JP2011171921A - Digital camera - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To make a voice uttered to an object person become the one suitable for the person. <P>SOLUTION: A face expression detection part 22 obtains object character information, for example, face expression information detected by a face detection part 21. A voice data selection part 25 selects, on the basis of the face expression information, voice data suitable for the face expression information from a plurality of pieces of voice data stored in a voice data storage part 35, and sends the selected voice data to a speaker 43 in accordance with the operation of a release switch by an operation part 41. Voice data such as "Smile, more" or "Do not cry and Say cheese" is reproduced from the speaker 43. Besides, as the object character information, there are age/gender information and character registration information. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a digital camera, and more particularly to a digital camera having a function of detecting a subject person in an image.

When you want to shoot a smile on the subject person, guide the subject person to utter a predetermined word, for example, “yes, cheese”, which is relatively popular. After recognizing the utterance, shoot at a preset timing. A person photographing apparatus is known (see, for example, Patent Document 1).
This person photographing apparatus is suitable for use in, for example, an ID photo photographing system, and a photographing procedure and the like will be described with a predetermined sound predetermined for a subject person.

JP 2008-26604 A

  A general digital camera may shoot various facial expressions of a subject person, such as a laughing face, a crying face, an angry face, or a surprised face. It is completely meaningless and may not be preferable.

  According to a first aspect of the present invention, there is provided a digital camera that captures an image of a subject person and creates image data, an image capturing unit that starts an image capturing operation, and a subject person in image data captured by the image capturing unit in the image capturing preparation stage. Person information acquisition means for detecting an image and acquiring subject person information, sound data storage means for storing a plurality of sound data, and subject data acquired by the person information acquisition means are stored in the sound data storage means. Voice data selection means for selecting predetermined voice data from a plurality of voice data, and voice playback means for playing back the selected voice data prior to a shooting operation by the shooting means, To do.

  According to the digital camera of the present invention, a subject person is detected, voice data corresponding to the detected subject person information is selected, and voice suitable for subject person information such as facial expression information of the subject person before photographing is selected. Can be issued.

It is a block diagram which shows the structure of the digital camera which concerns on embodiment of this invention.

Hereinafter, a digital camera according to an embodiment of the present invention will be described with reference to the drawings.
As shown in FIG. 1, the digital camera includes a photographic lens 11, a diaphragm 12, an image sensor 13, a buffer memory 14, and an image processing unit 15. The digital camera also includes an image recording unit 16, a CPU (Central Processing Unit) 17, a ROM (Read Only Memory) 18, a bus 19, an operation unit 41, a display 42, a speaker 43, and a communication unit 44.

The image processing unit 15, the image recording unit 16, the CPU 17, the ROM 18, the operation unit 41, the display 42, the speaker 43, and the communication unit 44 are connected to each other via the bus 19.
The CPU 17 functions as a face detection unit 21, facial expression detection unit 22, age / gender reasoning unit 23, face recognition unit 24, voice data selection unit 25, effect evaluation unit 26, and ranking unit 27.
The CPU 17 controls the photographing lens 11, the diaphragm 12, the image sensor 13, and the like that are photographing means.
The ROM 18 functions as a face data storage unit 31, a facial expression data storage unit 32, an age / sex data storage unit 33, a face registration data storage unit 34, and an audio data storage unit 35.

  The photographing lens 11 includes a plurality of lenses including a zoom lens and a focus lens, and forms a subject image on the image sensor 13. In FIG. 1, for the sake of simplicity, the taking lens 11 is shown as a single lens. The imaging element 13 generates an image signal by photoelectrically converting the subject light L1 from the photographing lens 11.

The image signal output from the image pickup device 13 is sent to the image processing unit 15 via the buffer memory 14, where predetermined various image processing is performed.
At the stage before shooting is started, that is, at the shooting preparation stage, the image signal from the image sensor 13 is sent to the display 42 via the buffer 19 via the buffer memory 14 and the image processing unit 15 and displayed as a through image.
At the photographing stage, the image signal from the image sensor 13 is recorded in a non-volatile memory (storage medium) 16 a of the image recording unit 16 via the bus 19 via the buffer memory 14 and the image processing unit 15.

  The face detection unit 21 detects the face of the subject person in the image by comparing the subject image data for the through image with the face data stored in advance in the face data storage unit 31. The face data storage unit 31 stores, for example, feature point data relating to the shape of eyebrows, eyes, nose, and lips.

