CN102750555A - Expression robot applied to instant messaging tool - Google Patents
Expression robot applied to instant messaging tool Download PDFInfo
- Publication number
- CN102750555A CN102750555A CN2012102244961A CN201210224496A CN102750555A CN 102750555 A CN102750555 A CN 102750555A CN 2012102244961 A CN2012102244961 A CN 2012102244961A CN 201210224496 A CN201210224496 A CN 201210224496A CN 102750555 A CN102750555 A CN 102750555A
- Authority
- CN
- China
- Prior art keywords
- emoticon
- module
- expression
- image
- chat window
- 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.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an expression robot applied to an instant messaging tool. The expression robot can recognize expression marks used by users in real time and can make same responses as the meaning represented by the expression marks. In addition, an expression recognizing method overcomes the defects that the complexity degree is high, the real-time performance is poor, and a secret key needs to be decoded again after the instant messaging tool is updated. In a system, a chat window monitoring module intercepts chat window images as pictures and stores the pictures when the instant messaging tool has new chat message display, or the chat window monitoring module regularly is timed to intercept the chat window images as pictures and to store the pictures; an expression mark positioning module finds expression marks in the intercepted pictures, and the positions of the expression marks are sent to an expression mark recognizing module; the expression mark recognizing module comprises the positions of the expression marks and expression marks in the existing expression mark bank, and the meanings of the expression marks are determined and are sent to a response module; and the response module makes responses in set expression modes after receiving results sent by the expression mark recognizing module.
Description
Technical field
The present invention is a kind of expression robot based on immediate communication tool, is specifically related to screen capture, image recognition technology field.
Background technology
Immediate communication tool is called instant messenger again, is a kind of service based on the internet, through ten years development, has nowadays had a large amount of fixed-line subscribers, is penetrated into the every aspect in our live and work.Emoticon is born in the internet, is a kind of network subculture originally, but along with the developing rapidly and popularizing of network, it has obtained accepting extensively of people.
General immediate communication tool all has the function of inserting emoticon, has greatly made things convenient for user's expression, has strengthened interchange enjoyment and user experience.At present, emoticon is mainly towards more polynary, and more lively and complicated direction develops, and the present invention proposes a creationary road for development: let emoticon actualization more.This scheme can be monitored the window interface of immediate communication tool, discerns the implication of the emoticon of user's use then, and makes the response that meets this emoticon implication to the emoticon that is identified.Can experience employed emoticon in the chat process more intuitively through the expression user of robot, increase the experience sense and the enjoyment of instant communication user thus.This is the product of a novelty, rarely has the reference to forefathers' experience.
When carrying out the design of emoticon identifying schemes, what at first expect is that the immediate communication tool data packets for transmission is carried out cryptanalysis, therefrom extracts the code of emoticon, thereby realizes identification.But present immediate communication tool all can carry out very complicated the encryption to it in the transport process of chat content; Decoding key needs the long time, and difficulty is bigger, and the immediate communication tool irregular upgrading of meeting usually; Each upgrading all can reset key; Therefore need decode the defective of key after the immediate communication tool upgrading again, this has just brought, and the needs of this scheme are constantly decoded the defective of key, complexity is high, real-time is not good, thus production and popularization that can't be in batches.
Summary of the invention
In view of this, the invention provides a kind of expression robot that is applied to immediate communication tool, it can discern the employed emoticon of user in real time, and makes and the same response of this emoticon representative implication.And; Not to be employing carry out the method for cryptanalysis to the immediate communication tool data packets for transmission to its expression recognition method, and the complexity of having avoided adopting this scheme to bring is high, real-time is not good, need decode the defective of key after the immediate communication tool upgrading again.
This method is achieved in that
A kind of expression robot based on immediate communication tool comprises chat window monitoring modular, emoticon locating module, emoticon identification module and respond module;
Said chat window monitoring modular; Be used for after definite current focus window is the chat window of immediate communication tool, said chat window being monitored, regularly or when the user has new chat messages to show; The image interception of chat window is got off, and save as picture;
Said emoticon locating module is used to analyze the picture that the intercepting of chat window monitoring modular institute is got off, and seeks emoticon wherein, finds after the emoticon, and the position of emoticon is sent to said emoticon identification module;
Said emoticon identification module; Be used for behind the position that receives the emoticon that the emoticon locating module sends; The emoticon of this position and the emoticon in the existing emoticon storehouse are compared; Thereby confirm the meaning of this emoticon representative, then the result is sent to respond module;
Said respond module is used for after receiving the result that the emoticon identification module sends over, responding through the technique of expression of setting.
