CN101799996B - Click-reading method of click-reading machine based on video image - Google Patents
Click-reading method of click-reading machine based on video image Download PDFInfo
- Publication number
- CN101799996B CN101799996B CN 201010122524 CN201010122524A CN101799996B CN 101799996 B CN101799996 B CN 101799996B CN 201010122524 CN201010122524 CN 201010122524 CN 201010122524 A CN201010122524 A CN 201010122524A CN 101799996 B CN101799996 B CN 101799996B
- Authority
- CN
- China
- Prior art keywords
- books
- click
- image
- reading
- utilize
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to a click-reading method of a click-reading machine based on a video image, which is characterized in that: the steps of the method are that: (1) real time obtain video images of a click-reading pen and a book by a video camera; (2) lightly click a switch by the pen point of the click-reading pen and input the image to a microprocessor; (3) carry out correction to the edge contour of the book; (4) build a book coordinate system; (5) obtain the rod type characteristic of the click-reading pen by utilizing a maximum connected domain method; (6) obtain the pen point location of the click-reading pen by utilizing a line scanning method according to the rod type characteristic of the click-reading pen; (7) mark the image coordinates by utilizing the length and width values of a known book and the pixel values of the length and the width of the book in the image; (8) calculate the pen point coordinates of the click-reading pen by utilizing the mark result in the book coordinate system; (9) realize the click-reading of the click-reading machine based on the video image. The invention has the advantages that: the click-reading function of the click-reading machine is realized by utilizing the video camera, the click-reading pen and the micro processor; the noise after the image binarization and the interference of other non-target object are effectively removed by utilizing the maximum connected domain method; the click-reading machine has the advantages of being simple and practical, being convenient to carry, having good generality and high click-reading precision.
Description
Technical field
The present invention relates to a kind of click-reading method of click-reading machine, relate in particular to a kind of click-reading method of click-reading machine based on video image.
Background technology
Point reader (is called again the intelligent computer book reading machine, English interactive electronic textbook, synchronous book reading machine, the mechanical, electrical philosophical works of English Intelligent point-reading, electronic textbook etc.) be the study product of a kind of sound interaction of modern digital infotech and up-to-date teaching demand perfect adaptation, it can become the books teaching material of literal the Sound teaching material that can need by study any sounding.
In recent years, point reader has entered rapidly the home market, develops into one of main aid of domestic and international children for learning.At present popular point reader adopts pressure sensitive method acquisition point coordinate reading, realizes read-on-command function.Its reading principle is: the pressure transducer of placing dot matrix way in the pressure sensitive panel, utilize the method for horizontal ordinate and ordinate scanning to obtain the position (being x and y coordinate figure) of talking pen reading on the pressure sensitive panel, microprocessor receives the reading instruction, and reading coordinate conversion on the pressure sensitive panel become corresponding books coordinate, read corresponding voice document, realized read-on-command function.Adopt the point reader of pressure sensitive method, have the high advantage of reading precision, but since its pressure sensitive panel need the plastic casing protection and hold the books of all size, thereby bulky, Heavy Weight, carry inconvenience; The point reader that different manufacturers is produced, even the point reader of same producer different model all need special-purpose pressure sensitive panel, and versatility is poor.
Summary of the invention
The object of the present invention is to provide a kind of click-reading method of click-reading machine based on video image, this reading method is simple and practical, easy to carry, versatility is good, and has higher point and read precision.
