KR20170017427A

KR20170017427A - Automatic retrieval device of alternative content for the visually impaired

Info

Publication number: KR20170017427A
Application number: KR1020150111303A
Authority: KR
Inventors: 서인식
Original assignee: 서인식
Priority date: 2015-08-06
Filing date: 2015-08-06
Publication date: 2017-02-15
Also published as: KR101823734B1

Abstract

The present invention relates to an automatic search device for alternative content for the visually impaired. The automatic search device for alternative content for the visually impaired comprises: a main body unit on which a book and a document is placed; a support unit which is vertically installed on a middle portion of one end of the main body unit and includes a first and a second support unit to be folded; a head unit formed on an end of the support unit and provided with a camera and a lamp; a recognition processing unit including an image recognition unit to recognize an image photographed by the camera and a character recognition unit to recognize the image read by the image recognition unit in a character; a voice output unit to output the character recognized by the recognition processing unit in a voice; and a book fixing device and a fixing unit to fix the book and the document placed on the main body unit.

Description

Automatic retrieval device for alternative content for the visually impaired.

The present invention relates to an apparatus and method for automatically searching for a substitute content for a visually impaired person, and more particularly, to an apparatus and method for automatically searching for a substitute content for a visually impaired person, Or alternate contents automatically, and to provide a substitute content automatic searching device for a visually impaired person to solve the information access problem of a visually impaired person.

Generally, a reading book provided in a library or the like is simply a desk-shaped book, and the user simply reads the book after sitting on the reading desk after borrowing the book. However, there was no consideration for the blind or visually impaired, and I had no choice but to read the book using a magnifying glass. Also, in the case of the visually impaired, there was no way to read the book except Braille.

In order to solve such a conventional problem, a user puts a reading camera on a book, places a portion to be read in a hole of the reading camera, adjusts the focus and height adjusting ring of the body, A way to read through a connected monitor was provided.

However, such a function is inconvenient to operate, and in order to read a book, the user himself has to operate the camera directly, find a desired portion, and input the portion, which is not helpful for the visually impaired.

In addition, although an optical character reader for taking a document with a camera and playing a printed character by sound for a visually impaired person is performed, the conventional optical character reader has a drawback in that it is difficult to provide various book contents desired by the user.

KR 10-2006-0007496 A KR 10-1162068 B1

The present invention has been conceived to solve the above-mentioned problems, and its object is to automatically recognize text contents and alternative contents by recognizing characters of a textbook cover, provide information retrieved, The present invention provides an apparatus for automatically searching for a substitute content for a visually impaired person.

In addition, it is also possible to provide a method and apparatus for capturing an image of a book and a document in a camera, converting the photographed image to a character through a recognition processing unit, and reproducing the converted character through a voice output unit, Another object is to provide an automatic content search apparatus for disabled persons.

In order to accomplish the above object, according to the present invention, there is provided an apparatus for automatically searching optical substitute contents for a visually impaired person, comprising: a body part formed to mount a book and a document; A support portion in which the support portions are foldable with each other; A head unit formed at an end of the support unit and having a camera and an illumination lamp; A recognition unit configured to recognize an image photographed by the camera and a character recognition unit to recognize the image read through the image recognition unit as a character, a voice output unit configured to output a recognized character through the recognition processing unit; And a book fixing device for fixing the book and the document placed on the main body.

According to the present invention, the automatic searching device for optical substitute contents for the visually impaired can solve the problem of loss and failure compared with the separated camera by applying the folding stand type integrated camera considering the blindness characteristic, The system can optimize the character recognition by preventing the unreadable situation due to the book cover or the hand or other objects.

In addition, the present invention recognizes the characters of the textbook cover, automatically searches for the substitute contents, and provides the retrieved information, thereby enabling access to various educational substitute contents through the present invention.

In addition, the user recognizes the purpose of character recognition such as a bill or a business card, and provides data corresponding thereto, so that various data required by the user can be easily obtained.

1 is a perspective view of an automatic search apparatus according to the present invention;
FIG. 2 is a perspective view showing a support portion and a head portion of the automatic searching apparatus according to the present invention folded. FIG.
FIG. 3 is a perspective view showing a state where a book is fixed to the automatic searching apparatus of the present invention. FIG.
4 is a flowchart showing a step of receiving teaching material contents using the automatic searching apparatus of the present invention.
FIG. 5 is a flowchart showing a step of outputting a recognized character through a voice recognition apparatus through the automatic search apparatus according to the present invention. FIG.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of an automatic content search apparatus for a visually impaired person according to the present invention will be described in detail with reference to the accompanying drawings. It is to be understood that the present invention is not limited to the disclosed embodiments, but may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, It is provided to inform.

