JP2015082728A - Imaging device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To photograph a subject in a situation of a much better condition.SOLUTION: A sound data 282 corresponding to characteristic 281 of a subject corresponding to the highest value among evaluated values 283 stored in the column of this time evaluation is read out and outputted in voice. For example, if the subject is a female, by outputting the voice in which points as characteristic of the subject are praised, attraction can be further drawn out from the subject since the subject hearing this voice is relaxed. When any change does not occur in a smiling face or the like of the subject even after passage of a predetermined time interval, the other praising voice is outputted furthermore.

Description

  The present invention relates to an imaging apparatus.

  2. Description of the Related Art There is known an imaging apparatus that performs gender determination and age estimation from the face of a captured image, corrects the estimated age to be young if it is a woman, and notifies the estimated age by voice. (Patent Document 1)

JP 2009-89083 A

  However, although the estimated age was corrected to a younger age, it was not possible to shoot with the charm as a subject.

  The imaging apparatus according to claim 1, an imaging unit that captures a subject, a recognition unit that recognizes a feature of the subject, a voice data storage unit that stores voice data of a compliment corresponding to the feature of the subject, Voice data corresponding to the feature of the subject recognized by the recognition means is read out from the voice data storage means and output as voice. After the voice data is output by the voice output means, the subject is photographed by the imaging means and the image is taken. And a recording means for recording data.

  According to the present invention, by recognizing the characteristics of a subject and outputting an optimal compliment, it is possible to capture the attractiveness of the subject.

It is a block diagram which shows the structure of the imaging device in embodiment. It is a figure which shows the memory | storage state of the memory | storage part in embodiment. 6 is a flowchart illustrating an operation of the imaging apparatus according to the embodiment.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram illustrating a configuration of an imaging apparatus 20 according to an embodiment.
The imaging device 20 includes an imaging optical system 21, an imaging element 22, a lens driving circuit 23, a control unit 24, a display unit 25, an operation unit 26, a removable recording medium 27, a storage unit 28, And an audio output unit 29.

  The imaging optical system 21 includes a plurality of lens groups including a zoom lens and a focusing lens, and forms a subject image on the light receiving surface of the imaging element 22. In order to simplify FIG. 1, the imaging optical system 21 is illustrated as a single lens.

  Under the control of the control unit 24, the lens driving circuit 23 drives the zoom lens of the imaging optical system 21 to adjust the focal length, and drives the focusing lens of the imaging optical system 21 to perform focus adjustment. As the focus adjustment, AF (automatic focus adjustment) for automatically focusing on the subject is provided.

  The image pickup device 22 is configured by, for example, a CCD image sensor or a CMOS image sensor, picks up a subject image formed by the image pickup optical system 21, and outputs the obtained image signal to the control unit 24.

  The control unit 24 includes a CPU and other peripheral circuits, and controls the entire imaging device 20. The control unit 24 generates image data from the image signal acquired from the image sensor 22. Image data acquired based on the image signal from the image sensor 22 is temporarily stored in the storage unit 28 and then recorded on the recording medium 27.

  The display unit 25 includes a liquid crystal monitor (rear monitor) mounted on the rear surface of the imaging device 20, and displays an image captured by the image sensor 22, various setting menus, and the like.

  The operation unit 26 includes various input members operated by the photographer, such as a power switch and a release button. When each button is pressed, the operation unit 26 outputs an operation signal corresponding to each operation to the control unit 24.

  When the release button is pressed halfway, the AF is automatically focused, and the control unit 24 generates frame image data from the image signal acquired in time series from the image sensor 22 and outputs the frame image data to the display unit 25. As a result, a through image is displayed on the display unit 25. When the release button is fully pressed, the control unit 24 performs predetermined image processing on the image signal acquired from the image sensor 22 to generate still image data, and performs compression processing using a predetermined method such as JPEG. Are recorded on the recording medium 27.

  The storage unit 28 is configured by a static memory or the like, and stores a program shown in a flowchart to be described later, and also stores voice data of a compliment corresponding to the characteristics of the subject, as will be described in detail later.

  The audio output unit 29 is configured by a speaker or the like, and outputs audio that compliments the characteristics of the subject according to the audio data stored corresponding to the characteristics of the subject.

  FIG. 2 is a diagram illustrating a storage state of the storage unit 28 in the present embodiment. The storage unit 28 stores subject characteristics 281, audio data 282, and evaluation values 283 in association with each other.

  The features 281 of the subject are smile degree, round face degree, etc. for the entire face, eyes, mouth, etc. for the face parts, color etc. for the skin, style etc. for the whole body, dogs for pets, They are cats and memorize their characteristics. The audio data 282 is audio data stored corresponding to the subject feature 281 and giving up the subject feature. The evaluation value 283 stores any numerical value of 0 to 5 evaluated in six stages according to the degree of the feature 281 in association with the feature 281. For example, if the smile level is very good, 5 is set. Then, there are two evaluation values 283 of the previous and current evaluation values 283 depending on the evaluation time.

