CN107393356A - Control method, control device and early learning machine - Google Patents
Control method, control device and early learning machine Download PDFInfo
- Publication number
- CN107393356A CN107393356A CN201710223596.5A CN201710223596A CN107393356A CN 107393356 A CN107393356 A CN 107393356A CN 201710223596 A CN201710223596 A CN 201710223596A CN 107393356 A CN107393356 A CN 107393356A
- Authority
- CN
- China
- Prior art keywords
- text
- module
- database
- audio
- frequency information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
- G09B5/065—Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Educational Administration (AREA)
- Business, Economics & Management (AREA)
- Educational Technology (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of control method, for early learning machine.Early learning machine includes camera, player and the database for being stored with audio-frequency information corresponding with point reading nationality.Control method includes：Control camera shoots the text for putting reading nationality to obtain text image；Identify the body text in text image；The audio-frequency information matched with body text is found in database；Control player plays audio-frequency information.The invention also discloses a kind of control device and early learning machine.Control method, control device and the early learning machine of embodiment of the present invention carry out Text region and broadcasting after shooting books image using camera, without hand-held talking pen when user uses, the problem of avoiding user from needing to need frequent switching lettering pen and talking pen when taking notes on books, improves the convenience used and usage experience.
Description
Technical field
The present invention relates to electronic learning device field, more particularly to a kind of control method, control device and early learning machine.
Background technology
At present, most point readers are to lay crisscross conduction by an inside similar with notebook computer on the market
The housing of nethike embrane and a click pen that may only sense or send wireless signal form.During use books horizontal expansion shell
On body, the position for having word on textbook is clicked on click pen, clicking on the wireless signal that pen goes out will be led by what casing internal was laid
Power network film receives, or caused alternating electromagnetic field can be clicked pen and be experienced in conductive mesh film.By handling, in casing
CPU just can obtain the coordinate value of click location, and then is somebody's turn to do according to coordinate value corresponding in speech data memory is stored in
The speech data of coordinate is read out, be sent to speech processing circuit send the position word corresponding to sound, play " point read "
Effect.Using must all hold talking pen during the whole use of user during this point reader, if user needs to do on books
, it is necessary to which continually switching writing pencil and talking pen, Consumer's Experience are poor during notes.
The content of the invention
It is contemplated that at least solves one of technical problem present in prior art.Therefore, the present invention provides a kind of control
Method, control device and early learning machine processed.
The control method of embodiment of the present invention, for early learning machine, the early learning machine includes camera, player and storage
There is the database of audio-frequency information corresponding with point reading nationality, the control method includes：
The camera shooting text for putting reading nationality is controlled to obtain text image；
Identify the body text in the text image；
The audio-frequency information matched with the body text is found in the database；With
Control audio-frequency information described in the player plays.
In some embodiments, the database is also stored with the books that prestore, and the control method also includes：
The camera shooting front cover for putting reading nationality is controlled to obtain cover image；
Identify the Periodical front cover information in the cover image；With
According to the Periodical front cover information find in the database with it is described point reading nationality it is consistent prestore books to obtain
Target prestores books；
Wherein, described the step of finding the audio-frequency information matched with the body text in the database, includes：
The audio-frequency information that is matched with the body text is found in the database according to the target books that prestore.
In some embodiments, the control method also includes：
Identify the current page number in the text image；
Wherein, the step of finding the audio-frequency information matched with the body text in the database includes：
Books are prestored according to the target and the current page number is found and the body text in the database
The audio-frequency information matched somebody with somebody.
In some embodiments, the step of current page number in the identification text image includes：
Digital information is filtered out from the body text；
The text image is handled to orient the digit position where the digital information；
Calculate the quantity of the blank pixel of the digit position within a predetermined range；With
If the quantity is more than predetermined number, it is determined that the digital information is the current page number.
In some embodiments, the control method also includes：
The text image is handled to judge whether user's finger；
When the user's finger be present：
Judge the point reading location at the finger；With
The body text is divided into by reading area and non-read area with predetermined character area according to described reading location
Domain；
When in the absence of the user's finger：
Determine that all body texts are reading area in the text image；With
Described the step of finding the audio-frequency information matched with the body text in the database, includes：
The audio-frequency information matched with the body text in the reading area is found in the database.
The control device of embodiment of the present invention, for early learning machine, the early learning machine includes camera, player and storage
There is the database of audio-frequency information corresponding with point reading nationality, the control device includes control module, identification module and matching mould
Block.The control module is used to control the camera shooting text for putting reading nationality to obtain text image；The knowledge
Other module is used to identify the body text in the text image；The matching module is used to find in the database and institute
State the audio-frequency information of body text matching；The control module is additionally operable to control audio-frequency information described in the player plays.
In some embodiments, the database is also stored with the books that prestore, and the control module also includes finding mould
Block.The control module is additionally operable to control the camera shooting front cover for putting reading nationality to obtain cover image；It is described
Identification module is additionally operable to identify the Periodical front cover information in the cover image；The searching module is used to be existed according to the Periodical front cover information
Found in the database and read that nationality is consistent to prestore books and prestored books to obtain target with the point；The matching module enters
One step is used to find the audio-frequency information that matches with the body text in the database according to the target books that prestore.