1 is a perspective view of an automatic search apparatus according to the present invention.

1, the automatic searching apparatus 1 includes a main body 10 on which a book and a document are loaded, a support portion 20 vertically formed at one end of the main body portion 10 and coupled to an end of the support portion 20 And a book fixing device 11 formed at the center of the other end of the main body 10.

The main body 10 has a rectangular housing shape so that books and documents can be easily mounted. A storage groove 13 is formed in the center of the main body 10 along the longitudinal direction, And the head portion 30 can be folded and stored.

The stationary part 12 is formed symmetrically with respect to the support part 20 so that a book and a document placed on the main part 10 are transferred to the book fixing device 11 and the fixing part 12, So that it can be easily fixed on the main body 10.

The supporting part 20 is configured such that the first supporting part 21 and the second supporting part 22 are hinged to each other so that the first supporting part 21 and the second supporting part 22 are folded together to adjust the angle, 2 end of the support portion 22 and the head portion 30 are also hinged to each other so that the angle of the head portion 30 can be adjusted.

The head unit 30 is provided with a camera (not shown) for photographing a book or a document and an illuminating lamp (not shown) formed for accurate reading of a book and a document placed on the main body 10, 10 are made to be clearly photographed in the camera.

Preferably, the camera is capable of recognizing two A4-sized documents at a time by applying a dual camera installed on both sides of the head unit, so that two pages of a book can be recognized at a time, It is preferable to consecutively read and read consecutive pages for a time period during which characters recognized through the camera are output by voice, thereby reading the book continuously without page breaks, thereby reducing the reading time.

In addition, it is preferable that a camera module supporting a minimum font of 2 mm is applied to easily recognize characters of a book having various curvatures and steps, so that the book characters can be correctly recognized through the camera.

A sound output unit 14 is formed in the main body 10 to output images and texts photographed through the camera and a braille output unit 14 for outputting characters recognized through the camera as braille characters, (Not shown).

The audio output unit 14 preferably includes a built-in speaker (not shown) for outputting audio and an earphone output unit (not shown) for allowing the user to listen to the audio through the earphone.

In addition, an SD memory card insertion unit (not shown) and a USB port (not shown) are further formed in the main body unit 10 so that memory expansion through the SD memory card and work using USB can be performed.

In addition, the main body 10 is provided with a recognition processing unit (not shown) for recognizing the image read through the camera as a character, a control unit for correcting the recognized character through the recognition processing unit and storing the corrected result Not shown) is further formed.

Wherein the recognition processing unit comprises: an image processing unit for processing image data of a book and a document photographed by the camera; an image recognizing unit recognizing a character portion extracted from the image processing unit; A voice signal generator for converting the text file into a voice signal and outputting the voice file, and a voice signal generator for outputting the image data processed by the image processor to the voice output unit .

A process of outputting a photographed image by using the recognition processing unit will be described as follows.

The image processing unit processes image data of a document input from a camera, and extracts only a character portion through a document image rotation, line separation, extraction, and character separation.

Since the image input through the camera is not always horizontal, add the RGB value of the black pixel corresponding to the character in the horizontal direction, and find the best direction to distinguish the character area and the space between the line and the line in the horizontal direction . The text portion has a strong RGB value for black, and the space between the line and the line has RGB values close to white. Rotate the document in the direction that clearly distinguishes the black and white spaces that are most likely to be typed.

In addition, it is possible to separate lines based on the data used in the rotation of the document image. Since the space between the character and the line and the line are clearly distinguished, only the image corresponding to the character in each line is separated .

When the image corresponding to one line of the document is separated in this manner, character separation is performed, and the value of the pixel in the vertical direction of the image corresponding to one line of the document is added to the character portion, . Since the ratio of the letters to the letters is constant, the width of each letter can be predicted more accurately by using the information of the letters' vertical size, so that the images corresponding to one letter can be separated. The image of each separated character is stored in a file.

The image recognizing unit recognizes each character stored in the image separating unit. In the process of recognizing the character image, first, a character image is input and thinning is applied. Thinning removes the parts that are not helpful for character recognition, and then obtains the skeleton of the text so that the thickness of the line is one pixel thick. The stroke information is extracted using the character skeleton information.

In addition, a data output unit (not shown) is formed in the main body 10 to determine a character recognition purpose such as a bill or a business card placed on the main body 10 and provide data corresponding thereto. For example, If the electric bill is placed on the main unit 10, the electric bill amount is outputted as data or if the business card is placed, the name, title, and phone number of the business card, .

FIG. 2 is a perspective view showing a support part and a head part 30 of the automatic content search apparatus 1 according to the present invention folded. FIG.