The present invention is achieved like this, and it is characterized in that method step is:
(1) video image of usefulness video frequency pick-up head Real-time Obtaining talking pen and books;
(2) utilize the nib touch-switch of talking pen, trigger microprocessor and catch single-frame images, and this image is input in the microprocessor;
(3) utilize first edge detection operator and thresholding method with image binaryzation, adopt again image expansion, Image erosion, image filtering and largest connected territory method to get rid of the interference of non-target object, accurately extract the edge contour of books, and the books edge contour is proofreaied and correct;
(4) utilize the books edge contour to obtain the pixel value of books length and width, and set up the books coordinate system;
(5) first according to the colouring information of talking pen, utilize thresholding method with image binaryzation, adopt again largest connected territory method to obtain the shaft-like feature of talking pen;
(6) according to the shaft-like feature of talking pen, utilize the line scanning method to obtain the pen tip position of talking pen;
(7) utilize the pixel value of books length and width in the length and width value of known books and the image, image coordinate is demarcated;
(8) under the books coordinate system, utilize calibration result to calculate the nib coordinate of talking pen;
(9) according to the coordinate figure of nib under the books coordinate system, access corresponding voice messaging, thereby realized the point reader reading based on video image.
Utilize video frequency pick-up head, talking pen and microprocessor to realize the read-on-command function of point reader.
Described talking pen has the penholder of special color, and nib has touch-switch, can produce signal during switch triggering and also can be identified and receive by microprocessor.
Principle is: the video image that utilizes video frequency pick-up head Real-time Obtaining talking pen and books; Utilize Image Edge-Detection operator and thresholding method with image binaryzation, the books edge contour is split from background, for accurately extracting the books edge contour, adopt image expansion and burn into image filtering and largest connected territory method to eliminate background and noise; Adopt least square fitting method to obtain the coboundary straight line of books, calculate the coboundary straight line of books and the angle of horizontal direction, and utilize this angle to proofread and correct the books edge contour; On this basis, the recycling least square fitting method obtains the edge line of books, and sets up the books coordinate system; Special colouring information according to talking pen utilizes thresholding method with image binaryzation, and adopts largest connected territory method to extract the position of profile and definite its nib of talking pen; Utilize the pixel value of books length and width in the length and width value of known books and the image, image coordinate is demarcated; Utilize calibration result to calculate the nib coordinate of talking pen, the coordinate figure of nib under the books coordinate system according to talking pen accesses corresponding voice messaging, realizes the point reader reading based on video image.
Advantage of the present invention is: utilize largest connected territory method effectively to get rid of the interference of the noise behind the image binaryzation and other non-target objects; Utilize least square fitting method to obtain the edge line equation of books, accurately detect the edge contour of books; Utilize the shaft-like feature of the special color Obtaining Accurate talking pen of talking pen; Adopt said method to improve the reading precision, utilize video frequency pick-up head, talking pen and microprocessor realization based on the point reader read-on-command function of video image.Therefore, the point reader based on video image has advantage simple and practical, easy to carry, that versatility is good, the reading precision is high.
Description of drawings
Fig. 1 is workflow diagram of the present invention.
Embodiment
The inventive method requires to support common wide-angle camera with simple beam and enables vertical shooting, only have single books in the scene of taking, and can comprise whole book fully, background in the scene is common any monochromatic desktop, talking pen in the scene is that pure color and nib have touch-switch, microprocessor can receive the signal that produces when the nib touch-switch triggers, and the control camera obtains image.Simultaneously, the actual length and width of books should be known.
The present invention adopts the process flow diagram based on the click-reading method of click-reading machine of video image as shown in Figure 1, carries out the some reading location Measurement accuracy of point reader and reads corresponding voice, and its implementation step is as follows:
1, video image Real-time Obtaining
The correct position in books dead ahead, the video image of Real-time Obtaining talking pen and books will be placed on standoff camera.
2, whether the nib touch-switch triggers
Judge whether the nib exploitation triggers, if trigger, then microprocessor is carried out the single-frame images collection of talking pen and books, otherwise, wait for reading.
3, single-frame images collection
When the talking pen reading, the touch-switch on the nib triggers, and produce signal and import microprocessor into, control camera collection single-frame images data, and in the input microprocessor.
4, the profile of books extracts and proofreaies and correct
The single-frame images that the 3rd step was obtained carries out edge contour extraction and the correction of books, and its key step is as follows:
1) utilize edge detection operator to extract the marginal information of books, wherein edge detection operator can be used Canny, Robert or Sobel.