  For the face detection, for example, a detection method disclosed in Japanese Patent Laid-Open No. 2001-16573 can be used. In this detection method, feature points are extracted from an input image to detect the face area, face size, etc. of the subject. The feature points include end points of eyebrows, eyes, nose, lips, and face contour points, such as the head vertex and the lower end point of the chin.

  As other face detection, for example, a detection method disclosed in JP-A-2005-157679 can be used. In this detection method, first, a luminance difference between two pixels in an input image is learned as a feature amount, and an estimated value indicating whether or not a face exists in a predetermined region in the input image based on the feature amount. And when the estimated value is 1 or more, it is determined that a face exists in the predetermined area.

The facial expression detection unit 22 compares the facial expression of the image of the face area detected by the face detection unit 21 with a plurality of facial expression data stored in advance in the facial expression data storage unit 32, thereby The type of facial expression of the subject person is detected.
There are various types of facial expressions such as a smiling face, a crying face, an angry face, and a surprised face, and the facial expression data storage unit 32 stores these various facial expressions as data.

  When the facial expression detection unit 22 detects a facial expression of an image in the face area, for example, a detection method disclosed in Japanese Patent Application Laid-Open No. 2008-42319 can be used. In this detection method, for example, in order to detect a smile, the type of facial expression is determined based on whether the face of the detected image is close to the two facial expressions of a smile and a normal face. . The facial expression detection unit 22 outputs a detection signal corresponding to the type of facial expression of the subject person.

The age / sex reasoning unit 23 infers the age / sex of the subject person based on the image of the face area detected by the face detection unit 21. That is, the age / gender reasoning unit 23 uses the feature amount of each feature point for each feature point in the face image of the subject person and each feature point of the face stored in advance in the age / sex data storage unit 33. Inferring age and gender of subject person by comparing color and color data. Then, the age / sex reasoning unit 23 outputs the reasoning result, for example, inference data that the age of the subject person is an infant and the sex is a boy, and the age is a 20's and the sex is a woman.
The age / sex data storage unit 33 stores, for each age of each gender, data of feature amounts (dimensions, intervals) and color data possessed by feature points such as eyebrows, eyes, nose and lips.

  As a method for inferring age / sex, for example, a method disclosed in Japanese Patent Application Laid-Open No. 2004-222118 is used, and the above-described feature amount is input to a system called a support vector machine.

The face recognition unit 24 has a person registration function for recording the feature information of the face image of the subject person photographed in advance as face registration data in the face registration data storage unit 34, and the face image of the subject person to be newly photographed is the face registration data. It has a person recognition function for identifying whether it corresponds to the face registration data recorded in the storage unit 34.
In detail, the face recognition unit 24 analyzes the characteristics of the face image of a person photographed in advance and records it as face registration data in the face registration data storage unit 34. At this time, the name information, age information, and gender information of the person are also associated with the face registration data and recorded in the face registration data storage unit 34. In this way, the subject person is registered.
The name information, age information, and gender information are input by the photographer from an information input unit (not shown).

In addition, the face recognition unit 24 compares the face image of the subject person detected by the face detection unit 21 with the face registration data recorded in the face registration data storage unit 34, that is, the person who has the subject person registered, that is, It is determined whether or not the person is a registered person.
Note that the face registration data stored in the face registration data storage unit 34 is information on face information of a registered person's face image, for example, feature points such as eyebrows, eyes, nose, and lips.

  The audio data selection unit 25 selects the audio data recorded in the audio data storage unit 35 based on the information related to the subject person, and causes the speaker 43 to reproduce the selected audio data as audio. Specifically, the voice data selection unit 25 detects the type of facial expression detected by the facial expression detection unit 22, age / gender information inferred by the age / gender inference unit 23, and the registered person recognized by the face recognition unit 24. Audio data to be reproduced is selected according to the information.