Wherein, said respond module responds through sound, image and/or action.
Preferably, said emoticon locating module comprises cutting module, gray processing module, level and smooth module and Hough Hough detection module:
Cutting module is used for according to the position of dialog boxes at chat window, and the image with dialog boxes from the image of chat window cuts out, and the image that cuts out is sent to the gray processing module;
The gray processing module is used for that the image that is received is carried out gray processing and comes out, and obtains gray-scale map, sends to level and smooth module;
Level and smooth module is used for the gray-scale map that receives is carried out Gauss's smoothing processing;
The Hough detection module is used for the image after Gauss's smoothing processing is carried out the Hough conversion, detects the position at circular emoticon place; Only coordinate x, y are the positions of maximum emoticon in the emoticon that identifies of output; Wherein x axle, y axle are zero point with the upper left corner of dialog boxes.Preferably, the Hough conversion of said Hough detection module begins from the lower right corner of dialog boxes, and according to from right to left, order computation from bottom to up when detecting first bowlder, is exported home position, and stops to detect.
Preferably, said emoticon identification module comprises extraction module, matching module and identification module;
Said extraction module is used for the position according to emoticon locating module output, obtains the emoticon image the image of the said dialog boxes that obtains from cutting module, sends to matching module;
Said matching module is used for the emoticon image that is received as template, and images that comprise all acquiescence emoticons of storage in advance as global image, are carried out template matches then, finds out the position of emoticon image in global image at last;
Said identification module is used for position range and expression implication according to each acquiescence emoticon of known global image, judges corresponding which the expression implication in position of the emoticon image that said matching module is found out, and the implication of will expressing one's feelings sends to respond module.
Beneficial effect:
The invention provides a kind of expression robot that is applied to immediate communication tool; Can discern the employed emoticon of user in real time, and make and the same response of this emoticon representative implication, and the more important thing is; This expression and people's thereof expression recognition method is not cryptanalysis is carried out in employing to the immediate communication tool data packets for transmission a method; Do not need to decode key again after the immediate communication tool upgrading, so versatility is good, is applicable to various immediate communication tools.And this method relies on sectional drawing to carry out Expression Recognition, and method is simple, can be by a lot of existing image processing methods, implement very simply, and and calculated amount is also little, thereby helps improving the real-time of Expression Recognition.
Secondly;, the Hough circle may obtain a plurality of circles that are positioned at diverse location after detecting; Here only export the position of the circle of x, y maximum according to the characteristics of immediate communication tool, thereby the follow-up coupling calculated amount of having avoided a plurality of round positions outputs to bring is many, defectives such as response confusion.
Once more, carrying out the Hough detection computations be, directly the lower right corner from dialog boxes begins to calculate, and according to from right to left, order from top to bottom with first detected round position output, and need not be carried out subsequent calculations, can reduce calculated amount like this.
Description of drawings
Fig. 1 is system function module figure of the present invention.
Fig. 2 is a sectional drawing module process flow diagram.
Fig. 3 is a sectional drawing module design sketch.
Fig. 4 is QQ acquiescence expression graphical diagram.
Fig. 5 is an emoticon locating module processing flow chart.
Fig. 6 is a QQ chat window exploded view.
Fig. 7 is the design sketch behind the gray processing.
Fig. 8 is the level and smooth design sketch afterwards of Gauss.
Fig. 9 is emoticon positioning result figure.
Figure 10 is an emoticon identification module process flow diagram.
Figure 11 all gives tacit consent to emoticon division figure for QQ.
Figure 12 is emoticon recognition result figure.
Embodiment
Below in conjunction with the accompanying drawing embodiment that develops simultaneously, describe the present invention.
The present invention has adopted a kind of method that need not chat content is carried out cryptanalysis, through to chat window monitoring sectional drawing, analyzes emoticon, is called sectional drawing comparison method.
