JP2003348411A - Camera for permitting voice input - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a camera for permitting voice input capable of composing received voice with an object image whereby a user can be sensible of a photographing state by having only to view a printed photo image. <P>SOLUTION: The camera is provided with: an imaging optical system 2 for acquiring an electronic image; a microphone 15 for picking up voice information in an imaging operation; a voice recognition circuit 16 for converting the voice information into text data; a character image output circuit 17 for converting the text data into a character image; a liquid crystal panel 7 for displaying an image resulting from composing the object electronic image with the character image; and the voice recognition circuit 16 for deducing the photographing state on the basis of the voice information, the character image output circuit 17 is characterized in to revise the character image on the basis of the photographing state. <P>COPYRIGHT: (C)2004,JPO

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a camera capable of inputting voice, and more particularly, to a camera having a microphone, which has a function of converting input voice into a character image, synthesizing the character image with a captured subject image, and displaying the image. The present invention relates to a camera capable of inputting voice.

[0002]

2. Description of the Related Art As is well known, a microphone is provided,
Various digital cameras capable of voice input have been conventionally provided. In this type of camera, when a captured subject image is reproduced by a monitor device attached to the camera, input sound is reproduced at the same time. But,
This type of camera, when printing images on paper,
Even the audio information cannot be reproduced.

Therefore, the camera disclosed in Japanese Patent Laid-Open No. 5-184544 not only reproduces the input sound at the same time as displaying the image, but also analyzes the input sound and converts the sound into "Hiragana" and "Hiragana". By converting the image into a character image such as "Katakana", "Kanji", or "Alphabet" and synthesizing it with the subject image, it is possible to print the character when printing the photographed image.

Therefore, according to this camera, the conversation content at the time of shooting is written on the printed image, so that the "atmosphere at the time of shooting" or "realism" that cannot be obtained by simply viewing a still image is printed. Can be sensed from the rendered image.

[0005]

By the way, when a person utters a voice, the inflection, the size, the volume, the speed, and the like of words usually change greatly depending on the situation. There is a difference in the inflection of the words when speaking the same words with a friend and when speaking at a ceremony such as a funeral ceremony or a public place, even if the same words are spoken.

However, in the camera capable of voice input disclosed in the above-mentioned Japanese Patent Application Laid-Open No. 5-184544, since such a method of uttering a person is not taken into account, characters printed on a printed image are not considered. However, since the information is written uniformly regardless of the situation at the time of shooting, there is a problem that it is difficult to feel the atmosphere at the time of shooting from the printed characters.

SUMMARY OF THE INVENTION The object of the present invention has been made in view of the above circumstances, and a photographic image printed by a camera capable of analyzing input speech, converting it into a character image, and synthesizing it with a subject image. It is an object of the present invention to provide a camera capable of inputting voice so that an "atmosphere at the time of shooting" or "realism" can be sensed just by looking at the camera.

[0008]

In order to achieve the above object, a camera capable of voice input according to the present invention comprises:
Imaging means for imaging a subject via a photographing optical system and acquiring an electronic image of the subject; voice input means for capturing voice information during the imaging operation by the imaging means; and text data for converting the voice information to text data Setting means; character image generating means for converting the text data into a character image; display means capable of displaying an image obtained by synthesizing the electronic image of the subject obtained by the imaging means with the character image; A photographing situation analogy means for inferring a photographing situation based on the character image generating means, based on the photographing situation analogized by the photographing situation analogy means,
The characteristic of the character image is changed, and the photographing situation analogy means judges the photographing situation based on the volume of the audio information and / or intonation, The photographing situation analogy means is further characterized in that the analogy also takes into account the frequency of the audio information, and further, the character image generating means, according to the photographing situation analogized by the photographing situation analogy means, At least one of the shape, the color, and the size of the character image is changed.

[0009]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Before describing an embodiment of the present invention, an outline of a camera capable of inputting voice according to the present invention will be described.

The camera capable of voice input according to the present invention captures an image of a subject by an image capturing means including an image sensor such as a CCD and records the captured electronic image on a recording medium such as a memory card, similarly to a conventional digital camera. Further, it is possible to read out the recorded electronic image from the recording medium and display it on a display means such as a liquid crystal display device. And it has voice input means including a microphone for capturing voice information, can obtain voice at the time of shooting together with image information, and further replaces the voice information with character image data,
An image synthesized with the electronic image of the subject image can be displayed on the liquid crystal monitor screen. The character image data has an optimal shape selected according to the volume (volume) and inflection (dynamic range) of the input voice, and the character image data can be changed according to the photographer's intention. .

