JP5152583B2 - Imaging apparatus, imaging guide method, and program - Google Patents

Description

  The present invention relates to a photographing apparatus, a photographing guidance method, and a program that have a face recognition function and guide a subject to be in a better photographing state.

  Conventionally, a photographing device such as a digital camera or a mobile phone has a function of automatically photographing using face detection / face recognition technology, for example, autofocusing on a human face in a photographing frame as a subject. There are known techniques for taking a picture and automatically taking a picture of a smiling face. Furthermore, before shooting, feature points are extracted and registered from face data from still images, and determined by the degree of matching with feature points at the time of face detection. For example, when all specified persons are recognized, In the case where the designated person is not included, a technique for guiding the camera direction, the moving direction of the subject, the standing position, and the like with LEDs, operation sounds, voices, and the like is known (for example, patents). Reference 1, Patent Document 2, Patent Document 3, and Patent Document 4).

JP-A-2005-341016 JP 2005-269562 A JP 2006-74368 A JP 2004-349959 A

  However, in the above prior art, when a designated person is not included or when it is not in a best state (such as being within a shooting frame), a guidance function such as a warning is insufficient. For example, in the prior art, when the designated person is not included or when the person is not in the best state (e.g., within the shooting frame), the LED emits light or the operation sound or voice guides. In particular, there is a problem that there is no way of knowing who is not included and who is not within the shooting frame, so that proper guidance cannot be performed.

  SUMMARY OF THE INVENTION An object of the present invention is to provide an imaging apparatus capable of providing appropriate guidance to a specific person using a face recognition function so as to obtain a better imaging state.

In order to achieve the above object, an imaging apparatus according to the present invention includes an imaging unit that captures an image of a subject, a face recognition unit that recognizes a plurality of human face portions from an image captured by the imaging unit, and the face recognition. State determination means for determining whether or not the face portions of a plurality of persons recognized by the means are in a predetermined state, and the faces of the plurality of persons when the state determination means determines that the face portions are not in a predetermined state In order to make a part into a predetermined state, a specifying means for specifying which person's state needs to be changed, and a specifying means for the person specified by the specifying means as a guidance information for instructing to change the state, and a guidance information output means for outputting the guidance information which can specify the relevant person and content of the state change, the state determining means, before Determining whether or not a deviation amount between a center point of all of a plurality of persons recognized by the face recognition unit and a center point of a predetermined imaging area captured by the imaging unit is within a predetermined value; When the state determination unit determines that the shift amount is not within a predetermined value, the whole of the plurality of persons recognized by the face recognition unit moves in the direction of the center point of the predetermined imaging area. In order to do this, it is characterized by specifying which person's position needs to be changed and how.

In order to achieve the above object, an imaging apparatus according to another aspect includes an imaging unit that images a subject, a face recognition unit that recognizes a plurality of human face parts from an image obtained by imaging by the imaging unit, A state determining unit that determines whether or not the face portions of the plurality of persons recognized by the face recognizing unit are in a predetermined state; and when the state determining unit determines that the face portions are not in the predetermined state, In order to make a person's face part into a predetermined state, a specifying means for specifying which person's state needs to be changed and how to specify the person specified by the specifying means by the specifying means a guidance information for instructing to change the state as specified, and guidance information output means for outputting the guidance information which can specify the relevant person and content of the state change, corresponding to each of a plurality of persons A personal information storage means for preliminarily storing the face recognition data characterizing each person's face portion and the personal information of each person, and a person corresponding to the face portion recognized by the face recognition means. Personal identification means for identifying based on the face recognition data stored in the personal information storage means, and personal information reading means for reading out personal information of the person identified by the person identification means from the personal information storage means The guidance information output means instructs the person to change the state as specified by the specifying means based on the personal information read by the personal information reading means. A guide sentence creating means for creating a guide sentence that can identify the person and the contents of the state change, and a guide sentence created by the guide sentence creating means. , Characterized in that it comprises a guide voice output means for outputting a guidance voice synthesis to.

Further, as a preferred aspect , the personal information includes a name of a person, and the guide sentence creating means creates the guide sentence including the name of the person.

Further, as a preferred aspect, the information processing device further includes basic guide sentence storage means for storing a plurality of basic guide sentences corresponding to each of the plurality of state changes that can be specified by the specifying means, Basic guidance sentence selecting means for selecting at least one basic guidance sentence corresponding to the state change specified by the specifying means from a plurality of guidance sentences stored in the basic guidance sentence storage means; and the basic A guidance sentence synthesizing unit that synthesizes at least one basic guidance sentence selected by the guidance sentence selection unit and the personal information read by the personal information reading unit to create the guidance sentence. Features.