This method thinking is; At first immediate communication tool user's chat window is monitored, choose then and carry out sectional drawing and preservation suitable opportunity, next the image of chat window is analysed and compared; Find out the emoticon position, identify the implication of emoticon representative at last.Because the size of emoticon is fixed, so can take that the scheme of template matches realizes in the pattern-recognition.
The advantage of this sectional drawing comparison method is to have walked around the link that cracks encrypting messages, so method is simple, real-time is good, and can accomplish to stride immediate communication tool easily.
Fig. 1 is the composition frame chart of the expression robot of immediate communication tool of the present invention, and as shown in Figure 1, this expression robot comprises chat window monitoring modular, emoticon locating module, emoticon identification module and respond module.Wherein,
The chat window monitoring modular; Be used for after definite current focus window is the chat window of immediate communication tool, said chat window being monitored, regularly or when the user has new chat messages to show; The image interception of chat window is got off, and save as picture; Wherein, focus window is meant the current window of operating of user, can judge focus window easily through the api function under the Windows.
The emoticon locating module is used to analyze the picture that the intercepting of chat window monitoring modular institute is got off, and seeks emoticon wherein, finds after the emoticon, and the position of emoticon is sent to said emoticon identification module;
The emoticon identification module; Be used for behind the position that receives the emoticon that the emoticon locating module sends; The emoticon of this position and the emoticon in the existing emoticon storehouse are compared; Thereby confirm the meaning of this emoticon representative, then the result is sent to respond module;
Respond module is used for after receiving the result that the emoticon identification module sends over, responding through the technique of expression of setting.
Function to each module is described in detail below.
● the chat window monitoring modular
Chat window monitoring sectional drawing module functions is that user's chat window is kept watch on; When the user has new chat messages to show, just the chat window intercepting is got off, and save as picture; In order to the processing and the analysis in later stage, chat window monitoring modular workflow is as shown in Figure 2.
QQ with company of Tengxun is an example, and chat window monitoring modular flow process roughly is like this, and at first the current focus window of judges is the QQ chat window when system moves, if just get into next step, if not just not doing response.After the focus window of confirming the user is the QQ chat window, need judge whether that new message gets into, and also preserves if having with regard to sectional drawing.Perhaps can adopt regularly the way of sectional drawing, whenever at a distance from a regular time just to the chat window sectional drawing.Can realize that for the adding whether new chat messages is arranged when in the chat window during image change, thinking has new chat messages to get into through the variation of monitoring chat window epigraph.The effect of sectional drawing module is as shown in Figure 3.
● the emoticon locating module
Obtained the sectional drawing of QQ chat window through the chat window monitoring modular, the problem that next faces is exactly how to analyze whether to contain emoticon in the picture that is truncated to, and position how to confirm emoticon.
At first analyze the acquiescence emoticon that QQ carries, as shown in Figure 4.From the consideration of practicality and technical reason, native system only considers to support the circular classical emoticon in the QQ acquiescence expression at present.This serial emoticon has two very outstanding characteristics:
1) be circular in shape.
2) be main color all with yellow.
Consider the user when chat used mainly be Chinese character, English alphabet, numeral, emoticon; First three items is as the distracter in the identifying; The shape facility that does not possess the circle of emoticon; But the color that QQ user can self-defined chat text, so also possibly have yellow this characteristic.Decision comes mark and extracts emoticon through circular this characteristic after taking all factors into consideration, and this also is the characteristic of the mostly timely employed emoticon of communication tool.
Before surface analysis emoticon be different from the characteristic of man, English alphabet, numeral, the technology that just need use some Flame Image Process is here sought the emoticon of circle, and is as shown in Figure 5; The processing that at first will cut image; Removing unwanted interference region and can improve the efficient of subsequent treatment, is that image is carried out gray processing and image smoothing after the cutting, and the purpose of these two flow processs all is to strengthen image; So that improve the accurate rate that detects; Be exactly to detect emoticon at last, used Hough circle detection function, the result returns the promptly circular coordinate in position of emoticon.
Therefore, this emoticon locating module comprises cutting module, gray processing module, level and smooth module and Hough detection module.
Cutting module is used for according to the position of dialog boxes at chat window, and the image with dialog boxes from the image of chat window cuts out, and the image that cuts out is sent to the gray processing module.
