JP4197419B2 - camera - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a camera for photographing a subject.
[0002]
[Prior art]
Conventionally, an input voice is recognized and converted into character data, the converted character string is combined with a photographed image, and a comment on the image is displayed, so that a desired image can be selected from many images. A camera that can be easily found has been proposed (see, for example, Patent Document 1).
[0003]
In addition, a camera that changes the pan / tilt angle etc. by an amount corresponding to the input sound volume (analog amount) has been proposed. Further, as a modified example of this camera, default utterances of a plurality of users are registered. A technique for performing speech recognition by comparing a registered default utterance with the utterances of each of a plurality of users has been proposed (see, for example, Patent Document 2).
[0004]
[Patent Document 1]
Japanese Patent Laid-Open No. 9-252453 (paragraph number 0017, FIG. 1)
[Patent Document 2]
JP 2000-284794 (paragraph number 0013-paragraph number 0023, FIG. 1, and paragraph number 0034-paragraph number 0037)
[0005]
[Problems to be solved by the invention]
In a camera that recognizes input voice and performs various controls, if voice recognition is performed using a voice dictionary appropriate for the voice of a user who uses the camera, voice recognition can be performed with high accuracy. However, Patent Document 1 does not propose such a technique. Also, Patent Document 2 proposes a technique for performing speech recognition by comparing a pre-registered default utterance with the utterances of each of a plurality of users. No technology has been proposed for identifying a user (speaker) to be used and selecting an appropriate speech dictionary for the voice of the speaker.
[0006]
In view of the above circumstances, an object of the present invention is to provide a camera that can select a speech dictionary appropriate for a speaker's voice with a simple operation.
[0007]
[Means for Solving the Problems]
The camera of the present invention that achieves the above object is a camera for photographing a subject.
A microphone that picks up the sound,
It is determined whether or not a predetermined word has been input, and when it is determined that the predetermined word has been input , the voice characteristics of the speaker based on the respective voices of the plurality of speakers input from the microphone A speech dictionary creating unit that creates a speech dictionary for each of the plurality of speakers and associates each speech dictionary with each symbol image for recognizing each speaker;
An image display unit for displaying an image;
A speech dictionary selection unit that displays the symbol image list on the image display unit and selects a speech dictionary corresponding to the selected symbol image by operating any symbol image in the symbol image list by operation; ,
And a voice control unit that performs control in accordance with the voice recognized by recognizing the voice input from the microphone using the voice dictionary selected by the voice dictionary selection unit.
[0008]
The camera of the present invention extracts voice features of each of a plurality of speakers to create a speech dictionary for each of the plurality of speakers, and each created speech dictionary and each symbol for recognizing each speaker Correspondence with images is performed, and for voice control, a symbol image corresponding to the voice of a speaker who is a camera user is selected from the symbol image list. Therefore, it is possible to easily select a speech dictionary appropriate for the speaker's voice.
[0009]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described.
[0010]
FIG. 1 is an external view of a camera according to an embodiment of the present invention. 1A is a front view, FIG. 1B is a top view, FIG. 1C is a side view, and FIG.
[0011]
A camera 100 shown in FIGS. 1A to 1D is a digital camera that performs photographing by forming an image of a subject on an image sensor and taking in an image signal representing the subject. The camera 100 is a digital camera that recognizes input voice and performs various operations.
[0012]
As shown in FIG. 1A, a photographing zoom lens 101 and a microphone 151 for picking up sound are provided in front of the camera 100 of the present embodiment. As will be described in detail later, the camera 100 recognizes the voice input from the microphone 151 and, for example, zooms up (moves to the telephoto side) or zooms down (wide) according to the recognized voice. Voice control such as movement to the side). In addition, a flash light emitting device 105 having a flash light emitting tube 105a that emits flash light is disposed on the upper portion of the camera 100.
[0013]
Further, as shown in FIG. 1D, an operation unit 120 for performing various operations when the user uses the camera 100 is provided on the back surface of the camera 100.