2) adopt threshold method that image is carried out binaryzation, and adopt image expansion, Image erosion, image filtering and largest connected territory method to get rid of the interference of non-target object, accurately extract the edge contour of books.
3) adopt vertical scanning method and twice least square fitting method to obtain the coboundary straight line of books after, calculate the angle α of this straight line and horizontal direction, with the image α angle that turns clockwise, finished the correction of image.
Twice least square fitting method is as follows:
At first, the coboundary point set of books is carried out first time least square fitting method obtain the coboundary straight-line equation, secondly, calculation level concentrates at every to the distance of this straight line and by from small to large ordering, remove point set middle distance 1/2nd point far away, got rid of the impact of noise spot, last, utilize the concentrated remaining point of this point to carry out second time least square fitting method and obtain the coboundary straight line.
5, the foundation of books coordinate system
Utilize corrected books edge contour image of the 4th step, the key step of setting up the books coordinate system is as follows:
1) utilizes the books summit to divide and be clipped to the shortest feature of respective image vertex distance, determine upper left and upper right two vertex positions of books, and calculate the pixel value of books length of upper edge, be the long pixel value of books.
2) utilize the books coboundary straight-line equation of books left upper apex position and the acquisition of the 4th step, and utilize the books coboundary feature vertical with left hand edge, calculate books left hand edge straight-line equation.
3) pixel value of known books length and width value and the books length of upper edge that obtains calculates the pixel value of books lower-left vertex position and left hand edge length, is the wide pixel value of books.
4) take left upper apex as initial point, take books coboundary straight line and left hand edge straight line as coordinate system x axle and y axle, set up the books coordinate system respectively.
6, the shaft-like feature extraction of talking pen and pen tip position thereof are determined
The present invention utilizes the special color of talking pen to extract the shaft-like feature of talking pen, and obtains its pen tip position with scanning method, and its key step is as follows:
1) utilizes the redness (or blue, green etc.) of talking pen, and with thresholding method the edge contour of talking pen is separated from image.
2) adopt largest connected territory method to remove other and disturb, extract the shaft-like feature of talking pen.
3) adopt the line scanning method to obtain pen tip position, if the right hand is held talking pen, then the pen tip position of talking pen is obtained in from left to right scanning; If left hand is held talking pen, then the pen tip position of talking pen is obtained in from right to left scanning.
7, the nib coordinate Calculation of image coordinate demarcation and talking pen
Utilize the pixel value of books length and width in the length and width value of known books and the image, image coordinate is demarcated, namely obtain the corresponding actual coordinate value of each pixel in the image.Utilize the pen tip position of calibration result and the acquisition of the 6th step, calculate the nib coordinate of talking pen.
8, read-on-command function is realized
Nib coordinate according to talking pen accesses corresponding voice messaging, has realized the point reader read-on-command function based on video image.