It still is example with QQ; The sectional drawing of QQ chat window is as shown in Figure 6, at first analyzes the sectional drawing of input, can see that the QQ chat window mainly can be divided into four zones; With red line they are divided out; Be respectively function hurdle, chat record display window, input field, QQ show hurdle, what clearly in native system, need is the information of chat record display window, and other three zones emoticon can not occur.So cutting this step purpose is that the chat record display window is separated from other trizonal encirclement, though find that through testing me the size of QQ chat window is to change the height on function hurdle: " H according to user's needs
Function", the height of input field: " H
Input" and QQ show hurdle is wide: " W
Elegant", be a fixed value, can not change along with the convergent-divergent of window.Through measuring H
Function=105 pixels, H
Input=155 pixels, W
Elegant=145 pixels.The origin coordinates that is easy to just can to extrapolate the chat record display window according to these three data is (0,105), lower right corner coordinate be (W-145, H-155) wherein W is the wide of whole sectional drawing, H is the height of whole sectional drawing.Be easy to just can the chat record display window have been shown separately through these data, do like this and rejected very big interference region, make that follow-up processing is more efficient.
The gray processing module is used for that the image that is received is carried out gray processing and comes out, and obtains gray-scale map, sends to level and smooth module.
Gray processing is to convert coloured image into gray level image.The image that sectional drawing module in native system is obtained is a coloured image, and coloured image is a kind of like this image, and its each pixel is all to there being three component (R; G, B), it is red, green, blue that these three components are represented; Each component can be got the round values in 0 to 255, and each class value has just been represented a color, and such pixel can have the value of more than 1,600 ten thousand color to select; Even this numeral also is very huge for computing machine; So processing for ease need be carried out gray processing to image, gray level image is a kind of like this image, and its pixel is also represented by R, G, three components of B; But the value of these three components is identical; It is thus clear that the span of a pixel has only 255 kinds in gray level image, and with the same integral body that it still can reflect entire image of coloured image and the local colourity and the distribution and the characteristic of brightness degree.So when digital picture is handled, generally will be processed object earlier and convert gray level image to, do the calculated amount that can significantly reduce subsequent treatment like this.The gray processing result is as shown in Figure 7.
Level and smooth module is used for the gray-scale map that receives is carried out Gauss's smoothing processing.
The fundamental purpose of image smoothing is in order to eliminate the noise in the original image, and keeps the edge contour and the lines of original image as far as possible.Noise in the image is not restricted to image fault and the distortion that human eyes can be awared, and a lot of noises are just can come to light carrying out Computer Image Processing only, and these noises all are stochastic distribution, and size, shape also all are irregular.The method of image smoothing has a variety of, comprises linearity, nonlinear smoothing and sharpening processing, and pseudo-colours is handled, filtering etc.When utilizing Gauss smoothly to remove the noise of disorderly and unsystematic and stochastic distribution; Can receive than the better effect of other several kinds of smoothing methods; The most important is that it can obtain reasonable image border, when circle detects good degree of accuracy can be arranged follow-up carrying out like this.So the image to input carries out Gauss's smoothing processing, the effect after the processing is as shown in Figure 8.
Through the image after Gauss's this step of smoothing processing, be a gray level image of accomplishing denoising, possessed and carried out the circular precondition that detects.In the time in Flame Image Process, need from image, discerning the simple geometry pattern; There is a kind of fundamental method to be called Hough (Hough) conversion; The Hough conversion is a kind of basic effective ways of realizing rim detection, is one of basic skills that from original image, identifies in the Flame Image Process simple geometric shape.The ultimate principle of Hough conversion is to utilize point and the duality of line in mathematics; With the Chosen Point in the original image space transform to parameter space curve or curved surface; Point with same parameter characteristic can be that peak value is accomplished the detection to characteristic curve through the accumulation degree of judging the intersection point place so just through in parameter space, intersecting after the conversion.Utilize the Hough conversion can be converted into the curve detection problem in the original image spike problem of seeking in the parameter space, just be converted into the detection local characteristics detecting overall permanence.Based on the difference of parameter character, the Hough conversion can detection of straight lines, circle, ellipse, curve etc.