In some embodiments, the identification module is additionally operable to identify the current page number in the text image；It is described
Matching module is further used for prestoring books according to the target and the current page number find in the database with it is described
The audio-frequency information of body text matching.
In some embodiments, the identification module includes screening unit, positioning unit, computing unit and determined single
Member.The screening unit is used to filter out digital information from the body text；The positioning unit be used for handle it is described just
Texts and pictures are as with the digit position where orienting the digital information；The computing unit is used to calculate the digit position pre-
Determine the quantity of the blank pixel in scope；The determining unit is used to determine the numeral when the quantity is more than predetermined number
Information is the current page number.
In some embodiments, control device also includes judge module, determination module, division module and determining module.
The judge module is used to handle the text image to judge whether user's finger；The determination module is used to exist
The point reading location at the finger is judged during the user's finger；The division module is used for according to described reading location with predetermined
The body text is divided into reading area and non-reading area by character area；The determining module is used in the absence of described
Determine that all body texts are reading area in the text image during user's finger；The matching module is further used for
The audio-frequency information matched with the body text in the reading area is found in the database.
The early learning machine of embodiment of the present invention includes camera, player and above-mentioned control device.The control device
Electrically connected with the camera and the player.
Control method, control device and the early learning machine of embodiment of the present invention are carried out after shooting books image using camera
Text region and broadcasting, without hand-held talking pen when user uses, user is avoided to need the needs when being taken notes on books frequent
The problem of switching lettering pen and talking pen, improves the convenience used and usage experience.
The additional aspect and advantage of the present invention will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
The above-mentioned and/or additional aspect and advantage of the present invention is from combining in description of the accompanying drawings below to embodiment by change
Obtain substantially and be readily appreciated that, wherein：
Fig. 1 is the schematic flow sheet of the control method of some embodiments of the present invention；
Fig. 2 is the module diagram of the early learning machine of some embodiments of the present invention；
Fig. 3 is the view of the control method of some embodiments of the present invention；
Fig. 4 is the schematic flow sheet of the control method of some embodiments of the present invention；
Fig. 5 is the module diagram of the control device of some embodiments of the present invention；
Fig. 6 is the schematic flow sheet of the control method of some embodiments of the present invention；
Fig. 7 is the schematic flow sheet of the control method of some embodiments of the present invention；
Fig. 8 is the module diagram of the identification module of some embodiments of the present invention；
Fig. 9 is the view of the control method of some embodiments of the present invention；
Figure 10 is the schematic flow sheet of the control method of some embodiments of the present invention；
Figure 11 is the module diagram of the control device of some embodiments of the present invention；With
Figure 12 is the view of the control method of some embodiments of the present invention.
Embodiment
Embodiments of the present invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning
Same or similar element is represented to same or similar label eventually or there is the element of same or like function.Below by ginseng
The embodiment for examining accompanying drawing description is exemplary, is only used for explaining the present invention, and is not considered as limiting the invention.
Also referring to Fig. 1 to 2, the control method of embodiment of the present invention is used for early learning machine 100.Early learning machine 100 includes
Camera 20, player 30 and the database for being stored with audio-frequency information corresponding with point reading nationality.Control method includes：
S12：The text of control camera 20 shooting point reading nationality is to obtain text image；
S14：Identify the body text in text image；
S16：The audio-frequency information matched with body text is found in database；With
S18：Control player 30 plays the audio-frequency information.
The control method of embodiment of the present invention can be realized by the control device 10 of embodiment of the present invention.It is of the invention real
Applying the control device 10 of mode includes control module 12, identification module 14 and matching module 16.Step S12 can be by control module
12 realize that step S14 can realize that step S16 can be realized by matching module 16 by identification module 14, and step S18 can be by
Control module 12 is realized.
In other words, the text that control module 12 is used to control the shooting point of camera 20 reading nationality is to obtain text image；
Identification module 14 is used to identify the body text in text image；Matching module 16 is used to find in database and body text
The audio-frequency information of matching；Control module 12 is additionally operable to control player 30 to play the audio-frequency information.
The control device 10 of embodiment of the present invention is applied to the early learning machine 100 of embodiment of the present invention.In other words, originally
The early learning machine 100 of invention embodiment includes the control device 10 of embodiment of the present invention.The control dress of embodiment of the present invention
Put 10 and camera 20 and player 30 electrically connect.
Existing early learning machine utilizes the internal housing for laying crisscross conductive mesh film and can sense or send wireless
The click pen of signal realizes the read-on-command function of books.However, during use, if user needs to add notes on books,
Need frequently to change writing pencil and click on pen.In this way, user is poor using the usage experience of early learning machine.