Claims (3)
1. click-reading method of click-reading machine based on video image is characterized in that method step is:
(1) video image of usefulness video frequency pick-up head Real-time Obtaining talking pen and books;
(2) utilize the nib touch-switch of talking pen, when the talking pen reading, the touch-switch on the nib triggers, and produce signal and import microprocessor into, control camera collection single-frame images data, and this image is input in the microprocessor;
(3) utilize first edge detection operator and thresholding method with image binaryzation, adopt again image expansion, Image erosion, image filtering and largest connected territory method to get rid of the interference of non-target object, accurately extract the edge contour of books, and the books edge contour is proofreaied and correct; The key step that the books profile extracts and proofreaies and correct is: at first, utilize the marginal information of edge detection operator extraction books, wherein edge detection operator Canny, Robert or Sobel; Secondly, adopt threshold method that image is carried out binaryzation, and adopt image expansion, Image erosion, image filtering and largest connected territory method to get rid of the interference of non-target object, accurately extract the edge contour of books; At last, adopt vertical scanning method and twice least square fitting method to obtain the coboundary straight line of books after, calculate the angle α of this straight line and horizontal direction, with the image α angle that turns clockwise, finished the correction of image;
(4) utilize the books edge contour to obtain the pixel value of books length and width, and set up the books coordinate system; The step of books establishment of coordinate system is:
1) utilizes the books summit to divide and be clipped to the shortest feature of respective image vertex distance, determine upper left and upper right two vertex positions of books, and calculate the pixel value of books length of upper edge, be the long pixel value of books;
2) utilize books left upper apex position and acquired books coboundary straight-line equation, and utilize the books coboundary feature vertical with left hand edge, calculate books left hand edge straight-line equation;
3) pixel value of known books length and width value and the books length of upper edge that obtains calculates the pixel value of books lower-left vertex position and left hand edge length, is the wide pixel value of books;
4) take left upper apex as initial point, take books coboundary straight line and left hand edge straight line as coordinate system x axle and y axle, set up the books coordinate system respectively;
(5) first according to the colouring information of talking pen, utilize thresholding method with image binaryzation, adopt again largest connected territory method to obtain the shaft-like feature of talking pen;
(6) according to the shaft-like feature of talking pen, utilize the line scanning method to obtain the pen tip position of talking pen;
(7) utilize the pixel value of books length and width in the length and width value of known books and the image, image coordinate is demarcated;
(8) under the books coordinate system, utilize calibration result to calculate the nib coordinate of talking pen;
(9) according to the coordinate figure of nib under the books coordinate system, access corresponding voice messaging, thereby realized the point reader reading based on video image.
2. a kind of click-reading method of click-reading machine based on video image according to claim 1 is characterized in that: utilize video frequency pick-up head, talking pen and microprocessor to realize the read-on-command function of point reader.
3. a kind of click-reading method of click-reading machine based on video image according to claim 1 is characterized in that described talking pen has the penholder of special color, and nib has touch-switch, can produce signal during switch triggering and also can be identified and receive by microprocessor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010122524 CN101799996B (en) | 2010-03-11 | 2010-03-11 | Click-reading method of click-reading machine based on video image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010122524 CN101799996B (en) | 2010-03-11 | 2010-03-11 | Click-reading method of click-reading machine based on video image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101799996A CN101799996A (en) | 2010-08-11 |
| CN101799996B true CN101799996B (en) | 2013-04-10 |
Family
ID=42595664
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010122524 Expired - Fee Related CN101799996B (en) | 2010-03-11 | 2010-03-11 | Click-reading method of click-reading machine based on video image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101799996B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390163B (en) * | 2012-05-10 | 2016-12-14 | 中邮科技有限责任公司 | A kind of Post address automatic acquiring method |
| CN104835361B (en) * | 2014-02-10 | 2018-05-08 | 陈旭 | A kind of electronic dictionary |
| CN104050838B (en) * | 2014-07-15 | 2016-06-08 | 北京网梯科技发展有限公司 | A kind of point-of-reading system, equipment and method that can identify the common printed thing with reading |