[0014]
The operation unit 120 includes a power switch 121 for turning on the power for operating the camera 100, a shooting / playback switching lever 122 for freely switching between shooting and playback, and a shooting mode for selecting auto shooting, manual shooting, and the like. Dial 123, cross switch 124 for setting, selecting or zooming various menus, flashing switch 125, execution switch 126a for executing the menu selected by cross switch 124, for canceling The cancel switch 126b is provided.
[0015]
An image display LCD 102 (corresponding to an example of an image display unit according to the present invention) for displaying a photographed image, a reproduced image, and the like on the back of the camera 100, an operation display LCD 103 for assisting operation, A speaker 152 is provided.
[0016]
Further, as shown in FIG. 1B, a release button 104 is provided on the upper surface of the camera 100. With this release button 104, an instruction to start shooting is transmitted to a main CPU, which will be described later, provided in the camera 100. In this camera 100, shooting / playback switching lever 122 can freely switch between shooting and playback. When shooting, the user switches shooting / playback switching lever 122 to shooting side 122a, and when playback, shooting / playback is performed. The reproduction switching lever 122 is switched to the reproduction side 122b.
[0017]
Furthermore, as shown in FIG. 1C, a video output terminal 106 to which a cable for outputting an image signal of a subject photographed by the camera 100 to a television or a projector is connected to the side surface of the camera 100. A cable for outputting an image signal of a subject photographed by the camera 100 to a personal computer or the like provided with a Universal Serial Bus (USB) terminal, and inputting an image signal from the personal computer or the like to the camera 100 Are connected to a USB terminal 107, and a DC voltage input terminal 108 to which a DC voltage from an AC adapter is input.
[0018]
FIG. 2 is a block diagram showing a circuit configuration of the camera shown in FIG.
[0019]
The camera 100 includes a photographing zoom lens 101, a diaphragm 131, and a CCD sensor which is an image sensor that converts an object image formed through the photographing zoom lens 101 and the diaphragm 131 into an analog image signal. 132. The CCD sensor 132 generates an image signal by accumulating charges generated by subject light irradiated on the CCD sensor 132 for a variable charge accumulation time.
[0020]
The camera 100 also adjusts the white balance of the subject image represented by the analog image signal from the CCD sensor 132 and adjusts the slope (γ) of the straight line in the gradation characteristics of the subject image. Is provided.
[0021]
The camera 100 further includes an A / D unit 134 for A / D converting an analog signal from the white balance / γ processing unit 133 into digital image data, and a buffer for storing the image data from the A / D unit 134. A memory 135 is provided.
[0022]
Further, the camera 100 includes a CG (clock generator) unit 136, a photometry / ranging CPU 137, a charge / light emission control unit 138, a YC processing unit 140, and a power source 141.
[0023]
The CG unit 136 outputs a drive signal for driving the CCD sensor 132 and a control signal for controlling the white balance / γ processing unit 133 and the A / D unit 134. Further, a control signal from the photometry / ranging CPU 137 is input to the CG unit 136.
[0024]
The photometry / ranging CPU 137 performs photometry and distance measurement by driving the photographing zoom lens 101 and the diaphragm 131 by means not shown, and controls the CG unit 136 and the charge / light emission control unit 138. Further, the photometry / ranging CPU 137 performs data communication with a main CPU 145 described later.
[0025]
The charging / light emission control unit 138 is supplied with electric power from the power source 141 to emit light from the flash light emission tube 105a, charges a flash light emission capacitor (not shown), and controls light emission from the flash light emission tube 105a.
[0026]
The YC processing unit 140 reads the image data stored in the buffer memory 135 via the bus line 142, and generates a color video signal YC separated into a luminance signal (Y) and a color signal (C). The generated color video signal YC is output from the video output terminal 106 (see FIG. 1C).
[0027]
A power supply 141 supplies power to each part of the camera 100.
[0028]
Further, the camera 100 includes a compression / decompression & ID extraction unit 143 and an I / F unit 144. The compression / decompression & ID extraction unit 143 reads and compresses the image data stored in the buffer memory 135 via the bus line 142 and stores the image data in the memory card 200 via the I / F unit 144. In addition, the compression / decompression & ID extraction unit 143 extracts an identification number (ID) unique to the memory card 200 and reads the image data stored in the memory card 200 when reading the image data stored in the memory card 200. Are decompressed and stored in the buffer memory 135.