As shown in FIG. 2, the support portion 20 and the head portion 30 are folded to be inserted into the storage groove 13 formed in the main body portion 10. As described above, the support portion 20 is formed such that the first support portion 21 and the second support portion 22 are foldable with each other, and the second support portion 22 and the head portion 30 are formed to be foldable The angle of the support part 20 and the head part 30 can be easily adjusted and can be easily stored in the storage groove 13 of the main body part 10, 1) can be easily carried and stored.

FIG. 3 is a perspective view showing a state where a book is fixed to the automatic searching apparatus of the present invention.

3, when the book and the document are placed on the main body 10, the book fixing device 11 and the fixing portion 12 are used to fix each end of the book to stably fix the book And photographs a book page using the camera formed on the head unit 30, reads out images and characters, and outputs the recognized characters through the audio output unit 14. [

The automatic search apparatus 1 is configured to be able to control functions such as recognition, start, stop, voice output speed control, favorite, page search, and list search by a portable controller (not shown) And a tactile button may be applied to easily control the function.

4 is a flowchart illustrating steps of receiving teaching material contents using the automatic searching apparatus of the present invention.

According to the automatic searching apparatus of the present invention, the book cover is photographed and the book content in the content server is automatically searched after the character is read to download the substitute contents, thereby improving the accuracy and accessibility. The following will be described later.

When the book cover is photographed through the camera provided in the automatic searching apparatus 1 and recognized as a character through the photographed image (S10), the process proceeds to a user verification step (S20) for verifying the user. The user verification S20 may be performed through a unique identification number registered in the automatic searching device or software, and after the user verification step S20, it is determined whether the user verification is a valid request (S30). If it is determined that the request is a valid request, the process proceeds to step S40 for searching for the content, and the content is retrieved by the user. If it is determined that the request is not a valid request, the connection is blocked and the content search can no longer be performed.

When it is determined that the request is valid and the process proceeds to the content retrieval step S40, the server stores the log data (S60) so that the user information can be stored in the server.

The process proceeds to a step S50 of verifying whether the retrieved content is a valid content through a content retrieving step S40. If the retrieved content is a valid content, the process proceeds to a step S60 of outputting a content result, The server proceeds to step S90 for searching for the substitute content 90 to provide the substitute content.

If the user receives the substitute content and receives the substitute content via the step S90 of receiving the substitute content, the user proceeds to step S60 of outputting the content result. If the substitute content is not received, So that alternative content can be provided.

If the user makes a selection through the content output step (S90), the user can download the selected content and use the content.

5 is a flowchart illustrating a step of outputting characters recognized through the automatic search apparatus of the present invention by voice.

Referring to FIG. 5, a book and a document placed on the main body 10 are photographed by the camera (S11), read (S12) the photographed image and read by the recognition processor The image is recognized as a character (S13).

When the read image can not be recognized as a character, the captured image is recognized as a character so that the captured image is repeatedly photographed until it is recognized as a character.

When the image photographed by the camera and recognized by the image and character recognition processor is recognized as a character, the recognized character is corrected and the result is stored (S14) To the output.

While the voice is being reproduced through the audio output unit, the camera is continuously photographed so that the next image is read and character recognition is continued.

Although the present invention has been described with reference to the exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the scope of the invention.

1: Automatic search device 10:
11: book fixing device 12: fixing part
13: Storage groove 20: Support
21: first support portion 22: second support portion
30: head portion

Claims

An optical substitute contents automatic searching device for a visually impaired person,
The automatic content search apparatus includes a main body configured to read books and documents;
A support vertically installed at a central portion of one end of the main body, the first support and the second support being foldable with each other;
A head unit formed at an end of the support unit and having a camera and an illumination lamp;
A recognition processing unit comprising an image recognition unit for recognizing an image photographed through the camera and a character recognition unit for recognizing an image read through the image recognition unit as a character;
An audio output unit for converting the recognized character into speech and outputting the recognized speech through the recognition processing unit;
A book fixing device for fixing the book and the document placed on the main body;
And an automatic content search apparatus for a visually impaired person.

The method according to claim 1,
Wherein the head portion and the support portion are formed to be foldable and stored in a storage groove formed along a longitudinal direction of the main body portion.

The method according to claim 1,
Wherein the camera captures and recognizes two pages at a time by applying a dual camera.

The method according to claim 1,
Wherein the automatic searching apparatus is configured to photograph a cover and recognize a character on a cover, and then to download a character string corresponding to the book content and the substitute contents in the content DB server or a searched character string.

The method according to claim 1,
Wherein the main body unit is further formed with a data output unit to determine the purpose of the document to be loaded on the main body unit and to provide data corresponding thereto.