The Hough conversion is a kind of detection method of overall importance that has, and it is insensitive that it hides phenomenon to random noise and part, has extremely strong antijamming capability, can be good at suppressing data point and too concentrates the interference that is produced.The Hough conversion has good fault-tolerance and robustness at the target side mask that detects known form, even target has damaged or pollution also can be by correct identification.So the present invention has adopted this method to detect the circle of emoticon.Because the radius of emoticon is known 25 pixels that are about, so as long as navigating to the center of circle just can find emoticon and separate, effect is as shown in Figure 9.
For validity and the antijamming capability of testing this method, in sectional drawing, comprised main interference projects such as numeral, English alphabet, Chinese character especially, observe testing result for ease, here testing result is exported and identified.Detected two circles as a result among the figure, and these two circles emoticon just, the circular center of circle with green point identification come out, and central coordinate of circle is exported, the result basically with expect the same.
After locating module has detected a secondary sectional drawing, have several seconds time, wait for the input of new sectional drawing; Because this time is very short, so the chat record content in the new sectional drawing can have the overlapping of part with former sectional drawing; If comprised emoticon in the lap; This emoticon was positioned so, if at this time with detected result's output, will produce repetition so.
The reason that produces this problem is that the zone of QQ demonstration chat record is fixed, when new chat record arrives; Old chat record will be got on by the top; If an emoticon has appeared at the bottom of a secondary sectional drawing, promptly the user has just received this emoticon, so; This emoticon will occur in several follow-up sectional drawings, up to there being abundant message this emoticon to be ejected the viewing area of chat record.
Because above situation; This module can not be arranged to all detected emoticons; All deposit to the result and export; In order to solve this problem of resetting, carried out such design: only to coordinate x in the emoticon that identifies, y, all be that export the position of maximum emoticon.
Therefore the function of Hough detection module is, the image after Gauss's smoothing processing is carried out the Hough conversion, detects the position at circular emoticon place; Only coordinate x, y are the positions of maximum emoticon in the emoticon that identifies of output; Wherein x axle, y axle are zero point with the upper left corner of dialog boxes.In order to reduce calculated amount, preferably, the Hough conversion of Hough detection module begins from the lower right corner of dialog boxes, and according to from right to left, order computation from bottom to up when detecting first bowlder, is exported home position, and stops to detect.
In the emoticon locating module, can obtain the position of emoticon, thereby can emoticon be separated separately.But system only knows just that emoticon has appearred in chat window in step to this; It does not also know the meaning of this emoticon representative; So can't make a corresponding response; Realize different emoticons are carried out correct response, also need identify the implication of isolated emoticon representative, this process be exactly the emoticon identification module the function that can realize.
● the emoticon identification module
The main thinking of emoticon identification module is that emoticon image that locating module is obtained is as template; The image that will comprise all acquiescence emoticons is as global image; Carry out template matches then; Find out the position of emoticon in global image at last; Owing in global image, comprised all emoticons and each emoticon oneself fixing position is arranged all, so just can confirm the meaning of emoticon representative according to the position, the basic procedure of this module is shown in figure 10.
Therefore the emoticon identification module comprises extraction module, matching module and identification module; Wherein,
Extraction module is used for the position according to emoticon locating module output, obtains the emoticon image the image of the said dialog boxes that obtains from cutting module, sends to matching module;
Matching module is used for the emoticon image that is received as template, and images that comprise all acquiescence emoticons of storage in advance as global image, are carried out template matches then, finds out the position of emoticon image in global image at last;
Identification module is used for position range and expression implication according to each acquiescence emoticon of known global image, judges corresponding which the expression implication in position of the emoticon image that said matching module is found out, and the implication of will expressing one's feelings sends to respond module.
Still be example with QQ, Figure 11 is all acquiescence emoticon sectional drawings of QQ.
As can be seen from the figure one have 8 row, 14 tabulation feelings symbols, amount to 105, each emoticon all occupies a fixing position; And a fixing boundary rectangle is arranged all; Through measuring the shared area size of emoticon rectangle is 33 * 33 pixels, just can Figure 11 be divided into 112 little rectangular areas here, emoticon of each Regional Representative; Want to discern emoticon and only need judge which zone the coordinate of the emoticon that returns in the template matches drops on and get final product, for example:
The zone of smile emoticon is 0＜x＜33,0＜y＜33.