[0029]
The camera 100 also includes a main CPU 145, an EEPROM 146, a YC / RGB conversion unit 147, and a display driver 148.
[0030]
The main CPU 145 controls the entire camera 100.
[0031]
The EEPROM 146 stores solid data unique to the camera 100 and the like.
[0032]
The YC / RGB conversion unit 147 converts the color video signal YC generated by the YC processing unit 140 into RGB signals of three colors, and outputs them to the image display LCD 102 via the display driver 148.
[0033]
The camera 100 further includes the microphone 152, the filter 153, the A / D unit 154, the speech dictionary creation unit 155, the speech dictionary memory 156, the speech dictionary selection unit 157, and the speech control unit 158 described above. Is provided.
[0034]
Voices from a plurality of users (speakers) are input to the microphone 152. The voices of the plurality of speakers input from the microphone 152 are converted into analog electrical signals and output to the filter 153.
[0035]
The filter 153 removes frequency components other than the necessary band from the analog electrical signal from the microphone 152 and outputs the result to the A / D unit 154.
[0036]
The A / D unit 154 converts the analog electrical signal from the filter 153 into a digital signal.
[0037]
Based on the digital signal from the A / D unit 154, the voice dictionary creation unit 155 extracts the voice features of a plurality of speakers and creates a voice dictionary for each of the plurality of speakers. Each symbol image for recognizing the speaker is associated with each other and stored in the memory card 200. Details will be described later.
[0038]
The voice dictionary selection unit 157 displays a list of symbol images on the image display LCD 102, and is selected by selecting any symbol image in the symbol image list by operating the cross switch 124 of the operation unit 120. A speech dictionary corresponding to the symbol image is selected. The selected speech dictionary is stored in the speech dictionary memory 156.
[0039]
The voice control unit 158 recognizes the voice input from the microphone 151 using the voice dictionary selected by the voice dictionary selection unit 157 and stored in the voice dictionary memory 156, and performs control according to the recognized voice. Here, an example of voice control will be described.
[0040]
In the present embodiment, a voice print by inputting a basic word of a speaker is stored in the voice dictionary memory 156. Here, the basic words may be the same as the words used when the camera 100 is photographed, or may be unrelated words (for example, “Aiueo”). Examples of the relationship between the words used when shooting with the camera 100 and the operation of the camera 100 include the following.
[0041]
When “shooting” is pronounced, the camera 100 performs a shutter release operation. Also, when the word “zoom up” is pronounced, the photographing zoom lens 101 is moved to the tele side, and when the word “zoom down” is pronounced, the photographing zoom lens 101 is moved to the wide side. Further, when “menu open” is pronounced, a setting screen is displayed on the image display LCD 102. In this state, when the word “up” is pronounced, the menu selection item is raised (carrying up), and when the word “down” is pronounced, the menu selection item is lowered (carrying down). If the user pronounces “set”, the menu selection item is confirmed. If the user pronounces “cancel”, the menu selection item is canceled. Further, when the word “play” is pronounced, the photographed image is reproduced. When the word “feed” is pronounced, the frame of the reproduced image is forwarded. When the word “back” is pronounced, one frame of the reproduced image is returned.
[0042]
FIG. 3 is a diagram showing an image file and an audio dictionary recorded on the memory card.
[0043]
As described above, the voice dictionary creation unit 155 extracts voice characteristics of a plurality of speakers to create a voice dictionary for each of the plurality of speakers, and for each voice dictionary to recognize each speaker. Corresponding to each symbol image. Each of these correlated voice dictionaries and each symbol image is stored in the memory card 200 as shown in FIG. Here, a pair of an image file 1 as a symbol image and a speech dictionary 1 associated with the image file 1, a pair of an image file 2 as a symbol image and the speech dictionary 2 associated with the image file 2. Etc. are memorized.