  The audio data selection unit 25 sends the selected audio data to the speaker 43 for playback slightly before the shooting operation, for example, 1 second before the shooting operation. Specifically, when a release switch of the operation unit 41 to be described later is operated, the audio data selection unit 25 sends the selected audio data to the speaker 43 for reproduction, and the photographing operation is started after a predetermined time of the reproduction. The

The audio data storage unit 35 stores various audio data uttered at the time of shooting. For example, “High, laugh”, “Smile more”, “Smile!”, “Smile”, “Don't get so angry”, “Don't cry, cheese”, “Smile,” “Lol” "Let's laugh", "A-chan, smile", "B-kun, laughter", "C-Let's laugh", "D-san, E-san, High, Cheese", "Laughter all together Voice data such as “Sho” is recorded in the voice data storage unit 35.
"A-chan, smile", "B-kun, laughter", "C-san, let's laugh", "D-san, E-san, Hai, cheese""A-chan","B “Kimi”, “Mr. C”, “Mr. D”, and “Mr. E” are names of registered persons stored in the face registration data storage unit 34. Voice data including these names, “A-chan, smile”, “B-kun, laughter”, “C-san, let's laugh”, “D-san, E-san, Hai, Cheese” are registered name information When age information and gender information are stored in the face registration data storage unit 34, they are automatically created by a voice data creation unit (not shown) and stored in the voice data storage unit 35.
The voice data may be a singing voice such as an animation song, and is not limited to a human voice, and may be a crying voice of a dog or a cat.

  In the manufacturing stage of the digital camera of the present embodiment, a large number of audio data is stored in the audio data storage unit 35, and the name of the registered person is registered when the subject person is registered in the face registration data storage unit 34. Audio data including information is additionally stored in the audio data storage unit 35, and further, audio data input from the outside by the communication unit 44 described later is additionally stored in the audio data storage unit 35.

  For example, when the facial expression detection unit 22 detects the smile of the subject person and acquires smile information, the audio data selection unit 25 selects, for example, audio data “more laugh” to invite a better smile. When the facial expression detection unit 22 detects the non-smile of the subject person, the voice data selection unit 25 selects, for example, voice data “Yes, laugh” to induce laughter.

  When the age / sex reasoning unit 23 infers that the subject is, for example, an infant, the voice data selection unit 25 uses, for example, the voice data of the infant word “Niko Nikote” or the dog's cry “One, One”. When the age / gender reasoning unit 23 selects and infers that the subject is, for example, a young man or a young woman, the voice data selection unit 25 selects “LOL”, “Let's laugh” or “Smile”, respectively. Select the voice data of “In”.

  When the face recognition unit 24 recognizes that the subject person is a registered person registered in the face registration data storage unit 34, the voice data selection unit 25 includes “A-chan, Nico Nico” including the name of the person. ”,“ B-kun, laughter ”,“ C-san, let's laugh ”,“ D-san, E-san, High, Cheese ”, etc. are selected.

  The effect evaluation unit 26 evaluates whether the facial expression of the subject person in the captured image data is a facial expression that reflects the content of the reproduced audio data at the time of shooting. Specifically, when the facial expression detection unit 22 detects the facial expression of the subject person in the photographed image data, the effect evaluation unit 26 reflects the content of the reproduced audio data at the time of photographing. Evaluate whether the facial expression is correct. For example, if the playback audio data that was played before shooting was “smiley”, determine whether the facial expression of the shot image was a laughing face, and if it was a laughing face, It is evaluated that there is a reproduction effect, and a score of 1 is given to this audio data.

  The ranking unit 27 gives a ranking to a plurality of audio data recorded in the audio data storage unit 35 based on the evaluation result of the effect evaluation unit 26. Specifically, the ranking unit 27 adds the score given to the audio data by the effect evaluation unit 26 for each audio data, and determines the ranking of the audio data from the addition result.

  The operation unit 41 includes a power switch for the digital camera, a release switch for starting a shooting operation, a playback switch for playing back a captured image, a selection / setting switch for selecting and setting a shooting condition mode, and the like. When operated, an operation signal corresponding to the operation is output to the CPU 17. For example, as the selection function of the operation unit 41, the facial expression detection unit 22, the age / gender reasoning unit 23, the face recognition unit 24, or the like is selected and operated.

The display 42 displays a through image, displays a reproduced image based on the image data stored in the memory 16a, and displays an operation menu and the like.
The speaker 43 reproduces the sound data recorded in the sound data storage unit 35 as sound.
The communication unit 44 is connected to an external server 100 via a communication network, downloads audio data from the server 100 as necessary, and the downloaded audio data is stored in the audio data storage unit 35.

The operation of the digital camera configured as described above will be described.
-Facial expression detection mode-
First, a description will be given of a case in which sound data appropriate for a facial expression is selected.
When the operator selects the facial expression detection mode using the operation unit 41, the face detection unit 21 and the facial expression detection unit 22 are activated.
The face detection unit 21 compares the subject person image in the through image data with the face data in the face data storage unit 31 to detect the face part of the subject person. The facial expression detection unit 22 compares the facial expression of the subject person detected by the face detection unit 21 with the facial expression data of the facial expression data storage unit 32, and the facial expression of the subject person is “smile” or “crying face” or It is detected whether it is “angry face” or the like, and laughing face information, crying face information, angry face information, etc. are acquired.