The positive texts and pictures of nationality referring to Fig. 3, the control method of embodiment of the present invention is read first with camera shooting point
Picture.The body text of this time point reading nationality is image format.Identification module 14 handles text image and identifies body text.Specifically
Ground, OCR OCR (Optical Character Recognition) can be used to carry out the identification of body text
And extraction.Firstly, since most of text image is coloured image, for convenience of follow-up Text region, first text image is entered
Row binary conversion treatment causes text image to turn into the image of only two colouring informations of black and white.Then, the image of binaryzation is entered
Row noise removal process is to filter out due to interference noise caused by the factors such as illumination.Specifically, median filter can be used
Processing is filtered, the value of some pixel in text image is replaced to realize that interference is made an uproar with the Mesophyticum of multiple pixels in its neighborhood
Sound removes.Then, rotation correction processing is carried out to the text image after binaryzation and denoising, to facilitate follow-up word to cut and
Identification.Specifically, most significant straight line in CNNNY edge detection algorithms and Hough change algorithm extraction text image can be used
Information, the principal direction of text image is judged by straight line information, then according to the principal direction of text image rotate text image with
Reach horizontal direction.After the completion of text image rotation, i.e., enter every trade cutting and word cutting to text image.Row cutting is to text
Image progressively scans simultaneously while calculates the number of the foreground pixel of often row scanning from top to bottom, to obtain the horizontal throwing of text image
Shadow, the position of literal line is determined according to floor projection value, utilize floor projection white space caused by word in the ranks white space
Can be separated by each style of writing word.Word cutting be from left to right search for a line word individual character left and right circle be syncopated as individual character and
Punctuation mark.After cutting out individual character, can also micronization processes be carried out to each individual character, word programming stroke width there was only a picture
The process of the word skeleton of element, in favor of feature extraction.Then, character features extraction is carried out to the word of micronization processes.Specifically
Ground, the statistical nature of word can be extracted, if the black of word, white point number are than with the numerical value vector in Special composition.It can also carry
The architectural feature of word is taken, such as obtains the stroke end points of word, the quantity in crosspoint and position to obtain the characteristic value of word.
Finally, word is identified using the grader trained.It is for instance possible to use Tree Classifier carries out Text region to be lifted
The speed of Text region and the degree of accuracy.
After the body text of text image is identified, you can the audio matched with body text is found in database
Information is to realize the read-on-command function of the body text of books.
Wherein, it when player plays audio-frequency information can be outer mode playback, user, which can also plug in the earphone, carries out audio letter
Breath is listened to.
The control method of embodiment of the present invention carries out Text region and broadcasting, user again after shooting books using camera
Without hand-held talking pen during use, user is avoided to need to need frequent switching lettering pen and talking pen on books when taking notes
Problem, improve the convenience used and usage experience.
In addition, the control method of embodiment of the present invention is using OCR technique identification word, the speed of Text region and accurate
Degree is higher.And the point reading nationality that user uses can be common paper book, without using the books of particular production, such as make
The books printed with the special coating that can reflect infrared light, therefore, have saved the cost of manufacture of early learning machine 100, what user used
Convenience also greatly improves.The point reading nationality that user uses can also be e-book.In this way, early learning machine 100 can put reading
Books species is more abundant, and the point that user can carry out more books by early learning machine 100 is read, and user experience is more preferably.
Referring to Fig. 4, in some embodiments, database is also stored with the books that prestore, control method also includes：
S111：The front cover of control camera 20 shooting point reading nationality is to obtain cover image；
S112：Identify the Periodical front cover information in cover image；With
S113：According in Periodical front cover information database find with point read nationality it is consistent prestore books to obtain the pre- books in stock of target
Nationality；
Wherein, step S16 finds the audio-frequency information matched with body text in database and included：
S161：The audio-frequency information that is matched with body text is found in database according to the target books that prestore.
Referring to Fig. 5, in some embodiments, control device 10 also includes finding module 11.Step S111 can be by
Control module 12 realizes that step S112 can be realized by identification module 14, and step S113 can be realized by searching module 11, step
S161 can be realized by matching module 16.
In other words, control module 12 is additionally operable to control the front cover of camera 20 shooting point reading nationality to obtain surface plot
Picture；Identification module 14 is additionally operable to identify the Periodical front cover information in cover image；Module 11 is found to be additionally operable to according to Periodical front cover information data
Found in storehouse and read that nationality is consistent to prestore books and prestored books to obtain target with point；Matching module 16 is further used for according to mesh
Mark the books that prestore and the audio-frequency information matched with body text is found in database.
It is appreciated that more point reading nationalitys are stored with database.If the matching of body text is directly carried out to carry out sound
The searching of frequency information, then the data volume of processing is too big needed for early learning machine 100, can not meet the need for the real-time that user uses
Ask.Therefore, user using during early learning machine 100, it is necessary to first carry out books title matching find and seal in the books that prestore
Information consistent target in face is prestored books, then directly prestored with the target word content of books of body text is matched to find
The audio-frequency information of target.In this way, early learning machine 100 directly finds target books by the matching of books title, now body text
Need to match is only the word content in target books, and the data volume of processing greatly reduces needed for early learning machine 100, finds sound
The time of frequency information greatly shortens, to meet real-time demand that user uses.