  Hereinafter, the operation of the imaging apparatus 20 in the present embodiment will be described with reference to the flowchart of FIG. The flowchart of FIG. 3 shows processing of a program that is started by the control unit 24 when the power switch of the imaging device 20 is turned on.

  In step S <b> 301, the control unit 24 generates frame image data from the image signal acquired in time series from the image sensor 22, outputs the frame image data to the display unit 25, and displays a through image on the display unit 25.

  In step S302, the control unit 24 determines whether or not the release button is half-pressed. If not, the control unit 24 returns to step S301. If the release button has been pressed halfway, the process proceeds to step S303.

  In step S303, the control unit 24 performs automatic exposure calculation and automatic focus adjustment. In the automatic focus adjustment, for example, focus adjustment is performed by continuous AF. Continuous AF keeps focusing on a moving subject continuously and continuously.

  In step S304, the control unit 24 captures the subject image formed by the imaging optical system 21, and determines the sex of the subject from the obtained image signal. For example, if a subject includes a plurality of persons, each gender is determined.

  In step S305, the control unit 24 determines whether the subject includes a woman. If the woman is included, the process proceeds to step S306. The female determination of the subject is based on known image processing.

  In step S306, the control unit 24 recognizes the characteristics of the entire face, for example, the smile degree, the round face degree, and the like. For example, it recognizes whether the smile level is very good or the round face level is conspicuous. The degree of smile level is determined by comparing with a plurality of predefined smile images. Whether or not the round face degree is conspicuous is determined by comparing with a plurality of round face images defined in advance.

  In step S307, the control unit 24 stores the evaluation of the feature 281 of the subject in the current column of the storage unit 28 as the evaluation value 283 according to the recognition in step S306. The evaluation value 283 stores a numerical value of 0 to 5 in a stepwise manner in accordance with the recognized feature. For example, 5 is stored if the smile level is extremely good, and 2 is stored if the round face level is small.

  In step S308, the control unit 24 recognizes the characteristics of the facial parts, such as eyes and mouth. For example, it recognizes whether the eyes are large or the lips are in order. A plurality of images are defined in advance for each part of the face, and by comparing with each part, it is recognized whether the eyes are large or the lips are prepared.

  In step S309, the control unit 24 stores the evaluation of the subject feature 281 in the current column of the storage unit 28 as the evaluation value 283 in accordance with the recognition in step S308. The evaluation value 283 stores a numerical value of 0 to 5 in a stepwise manner in accordance with the recognized feature. For example, if the eyes are large and the lips are in order, 5 is stored.

  In step S310, the control unit 24 recognizes skin characteristics, for example, skin color. For example, it recognizes whether the skin color is white. A plurality of images such as skin color are defined in advance, and the skin color or the like is recognized by comparing with the defined image.

  In step S311, the control unit 24 stores the evaluation of the feature 281 of the subject in the current column of the storage unit 28 as the evaluation value 283 according to the recognition in step S310. The evaluation value 283 stores a numerical value of 0 to 5 in a stepwise manner in accordance with the recognized feature. For example, if the skin color is a standard color, 3 is stored.

  In step S312, the control unit 24 recognizes the characteristics of the whole body style, for example, the balance of the whole body shape. For example, it recognizes whether the whole body is well balanced. A plurality of images of the body type of the whole body are defined in advance, and the body type and the like are recognized by comparing with the defined image.

  In step S313, the control unit 24 stores the evaluation of the subject feature 281 in the current column of the storage unit 28 as the evaluation value 283 in accordance with the recognition in step S312. The evaluation value 283 stores a numerical value of 0 to 5 in a stepwise manner in accordance with the recognized feature. For example, if the balance of the whole body is relatively good, 4 is stored.

  After the process in step S313, or in the process in step S305, if the subject does not contain a woman, the process proceeds to step S314.

  In step S314, the control unit 24 determines whether the subject includes a pet together with the person. If the pet is included, the process proceeds to step S315. A plurality of images of pets are defined in advance, and the pets are recognized by comparing the images with the defined images.

  In step S315, the control unit 24 recognizes the pet type. For example, it recognizes whether a subject photographed with a person is a dog, a cat, or another animal, and recognizes its size and the like. A plurality of pet images are defined in advance according to their types, and the types and sizes of the pets are recognized by comparison with the defined images.

  In step S316, the control unit 24 stores the evaluation of the pet characteristic 281 in the current column of the storage unit 28 as the evaluation value 283 in accordance with the recognition in step S315. The evaluation value 283 stores any numerical value of 0 to 5 in a stepwise manner in accordance with the recognized pet characteristics. For example, if the cat is a normal size, 3 is stored.