  The voice data selection unit 25 selects voice data suitable for the facial expression information from a plurality of voice data stored in the voice data storage unit 35 based on the facial expression information from the facial expression detection unit 22. For example, when the facial expression information acquired by the facial expression detection unit 22 represents, for example, a smiling face or a crying face, the voice data “Make me laugh more” or the voice data “Do not cry, cheese” is selected.

Thereafter, when the release switch of the operation unit 41 is operated, the audio data selection unit 25 sends the selected audio data to the speaker 43 in accordance with the operation of the release switch, so that “laugh more” or “do not cry, Audio data such as “Cheese” is reproduced.
A photographing operation is started after a predetermined time after reproduction of the audio data, and the image signal from the image sensor 13 is processed by the image processing unit 15 and then stored in the memory 16a by the image recording unit 16.

The facial expression detection unit 22 detects the facial expression of the photographed subject image, and the effect evaluation unit 26 determines whether the detected facial expression of the photographed subject image is a “laughing face” due to the reproduction effect of the audio data. That is, it is determined whether the “smiling face” or “crying face” before photographing is changed to the “laughing face” at photographing, and the effect of the voice data is evaluated.
When the effect evaluation unit 26 determines that the voice data has changed to “laughing face”, the score 1 is assigned to the voice data, and when it is determined that the voice data is not “laughing face”, the score 1 is not assigned.

The ranking unit 27 adds the score given to the audio data by the effect evaluation unit 26 for each audio data, and determines the ranking of the audio data.
This ranking is displayed on the display 42 according to the operation of the selection switch of the operation unit 41. This ranking display is performed, for example, as follows: 1st place “more laugh” 15 points, 2nd place “Don't cry, cheese” 14 points, 3rd place “smiley” 10 points.

-Age / gender inference mode-
Next, a description will be given of a case where sound data suitable for the age and gender is selected.
When the operator selects the age / gender inference mode using the operation unit 41, the face detection unit 21 and the age / gender inference unit 23 are thereby activated.
When the face detection unit 21 detects the face image of the subject person in the through image data, the age / sex reasoning unit 23 infers the age / sex of the subject person based on the image of the face area detected by the face detection unit 21. Then, information on the age and sex of the subject person is acquired.
The age / gender reasoning unit 23 infers that the subject person is, for example, “infant” or “female in his 20s”, and acquires “infant” information or “female in his 20s” information.

The voice data selection unit 25 selects voice data suitable for the age and gender information from a plurality of voice data stored in the voice data storage unit 35 based on the age and gender information from the age / gender reasoning unit 23. To do.
For example, when the age and gender information acquired by the age / sex reasoning unit 23 represents “infant” or “female in the 20s”, the voice data “smiley” or the voice data “smile” is selected. . In the case of an “infant”, a dog or cat cry may be selected.

When the release switch of the operation unit 41 is operated, the voice data selection unit 25 sends the selected voice data to the speaker 43 in accordance with the release switch operation, thereby reproducing “smiley” or “smile”. The
A photographing operation is started after a predetermined time after reproduction of the audio data, and the image signal from the image sensor 13 is processed by the image processing unit 15 and then stored in the memory 16a by the image recording unit 16.

The facial expression detection unit 22 detects the facial expression of the photographed subject image, and the effect evaluation unit 26 turns the detected facial expression of the photographed subject image into a “smile” by the reproduction effect of the audio data. Or “a woman in her 20s” has a “smiling face”, and the effect of the voice data is evaluated.
When the effect evaluation unit 26 determines that there is an effect, the score 1 is assigned to the voice data, and when it is determined that there is no effect, the score 1 is not provided.
The ranking unit 27 adds the score given to the audio data by the effect evaluation unit 26 for each audio data, and determines the ranking of the audio data.

  It is also possible to combine the facial expression detection mode described above and the age / gender inference mode. In this combination mode, the voice data selection unit 25 stores the voice data based on the facial expression of the subject person detected by the facial expression detection unit 22 and the age and sex of the subject person inferred by the age / sex reasoning unit 23. Audio data is selected from the unit 35.