Further, as a preferred aspect, the information processing device further includes a designation unit that designates at least one person to be identified by the person identification unit, and the personal information storage unit indicates whether or not the designation unit has designated The flag is stored in association with the personal information of the person, and the person specifying means corresponds to at least one person for which the designation flag is set to be effective corresponding to the face portion recognized by the face recognition means. The person is identified based on the face recognition data stored in the personal information storage means.

In order to achieve the above object, a shooting guidance method according to the present invention includes an imaging process for capturing an image of a subject in a computer of an imaging apparatus, and face recognition for recognizing a plurality of human face portions from the captured image. Processing , state determination processing for determining whether or not the recognized facial portions of the plurality of persons are in a predetermined state, and determining that the facial portions of the plurality of persons are not in the predetermined state In order to obtain a predetermined state, a specific process for specifying which person's state needs to be changed and how to change the state as specified for the specified person. a guidance information instructing, to execute the output process of outputting guidance information capable of specifying the relevant person and content of the state change, the state determination process, all of the plurality of persons recognized by the face recognition processing in Whether or not a deviation amount between a point and a center point of a predetermined imaging region imaged by the imaging process is within a predetermined value, and the specifying process determines that the deviation amount is a predetermined value by the state determination process. In order to move the whole of the plurality of persons recognized by the face recognition processing in the direction of the center point of the predetermined imaging area when it is determined that the position of the person is not within, the position of which person and how It is characterized by specifying whether it needs to be changed .

In order to achieve the above object, the program according to the present invention is a program for controlling the operation of an imaging apparatus including an imaging unit for imaging a subject, and has an imaging function for imaging a subject by the imaging unit on the computer, the imaging A face recognition function for recognizing a plurality of person's face parts from an image obtained by imaging by the unit, and a state for determining whether or not the plurality of person's face parts recognized by the face recognition function are in a predetermined state If it is determined by the determination function or the state determination function that the face portion of the plurality of persons is not in a predetermined state, which person's state needs to be changed in order to make the face portions of the plurality of persons into a predetermined state A specific function for identifying the person, guidance information for instructing the person specified by the specific function to change the state as specified by the specifying means, Guidance information output function of outputting an identifiable guidance information the content of the state change and, to realize the state determination function, the center point of the entire plurality of persons recognized by the face recognition function, the imaging function It is determined whether or not the amount of deviation from the center point of the predetermined imaging area imaged by is within a predetermined value, and the specific function is determined by the state determination function to be not within the predetermined value In this case, in order for the whole of the plurality of persons recognized by the face recognition function to move in the direction of the center point of the predetermined imaging region, which person's position needs to be changed and how It is characterized by specifying .
According to another aspect of the present invention, there is provided a photographing guide method in which an imaging process of capturing a subject on a computer of a photographing apparatus, a face recognition process for recognizing a plurality of human face parts from the image obtained by the imaging, and the recognition State determination processing for determining whether or not the plurality of face portions of the plurality of persons are in a predetermined state, and when it is determined that the face portions of the plurality of persons are not in the predetermined state, the face portions of the plurality of persons are set in a predetermined state In order to achieve this, it is necessary to use a specific process for specifying which person's state needs to be changed and guidance information for instructing the specified person to change the state as specified. In addition, output processing for outputting guidance information capable of specifying the relevant person and the contents of the state change, and face recognition data for characterizing each person's face corresponding to each of the plurality of persons and each person's individual Correspond with information Personal information storing process stored in advance, and a person specifying process for specifying a person corresponding to the face portion recognized by the face recognition process based on the face recognition data stored by the personal information storing process, A personal information reading process for reading the personal information of the person specified by the person specifying process from the face recognition data stored by the personal information storing process; A guidance sentence that instructs the person to change the state as specified by the specifying process based on the personal information read by the process, and specifies the person and the contents of the state change. Guidance text creation process for creating a possible guidance text, and guidance voice that synthesizes and outputs guidance voice based on the guidance text created by the guidance text creation processing Photographing guiding method which comprises a force canceling.
A program according to another aspect is a program for controlling an operation of a photographing apparatus including an imaging unit that images a subject. The program has an imaging function for imaging a subject by the imaging unit, and the imaging unit images the subject. A face recognition function for recognizing the face portions of a plurality of persons from the obtained image, a state determination function for determining whether or not the face portions of the plurality of persons recognized by the face recognition function are in a predetermined state, and the state A specific function that specifies which person's state needs to be changed and how to change the face portions of the plurality of persons to a predetermined state when the determination function determines that the state is not the predetermined state Guidance information for instructing the person specified by the specifying function to change the state as specified by the specifying unit, the person and the state change Guidance information output function for outputting guidance information capable of specifying the content, corresponding to each of a plurality of persons, and storing in advance the face recognition data characterizing each person's face and the personal information of each person A personal information storing function, a person specifying function for specifying a person corresponding to the face portion recognized by the face recognition function based on the face recognition data stored by the personal information storing function, and the person specifying A personal information reading function for reading personal information of a person specified by the function from the face recognition data stored by the personal information storage function is realized, and the guide information output function is read by the personal information reading function. A guidance sentence instructing the person to change the state as specified by the specific function based on the personal information issued, A guidance sentence creating function for creating a guidance sentence capable of specifying the contents of the state change, and a guidance voice output function for synthesizing and outputting a guidance voice based on the guidance sentence created by the guidance sentence creating function. It is characterized by that.