The curl one's lip zone of emoticon is 33＜x＜66,0＜y＜33.
The zone of surprised emoticon is 0＜x＜33,33＜y＜66.
The zone of sad emoticon is 33＜x＜66,33＜y＜66.
Matching result is shown in figure 12; Observe recognition result for ease; Here the image with emoticon to be identified has shown to come out with the image of all acquiescence emoticons and the output of recognition result together; And identified the result of template matches with lines, visiblely utilized this method can success carry out template matches and utilize location recognition to go out the implication of emoticon.
● respond module
The more satisfactory response mode of respond module is to have accuracy and certain interest; That is to say that this module should be able to make and the pairing response of emoticon accurately; Let the user be easy to just can understand the implication of response; And require certain interest, can improve user experience like this.
This respond module is to seek a kind of special peripheral hardware in the plan at paper studies initial stage, and this peripheral hardware should have following characteristic:
1) can imitate people's face and make various expressions such as happiness, anger, grief and joy.
2) can be connected to by some way on user's the main frame, communicate with subscriber's main station.
3) can control this peripheral hardware through programming and make different expressions.
Transmission mode can be selected according to actual needs; The content of the data of transmission should be done following design; 105 emoticons are numbered at identification module; The result of identification is exactly the numbering of emoticon, so can the state of expression robot also be numbered, this numbering should be consistent with the numbering of emoticon.So only need numbering be sent to respond module; Just can make corresponding expression has responded; So the data content that transmits can be designed to the integer between 1 to 105; When respond module is received numbering, just can change to corresponding state, this state just in time is exactly the corresponding state of emoticon so.
In sum, more than being merely preferred embodiment of the present invention, is not to be used to limit protection scope of the present invention.All within spirit of the present invention and principle, any modification of being done, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (5)
1. the expression robot based on immediate communication tool is characterized in that, comprises chat window monitoring modular, emoticon locating module, emoticon identification module and respond module;
Said chat window monitoring modular; Be used for after definite current focus window is the chat window of immediate communication tool, said chat window being monitored, regularly or when the user has new chat messages to show; The image interception of chat window is got off, and save as picture;
Said emoticon locating module is used to analyze the picture that the intercepting of chat window monitoring modular institute is got off, and seeks emoticon wherein, finds after the emoticon, and the position of emoticon is sent to said emoticon identification module;
Said emoticon identification module; Be used for behind the position that receives the emoticon that the emoticon locating module sends; The emoticon of this position and the emoticon in the known emoticon storehouse are compared; Thereby confirm the meaning of this emoticon representative, then the result is sent to respond module;
Said respond module is used for after receiving the result that the emoticon identification module sends over, responding through the technique of expression of setting.
2. expression as claimed in claim 1 robot is characterized in that said respond module responds through sound, image and/or action.
3. expression as claimed in claim 1 robot is characterized in that, said emoticon locating module comprises cutting module, gray processing module, level and smooth module and Hough Hough detection module:
Cutting module is used for according to the position of dialog boxes at chat window, and the image with dialog boxes from the image of chat window cuts out, and the image that cuts out is sent to the gray processing module;
The gray processing module is used for that the image that is received is carried out gray processing and comes out, and obtains gray-scale map, sends to level and smooth module;
Level and smooth module is used for the gray-scale map that receives is carried out Gauss's smoothing processing;
The Hough detection module is used for the image after Gauss's smoothing processing is carried out the Hough conversion, detects the position at circular emoticon place; Only coordinate x, y are the positions of maximum emoticon in the emoticon that identifies of output; Wherein x axle, y axle are zero point with the upper left corner of dialog boxes.
4. expression as claimed in claim 3 robot is characterized in that the Hough conversion of said Hough detection module begins from the lower right corner of dialog boxes; According to from right to left, order computation from bottom to up is when detecting first bowlder; The output home position, and stop to detect.