-Person registration + facial expression detection mode-
When the operator selects the person registration + facial expression detection mode using the operation unit 41, the face detection unit 21, the facial expression detection unit 22, and the face recognition unit 24 are activated.
First, creation of face registration data will be described.
A subject person to be registered as a person is photographed and face image data of the person is created. The face recognition unit 24 analyzes the characteristics of the face image of the person photographed in advance in this way, and records it as face registration data in the face registration data storage unit 34. At this time, the person's name information, age information, gender information, etc. are input by the information input unit (not shown), and the name registration information, age information, gender information, etc. are associated with the face registration data. Record in the storage unit 34.

In response to recording of the face registration data, name information, age information, and gender information in the face registration data storage unit 34, voice data including name information related to the face registration data is created, and the voice data is stored in the voice data. Is stored in the voice data storage unit 35 in association with the face registration data.
By repeating the above operation, the face registration data and name information of a plurality of persons are recorded in the face registration data storage unit 34, and voice data related to the face registration data is stored in the voice data storage unit 35. Is done.

Thereafter, in the shooting preparation stage, the face detection unit 21 compares the image of the subject person in the through image data with the face data in the face data storage unit 31 to detect the face part of the subject person. In this description, it is assumed that there is only one subject person.
The facial expression detection unit 22 compares the facial expression of the subject person detected by the face detection unit 21 with the facial expression data of the facial expression data storage unit 32, and the facial expression of the subject person is “smile” or “crying face” or It is detected whether it is “angry face” or the like, and facial expression information such as laughing face information, crying face information, and angry face information is acquired.
At the same time, the face recognition unit 24 compares the face image of the subject person detected by the face detection unit 21 with the face registration data recorded in the face registration data storage unit 34, so that the subject person has been registered. To which of the following.

  The voice data selection unit 25 is stored in the voice data storage unit 35 based on the name information, age information, and gender information about the registered person determined by the face recognition unit 24 and the facial expression information acquired by the facial expression detection unit 22. Audio data suitable for the facial expression information is selected from the plurality of audio data. The voice data selected at this time is voice data including the above name information. For example, “A-chan, smile”, “B-kun, laughter”, “C-san, let's laugh” Audio data is selected.

Next, when the release switch of the operation unit 41 is operated, the audio data selection unit 25 sends the selected audio data to the speaker 43 according to the operation of the release switch. Is played.
A photographing operation is started after a predetermined time after reproduction of the audio data, and the image signal from the image sensor 13 is processed by the image processing unit 15 and then stored in the memory 16a by the image recording unit 16.

The facial expression detection unit 22 detects the facial expression of the photographed subject image, and the effect evaluation unit 26 determines whether the detected facial expression of the photographed subject image is a “laughing face” due to the reproduction effect of the audio data. to decide.
The effect evaluation unit 26 assigns a score of 1 to the voice data when the facial expression detection unit 22 detects a “laughing face”, and does not assign a score of 1 when it is determined that it is not a “laughing face”. .
The ranking unit 27 adds the score given to the audio data by the effect evaluation unit 26 for each audio data, and determines the ranking of the audio data.

Next, a case where the face detection unit 21 detects face images of a plurality of subject persons from through image data will be described.
When the face recognition unit 24 determines that there is only one registered person among the plurality of subject persons detected by the face detection unit 21, the voice data selection unit 25 selects a plurality of people such as “you”. Voice data that calls the user is selected, or voice data that does not include name information is selected. This is because, when shooting a plurality of subject persons, only the registered person smiles by playing back audio data including the name of one registered person, for example, “Mr. C, let's laugh.” This is to avoid the situation where the person remains unsmiling.

When the face recognition unit 24 determines that there are more than a predetermined number of registered persons, for example, three or more, among the plurality of subject persons detected by the face detection unit 21, the voice data selection unit 25 The voice data that calls out to a plurality of people such as “” is selected, or the voice data that does not include the name information is selected.
When there are two subject persons detected by the face detection unit 21 and both of them are registered persons, the audio data selection unit 25 selects audio data including name information of the two persons, for example, Select “Mr. A, Mr. B, laugh”.