  According to the present invention, in order to obtain a better shooting state, it is automatically determined who the subject should do and how to guide the person to be guided and the operation thereof. The advantage is that appropriate guidance can be provided by sentences.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

A. Configuration of Embodiment FIG. 1 is a block diagram showing a configuration of a digital camera according to an embodiment of the present invention. In the figure, the input device 1 includes a plurality of button switches such as a shutter button, a cross key, and a function selection button. The internal storage device 2 includes a ROM, a RAM, and the like, and stores a predetermined program, data, and the like. In particular, in the present embodiment, a guidance sentence for guiding a person who is not in the photographing frame at the time of photographing to enter the photographing frame and personal information used to create the guidance sentence are stored. The camera device 3 includes an optical lens, an image sensor, a driver, and the like, and captures captured images. The display device 4 includes a liquid crystal display and displays a through image at the time of shooting, a captured image after shooting, various menus, shooting parameters, and the like.

  The voice input / output device 5 includes a microphone, a speaker, a voice processing unit, and the like. The voice input / output device 5 inputs external voice from the microphone, DA-converts voice data, and outputs the voice data from the speaker. In particular, the present embodiment has a function for synthesizing a guidance sentence (such as movement into a shooting frame) for a specific person during shooting. The external storage device 6 includes an interface for mounting an external storage medium such as an SD slot, and exchanges data with the external storage medium. The external storage medium stores captured images and the like in a predetermined format. Note that the above-described personal information and guidance text may be stored in the external recording medium. The strobe light emitting device 7 is a light emitting means for compensating for underexposure.

  The CPU 8 executes a predetermined program and controls the operation of each unit described above. In particular, in the present embodiment, registration of personal information, personal recognition by face recognition, determination of whether or not a recognized individual is imaged in a predetermined state, and a specific individual is imaged in a predetermined state in a shooting frame When there is not, guidance by voice output is performed. In the following, according to the present invention, registration of personal information as described above, personal recognition by face recognition, determination of whether or not a recognized individual is imaged in a predetermined state, and a specific individual is imaged in a predetermined state within a shooting frame Guidance by voice output when not performed will be described in detail.

  FIG. 2 is a conceptual diagram showing an example of personal information registered in the digital camera according to the present embodiment. In the present embodiment, the user registers a target person who performs voice guidance during shooting. As shown in FIG. 2, registered contents include name nickname, age, favorite character, favorite music, language, country, face image, face feature point data, designated ON / OFF flag, and the like. First, the name nickname is a name used when calling a person who is a target for guidance during voice guidance. The age is the age of the person, and is referred to in order to select a title to be given to the name at the time of voice guidance or a sentence at the end of the sentence (~. ~. ~~ .. etc.).

  Like the age, favorite characters and music are referred to in order to select a voice color (popular idol, entertainer, anime character, etc.) at the time of voice guidance. The music is referred to in order to select music that is output together with the voice guidance during voice guidance. The language and the country are referred to select a language (Japanese, English, Chinese, etc.) at the time of creating the guide sentence. The face image is the face image of the person taken at the time of registration, or used for extraction of face feature point data that characterizes the face (which enables individual identification) and is specified at the time of voice guidance setting. Used as a thumbnail when specifying a person. The face feature point data is extracted and registered when the face image is registered, and is used for specifying a person at the time of photographing. The designated ON / OFF flag is a flag for setting whether to designate as a person to be photographed.