5. like claim 3 or 4 described expression robots, it is characterized in that said emoticon identification module comprises extraction module, matching module and identification module;
Said extraction module is used for the position according to emoticon locating module output, obtains the emoticon image the image of the said dialog boxes that obtains from cutting module, sends to matching module;
Said matching module is used for the emoticon image that is received as template, and images that comprise all acquiescence emoticons of storage in advance as global image, are carried out template matches then, finds out the position of emoticon image in global image at last;
Said identification module is used for position range and expression implication according to each acquiescence emoticon of known global image, judges corresponding which the expression implication in position of the emoticon image that said matching module is found out, and the implication of will expressing one's feelings sends to respond module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210224496.1A CN102750555B (en) | 2012-06-28 | 2012-06-28 | Expression identification device applied to instant messaging tool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210224496.1A CN102750555B (en) | 2012-06-28 | 2012-06-28 | Expression identification device applied to instant messaging tool |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102750555A true CN102750555A (en) | 2012-10-24 |
| CN102750555B CN102750555B (en) | 2015-04-22 |
Family
ID=47030719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210224496.1A Expired - Fee Related CN102750555B (en) | 2012-06-28 | 2012-06-28 | Expression identification device applied to instant messaging tool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102750555B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914005A (en) * | 2012-12-31 | 2014-07-09 | 北京新媒传信科技有限公司 | Robot control method and terminal |
| CN104680166A (en) * | 2013-11-27 | 2015-06-03 | 施耐德电器工业公司 | Information identification method and information identification device |
| CN104699662A (en) * | 2015-03-18 | 2015-06-10 | 北京交通大学 | Method and device for recognizing whole symbol string |
| CN105204748A (en) * | 2014-06-27 | 2015-12-30 | 阿里巴巴集团控股有限公司 | Terminal interaction method and device |
| CN106228156A (en) * | 2016-07-18 | 2016-12-14 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus determining information alert content |
| CN106445478A (en) * | 2015-08-12 | 2017-02-22 | 腾讯科技（深圳）有限公司 | Graphic expression conversion method and apparatus |
| CN106530096A (en) * | 2016-10-08 | 2017-03-22 | 广州阿里巴巴文学信息技术有限公司 | Emotion icon processing method, device and electronic apparatus |
| CN108268583A (en) * | 2017-08-21 | 2018-07-10 | 广州市动景计算机科技有限公司 | The method and apparatus of emoticon meaning displaying |
| CN110689009A (en) * | 2019-09-18 | 2020-01-14 | 北京三快在线科技有限公司 | Information identification method and device, electronic equipment and computer readable storage medium |
| CN111597966A (en) * | 2020-05-13 | 2020-08-28 | 北京达佳互联信息技术有限公司 | Expression image recognition method, device and system |
| CN112784293A (en) * | 2019-11-08 | 2021-05-11 | 游戏橘子数位科技股份有限公司 | Recording notification method for picture capture |
| CN112784293B (en) * | 2019-11-08 | 2024-06-04 | 游戏橘子数位科技股份有限公司 | Method for recording notice of picture acquisition |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101494618A (en) * | 2008-11-28 | 2009-07-29 | 腾讯科技（深圳）有限公司 | Display system and method for instant communication terminal window |
| CN102289339A (en) * | 2010-06-21 | 2011-12-21 | 腾讯科技（深圳）有限公司 | Method and device for displaying expression information |
-
2012
- 2012-06-28 CN CN201210224496.1A patent/CN102750555B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101494618A (en) * | 2008-11-28 | 2009-07-29 | 腾讯科技（深圳）有限公司 | Display system and method for instant communication terminal window |
| CN102289339A (en) * | 2010-06-21 | 2011-12-21 | 腾讯科技（深圳）有限公司 | Method and device for displaying expression information |
Non-Patent Citations (1)
| Title |
|---|
| 崔忠艾: "聊天工具仿真表情插件的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 30 September 2010 (2010-09-30), pages 9 - 54 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914005A (en) * | 2012-12-31 | 2014-07-09 | 北京新媒传信科技有限公司 | Robot control method and terminal |
| CN104680166A (en) * | 2013-11-27 | 2015-06-03 | 施耐德电器工业公司 | Information identification method and information identification device |
| CN105204748A (en) * | 2014-06-27 | 2015-12-30 | 阿里巴巴集团控股有限公司 | Terminal interaction method and device |