Referring to Fig. 6, in some embodiments, control method also includes：
S151：Identify the current page number in text image；
Step S16 finds the audio-frequency information matched with body text in database to be included：
S162：Books are prestored according to target and the current page number is found the audio matched with body text in database and believed
Breath.
Referring again to Fig. 5, in some embodiments, step S151 can be realized that step S162 can by identification module 14
To be realized by matching module 16.
In other words, identification module 14 is additionally operable to identify the current page number in text image；Matching module 16 is additionally operable to root
Books are prestored according to target and the current page number finds the audio-frequency information matched with body text in database.
It is appreciated that most of books all carry page-number marker.Find module 11 and search out target and prestore after books, identification
Module 14 identifies the current page number in text image, and matching module 16 prestores books according to target and the current page number carries out text
The matching of word is to find audio-frequency information.In this way, all word contents of the matching range of body text from a point reading nationality
Narrow down to a word content of reading nationality one page.In this way, the matching speed of body text is faster, matching process is shorter.Early education
Machine 100 can be quickly found the audio-frequency information of target and play out, and improve real-time and user experience.
Referring to Fig. 7, in some embodiments, the current page number in step S151 identification text images includes：
S1511：Digital information is filtered out from body text；
S1512：Text image is handled to orient the digit position where digital information；
S1513：Calculate the quantity of the blank pixel of digit position within a predetermined range；With
S1514：If quantity is more than predetermined number, it is determined that digital information is the current page number.
Referring to Fig. 8, in some embodiments, identification module 14 includes screening unit 141, positioning unit 142, calculated
Unit 143 and determining unit 144.Step S1511 can be realized that step S1512 can be by positioning unit by screening unit 141
142 are realized, step S1513 can be realized that step S1514 can be realized by determining unit 144 by computing unit 143.
In other words, screening unit 141 is used to filter out digital information from body text；Positioning unit 142 is used to locate
Text image is managed to orient the digit position where digital information；Computing unit 143 is used to calculate digit position in predetermined model
The quantity of blank pixel in enclosing；Determining unit 144 is used to determine that digital information is current page when quantity is more than predetermined number
Code.
Referring to Fig. 9, it is appreciated that region is generally not present it near current page number position in text image
His word, in other words, the adjacent pixels of current page number position are usually blank pixel, and the digital institute in body text
Region generally there are other words near position, and therefore, the quantity of blank pixel is typically less in adjacent pixels.Therefore,
Identify all digital informations in text by text image first, digital information includes page number word information and body text
Digital information.Then, the location of each digital information is oriented to carry out the judgement of the hollow number of white pixels of adjacent pixels.
It is the current page number that current digital information is can determine that when the quantity of blank pixel is more than predetermined number.So, it is determined that when
After the preceding page number, matching module 16 can prestore books according to target and the current page number is quickly found out the target matched with body text
Audio-frequency information.
Referring to Fig. 10, in some embodiments, control method also includes：
S152：Text image is handled to judge whether user's finger；
S153：When user's finger be present：Judge the point reading location at finger；With
S154：Body text is divided into by reading area and non-reading area with predetermined character area according to a reading location；
S155：When in the absence of user's finger：Determine that all body texts are reading area in text image；With
Step S16 finds the audio-frequency information matched with body text in database to be included：
S163：The audio-frequency information matched with the body text in reading area is found in database.
Refer to Figure 11, in some embodiments, control device 10 also include judge module 151, determination module 152,
Division module 153 and determining module 154.Step S152 can be realized that step S153 can be by determination module by determination module 151
152 are realized, step S154 can be realized that step S155 can be realized by determining module 154, step S163 by division module 153
It can be realized by matching module 16.
In other words, judge module 151 is used to handle text image to judge whether user's finger；Determination module
152 are used for when user's finger be present, judge the point reading location at finger；Division module 153 is used for according to a reading location with pre-
Determine character area and body text is divided into reading area and non-reading area；Determining module 154 is used in the absence of user's hand
During finger, determine that all body texts are reading area in text image；Matching module 16 is further used for finding in database
The audio-frequency information matched with the body text in reading area.