  FIGS. 3A and 3B are schematic diagrams illustrating examples of screens when personal information is set or setting contents are changed in the digital camera according to the present embodiment. When the user performs a predetermined operation to set personal information, a setting screen as shown in FIG. 3A is displayed. On the setting screen, the user sets a face image, name nickname, age, favorite character, favorite music, and the like. Further, when the cursor is moved to a person whose setting content is to be changed on the setting screen, personal information set for the person is displayed as shown in FIG. 3B, and correction is possible. In the setting screen, a designation ON / OFF flag for designating a person to be guided can also be set, and a person whose designation ON / OFF flag is ON is designated as a person to be photographed. In the example shown in FIGS. 3A and 3B, four persons “Dad”, “Mama”, “Ken”, and “Yu” are designated as persons to be photographed.

B. Operation of Embodiment Next, the operation of the above-described embodiment will be described.

  4 and 5 are flowcharts for explaining the operation (photographing by voice guidance) of the digital camera according to the present embodiment. First, the user designates a person to be photographed on the setting screen shown in FIGS. Next, the user grasps the digital camera and looks at the through image displayed on the display device, and determines the composition including the background so that the subject (single or plural) fits within the shooting frame.

  In the digital camera, first, a face position of a person is detected from an image within a shooting frame of the image sensor, thereby maintaining a shooting start waiting state (through image display) while following the person who is the subject (step S10). . In this state, it is determined whether or not the cancel key has been operated (step S12). If the cancel key has been operated, the process ends.

  On the other hand, when the cancel key is not operated, the feature point of the person's face is analyzed from the image in the photographing frame photographed by the image sensor (step S14), and designated as the photographing target, that is, designated ON / OFF. Faces corresponding to the number of persons whose OFF flag is set to ON are analyzed (step S16), and it is determined whether or not all the members whose specified ON / OFF flag is set to ON are within the shooting frame (step S16). S18). At this time, if everyone is not within the shooting frame, the person outside the shooting frame (a person who is designated as a shooting target but not within the shooting frame) A guidance sentence is created according to the information (step S20).

  In the present embodiment, basic sentences as guidance sentences are stored, for example, in phrase units, and a guidance sentence that can identify a person is created by combining them with personal information in various ways. Details of the creation of the guidance text will be described later. Next, the created guidance sentence is synthesized by voice and output from the speaker of the voice input / output device 5 (step S22). Then, it returns to step S10 and repeats the process mentioned above.

  On the other hand, if all the members are within the shooting frame in step S18, the distance from the central point of the plurality of designated persons to each person (face) is analyzed (step S24), and the specific person is identified according to the analysis result. It is determined whether or not a predetermined distance from the center point (step S26). If the specific person is more than a predetermined distance from the center point of the plurality of designated persons, a guidance sentence is created for the specific person according to the personal information of the person (step S28). Next, the created guidance sentence is synthesized by voice and output from the speaker of the voice input / output device 5 (step S22). Then, it returns to step S10 and repeats the process mentioned above.

  In addition, when there is no person who is more than a predetermined distance from the center point of the plurality of designated persons, the distance between the center point of the plurality of designated persons within the shooting frame and the center point of the shooting frame is analyzed ( Step S30), in accordance with the analysis result, it is determined whether or not the center point of the plurality of designated persons is more than a predetermined distance from the center point of the shooting frame (step S32). If the center points of the plurality of designated persons are separated from the center of the shooting frame by a predetermined distance or more, a guidance sentence is created for all of the plurality of designated persons according to the personal information of each person (step S34). Next, the created guidance sentence is synthesized by voice and output from the speaker of the voice input / output device 5 (step S22). Then, it returns to step S10 and repeats the process mentioned above.

  On the other hand, if the center points of the plurality of designated persons are not separated from the center point of the shooting frame by a predetermined distance or more in step S32, the facial expressions (smiles) of each person of the plurality of designated persons are analyzed (step S36). Then, according to the analysis result, it is determined whether or not all are smiling (step S38). If not all are smiling, a guidance sentence is created for a person who is not smiling according to the personal information of the person (step S40).

  Next, the favorite information of the person is analyzed (step S42), and it is determined whether the favorite information is registered in the personal information (step S44). If the favorite information is not registered in the personal information of the person, the guidance sentence created in step S40 is synthesized by voice and output from the speaker of the voice input / output device 5 (step S22). Then, it returns to step S10 and repeats the process mentioned above.