[0044]
The camera 100 according to the present embodiment extracts voice characteristics of a plurality of speakers to create a voice dictionary for each of the plurality of speakers, and recognizes each created voice dictionary and each speaker. Each symbol image is associated with each other, and when the camera 100 is used, a symbol image corresponding to the user who uses the camera 100 is selected by operation from the symbol image list, and the user (speaker) is selected. The voice dictionary corresponding to is selected and voice recognition is performed. Details will be described below.
[0045]
FIG. 4 is a diagram showing a list of symbol images made up of the image files shown in FIG.
[0046]
The symbol image list 160 includes family symbol images, and is displayed on the image display LCD 102. Specifically, the symbol image 161 of “father” (corresponding to the image file 1), the symbol image 162 of “son” (corresponding to the image file 2), the symbol image 163 of “mother”, and the “daughter” ”Symbol image 164 is displayed. When such a family operates the camera 100 by voice, it is necessary to first create a voice dictionary.
[0047]
FIG. 5 is a flowchart of an audio dictionary creation routine of the camera of this embodiment.
[0048]
Here, the case of creating a speech dictionary file for the symbol image 162 of “son” shown in FIG. 4 will be described, but the case of creating a speech dictionary file for the other symbol images 161, 163, and 164 is also described. It is the same.
[0049]
When the power switch 121 is pressed with the shooting / playback switching lever 122 switched to the playback side 122b to turn on the camera 100, the personal setting mode is selected with the cross switch 124, and the execution switch 126a is operated. This speech dictionary creation routine starts.
[0050]
First, in step S1, voice input is permitted and the process proceeds to step S2. In step S2, it is determined whether or not a predetermined word (here, a word uttered by “son”) has been input. If the predetermined word is not input, this step S2 is repeatedly executed until the predetermined word is input. If it is determined that a predetermined word has been input, the process proceeds to step S3.
[0051]
In step S3, the voice feature is extracted and the process proceeds to step S4. In step S4, an audio dictionary file is created.
[0052]
Next, in step S5, an image file to be associated is selected. Here, as shown in FIG. 4, a symbol image list 160 is displayed on the image display LCD 102, the symbol image 162 of “son” is selected, and the execution switch 126a is operated. Then, in step S6, the voice dictionary file is associated with the image file and recorded in the memory card 200 as a recording medium, and this routine is terminated.
[0053]
FIG. 6 is a flowchart of an audio dictionary selection routine of the camera of this embodiment.
[0054]
Here, the case where the speech dictionary for the symbol image 162 of “son” shown in FIG. 4 is selected will be described.
[0055]
When the power switch 121 is pressed with the shooting / playback switching lever 122 switched to the playback side 122b to turn on the camera 100, the personal identification mode is selected with the cross switch 124, and the execution switch 126a is operated. This speech dictionary selection routine starts.
[0056]
First, in step S21, an image is read from the recording medium (memory card 200), and the process proceeds to step S22. In step S22, image list data (symbol image list) is created. Next, in step S23, the image list is reproduced and the process proceeds to step S24.
[0057]
In step S <b> 24, it is determined whether or not the user image (here, “son” image) has been selected. If the user's image is not selected, this step S24 is repeatedly executed until the user's image is selected (specifically, the cross switch 124 is operated until the “son” image is selected). If it is determined that the user image has been selected, the process proceeds to step S25 by operating the execution switch 126a.
[0058]
In step S25, the voice dictionary associated with the image is read. Next, in step S26, it is stored in the voice dictionary storage location (voice dictionary memory 156) of the camera body, and this routine is terminated.
[0059]
FIG. 7 is a flowchart of a routine for controlling the camera by recognizing the voice using the voice dictionary stored in the voice dictionary memory of the camera of the present embodiment.
[0060]
This routine starts when the power switch 121 is pressed and the camera 100 is turned on with the photographing / reproduction switching lever 122 switched to the photographing side 122a.
[0061]
First, in step S31, it is determined whether or not the voice input mode has been selected (selected by the cross switch 124). If the voice input mode is not selected, the process proceeds to step S37 and a normal operation is performed. If it is determined that the voice input mode has been selected, the process proceeds to step S32.