Figure 12 is referred to, user can point out to need a position read to realize the body text of the position by finger
Point is read to play.First, it is determined that module 151, which is detected in text image, whether there is finger.Have in some embodiments, Ke Yitong
Cross in skin color model detection text image and whether there is finger.Specifically, the text image of rgb format is converted into YCrCb lattice
The image of formula, it can be changed with below equation to calculate in text image each pixel in the coloured silk of YCrCb color spaces
Chromatic number evidence：Y=0.299R+0.587G+0.114B, Cr=0.500R+0.419G-0.081B+128, Cb=-0.169R-
0.331G+0.500B+128.Each pixel is detected in the image of YCrCb forms, if the picture of a predetermined level is exceeded
The color data of vegetarian refreshments falls into preset range, i.e. 133≤Cr≤173 and 77≤Cb≤127, then hand be present in clarifying text image
Refer to.Then, determination module 152 detects the point reading location at finger.It is determined that division module is with predetermined character area after point reading location
It is reading area and non-reading area to divide body text.Wherein, predetermined character area can be the signified point reading location of finger
Word segment before corresponding word or the word segment after word corresponding to the point reading location of finger meaning,
It can also be paragraph of the finger signified point corresponding to reading location where word.After marking off reading area and non-reading area,
Matching module 16 only carries out the matching of audio-frequency information to the body text part of reading area, so that player 30 plays read area
The audio-frequency information of the body text content in domain.If finger is not present in text image, determining module 154 is then determined in text image
All body texts be reading area, matching module 16 is matched to all body texts in text image to find
The audio-frequency information matched somebody with somebody, player 30 play the audio-frequency information of all body text contents.
In this way, user can carry out specifying for a word content read, free degree when lifting user uses, further carry
Rise Consumer's Experience.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress used with reference to these instruction execution systems, device or equipment
Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following：Electricity with one or more wiring
Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium, which can even is that, to print the paper of described program thereon or other are suitable
Medium, because can then enter edlin, interpretation or if necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, have suitable combinational logic gate circuit application specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that by program the hardware of correlation can be instructed to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and as independent production marketing or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although have been shown and retouch above
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (11)
1. a kind of control method, for early learning machine, it is characterised in that the early learning machine includes camera, player and is stored with
The database of audio-frequency information corresponding with a reading nationality, the control method include：
The camera shooting text for putting reading nationality is controlled to obtain text image；
Identify the body text in the text image；
The audio-frequency information matched with the body text is found in the database；With
Control audio-frequency information described in the player plays.
2. control method according to claim 1, it is characterised in that the database is also stored with the books that prestore, described
Control method also includes：
The camera shooting front cover for putting reading nationality is controlled to obtain cover image；
Identify the Periodical front cover information in the cover image；With
According to the Periodical front cover information find in the database with it is described point reading nationality it is consistent prestore books to obtain target
Prestore books；
Wherein, described the step of finding the audio-frequency information matched with the body text in the database, includes：
The audio-frequency information that is matched with the body text is found in the database according to the target books that prestore.
3. control method according to claim 2, it is characterised in that the control method also includes：
Identify the current page number in the text image；
Wherein, the step of finding the audio-frequency information matched with the body text in the database includes：
Books are prestored according to the target and the current page number finds what is matched with the body text in the database
Audio-frequency information.
4. control method according to claim 3, it is characterised in that the current page number in the identification text image
The step of include：
Digital information is filtered out from the body text；
The text image is handled to orient the digit position where the digital information；
Calculate the quantity of the blank pixel of the digit position within a predetermined range；With
If the quantity is more than predetermined number, it is determined that the digital information is the current page number.
5. according to control method described in Claims 1-4 any one, it is characterised in that the control method also includes：
The text image is handled to judge whether user's finger；
When the user's finger be present：
Judge the point reading location at the finger；With
The body text is divided into by reading area and non-reading area with predetermined character area according to described reading location；
When in the absence of the user's finger：
Determine that all body texts are reading area in the text image；With
Described the step of finding the audio-frequency information matched with the body text in the database, includes：
The audio-frequency information matched with the body text in the reading area is found in the database.
6. a kind of control device, for early learning machine, it is characterised in that the early learning machine includes camera, player and is stored with
The database of audio-frequency information corresponding with a reading nationality, the control device include：
Control module, the control module are used to control the camera shooting text for putting reading nationality to obtain positive texts and pictures
Picture；
Identification module, the identification module are used to identify the body text in the text image；
Matching module, the matching module are used to find the audio-frequency information matched with the body text in the database；
With
The control module is additionally operable to control audio-frequency information described in the player plays.
7. control device according to claim 6, it is characterised in that the database is also stored with the books that prestore, described
Control module is additionally operable to：
The camera shooting front cover for putting reading nationality is controlled to obtain cover image；
The identification module is additionally operable to identify the Periodical front cover information in the cover image；
The control device also includes finding module, and the searching module is used for according to the Periodical front cover information in the database
Find and read that nationality is consistent to prestore books and prestored books to obtain target with the point；
The matching module be further used for according to the target prestore books find in the database and the text text
The audio-frequency information of word matching.
8. control device according to claim 7, it is characterised in that the identification module is additionally operable to：
Identify the current page number in the text image；
The matching module is further used for：
Books are prestored according to the target and the current page number finds what is matched with the body text in the database
Audio-frequency information.
9. control device according to claim 8, it is characterised in that the identification module includes：
Screening unit, the screening unit are used to filter out digital information from the body text；
Positioning unit, the positioning unit are used to handle the text image to orient the digit order number where the digital information
Put；
Computing unit, the computing unit are used for the quantity for calculating the blank pixel of the digit position within a predetermined range；With
Determining unit, the determining unit are used to determine that the digital information is worked as to be described when the quantity is more than predetermined number
The preceding page number.