  On the other hand, if favorite information is registered in the personal information of the person, the guidance sentence created in step S40 is synthesized with the voice of the favorite character and output from the speaker of the voice input / output device 5 (step S46). ) In addition, / or the favorite music is also output from the speaker of the voice input / output device 5 (step S48).

  Then, when everyone is within the shooting frame and everyone's facial expression is smiling, the camera automatically guides the user to take a picture or is ready to take a picture (by voice or text). Shooting is performed when the button is pressed, or shooting is automatically performed several seconds after the guidance (step S50). The captured image is stored in the external storage device 6 as image data in a predetermined format (JPEG or the like).

  FIG. 6 is a flowchart for explaining the operation (guidance creation) of the digital camera according to the present embodiment. First, according to the language of the personal information of the person concerned (a person who is designated as the subject of photography but is not within the photography frame, a person who is within the photography frame but is far from the whole, or a person who is not smiling) The language of the guidance sentence is set (step S60). In other words, if “Japanese” is set for the language, set it to “Japanese” to create the guide text in Japanese, and if “English” is set for the language, create the guide text in English Set to "English" as much as possible.

  Next, the name nickname of the personal information of the person is set as the name of the guidance text (step S62). That is, for example, if the name nickname of the person is “Daddy”, the sentence of the guidance sentence to be called to the person is “Dad”, and if the name nickname of the person is “Yu”, the sentence head of the guidance sentence is “Yu”. Next, an instruction is selected according to the shooting state of the person (step S64). The shooting state is a case where it is not within the shooting frame, a case where it is within the shooting frame but is far from the whole, a case where it is away from the center of the shooting frame, or a case where it is not a smile.

  When the shooting state does not fit in the shooting frame, or within the shooting frame but is far from the whole, or away from the center of the shooting frame, the deviation direction and amount of the corresponding person , If you select “more” + “move to the right”, “a little more” + “move to the left”, “enter the shooting frame”, etc. as the directive, and the shooting state is not a smile Selects “laughing” or the like as the directive.

  Next, according to the age of the person concerned, a title and a sentence end word are selected (step S66). That is, “Chan” is selected when the corresponding person is young and a child, and “San” is selected when the corresponding person is older and an adult. Furthermore, “Please”, “Ne”, etc. are selected as the end of the guidance sentence according to the age.

  Finally, the words set and selected in each step described above are combined to create a final guide sentence (step S68). For example, if the father is not in the shooting frame, the name nickname is “Daddy”, the age is “38”, and the language is “Japanese”, so “Dad” + “San” + “Enter the shooting frame” ”+“ Please ”, and finally“ Daddy, please enter the shooting frame ”. Also, if the child's Yu is slightly off, the name nickname is “Yu”, the age is “5”, and the language is “Japanese”, so “Yu” + “Chan” + “A little more” + “ “Move to the right” + “Ne”, and finally “Yu-chan, move right a little more”.

Similarly, for example, when the mother is not smiling, the name nickname is “Mama”, the age is “35”, and the language is “Japanese”, so “Mama” + “san” + “smile” + “ "Please," and finally "Mom, please laugh". Also, if the child Ken is not smiling, the name nickname is “Ken”, the age is “10”, and the language is “Japanese”, so “Ken” + “Chan” + “Laughing” + “Ne And finally, “Ken-chan, laugh.”
Thereafter, the process returns to the main routine of FIG. 4 or FIG.

  Here, FIG. 7 is a schematic diagram showing a photographing situation with the digital camera according to the present embodiment. FIG. 7 shows a situation when taking a commemorative photo with four family members (designated persons) against the background of the landscape. A thick frame is the photographing frame 101, which is an image captured within the effective range of the image sensor. The small frames are the face detection frames 102, 102,. A tracking frame 103 including the face detection frame is set around the face detection frame 102. The user holds the camera so that the desired scenery falls within the shooting frame. In this state, the person stands in front of the camera, but naturally not all the designated persons enter the photographing frame 101. In the illustrated example, the person (child) on the right side of the front row is out of the shooting frame 101.

  In this embodiment, since a plurality of persons to be photographed are designated and registered in advance, for example, among the four persons designated as the objects to be photographed, three persons are within the photographing frame, so that an individual is specified. However, even when one person is outside the shooting frame and cannot identify an individual, it is possible to specify who is outside the shooting frame.

  In the present embodiment, the entire effective range of the image sensor is defined as the imaging frame 101. However, the entire image 100 actually captured by the image sensor is defined as the entire effective range of the image sensor, and a part of the region is included therein. You may make it set as the imaging | photography frame 101 used as the object of recording.