  After the process of step S316, or in the process of step S314, if the subject does not include a pet, the process proceeds to step S317.

  In step S317, the control unit 24 determines whether or not an evaluation value is stored in the previous column of the evaluation value 283 in the storage unit 28. The evaluation value 283 in the storage unit 28 is deleted when the photographing is completed, and the evaluation value in the current column is moved to the previous column when the subject changes as will be described later. Therefore, in the first state, the evaluation value in the previous column is blank, and the process proceeds to step S318.

  In step S318, the control unit 24 determines whether or not an evaluation value is stored in the current column of the evaluation value 283 in the storage unit 28. If the subject does not include a woman in the process of step S305 and the subject does not include a pet in the process of step S314, the evaluation value is not stored in this column. If an evaluation value is stored in the current column, the process proceeds to step S319.

  In step S319, the control unit 24 obtains the subject feature 281 corresponding to the highest value among the evaluation values 283 stored in the current column, and the audio data 282 corresponding to the feature 281 from the storage unit 28. The data is read out and output from the audio output unit 29 as audio. For example, if the subject is a woman, by outputting a voice that praises the part that is characteristic of the subject, the subject who heard the voice can relax and further draw out the charm from the subject. Thereafter, the process proceeds to step S320. In step S319, when there are a plurality of the highest evaluation values 283 stored in the current column, any one of them is selected at random, and the voice corresponding to the selected evaluation value 283 is selected. Data 282 is read from the storage unit 28 and output from the audio output unit 29 by voice.

  When the evaluation value is stored in the previous column of the evaluation value 283 in the storage unit 28 in step S317, the subject has changed and the feature of the subject has been newly recognized, and as a result, the feature of the subject that has been recognized last time is determined. Is a case where the previous evaluation value is stored in the previous column. In this case, the process proceeds to step S321.

  In step S321, the control unit 24 determines whether or not an evaluation value is stored in the current column. If the subject does not include a woman in the process of step S305 and the subject does not include a pet in the process of step S314, the evaluation value is not stored in this column. If no evaluation value is stored in the current column, the process proceeds to step S320. If an evaluation value is stored in the current column, the process proceeds to step S322.

  In step S322, the control unit 24 determines whether or not the current evaluation value is higher than the previous time. The case where the current evaluation value is higher than the previous time is the case where the evaluation value for the feature of the subject has increased as a result of outputting the sound of giving up the subject in step S319 last time. For example, this applies to a case where the subject who heard the voice to give up relaxed and smiled.

  If it is determined in step S322 that the current evaluation value is higher than the previous time, the process proceeds to step S323, and the control unit 24 performs predetermined image processing on the image signal acquired from the image sensor 22. To generate still image data and shoot. In other words, when the degree of the feature of the subject is improved and the evaluation value for the feature of the subject is higher than the previous time, the photographing is automatically performed.

  In step S322, if the current evaluation value is not higher than the previous time, the process proceeds to step S320. In step S318, if the evaluation value is not stored in the current column, the process proceeds to step S320.

  In step S320, the control unit 24 determines whether the release button has been fully pressed. If the release button is fully pressed by the user, the process proceeds to step S323 to perform shooting. For example, in step S319, when a sound that gives up the location that is characteristic of the subject is output, the user who has determined that the attractiveness of the subject has been pulled out operates the release button fully to perform shooting. If the release button has not been fully pressed in step S320, the process proceeds to step S324.

  In step S324, the control unit 24 generates frame image data from the image signal acquired in time series from the image sensor 22, and determines whether the subject has changed based on the frame image data. For example, this is the case when the subject smiles. If the subject has changed, the process proceeds to step S325, and the values in the current column of the evaluation value 283 are moved to the previous column for all items of the subject characteristics in the storage unit 28. Thereafter, the process proceeds to step S303 and subsequent steps, and the above-described recognition of the characteristics of the subject is newly repeated, and a new value is stored in the current column of the evaluation value 283. If the subject has not changed in step S324, the process proceeds to step S326.

  In step S326, the control unit 24 determines whether a predetermined time has elapsed in step S320, step S324, and step S326. If the predetermined time has elapsed, the release button has not been fully pressed and the subject has not changed to a smile or the like, and the process proceeds to step S327.

  In step S327, the control unit 24 reads out the audio data 282 corresponding to the subject feature 281 corresponding to the next highest value from the evaluation values 283 stored in the current column from the storage unit 28, and outputs the audio output unit 29. Output more voice. That is, if there is no change in the smile of the subject even after a predetermined time has elapsed, another voice giving up is further output. If there are a plurality of next highest values among the evaluation values 283 stored in the current column in step S327, one of them is selected at random, and the voice corresponding to the selected evaluation value 283 is selected. Data 282 is read from the storage unit 28 and output from the audio output unit 29 by voice. This increases the possibility that the subject who has heard the voice to give up will relax and smile. Thereafter, the process proceeds to step S320.