10. according to the control device described in claim 6 to 9 any one, it is characterised in that the control device also includes：
Judge module, the judge module are used to handle the text image to judge whether user's finger；
Determination module, the determination module are used to judge the point reading location at the finger when the user's finger be present；With
Division module, the division module are used to be divided the body text with predetermined character area according to described reading location
For reading area and non-reading area；
The control device also includes determining module, and the determining module is used for when in the absence of the user's finger described in determination
All body texts are reading area in text image；With
The matching module is further used for finding in the database and the body text in the reading area
The audio-frequency information matched somebody with somebody.
11. a kind of early learning machine, it is characterised in that the early learning machine includes：
Camera；
Player；With
Control device described in claim 6 to 10 any one, the control device and the camera and the player are equal
Electrical connection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710223596.5A CN107393356A (en) | 2017-04-07 | 2017-04-07 | Control method, control device and early learning machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710223596.5A CN107393356A (en) | 2017-04-07 | 2017-04-07 | Control method, control device and early learning machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107393356A true CN107393356A (en) | 2017-11-24 |
Family
ID=60338901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710223596.5A Pending CN107393356A (en) | 2017-04-07 | 2017-04-07 | Control method, control device and early learning machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107393356A (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037882A (en) * | 2017-11-29 | 2018-05-15 | 佛山市因诺威特科技有限公司 | A kind of reading method and system |
| CN108665742A (en) * | 2018-05-11 | 2018-10-16 | 亮风台（上海）信息科技有限公司 | A kind of method and apparatus read by arrangement for reading |
| CN108665764A (en) * | 2018-05-11 | 2018-10-16 | 亮风台（上海）信息科技有限公司 | A kind of method and apparatus read by arrangement for reading |
| CN108681389A (en) * | 2018-05-11 | 2018-10-19 | 亮风台（上海）信息科技有限公司 | A kind of method and apparatus read by arrangement for reading |
| CN109035908A (en) * | 2018-07-27 | 2018-12-18 | 安徽豆智智能装备制造有限公司 | Interact reading method |
| CN109064787A (en) * | 2018-07-17 | 2018-12-21 | 广东小天才科技有限公司 | Point reading equipment |
| CN109255346A (en) * | 2018-08-31 | 2019-01-22 | 深圳闳宸科技有限公司 | Reading method, device and electronic equipment |
| CN109545009A (en) * | 2018-09-30 | 2019-03-29 | 与德科技有限公司 | A kind of reading method and a kind of server data processing method based on talking pen |
| CN109657095A (en) * | 2018-12-19 | 2019-04-19 | 广州绿桦环保科技有限公司 | Equipment that a kind of intelligence listens to storytelling method and intelligence is listened to storytelling |
| CN110032994A (en) * | 2019-06-10 | 2019-07-19 | 上海肇观电子科技有限公司 | Character detecting method, reading aids, circuit and medium |
| CN110059678A (en) * | 2019-04-17 | 2019-07-26 | 上海肇观电子科技有限公司 | A kind of detection method, device and computer readable storage medium |
| CN111079777A (en) * | 2019-06-09 | 2020-04-28 | 广东小天才科技有限公司 | Page positioning-based point reading method and electronic equipment |
| CN111079495A (en) * | 2019-06-09 | 2020-04-28 | 广东小天才科技有限公司 | Point reading mode starting method and electronic equipment |
| CN111083434A (en) * | 2019-05-15 | 2020-04-28 | 广东小天才科技有限公司 | Method for starting dictation detection and electronic equipment |
| CN111078982A (en) * | 2019-06-09 | 2020-04-28 | 广东小天才科技有限公司 | Electronic page retrieval method, electronic device and storage medium |
| CN111276017A (en) * | 2020-01-21 | 2020-06-12 | 上海万得维进出口有限公司 | System and method for realizing self-service home-default control for students based on intelligent marks |
| CN111353501A (en) * | 2020-02-25 | 2020-06-30 | 暗物智能科技(广州)有限公司 | Book point-reading method and system based on deep learning |
| CN111524507A (en) * | 2019-01-16 | 2020-08-11 | 北京字节跳动网络技术有限公司 | Voice information feedback method, device, equipment, server and storage medium |
| CN111610901A (en) * | 2020-05-11 | 2020-09-01 | 上海翎腾智能科技有限公司 | AI vision-based English lesson auxiliary teaching method and system |
| US10796187B1 (en) | 2019-06-10 | 2020-10-06 | NextVPU (Shanghai) Co., Ltd. | Detection of texts |
| CN112132127A (en) * | 2020-08-10 | 2020-12-25 | 北京网梯科技发展有限公司 | Method and device for realizing automatic book switching in point reading |