  In this case, a recognition process for a person not included in the shooting frame 101 may be performed using an effective imaging area outside the shooting frame 101. In this way, it is possible to provide guidance specifying a person who is not included in the shooting frame 101 without having previously designated and registered a plurality of persons to be shot.

  In this case, the position and size of the shooting frame 101 to be recorded may be changed manually or automatically within the entire effective range of the image sensor.

  In the example shown in FIG. 7, since the person (child) on the right side of the front row is out of the shooting frame 101, the individual cannot be directly identified from the face recognition, but in this case, as described above, the person is designated as the shooting target. Since the other three of the four persons are identified, the person who is out of the shooting frame 101 has the name nickname “Yu”, the age “5”, and the language “Japanese”. It turns out that it is. Also, since the positional relationship between the tracking frame 103 and the shooting frame 101 shows that it is shifted to the left side, for example, a guidance sentence such as “Yu-chan, move a little more to the right” is created and synthesized. Output from the speaker.

  Also, as shown in FIG. 7, since there is a person (Ken) in the shooting frame 101 on the right side of the person (Yu) who has deviated from the shooting frame 101, “Yu-chan, Ken-kun. Or the like may be created. Also, if you are completely out of the shooting frame, for example, “Yu, enter the shooting frame”, “Yu, do n’t enter the shooting frame”, “Yu, Create a guide sentence such as “Please stop by everyone”, and synthesize the speech and output it.

  Next, FIGS. 8A and 8B are schematic diagrams for explaining guidance when the entire designated person is displaced from the center of the shooting frame. As shown in FIG. 8A, when the center point P1 of the designated person (four people) is more than a predetermined distance from the center point P2 of the shooting frame, According to the personal information of the person, for example, “Guide, please move to the right a little” or “Everyone, please move to the right more”, etc. . Then, as shown in FIG. 8B, when all the members move to the right according to the voice guidance and the center point P1 of the designated person (four people) substantially coincides with the center point P2 of the shooting frame (not more than a predetermined distance). And) to shoot.

  Next, FIG. 9 is a schematic diagram for explaining guidance when there is a person who is not a smile among the designated persons. As shown in FIG. 9, when the child in front is not smiling, a guidance sentence such as “Ken and Yu-chan laugh more” is created for the two children, and the guidance sentence is displayed. Speech synthesis and output. And if everyone smiles, they will shoot.

  According to the above-described embodiment, it corresponds to a case where there is a person who is out of the shooting frame among persons designated as shooting targets, a case where the whole is out of the shooting frame, or a person who is not smiling. Identify a person, create a guidance sentence that can recognize the person according to the personal information of the person, and guide it by voice. Furthermore, depending on the person's age, favorite character, etc. By synthesizing the voice with the voice color or outputting the favorite music together, it is possible to clarify who the guidance is and to be surely guided to an appropriate shooting state. In particular, by outputting a favorite character, idle voice, or music together, it is possible to draw the attention of the person in question and to guide it reliably.

  Also, by providing a blink recognition function (a well-known technology) that recognizes that a person has closed his eyes, when the person to be photographed detects his closed eyes, he says, "Do not blink." Such a guidance sentence may be output by speech synthesis.

It is a block diagram which shows the structure of the digital camera by embodiment of this invention. It is a conceptual diagram which shows an example of the personal information registered in the digital camera by this embodiment. It is a schematic diagram which shows an example of the screen at the time of setting personal information with the digital camera by this embodiment, or changing a setting content. It is a flowchart for demonstrating operation | movement (photographing by voice guidance) of the digital camera by this embodiment. It is a flowchart for demonstrating operation | movement (photographing by voice guidance) of the digital camera by this embodiment. It is a flowchart for demonstrating operation | movement (guide sentence preparation) of the digital camera by this embodiment. It is a schematic diagram which shows the imaging | photography condition with a digital camera by this embodiment. It is a schematic diagram for demonstrating guidance in case the whole designated person has shifted | deviated from the center of the imaging | photography frame. It is a schematic diagram for demonstrating guidance when there is a person who is not a smile among designated persons.