[0062]
In step S32, it is determined whether there is a voice input. If it is determined that there is no voice input, step S32 is repeatedly executed until there is a voice input. If it is determined that there is a voice input, the process proceeds to step S33. In step S33, recognition is performed using a speech dictionary.
[0063]
Next, in step S34, it is determined whether or not the command is a valid command, that is, the voice such as “shooting” and “zoom-up” described above. If it is determined that the command is valid, the command is executed in step S35, and the process returns to step S31. On the other hand, if it is determined that the command is not valid, a warning is displayed on the image display LCD 102 in step S36, and the process returns to step S31.
[0064]
In the present embodiment, the speech dictionary creation unit 155 associates each speech dictionary with each symbol image and records it in the memory card 200. However, the speech dictionary creation unit referred to in the present invention What is necessary is just to associate a speech dictionary with each symbol image.
[0065]
In this embodiment, the voice control unit 158 recognizes the voice dictionary stored in the voice dictionary memory 156. However, the voice control unit according to the present invention is selected by the voice dictionary selection unit. Any device that recognizes speech using a speech dictionary may be used.
[0066]
【The invention's effect】
As described above, according to the camera of the present invention, it is possible to select a voice dictionary appropriate for the voice of the speaker with a simple operation.
[Brief description of the drawings]
FIG. 1 is an external view of a camera according to an embodiment of the present invention.
2 is a block diagram showing a circuit configuration of the camera shown in FIG. 1. FIG.
FIG. 3 is a diagram showing an image file and an audio dictionary recorded on a memory card.
4 is a diagram showing a list of symbol images made up of the image files shown in FIG. 3. FIG.
FIG. 5 is a flowchart of an audio dictionary creation routine of the camera of the present embodiment.
FIG. 6 is a flowchart of an audio dictionary selection routine of the camera of the present embodiment.
FIG. 7 is a flowchart of a routine for recognizing voice using a voice dictionary stored in a voice dictionary memory and controlling the camera of the camera according to the present embodiment.
[Explanation of symbols]
100 Camera 101 Shooting Zoom Lens 102 Image Display LCD
103 Operation display LCD
104 Release button 105 Flash light emitting device 105a Flash light emitting tube 106 Video output terminal 107 USB terminal 108 DC voltage input terminal 120 Operation unit 121 Power switch 122 Shooting / playback switch lever 123 Shooting mode dial 124 Cross switch 125 Flash light emitting switch 126a Execution switch 126b Cancel switch 131 Aperture 132 CCD sensor 133 White balance / γ processing unit 134, 154 A / D unit 135 Buffer memory 136 CG unit 137 Metering / ranging CPU
138 Charging / light emission control unit 139 Communication control unit 140 YC processing unit 141 Power supply 142 Bus line 143 Compression / decompression & ID extraction unit 144 I / F unit 145 Main CPU
146 EEPROM
147 YC / RGB conversion unit 148 Driver 151 Microphone 152 Speaker 153 Filter 155 Audio dictionary creation unit 156 Audio dictionary memory 157 Audio dictionary selection unit 158 Audio control unit 160 Symbol image list 161, 162, 163, 164 Symbol image 200 Memory card

Claims (1)

In a camera that shoots a subject,
A microphone that picks up the sound,
It is determined whether or not a predetermined word has been input, and when it is determined that a predetermined word has been input , the voice characteristics of the speaker based on the respective voices of the plurality of speakers input from the microphone A speech dictionary creation unit that creates a speech dictionary for each of the plurality of speakers and associates each speech dictionary with each symbol image for recognizing each speaker;
An image display unit for displaying an image;
A speech dictionary selection unit that displays the symbol image list on the image display unit and selects a speech dictionary corresponding to the selected symbol image by operating any symbol image in the symbol image list by operation; ,
A camera comprising: a voice control unit that recognizes voice input from the microphone using a voice dictionary selected by the voice dictionary selection unit and performs control according to the recognized voice.

Images