The above-described embodiment has the following effects.
(1) It is possible to detect a facial expression of a subject person, select audio data based on the facial expression, and reproduce the selected audio data immediately before the shooting operation.
(2) The age / gender of the subject person can be inferred, audio data can be selected based on the inferred age / sex, and the selected audio data can be reproduced immediately before the shooting operation.
(3) detecting the facial expression of the subject person, recognizing that the subject person is a registered person, selecting voice data based on the facial expression and the recognized registered person information, and selecting the selected voice data Can be played immediately before the shooting operation.
(4) When it is recognized that the subject person corresponds to a registered person registered in advance, audio data including the name information of the registered person is selected, and the selected audio data is reproduced immediately before the shooting operation. can do.
(5) When there are a plurality of subject persons and only one registered person is among the plurality of subject persons, audio data that does not include the name of the registered person can be selected.
(6) When there are a plurality of subject persons, it is possible to select audio data that calls to a plurality of persons such as “you”.

In the above-described embodiment, the facial expression detection unit 22 simply detects the facial expression of the subject person. However, the degree of facial expression, that is, the expression level is also detected, and the voice is detected according to the facial expression level. Data may be selected.
For example, the CPU 17 is provided with a facial expression level detection unit capable of distinguishing and detecting the degree of facial expression, that is, the facial expression level, for example, “smile”, “medium laughter”, and “big laughter”. Audio data can also be selected according to the facial expression level detected by the section.
In this case, when the facial expression level detection unit detects the “middle laughter” level, for example, voice data such as “laugh more loudly” is selected.

13: Image sensor 17: CPU
18: ROM 19: Bus 22: Facial expression detection unit 23: Age / gender reasoning unit 24: Face recognition unit 25: Speech data selection unit 26: Effect evaluation unit 27: Ranking unit 32: Facial expression data storage unit 33: Age / Gender data storage unit 34: Face registration data storage unit 35: Audio data storage unit 41: Operation unit 42: Display 43: Speaker

Claims (9)

Imaging means for imaging a person and creating image data;
Photographing means for starting the photographing operation;
A person information acquisition unit that detects a subject person image in the image data captured by the imaging unit in a shooting preparation stage and acquires the subject person information;
Voice data storage means for storing a plurality of voice data;
Voice data selection means for selecting predetermined voice data from the plurality of voice data stored in the voice data storage means based on the subject person information acquired by the person information acquisition means;
A digital camera comprising: an audio reproducing unit that reproduces the selected audio data prior to an imaging operation by the imaging unit. The digital camera according to claim 1, wherein
The person information acquisition means includes face expression detection means for detecting that the face image of the subject person in the image data is a predetermined facial expression and acquiring facial expression information,
The digital camera according to claim 1, wherein the voice data selection means selects the predetermined voice data based on the facial expression information acquired by the facial expression detection means. The digital camera according to claim 1, wherein
The person information acquisition means includes inference means for inferring at least one of the age and sex of the person as the subject person information based on the subject person image in the image data,
The digital camera, wherein the audio data selection means selects the predetermined audio data based on at least one of the age and sex inferred by the inference means. The digital camera according to any one of claims 1 to 3,
Face registration data storage means for storing face information of a predetermined person as face registration data;
Face recognition means for detecting that a face image of a subject person in the image data corresponds to predetermined face registration data stored in the face registration data storage means, and recognizing that the subject person is a registered person; Further comprising
The voice data storage means stores voice data including the name of the registered person,
The voice data selection unit selects voice data including the name of the registered person from a plurality of voice data stored in the voice data storage unit according to the registered person recognized by the face recognition unit. A digital camera characterized by that. The digital camera according to claim 4, wherein
When there are a plurality of subject persons in the image data, and the predetermined number or more of registered persons are included in the plurality of subject persons, the sound data selecting unit does not include the names of the registered persons. A digital camera characterized by selecting. The digital camera according to claim 4, wherein
When there are a plurality of subject persons in the image data, and the number of registered persons is less than the predetermined number among the plurality of subject persons, the audio data selection unit includes the names of all of the registered persons. A digital camera characterized by selecting audio data. The digital camera according to claim 4, wherein
When there are a plurality of subject persons in the image data, and only one registered person is among the plurality of subject persons, the sound data selecting means selects sound data not including the name of the registered person. A digital camera characterized by selection. The digital camera according to claim 2,
Evaluation means for evaluating whether or not the effect of the audio data reproduced by the audio reproduction means is reflected in the face image of the subject person in the image data imaged by the imaging means in the imaging stage by the imaging means; ,
Ranking means for assigning rankings to a plurality of audio data recorded in the audio data storage means based on the evaluation result of the evaluation means;
A digital camera further comprising display means for displaying the ranking result given by the ranking means. The digital camera according to any one of claims 1 to 8,
A digital camera, wherein a plurality of audio data stored in the audio data storage means is downloaded from a server.

Images