

Furthermore, although one embodiment of the present invention and related technology have been described using a digital camera, the digital camera may be a digital single-lens reflex camera or a compact digital camera, and may be a mobile phone or a personal digital assistant (PDA). Of course, a camera built in Personal Digital Assist) may be used. Of course, a personal computer or the like that records image data taken by a digital camera or the like may be used. Furthermore, the present invention may be implemented inside an external database that records image data captured by a digital camera or the like.

The present invention is not limited to the above-described embodiments as they are, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage. In addition, various inventions can be formed by appropriately combining a plurality of components disclosed in the embodiment. For example, you may delete some components of all the components shown by embodiment. Furthermore, constituent elements over different embodiments may be appropriately combined.

It is a figure which shows the outline | summary of the digital camera concerning the 1st technique relevant to this invention, (A) is a block diagram, (B) is the data content of an image database. It is a flowchart which shows the party search in the digital camera concerning the 1st technique relevant to this invention. It is a figure which shows the display state in the digital camera concerning the 2nd technique relevant to this invention. It is a flowchart which shows the camera control in the digital camera concerning the 2nd technique relevant to this invention. It is a flowchart which shows the related party search in the digital camera concerning one Embodiment of this invention. It is a figure which shows the display state in the digital camera concerning one Embodiment of this invention. It is a flowchart of the face correction in the digital camera concerning one Embodiment of this invention. In the digital camera concerning one Embodiment of this invention, it is a figure which shows the process in which an aging state is corrected from an aging state. It is a figure which shows the display state in the digital camera concerning the 3rd technique relevant to this invention. It is a flowchart which shows the same person face DB preparation in the digital camera concerning the 3rd technique relevant to this invention. It is a figure which shows the display method of the similar face image in the digital camera concerning 3rd technique relevant to this invention, (A) is a figure which shows the display state in a digital camera, (B) is a flowchart which shows a face search. is there.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Control part, 2 ... Imaging part, 3 ... Lens determination part, 4 ... Recording part, 4b ... Image database (DB), 5 ... Face detection part, 6 ... Operation determination unit, 7 ... age processing unit, 8 ... display unit, 9 ... clock unit, 10 ... camera, 11 ... similarity detection unit, 14 ... communication unit, 15 ... ..Internet network, 21 ... external recording unit, 22 ... external server, 23 ... other user, 51 ... image (Mr. A), 52 ... representative image, 53 ... representative Image 54 ... Representative image 55 ... Image (Mr. A) 56 ... Image (Ms. X) 57 ... Image (Ms. Y) 58 ... Image (Ms. X) 59 ... Image (Mr. Y), 61 ... Wrinkles in the corners of the eyes, 62 ... Lines next to the lips, 63 ... Cheeks

Claims (3)

An image recording unit for recording images;
An image designating unit for designating a first image including the first person;
An age processing unit for performing age processing on the first image;
A second image including a first person designated by the image designating unit and an image similar to the first image age-aged by the age processing unit , and other than the first person, An image search unit for searching from the images recorded in the image recording unit;
A display unit for displaying the first image and the second image;
An image handling apparatus comprising: The image handling apparatus according to claim 1, wherein the age processing unit performs an age process on an eye or a mouth of the first person. The image handling apparatus according to claim 2, wherein the age processing unit performs a process of eliminating an aging sign as the age process for the first person.