| CN105204748B (en) * | 2014-06-27 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Terminal interaction method and its device |
| CN104699662A (en) * | 2015-03-18 | 2015-06-10 | 北京交通大学 | Method and device for recognizing whole symbol string |
| CN104699662B (en) * | 2015-03-18 | 2017-12-22 | 北京交通大学 | The method and apparatus for identifying overall symbol string |
| CN106445478A (en) * | 2015-08-12 | 2017-02-22 | 腾讯科技（深圳）有限公司 | Graphic expression conversion method and apparatus |
| CN106228156B (en) * | 2016-07-18 | 2019-09-20 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus of determining information alert content |
| CN106228156A (en) * | 2016-07-18 | 2016-12-14 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus determining information alert content |
| CN106530096A (en) * | 2016-10-08 | 2017-03-22 | 广州阿里巴巴文学信息技术有限公司 | Emotion icon processing method, device and electronic apparatus |
| CN108268583A (en) * | 2017-08-21 | 2018-07-10 | 广州市动景计算机科技有限公司 | The method and apparatus of emoticon meaning displaying |
| CN108268583B (en) * | 2017-08-21 | 2022-06-14 | 阿里巴巴（中国）有限公司 | Method and equipment for displaying emoticon meanings |
| CN110689009A (en) * | 2019-09-18 | 2020-01-14 | 北京三快在线科技有限公司 | Information identification method and device, electronic equipment and computer readable storage medium |
| CN110689009B (en) * | 2019-09-18 | 2021-09-07 | 北京三快在线科技有限公司 | Information identification method and device, electronic equipment and computer readable storage medium |
| CN112784293A (en) * | 2019-11-08 | 2021-05-11 | 游戏橘子数位科技股份有限公司 | Recording notification method for picture capture |
| CN112784293B (en) * | 2019-11-08 | 2024-06-04 | 游戏橘子数位科技股份有限公司 | Method for recording notice of picture acquisition |
| CN111597966A (en) * | 2020-05-13 | 2020-08-28 | 北京达佳互联信息技术有限公司 | Expression image recognition method, device and system |
| CN111597966B (en) * | 2020-05-13 | 2023-10-10 | 北京达佳互联信息技术有限公司 | Expression image recognition method, device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102750555B (en) | 2015-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102750555A (en) | Expression robot applied to instant messaging tool | |
| US10713528B2 (en) | System for determining alignment of a user-marked document and method thereof | |
| US9607199B2 (en) | Decoding machine-readable optical codes with aesthetic component | |
| CN103400099B (en) | Terminal and two-dimensional code identification method | |
| KR20170016961A (en) | Method and apparatus for identifying television channel information | |
| US20030072490A1 (en) | Method and arrangement for image analysis | |
| CN102385707A (en) | Digital picture recognizing method and device and crawler server | |
| CN109522807B (en) | Satellite image recognition system and method based on self-generated features and electronic equipment | |
| CN106845314B (en) | A kind of method for rapidly positioning of two dimensional code | |
| CN108563984A (en) | A kind of automatic identification and understanding method of procedural model figure | |
| CN110119742A (en) | A kind of recognition methods of container number, device and mobile terminal | |
| CN103946865A (en) | Methods and apparatuses for facilitating detection of text within an image | |
| KR20230012651A (en) | Method for generating table information based on the image | |
| CN111738252B (en) | Text line detection method, device and computer system in image | |
| CN106326801A (en) | Scanning method of stereoscopic two-dimensional codes | |
| US20240062513A1 (en) | Industrial internet of things (iiot) system for industrial production data management, control method, and storage medium thereof | |
| CN104881641A (en) | Mobile device based digital recognition method and system for questionnaires and tables | |
| CN103854020A (en) | Character recognition method and device | |
| CN105069393A (en) | Two-dimensional code malicious reading-preventing method and device | |
| CN112699776B (en) | Training sample optimization method, target detection model generation method, device and medium | |
| CN108960234A (en) | A kind of Logo recognition methods and system based on bag of words | |
| KR102396885B1 (en) | Method for alligning the image include the text | |
| CN102156876A (en) | Symbol identification method based on hexadecimal conversion | |
| CN117077711A (en) | Desktop digital interaction method and device, electronic equipment and storage medium | |
| CN114663894A (en) | Bill identification method and device based on target detection, electronic equipment and medium |
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: 20150422 Termination date: 20170628 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |