KR20060031769A - Mobile communication terminal and method for converting photographed text into voice - Google Patents

Abstract

The present invention relates to a voice conversion system and method of a mobile communication terminal having an image capturing function, and to photograph characters displayed on a street sign or signboard by using a video camera that is basically installed in most mobile communication terminals. When the user can receive the contents of the sign by voice, tourists who are not familiar with geography, children, old people, and blind who are not familiar with English and Chinese characters can easily recognize the surrounding situation.

The present invention system for achieving this, and the image recognition unit 40 for recognizing the image taken by the camera 20; A text converter 50 for extracting a text included in an image recognized by the image recognizer 40 into an image and converting the text into a text signal; A voice converter 61 for converting the text signal converted by the text converter 50 into a voice signal; It is characterized in that it is composed of a voice output unit 62 for outputting the voice converted by the voice conversion unit 61 to the outside.

Camera, translation, voice, text, conversion, panorama, visual

Description

MOBILE COMMUNICATION TERMINAL AND METHOD FOR VOICE TRANSFORMING CHARACTER TEXT {MOBILE COMMUNICATIO DEVICE HAVING FUNCTION OF VOICE TRANSFORMATION OF PHOTOGRAPHED CHARACTER}

1 is a block diagram showing the configuration of the present invention voice conversion system.

2 is a flowchart of a voice conversion process according to an embodiment of the present invention.

3 is a view showing an active window of a language selection mode according to an embodiment of the present invention;

4 is a schematic diagram of a data storage form of a pre-storage unit according to an embodiment of the present invention.

<Description of the symbols for the main parts of the drawings>

10: control unit 20: camera

30: memory unit 40: image recognition unit

50: character conversion unit 60: speech processing unit

61: voice conversion unit 62: voice output unit

70: text translation unit 80: dictionary storage unit

The present invention relates to a mobile communication terminal system having an image capturing function, and more particularly, to automatically translate a character appearing on a street sign or signage to be transmitted as a voice through a speaker to greatly improve the functionality of the terminal. It is for.

Recently, as the number of users of mobile communication terminals (cellular phones, PCS phones, PDA phones, etc.) has increased rapidly, terminals with more diverse functions and designs have been released. In recent years, high-pixel cameras that can easily input or transmit images are available. Built-in camera phones are the mainstream.

Such a camera phone receives an image (still image or a video) from a camera module mounted on the outside of the terminal, and stores it in an internal memory or outputs and transmits it to the outside by a control signal. The image capturing function applied to is mainly used to recognize documents such as business cards and magazines, and to store and search them in DB.

However, the character recognition itself is useless to people who do not know English or Chinese characters, such as the elderly and children, and especially when the eyesight is poor, such as the elderly had a problem that it is difficult to check the contents through a small LCD window.

In addition, most terminals deal only with still images, and signs or signs that contain a lot of contents may not contain all the contents in a single picture. There is a case.

 The present invention is proposed to further advance the function of the conventional camera phone, by extracting the characters appearing on the street sign or signboard photographed by the video function in the terminal so that the contents can be delivered to the user by voice. There is a purpose.

In addition, another object of the present invention is to maximize the functionality of the terminal to be output in the translated state in the case of the image character is taken Chinese characters or foreign language.

The object of the present invention is a conventional mobile communication terminal comprising a camera for photographing an external image, a memory unit for storing input or transmitted data, and a control unit for controlling the respective functions. An image recognition unit for recognizing an image; A text converter configured to extract a character included in the image recognized by the image recognizer and convert the text into a text signal; A voice converter for converting the text signal converted by the text converter into a voice signal; A voice output unit for outputting the voice converted by the voice conversion unit to the outside; It is possible to achieve through the voice conversion system of the mobile communication terminal having a video shooting function characterized in that consisting of.

Also, an image input step of inputting an image input through a camera while a voice conversion mode of an input image is selected, a continuous shooting confirmation step of confirming whether the input image is a continuous image, and the input image A text extraction step of extracting a text area into an image form, a text signal conversion step of converting the extracted text into a text signal, and a translation decision to determine whether to translate the converted text signal into a specific language. And a voice signal conversion step of converting the text signal into a voice signal, and a voice output step of outputting the converted voice signal to an external device through a voice output unit to deliver the converted voice signal to a user. It is possible to achieve through the voice conversion method of the mobile communication terminal having.

Hereinafter, specific embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram showing a system configuration for the implementation of the present invention, FIG. 2 is a flow chart showing the voice conversion process of the present invention, FIG. 3 is an illustration of an active window for selecting a language to be translated, and FIG. 4 is an embodiment of the present invention. The following is an example of the characters stored in the dictionary storage of the system.

First, a main system configuration of the mobile communication terminal of the present invention will be described with reference to FIG. 1, the control unit 10 in which overall function control of the terminal system is performed, the camera 20 for capturing an external still image or a video, and In addition to the conventional configuration of the memory unit 30, which stores the data input or transmitted through the camera 20, the image recognition unit 40 for recognizing the image taken through the camera 20, A text conversion unit 50 which extracts a character included in the image recognized by the image recognition unit 40 and converts it into a text signal, and converts the text signal converted by the text conversion unit 50 into an audio signal. Characteristic configuration of the speech output unit 62 consisting of a text-to-speech (61) for converting the speech conversion unit and a speaker for outputting the speech converted by the speech conversion unit 61 to the outside. It is good.

The camera 20 is equipped with a high-definition digital camera to secure the image clarity, a flash device for obtaining a bright image even in a dark place, and a zoom (Zoom) device for taking a distant sign up close Do.

In addition, the image recognition unit 40 may implement a panorama image when the input image is taken by continuous shooting.

In addition, a text translator 70 for translating the text signal converted by the text conversion unit 50 into a selected language to perform a translation function, and dictionary data (Chinese, English) for the text translation. , Japanese, etc.) to configure the dictionary storage unit 80 is stored.

On the other hand, in addition to the above configuration, there is a key input unit through which a user's external input is made through a button, and a display unit displayed through an LCD window. Since there is a distance, a description thereof will be omitted.

The operation process and the resulting effects of the mobile communication terminal of the present invention constituting such a system will be described.

The present invention uses the camera 20 and the speaker 62 mounted on the terminal when the tourist, the elderly, young children lost in unfamiliar areas when taking pictures of the letters written on the signs or signs in the key input unit of the terminal The operation is started by pressing the execution button mounted on the (not shown), which is shown through the flowchart of FIG.

That is, when a still image such as a signboard or a sign taken by the camera 20 is input, the input image image is temporarily stored in the memory unit 30 under the control of the controller 10. (ST One)

In this case, when all the sign letters do not enter a single picture, the user performs continuous shooting to input several images. The controller 10 determines whether the input image is a continuous picture (ST 2). In the case of continuous shooting, multiple input images are combined to realize a single panoramic image. (ST 2-1)

In the case of non-continuous shooting, the image recognition unit 40 extracts the text area directly from the input still image. (ST 3) In other words, the background and text are extracted using the characteristic of only the text area. By separating the area, only the text area in the background image remains in the form of an image.

In addition, the text conversion unit 50 performs a process of converting the extracted text area into a text signal. (ST 4)

On the other hand, if the character on the bulletin board is converted to Chinese or English rather than Korean, the text translation function is first selected before processing the voice signal. (ST 5)

At this time, in the step of the present invention, two modes can be set for more accurate judgment, one of which is to recognize the character of the input image belongs to Hangul / English / Hanja first to select the translation function in advance Method, and the program automatically selects and processes it.

In particular, in the automatic selection mode, since the language must be automatically determined from the input image, it is preferable to classify the characteristics of each language and reflect them in the algorithm. In other words, Hangul is case-insensitive and similar in size when listed, English is case-insensitive and size is not uniform when listed. There is a lot and when the outline is drawn on one letter, the proportion of letters is bigger than Korean or English.

In the present embodiment, a description will be made mainly based on a case where the user has previously designated a language selection mode, and the language to be translated is first set in a state in which a setting window with Korean as a default character as shown in FIG. 3 is activated. When the Chinese character or the English character signal is input in the character translation unit 70 searches for the corresponding character stored in the DB of the dictionary storage unit 80 to perform a character translation to translate it into Korean as shown in FIG. (ST 5-1)

In this way, the text signal is translated into Hangul or the video signal input from the beginning into Hangul is converted into a voice signal by the voice converter 61 in the next step. (ST 6)

Thereafter, the converted voice signal is output through the speaker, which is the voice output unit 62, and is transmitted to the user so that the user can recognize the corresponding character. (ST 7)

Therefore, such a voice conversion operation can be performed continuously in a set state, so that when the terminal equipped with the voice conversion system of the present invention is carried, the elderly with dark eyes or children who are difficult to read are described in signs or signs. It can be seen that it is possible to easily obtain geographic information by receiving the announcement by voice.

In particular, if there is an unfamiliar Chinese guide or signage in the daily life of modern people, the phrase is easily received through the present invention will be able to easily understand the content.

In addition, although specific embodiments of the present invention have been described and illustrated above, it is obvious that the voice conversion process and system of the present invention may be variously modified and implemented by those skilled in the art.

For example, in the above embodiment, Chinese characters and English are stored as characters to be translated, but this may add a translation function for the corresponding foreign language by storing Chinese or Japanese data as necessary.

In addition, although the Korean language is set as a language to be transmitted to the user as a basic language, it can be seen that when the user is a foreigner, it can be set as a native language and the Korean language can be designated as a translation target character.

Therefore, such modified embodiments should not be understood individually from the technical spirit or prospect of the present invention, and such modified embodiments should fall within the appended claims of the present invention.

The present invention as described above, by extracting the characters appearing on the street signs or signboards, etc. by using a video camera that is basically installed in the majority of mobile communication terminal to receive the contents of the signs by voice Will be.

In particular, when characters in languages other than Hangul are written, the characters can be translated and translated, so that tourists who are not familiar with geography, children, seniors, and blind people who are not familiar with English and Chinese characters can easily get around. It can be seen that can be recognized.

Claims (5)

A mobile communication terminal comprising a camera for photographing an external image, a memory unit for storing input or transmitted data, and a control unit for controlling the respective functions. An image recognition unit for recognizing an image photographed by the camera; A text converter which extracts the text included in the image recognized by the image recognizer into an image form and converts the text into a text signal; A voice converter for converting the text signal converted by the text converter into a voice signal; And a voice output unit for outputting the voice converted by the voice conversion unit to the outside. The method of claim 1, A text translation unit for translating the text signal converted by the text conversion unit into a selected language; And a dictionary storage unit for storing dictionary data for the text translation. An image input step of inputting an image input through a camera while selecting a voice conversion mode of the input image; A continuous shooting checking step of checking whether the input image is a continuous shooting image; A character extraction step of extracting a character region from the input image in an image form; A text signal conversion step of converting the extracted text into a text signal; A determination and translation step of judging and translating the translated text signal into a specific language; A voice signal conversion step of converting the text signal into a voice signal; A voice output step of outputting the converted voice signal to the outside through a voice output unit to transmit the converted voice signal to a user; Voice conversion method of a mobile communication terminal having a video recording function comprising a. The method of claim 3, The continuous shooting confirmation step, If the input image is a continuous image, the voice conversion method of a mobile communication terminal having a video recording function further comprising the step of implementing a panoramic image. The method of claim 3, The determination and translation step, And a translation operation is selected, wherein the converted text signal is translated into a text signal of a corresponding language selected through the dictionary storage.

Images