Explanation of symbols

1 Input Device 2 Internal Storage Device 3 Camera Device 4 Display Device 5 Audio Input / Output Device 6 External Storage Device 7 Strobe Light Emitting Device

Claims (11)

Imaging means for imaging a subject;
Face recognition means for recognizing face portions of a plurality of persons from an image obtained by imaging by the imaging means;
State determination means for determining whether or not the face portions of a plurality of persons recognized by the face recognition means are in a predetermined state;
When it is determined by the state determination means that the state is not a predetermined state, it is specified which person's state needs to be changed and how to change the face portions of the plurality of persons to a predetermined state Specific means,
Guidance information for instructing the person specified by the specifying means to change the state as specified by the specifying means, and outputting guidance information that can specify the person and the contents of the state change Guidance information output means to
Comprising
The state determination means determines whether or not the amount of deviation between the center point of all of the plurality of persons recognized by the face recognition means and the center point of a predetermined imaging area imaged by the imaging means is within a predetermined value. And
When the state determining unit determines that the deviation amount is not within a predetermined value, the specifying unit determines that the whole of the plurality of persons recognized by the face recognizing unit is in the direction of the center point of the predetermined imaging region. An imaging device characterized by specifying which person's position needs to be changed in order to move to the next. The state determining means determines whether or not the positions of the face portions of all persons who are to be imaged are within a predetermined imaging area imaged by the imaging means,
When the state determining unit determines that the positions of the face portions of all persons to be imaged are not within a predetermined imaging area imaged by the imaging unit, the specifying unit 2. The method according to claim 1 , further comprising: identifying which person needs to change the state so as to move into the shooting area in accordance with the positional relationship of the face portions of all persons specified by the determination unit. Shooting device. The state specifying means determines whether or not the positional relationship of the face portions of a plurality of persons recognized by the face recognition means is within a predetermined distance range,
The specifying means specifies a person who is separated from the whole of the plurality of persons recognized by the face recognition means, and the person is approaching another person The imaging apparatus according to claim 1 , wherein a change is specified. Imaging means for imaging a subject;
Face recognition means for recognizing face portions of a plurality of persons from an image obtained by imaging by the imaging means;
State determination means for determining whether or not the face portions of a plurality of persons recognized by the face recognition means are in a predetermined state;
When it is determined by the state determination means that the state is not a predetermined state, it is specified which person's state needs to be changed and how to change the face portions of the plurality of persons to a predetermined state Specific means,
Guidance information for instructing the person specified by the specifying means to change the state as specified by the specifying means, and outputting guidance information that can specify the person and the contents of the state change Guidance information output means,
Personal information storage means for previously storing the face recognition data characterizing each person's face portion in association with each person and personal information of each person in association with each other;
Person identifying means for identifying a person corresponding to the face portion recognized by the face recognizing means based on face recognition data stored in the personal information storage means;
Personal information reading means for reading out personal information of the person specified by the person specifying means from the personal information storage means;
The guidance information output means includes
Based on the personal information read by the personal information reading means, a guidance sentence that instructs the person to change the state as specified by the specifying means, the person and the state change A guide sentence creating means for creating a guide sentence capable of specifying the contents of
An imaging device comprising: guidance voice output means for synthesizing and outputting a guidance voice based on the guidance sentence created by the guidance sentence creation means. The personal information includes a name of a person,
The photographing apparatus according to claim 4, wherein the guide sentence creating unit creates the guide sentence including the name of the person. A basic guidance sentence storage means for storing a plurality of basic guidance sentences corresponding to each of the plurality of state changes that can be identified by the identification means;
The guidance sentence creating means includes:
Basic guidance sentence selecting means for selecting at least one basic guidance sentence corresponding to the state change specified by the specifying means from a plurality of guidance sentences stored in the basic guidance sentence storage means;
A guidance sentence synthesizing unit that creates the guidance sentence by synthesizing at least one basic guidance sentence selected by the basic guidance sentence selecting unit and the personal information read by the personal information reading unit; The photographing apparatus according to claim 4 or 5 , wherein Further comprising designation means for designating at least one person to be identified by the person identification means;
The personal information storage means stores a designation flag indicating whether or not designation is made by the designation means in association with personal information of a person;
The person specifying means stores at least one person with the designation flag being effectively set from the persons corresponding to the face portion recognized by the face recognition means in the personal information storage means. Based on the face recognition data
The photographing apparatus according to claim 4, wherein In the computer of the shooting device,
Imaging processing for imaging a subject;
Face recognition processing for recognizing the face portions of a plurality of persons from the image obtained by imaging,
A state determination process for determining whether or not the face portions of the plurality of recognized persons are in a predetermined state;
A specific process for specifying which person's state needs to be changed and how to change the face portions of the plurality of persons into a predetermined state when it is determined that the predetermined state is not;