An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing a configuration of an electric circuit of a camera capable of inputting audio according to an embodiment of the present invention.

A camera (hereinafter referred to as a digital camera) 1 capable of voice input according to the present invention has a built-in system controller 13 for performing overall control for realizing an operation according to a photographer's operation. The system controller 13 includes a photographing optical system 2 and a photographing processing system (CCD, A
/ D) 3, an image processing controller 4, a recording system (memory card) 5, an LCD driver 6, a control panel (LCD) 8, a finder information liquid crystal panel 9, and a finder optical system (OVF) 11. A finder observation unit 10 and an input unit 12 are connected to each other.
Further, a character image output circuit 17 is connected to the image processing controller 4.
Is connected to a speech recognition circuit 16, and a microphone (hereinafter, referred to as a microphone) 15 for converting speech into an electric signal is connected to the speech recognition circuit 16. Furthermore,
A liquid crystal panel 7 is connected to the LCD driver 6.

In the digital camera 1 configured as described above, a light beam from a subject is transmitted to the CCD of the photographing processing system 3 via the photographing optical system 2 comprising a plurality of photographing lens groups.
Is incident on. The photographing processing system 3 includes a CC (not shown).
D, an imaging circuit, an A / D converter, etc., the output from the CCD is A / D converted and output from the photographing processing system 3, and the A / D converted output is subjected to image processing by the image processing controller 4 and stored in a memory. The data is recorded by a recording system 5 including a card and the like.

The image processing controller 4 converts the electronic image signal, which has been A / D converted and output from the photographing processing system 3, into a known white balance process and color image by using an image buffer such as a RAM (not shown). Processing, gamma correction, image processing such as sharpness adjustment, and even JP
EG compression processing and decompression processing are executed, and output to the recording system 5 composed of a recording medium such as a memory card interface and a memory card body. The image processing controller 4 also performs image processing of character image data described later.

The recording system 5 is for recording electronic image signals subjected to the various processes described above by the image processing controller 4 and character image data to be described later. , A magnetic disk such as a hard disk or a floppy disk,
And the like may be used.

The image recorded on the memory card or the image processed is displayed on the liquid crystal panel 7 for reproduction via the LCD driver 6. In addition, it is possible to display an image obtained by combining character data described later. Further, the reproduction liquid crystal panel 7 is configured to display a menu screen in addition to the reproduction image, and to perform various processing operations such as image input, processing input, time setting, and the like for image reproduction, image processing, deletion, and the like. Settings can be made from the menu displayed here.

Further, the digital camera 1 has a built-in optical view finder, and
Can be observed by the finder observation unit 10.

The control panel (LCD) 8 includes:
Various kinds of photographing-related information such as a photographing mode, photographing conditions, and the number of remaining photographable images are displayed. A part of the photographing-related information can also be displayed on the liquid crystal panel 7 or the finder information liquid crystal panel 9 provided in the finder observation unit 10.

The system controller 13 sets a photographing / reproduction mode in accordance with an operation input from the input unit 12,
It controls the components 2 to 9 for setting photographing conditions, executing photographing, recording images, reproducing and displaying, and processing reproduced images.

The control includes AF (automatic focusing), shutter speed setting, continuous shooting / single shooting setting, AE (automatic exposure), metering mode, exposure correction, ISO sensitivity, white balance, strobe control, CCD control, image control In addition to processing-related control such as processing instructions, recording control, and image quality setting (hereinafter, referred to as shooting-related control), playback image display, display image selection, electronic zoom,
Index display, panorama synthesis, image protection, image deletion and other image display / processing control (hereinafter referred to as playback-related control), and further, clock setting, beep sound setting,
Controls for other various settings such as print reservation settings and liquid crystal panel brightness adjustment (hereinafter, referred to as other various setting controls) are included.

In the digital camera 1 of the present embodiment, the above three types of control (shooting-related control, reproduction-related control, and other various setting controls) exist, and the method of inputting settings and operations differs depending on the control type. .

Incidentally, the input related to the photographing-related control is performed by a condition setting dial and a condition type button (both not shown), and such a setting process is called a photographing condition setting process. On the other hand, inputs related to the reproduction-related control and other various setting controls are performed from a menu screen displayed on the liquid crystal panel 7, and such setting processing is referred to as reproduction-related / other processing. The system controller 13 executes each of the setting processes described above.

The digital camera 1 of the present embodiment is
The microphone 15 as the voice input means is provided, and the microphone 15 can capture voice information for a predetermined time (for example, 5 seconds) in synchronization with the imaging operation.

The voice recognition circuit 16 is connected to the microphone 15
Recognizes the voice information input in step (1) and converts it into text data. Further, it extracts features based on the voice data, analyzes the shooting situation based on the result, and performs a plurality of categories (chat / Public speaking, etc.). This speech recognition circuit 16
It constitutes text data setting means and photographing situation analogy means in the present invention.

The character image output circuit 17 converts the voice information output from the voice recognition circuit 16 into character image data. The character image data is output to the image processing controller 4, and the electronic image of the subject is output. It is stored in the memory card 5 together with the image (the image taken at the time of voice input). At this time, the two image data (the electronic image data and the audio image data) are associated but not combined. This character image output circuit 17 constitutes a character image generation unit in the present invention.

The image processing controller 4 has a function of reading out an image recorded on the memory card 5 in accordance with a photographer's instruction and displaying the image on the liquid crystal panel 7 through the LCD driver 6. At this time, if the character image data is associated with the image to be read, the character image data is also read out and displayed on the liquid crystal panel 7 after the synthesizing process. Note that the liquid crystal panel 7 constitutes a display unit in the present invention.

At this time, if the photographer feels that the shape of the composite character is inappropriate for the photographing situation, the photographer operates an instruction member (not shown) included in the input unit 12 to obtain another character. It can be changed to character data. Specifically, when the photographer operates an instruction member in the input unit 12, the operation signal is detected by the system controller 13 and output to the image processing controller 4. Upon receiving the operation signal, the image processing controller 4 operates the character image output circuit 17.
Is instructed to transmit the next appropriate character image data. In response to this, the character image output circuit 1
7, new character image data is returned to the image processing controller 4. Then, in response to this, the image processing controller 4 updates the character image data of the memory card 5 and displays the composite image again.

Next, the configuration and operation of the voice recognition circuit 16 and the character image output circuit 17 will be described in detail with reference to FIG.

As shown in FIG. 2, the speech recognition circuit 16
And the character image output circuit 17 have the connection relationship described above.

The voice recognition circuit 16 includes a filter means 30, a digital conversion means 31, a frequency analysis means 32
, Matching means 33 and identification pattern table 34
, Analoging means 35, and setting means 36.

The output terminal of the microphone 15 is
0, the output end of the filter means 30 is connected to the input end of the digital conversion means 31, and the output end of the digital conversion means 31 is connected to the input end of the frequency analysis means 32. End and the analogy means 35
Is connected to the input terminal of An output terminal of the frequency analysis unit 32 is connected to an input terminal of the matching unit 33 and an input terminal of the analogization unit 35. The input terminal of the matching unit 33 is connected to the identification pattern table. 34 output terminals are connected. An output terminal of the matching unit 33 is connected to an input terminal of the setting unit 36. Further, an output terminal of the analog inference means 35 is connected to an input terminal of a font selection means 37 of the character image output circuit 17 described later, and an output terminal of the setting means 36 is connected to a character output of the character image output circuit 17 described later. It is connected to the input end of the image generation means 38.

The character image output circuit 17 includes a font selecting means 37, a character image generating means 38, and a font table 39.

The output terminal of the font table 39 is connected to the input terminal of the font selecting means 37, and the output terminal of the font selecting means 37 is connected to the input terminal of the character image generating means 38. The output terminal of the character image generating means 38 is connected to the input terminal of the image processing controller 4. The font selection means 3
The output terminal of the image processing controller 4 is connected to the input terminal 7.

The voice information taken into the microphone 15 is filtered by the filter means 30 in the voice recognition circuit 16 to remove noise therefrom.
1 and converted to digital data.

The converted digital data is subjected to frequency feature extraction by the frequency analysis means 32 and subsequently stored by the matching means 33 in the identification pattern table 34 outputted thereto. Recognition is performed by pattern matching with the identification pattern. Then, based on the recognition result, the digital data is output to the setting means 36, and character data allocation setting is performed. That is, a series of processes for converting an analog audio signal into digital data and converting it into text data are performed.

The digital data converted by the digital conversion means 31 is input to the analogization means 35, and the volume and / or intonation of the audio data is analyzed to estimate the shooting condition.

When the volume is small and the inflection is small, the analogy inference means 35 determines that the situation is such that it is not possible to move around very actively, for example, at a ceremony hall. For example, it is determined that the situation is such as a party, a sports day, or the like, in which the movement is intense. Also, from the output of the frequency analysis means 32, when the frequency width of the frequency band is wide, it is determined that there are many people, and when the frequency is high, it is determined that there are children, and the frequency data is taken into account. I have.

Based on the result of the analogy, the analogy inference means 35 generates, for example, a "quiet ceremony", a "multiple party", a "snap including children", and a "commemorative photo outdoors".
In this way, the shooting situation is classified into several categories.

In the character image output circuit 17, the photo selecting means 37 selects a font of a character image from the font table 39 outputted thereto according to the analogy result output from the analog inference means 35. Is output to the character image generating means 38.

The character image generating means 38 generates a character image based on the text data output from the matching means 33 and the selected font, and outputs the character image to the image processing controller 4.

Further, as described above, when a character image change instruction is issued from the image processing controller 4, the font selecting means 37 receiving the signal selects the next character candidate and selects the next character candidate. Output to the character image generating means 38.

For example, if the font shape is "quiet ceremony", the font is based on the Mincho style, and if "the party is large", the font style is based on the pop style, and "including children". In the case of "snap", it is preferable to use a font having an atmosphere suitable for the subject and its shooting situation, such as a comic-based tone.

In addition, it may be possible to add a color expression such that a warm color is used in a pleasant situation and a cool color is used in a sad situation.

Further, a loud voice can be made into a large character,
Emphasis processing may be performed, such as using thick characters.

As described above, the character image output circuit 17 performs the character image (text data) output from the voice recognition circuit 16 and the category data on the basis of the category data.
Selectively output character image data.

As described above, in the camera according to the embodiment of the present invention, the microphone 15 of the digital camera 1 is used.
When a voice is input at the time of shooting, the voice recognition circuit 16
The photographing situation is inferred from the audio data such as the loudness, intonation, and frequency of the input voice by the analog inference means 35 incorporated in the CPU, and the font selection means 37 provided in the character image output circuit 17 by A process of selecting character data according to a shooting situation, subsequently creating character image data by the character image generating means 38, and further combining the image captured by the image processing controller 4 with the character image data Is performed, character image data according to the shooting situation can be displayed on the liquid crystal panel 7 together with the shot image.

[0047]

As described above, according to the present invention, it is possible to provide a camera capable of voice input that allows the user to feel "atmosphere at the time of shooting" or "realism" simply by looking at the printed photographic image. .

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of an electric circuit of a camera capable of inputting audio according to an embodiment of the present invention;

FIG. 2 is a block diagram showing a configuration of a voice recognition circuit and a character image output circuit in the camera capable of voice input according to the embodiment of the present invention.

[Explanation of symbols]

2. Photographing optical system (imaging means) 7 ... Liquid crystal panel (display means) 15 ... Microphone (voice input means) 16 ... Voice recognition circuit (text data setting means) (photographing situation analogy means) 17 ... Character image output circuit (characters) Image generation means)

Claims (4)

[Claims] 1. An image pickup means for picking up an electronic image of a subject through a photographic optical system, an audio input means for taking in audio information at the time of an image pickup operation by the image pickup means, and a text data for inputting the audio information. Text data setting means for converting the text data into a character image; character image generating means for converting the text data into a character image; and display means capable of displaying an image obtained by synthesizing the electronic image of the subject obtained by the imaging means with the character image. And photographing situation analogy means for inferring a photographing situation based on the audio information, and wherein the character image generating means is characterized in that the characteristic of the character image is based on the photographing situation analogized by the photographing situation analogy means. A camera capable of voice input, wherein the camera is changed. 2. The camera according to claim 1, wherein said photographing situation analogy means judges the photographing situation based on a volume and / or intonation of the voice information. 3. The camera capable of voice input according to claim 2, wherein said photographing situation analogy means further performs analogy in consideration of a frequency of said voice information. 4. The character image generating means changes at least one of a shape, a color, and a size of a character image according to a photographing situation estimated by the photographing situation analogizing means. The camera capable of voice input according to claim 1.