| CN112464872A (en) * | 2020-12-11 | 2021-03-09 | 广东电网有限责任公司 | Automatic extraction method and device based on NLP (non-line segment) natural language |
| CN112721500A (en) * | 2021-01-15 | 2021-04-30 | 盐城工学院 | Multifunctional teaching aid |
| JP2021129299A (en) * | 2020-02-11 | 2021-09-02 | ネクストヴイピーユー(シャンハイ)カンパニー リミテッドNextvpu(Shanghai)Co., Ltd. | Image text broadcast method and device, electronic circuit, and storage medium |
| CN114429632A (en) * | 2020-10-15 | 2022-05-03 | 腾讯科技（深圳）有限公司 | Method and device for identifying point-reading content, electronic equipment and computer storage medium |
| US11776286B2 (en) | 2020-02-11 | 2023-10-03 | NextVPU (Shanghai) Co., Ltd. | Image text broadcasting |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2701637Y (en) * | 2003-11-13 | 2005-05-25 | 深圳市御天电子有限公司 | Sound electronic book |
| CN102938061A (en) * | 2012-12-05 | 2013-02-20 | 上海合合信息科技发展有限公司 | Convenient and electronic professional laptop and automatic page number identification method thereof |
| CN103761892A (en) * | 2014-01-20 | 2014-04-30 | 广东小天才科技有限公司 | Method and device for playing paper book contents in voice mode |
| CN104157171A (en) * | 2014-08-13 | 2014-11-19 | 三星电子（中国）研发中心 | Point-reading system and method thereof |
| CN104217197A (en) * | 2014-08-27 | 2014-12-17 | 华南理工大学 | Touch reading method and device based on visual gestures |
| WO2016082895A1 (en) * | 2014-11-28 | 2016-06-02 | Longsand Limited | Method and system for displaying recognized text according to a speed reading pattern |
-
2017
- 2017-04-07 CN CN201710223596.5A patent/CN107393356A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2701637Y (en) * | 2003-11-13 | 2005-05-25 | 深圳市御天电子有限公司 | Sound electronic book |
| CN102938061A (en) * | 2012-12-05 | 2013-02-20 | 上海合合信息科技发展有限公司 | Convenient and electronic professional laptop and automatic page number identification method thereof |
| CN103761892A (en) * | 2014-01-20 | 2014-04-30 | 广东小天才科技有限公司 | Method and device for playing paper book contents in voice mode |
| CN104157171A (en) * | 2014-08-13 | 2014-11-19 | 三星电子（中国）研发中心 | Point-reading system and method thereof |
| CN104217197A (en) * | 2014-08-27 | 2014-12-17 | 华南理工大学 | Touch reading method and device based on visual gestures |
| WO2016082895A1 (en) * | 2014-11-28 | 2016-06-02 | Longsand Limited | Method and system for displaying recognized text according to a speed reading pattern |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037882A (en) * | 2017-11-29 | 2018-05-15 | 佛山市因诺威特科技有限公司 | A kind of reading method and system |
| CN108665742A (en) * | 2018-05-11 | 2018-10-16 | 亮风台（上海）信息科技有限公司 | A kind of method and apparatus read by arrangement for reading |
| CN108665764A (en) * | 2018-05-11 | 2018-10-16 | 亮风台（上海）信息科技有限公司 | A kind of method and apparatus read by arrangement for reading |
| CN108681389A (en) * | 2018-05-11 | 2018-10-19 | 亮风台（上海）信息科技有限公司 | A kind of method and apparatus read by arrangement for reading |
| CN108681389B (en) * | 2018-05-11 | 2021-12-14 | 亮风台（上海）信息科技有限公司 | Method and device for reading through reading device |
| CN109064787A (en) * | 2018-07-17 | 2018-12-21 | 广东小天才科技有限公司 | Point reading equipment |
| CN109035908A (en) * | 2018-07-27 | 2018-12-18 | 安徽豆智智能装备制造有限公司 | Interact reading method |
| CN109255346A (en) * | 2018-08-31 | 2019-01-22 | 深圳闳宸科技有限公司 | Reading method, device and electronic equipment |
| CN109545009A (en) * | 2018-09-30 | 2019-03-29 | 与德科技有限公司 | A kind of reading method and a kind of server data processing method based on talking pen |
| CN109657095A (en) * | 2018-12-19 | 2019-04-19 | 广州绿桦环保科技有限公司 | Equipment that a kind of intelligence listens to storytelling method and intelligence is listened to storytelling |
| CN111524507A (en) * | 2019-01-16 | 2020-08-11 | 北京字节跳动网络技术有限公司 | Voice information feedback method, device, equipment, server and storage medium |
| CN110059678A (en) * | 2019-04-17 | 2019-07-26 | 上海肇观电子科技有限公司 | A kind of detection method, device and computer readable storage medium |
| CN111083434A (en) * | 2019-05-15 | 2020-04-28 | 广东小天才科技有限公司 | Method for starting dictation detection and electronic equipment |
| CN111079495A (en) * | 2019-06-09 | 2020-04-28 | 广东小天才科技有限公司 | Point reading mode starting method and electronic equipment |
| CN111078982A (en) * | 2019-06-09 | 2020-04-28 | 广东小天才科技有限公司 | Electronic page retrieval method, electronic device and storage medium |
| CN111079495B (en) * | 2019-06-09 | 2024-03-22 | 广东小天才科技有限公司 | Click-to-read mode starting method and electronic equipment |
| CN111079777A (en) * | 2019-06-09 | 2020-04-28 | 广东小天才科技有限公司 | Page positioning-based point reading method and electronic equipment |