  After shooting is performed in step S323, the control unit 24 records the generated still image data on the recording medium 27 in step S328. In step S329, the control unit 24 deletes all the evaluation values 283 in the storage unit 28 and ends the process of the flowchart shown in FIG. If the power switch is in the on state, the processes after step S301 are continued and executed again.

(Modification)
The present invention can be implemented by modifying the embodiment described above as follows.
(1) When a subject includes a woman or a pet, the feature of the subject is recognized and voice data corresponding to the recognized feature of the subject is output as a voice. Even a male or the like may recognize each feature and output sound data corresponding to the feature of the subject.

(2) When a subject includes a woman or a pet, the feature of the subject is recognized, and voice data corresponding to the recognized feature of the subject is output as voice. If included, the audio data corresponding to the pet may be preferentially output. For example, when a person holding a pet is used as a subject, a voice for giving up the pet is first output.

(3) In the case where the subject has not changed and a predetermined time has elapsed, the example of outputting the sound relating to the feature of the subject having the next highest evaluation value has been described. However, the sound having the highest evaluation value may be output again.

(4) The audio data corresponding to the characteristics of the subject has been described as an example in advance. However, the user may be able to appropriately set arbitrary audio data in association with the characteristics of the subject. The user can output his / her favorite audio data.

(5) In the example described above, the voice data corresponding to the characteristics of the subject is stored and the voice data is directly output as voice. However, the text is stored as voice data, converted into voice by a voice synthesizer, and output. Also good.

(6) The voice data corresponding to the recognized feature of the subject is output as voice. However, in addition to the voice output, text data corresponding to the feature of the subject may be output to the display unit 25. The photographer can utter compliments based on the text data displayed on the display unit 25.

According to the imaging device and the modification in the embodiment described above, the following operational effects can be obtained.
(1) An image sensor 22 that captures a subject, a control unit 24 that recognizes the characteristics of the subject, a storage unit 28 that stores voice data of a compliment corresponding to the characteristics of the subject, and the control unit 24. A voice output unit 29 that reads out voice data corresponding to the characteristics of the subject from the storage unit 28 and outputs the voice, and after the voice data is output by the voice output unit 29, the subject is photographed by the imaging device 22 and the image data is recorded. Since the control unit 24 for recording on the medium 27 is provided, the subject can be photographed in a better condition by recognizing the feature of the subject and outputting the optimum compliment.

  The present invention is not limited to the above-described embodiment, and other forms conceivable within the scope of the technical idea of the present invention are also included in the scope of the present invention as long as the characteristics of the present invention are not impaired. It is. Moreover, it is good also as a structure which combined the above-mentioned embodiment and a some modification.

  DESCRIPTION OF SYMBOLS 20 ... Imaging device, 22 ... Image sensor, 24 ... Control part, 28 ... Memory | storage part, 29 ... Audio | voice output part

Claims (7)

Imaging means for photographing a subject;
Recognition means for recognizing the characteristics of the subject;
Voice data storage means storing voice data of compliments corresponding to the characteristics of the subject;
Voice output means for reading out voice data corresponding to the characteristics of the subject recognized by the recognition means from the voice data storage means and outputting the voice;
An imaging apparatus comprising: recording means for capturing the subject with the imaging means and recording the image data after the audio data is output by the audio output means. The imaging device according to claim 1,
Evaluation value storage means for storing evaluation values according to the degree of each of the plurality of features of the subject,
The recognizing means determines the degree of each feature of the subject, and stores each evaluation value corresponding to the degree of each feature in the evaluation value storage means. The imaging device according to claim 2,
The image pickup apparatus, wherein the sound output means outputs sound data corresponding to a feature of a subject having a high evaluation value among evaluation values in the evaluation value storage means. The imaging device according to any one of claims 1 to 3,
The imaging apparatus according to claim 1, wherein when the subject changes after the audio data is output, the recognition unit recognizes the feature of the subject again. The imaging apparatus according to claim 4,
An image pickup apparatus according to claim 1, wherein if the degree of the feature of the subject by the recognizing means recognized again is improved, the recording means photographs the subject by the imaging means and records image data. In the imaging device according to any one of claims 1 to 5,
The recognition apparatus outputs the audio data again when a predetermined time elapses without changing the subject after the audio data is output. In the imaging device according to any one of claims 1 to 6,
The recognition means recognizes the type of pet in the subject,
The imaging apparatus according to claim 1, wherein the voice output means outputs voice data of a compliment according to the recognized pet type.

Images