An output process for outputting guidance information for instructing the specified person to change the state as specified, and capable of specifying the person and the contents of the state change;
And execute
In the state determination process, whether or not a deviation amount between a center point of all of the plurality of persons recognized by the face recognition process and a center point of a predetermined imaging area captured by the imaging process is within a predetermined value. And
In the specifying process, when it is determined by the state determination process that the deviation amount is not within a predetermined value, the whole of the plurality of persons recognized by the face recognition process is in the direction of the center point of the predetermined imaging region. A shooting guide method characterized by specifying which person's position needs to be changed in order to move to the next. A program for controlling the operation of an imaging device including an imaging unit for imaging a subject,
On the computer,
An imaging function for imaging a subject by the imaging unit;
A face recognition function for recognizing face portions of a plurality of persons from an image obtained by imaging by the imaging unit;
A state determination function for determining whether or not the face portions of a plurality of persons recognized by the face recognition function are in a predetermined state;
If it is determined by the state determination function that the state is not a predetermined state, it is determined which person's state needs to be changed and how to change the face portions of the plurality of persons to a predetermined state Specific functions,
Guidance information for instructing the person specified by the specifying function to change the state as specified by the specifying means, and outputting guidance information that can specify the person and the contents of the state change Guidance information output function,
Realized,
The state determination function determines whether or not a deviation amount between a center point of all of a plurality of persons recognized by the face recognition function and a center point of a predetermined imaging region imaged by the imaging function is within a predetermined value. And
In the specific function, when the state determination function determines that the amount of deviation is not within a predetermined value, the whole of the plurality of persons recognized by the face recognition function is in the direction of the center point of the predetermined imaging region. A program characterized by specifying which person's position needs to be changed in order to move to the next.   In the computer of the shooting device,
  Imaging processing for imaging a subject;
  Face recognition processing for recognizing the face portions of a plurality of persons from the image obtained by imaging,
  A state determination process for determining whether or not the face portions of the plurality of recognized persons are in a predetermined state;
  A specific process for specifying which person's state needs to be changed and how to change the face portions of the plurality of persons into a predetermined state when it is determined that the predetermined state is not;
  An output process for outputting guidance information for instructing the specified person to change the state as specified, and capable of specifying the person and the contents of the state change;
  Personal information storage processing for storing in advance the face recognition data that characterizes the face portion of each person and the personal information of each person in association with each of a plurality of persons;
  A person identification process for identifying a person corresponding to the face portion recognized by the face recognition process based on the face recognition data stored by the personal information storage process;
  A personal information reading process for reading personal information of the person specified by the person specifying process from the face recognition data stored by the personal information storing process;
  And execute
  The guidance information output process includes:
  Based on the personal information read by the personal information reading process, a guidance sentence that instructs the person to change the state as specified by the specifying process, the person and the state change Guide sentence creation processing to create a guide sentence that can identify the contents of,
  And a guidance voice output process for synthesizing and outputting a guidance voice based on the guidance sentence created by the guidance sentence creation process.   A program for controlling the operation of an imaging device including an imaging unit for imaging a subject,
  On the computer,
  An imaging function for imaging a subject by the imaging unit;
  A face recognition function for recognizing face portions of a plurality of persons from an image obtained by imaging by the imaging unit;
  A state determination function for determining whether or not the face portions of a plurality of persons recognized by the face recognition function are in a predetermined state;
  If it is determined by the state determination function that the state is not a predetermined state, it is determined which person's state needs to be changed and how to change the face portions of the plurality of persons to a predetermined state Specific functions,
  Guidance information for instructing the person specified by the specifying function to change the state as specified by the specifying means, and outputting guidance information that can specify the person and the contents of the state change Guidance information output function,
  A personal information storage function that stores in advance the face recognition data that characterizes the face portion of each person and the personal information of each person in association with each of a plurality of persons;
  A person specifying function for specifying a person corresponding to the face portion recognized by the face recognition function based on the face recognition data stored by the personal information storage function;
  A personal information reading function for reading the personal information of the person specified by the person specifying function from the face recognition data stored by the personal information storage function;
  Realized,
  The guidance information output function is:
  Based on the personal information read by the personal information reading function, a guidance sentence for instructing the person to change the state as specified by the specific function, the person and the state change Guide text creation function to create a guide text that can identify the contents of,
  A program comprising: a guidance voice output function for synthesizing and outputting a guidance voice based on the guidance sentence created by the guidance sentence creation function.

Images