| CN111078982B (en) * | 2019-06-09 | 2023-11-24 | 广东小天才科技有限公司 | Electronic page retrieval method, electronic device and storage medium |
| CN111079777B (en) * | 2019-06-09 | 2023-10-27 | 广东小天才科技有限公司 | Page positioning-based click-to-read method and electronic equipment |
| US10796187B1 (en) | 2019-06-10 | 2020-10-06 | NextVPU (Shanghai) Co., Ltd. | Detection of texts |
| WO2020248346A1 (en) * | 2019-06-10 | 2020-12-17 | 上海肇观电子科技有限公司 | Detection of characters |
| CN110032994A (en) * | 2019-06-10 | 2019-07-19 | 上海肇观电子科技有限公司 | Character detecting method, reading aids, circuit and medium |
| CN111276017A (en) * | 2020-01-21 | 2020-06-12 | 上海万得维进出口有限公司 | System and method for realizing self-service home-default control for students based on intelligent marks |
| JP2021129299A (en) * | 2020-02-11 | 2021-09-02 | ネクストヴイピーユー(シャンハイ)カンパニー リミテッドNextvpu(Shanghai)Co., Ltd. | Image text broadcast method and device, electronic circuit, and storage medium |
| US11776286B2 (en) | 2020-02-11 | 2023-10-03 | NextVPU (Shanghai) Co., Ltd. | Image text broadcasting |
| CN111353501A (en) * | 2020-02-25 | 2020-06-30 | 暗物智能科技(广州)有限公司 | Book point-reading method and system based on deep learning |
| CN111610901A (en) * | 2020-05-11 | 2020-09-01 | 上海翎腾智能科技有限公司 | AI vision-based English lesson auxiliary teaching method and system |
| CN112132127A (en) * | 2020-08-10 | 2020-12-25 | 北京网梯科技发展有限公司 | Method and device for realizing automatic book switching in point reading |
| CN114429632A (en) * | 2020-10-15 | 2022-05-03 | 腾讯科技（深圳）有限公司 | Method and device for identifying point-reading content, electronic equipment and computer storage medium |
| CN114429632B (en) * | 2020-10-15 | 2023-12-12 | 腾讯科技（深圳）有限公司 | Method, device, electronic equipment and computer storage medium for identifying click-to-read content |
| CN112464872A (en) * | 2020-12-11 | 2021-03-09 | 广东电网有限责任公司 | Automatic extraction method and device based on NLP (non-line segment) natural language |
| CN112721500A (en) * | 2021-01-15 | 2021-04-30 | 盐城工学院 | Multifunctional teaching aid |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107393356A (en) | Control method, control device and early learning machine | |
| CN108765278B (en) | Image processing method, mobile terminal and computer readable storage medium | |
| Koo et al. | Scene text detection via connected component clustering and nontext filtering | |
| US9779295B2 (en) | Systems and methods for note content extraction and management using segmented notes | |
| KR100914515B1 (en) | Color classification method for color based image code recognition | |
| CN110991533B (en) | Image recognition method, recognition device, terminal device and readable storage medium | |
| US12124535B1 (en) | Systems, methods, and storage media for training a model for image evaluation | |
| CN103198316A (en) | Method, apparatus and system for identifying distracting elements in an image | |
| CN106557549A (en) | Method and device for identifying target object | |
| CN107682685A (en) | White balancing treatment method and device, electronic installation and computer-readable recording medium | |
| CN110070080A (en) | A kind of character detecting method and device, equipment and computer readable storage medium | |
| CN109919164B (en) | User interface object identification method and device | |
| CN110135412A (en) | Business card identification method and device | |
| Thyagharajan et al. | Prevalent color extraction and indexing | |
| CN107704884A (en) | Image tag processing method, image tag processing unit and electric terminal | |
| Fadhel et al. | Recognition of the unripe strawberry by using color segmentation techniques | |
| CN114998614B (en) | Image processing method, device and equipment and readable storage medium | |
| CN108229263B (en) | Target object identification method and device and robot | |
| Leonardis et al. | Computer Vision--ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006, Proceedings, Part I | |
| CN113837236A (en) | Method and device for identifying target object in image, terminal equipment and storage medium | |
| CN110674720A (en) | Picture identification method and device, electronic equipment and storage medium | |
| CN113344097B (en) | Image processing method and device based on multiple models | |
| KR102614062B1 (en) | Method and apparatus for quarantine of imported ornamental fish through data preprocessing and deep neural network-based image detection and classification | |
| CN111626074A (en) | Face classification method and device | |
| WO2024092957A1 (en) | Text area determination method and system, and related apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171124 |
|
| RJ01 | Rejection of invention patent application after publication |