| CN104157171B (en) * | 2014-08-13 | 2016-11-09 | 三星电子（中国）研发中心 | A kind of point-of-reading system and method thereof |
| CN104217197B (en) * | 2014-08-27 | 2018-04-13 | 华南理工大学 | A kind of reading method and device of view-based access control model gesture |
| CN104766501B (en) * | 2015-04-09 | 2017-07-14 | 广东小天才科技有限公司 | A kind of point reader and its method for correcting coordinate |
| CN107066919B (en) * | 2016-12-21 | 2020-09-29 | 网易（杭州）网络有限公司 | Method, apparatus and computer-readable storage medium for solving pen tip position |
| CN107765978A (en) * | 2017-09-26 | 2018-03-06 | 张超 | A kind of method and recognizing apparatus for object top layer marker location information |
| CN109360454A (en) * | 2018-09-30 | 2019-02-19 | 与德科技有限公司 | A kind of reading method |
| CN109545006B (en) * | 2018-12-29 | 2019-10-01 | 钟意 | A kind of teaching electronic reader |
| CN111078083A (en) * | 2019-06-09 | 2020-04-28 | 广东小天才科技有限公司 | Method for determining click-to-read content and electronic equipment |
| CN110767000A (en) * | 2019-10-28 | 2020-02-07 | 安徽信捷智能科技有限公司 | Children's course synchronizer based on image recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201159944Y (en) * | 2008-03-06 | 2008-12-03 | 东莞市步步高教育电子产品有限公司 | Point reading machine |
| CN201194112Y (en) * | 2008-05-12 | 2009-02-11 | 刘建生 | Video shooting type multifunctional click-to-read machine |
| CN201345173Y (en) * | 2009-02-05 | 2009-11-11 | 刘建生 | Point reading and learning machine based on optical identification |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10156040B4 (en) * | 2001-11-15 | 2005-03-31 | Océ Document Technologies GmbH | Method, apparatus and computer program product for equalizing a scanned image |
| US7190834B2 (en) * | 2003-07-22 | 2007-03-13 | Cognex Technology And Investment Corporation | Methods for finding and characterizing a deformed pattern in an image |
-
2010
- 2010-03-11 CN CN 201010122524 patent/CN101799996B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201159944Y (en) * | 2008-03-06 | 2008-12-03 | 东莞市步步高教育电子产品有限公司 | Point reading machine |
| CN201194112Y (en) * | 2008-05-12 | 2009-02-11 | 刘建生 | Video shooting type multifunctional click-to-read machine |
| CN201345173Y (en) * | 2009-02-05 | 2009-11-11 | 刘建生 | Point reading and learning machine based on optical identification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101799996A (en) | 2010-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101799996B (en) | Click-reading method of click-reading machine based on video image | |
| CN103530881B (en) | Be applicable to the Outdoor Augmented Reality no marks point Tracing Registration method of mobile terminal | |
| CN102902355B (en) | The space interaction method of mobile device | |
| CN104050838B (en) | A kind of point-of-reading system, equipment and method that can identify the common printed thing with reading | |
| CN106384355B (en) | A kind of automatic calibration method in projection interactive system | |
| CN101033962B (en) | Measurement method for displacement of model experiment based on optics | |
| CN101976464B (en) | Multi-plane dynamic augmented reality registration method based on homography matrix | |
| CN104885098A (en) | Mobile device based text detection and tracking | |
| WO2008099915A1 (en) | Road/feature measuring device, feature identifying device, road/feature measuring method, road/feature measuring program, measuring device, measuring method, measuring program, measured position data, measuring terminal, measuring server device, drawing device, drawing method, drawing program, and drawing data | |
| CN101137003A (en) | Gray associated analysis based sub-pixel fringe extracting method | |
| CN105513082A (en) | Method and device for identifying and counting number of rods in bundle | |
| CN106204633B (en) | Student tracking method and device based on computer vision | |
| CN103617642B (en) | A kind of digital book drawing method and device | |
| CN104517101A (en) | Game poker card recognition method based on pixel square difference matching | |
| CN103886107A (en) | Robot locating and map building system based on ceiling image information | |
| CN106097433A (en) | Object industry and the stacking method of Image model and system | |
| CN102722254A (en) | Method and system for location interaction | |
| CN104460951A (en) | Human-computer interaction method | |
| CN101188020A (en) | Method for precisely getting pixel geometric location mapping relation between projector image and computer frame buffer image | |
| CN111399634B (en) | Method and device for recognizing gesture-guided object | |
| CN103116892A (en) | Linear solving of video camera internal parameters by utilizing two intersected same circles and common tangent | |
| CN106403901A (en) | Measuring apparatus and method for attitude of buoy | |
| CN112033408A (en) | Paper-pasted object space positioning system and positioning method | |
| CN114627186A (en) | Distance measuring method and distance measuring device | |
| CN107705641B (en) | A kind of point reads the device and method of common printed reading matter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130410 Termination date: 20150311 |
|
| EXPY | Termination of patent right or utility model |