CN105094544B - Method and device for acquiring characters - Google Patents
Method and device for acquiring characters Download PDFInfo
- Publication number
- CN105094544B CN105094544B CN201510418501.6A CN201510418501A CN105094544B CN 105094544 B CN105094544 B CN 105094544B CN 201510418501 A CN201510418501 A CN 201510418501A CN 105094544 B CN105094544 B CN 105094544B
- Authority
- CN
- China
- Prior art keywords
- track
- character
- acquiring
- characters
- contained
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000005070 sampling Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 10
- 238000007635 classification algorithm Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 238000010422 painting Methods 0.000 claims 2
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Landscapes
- Character Input (AREA)
- Machine Translation (AREA)
Abstract
The embodiment of the invention provides a method and a device for acquiring a character. On one hand, the embodiment of the invention obtains a first track input by a user; thus, the first track is identified by utilizing an identification model to obtain at least two characters contained in the first track; and then, according to at least two characters contained in the first track, obtaining a target character and outputting the target character. Therefore, the technical scheme provided by the embodiment of the invention can realize automatic output of the target color characters according to the track input by the user, reduce the operation cost for acquiring the color characters and improve the acquisition efficiency.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the technical field of internet application, in particular to a method and a device for acquiring a character and a word.
[ background of the invention ]
At present, input method software is one of the most frequently used applications of users, and when a user sends information and applies social contact, the user needs to use the input method software to input information such as characters, punctuations, expressions or characters.
However, in the prior art, if a user wants to input a desired color character in the input method software, the user needs to manually screen a large amount of color characters provided by the input method software to find the color character required to be input. Therefore, the operation cost is high when the required characters are obtained, and the obtaining efficiency is low.
[ summary of the invention ]
In view of this, embodiments of the present invention provide a method and an apparatus for acquiring a color word, which can automatically output a target color word according to a trajectory input by a user, reduce an operation cost of acquiring the color word, and improve acquisition efficiency.
In one aspect of the embodiments of the present invention, a method for acquiring a text-in-color includes:
acquiring a first track input by a user;
identifying the first track by using an identification model to obtain at least two characters contained in the first track;
obtaining target characters according to at least two characters contained in the first track;
and outputting the target text.
The above-mentioned aspect and any possible implementation manner further provide an implementation manner, before the recognizing the first track by using the recognition model to obtain at least two characters included in the first track, the method further includes:
acquiring at least one character with the largest occurrence frequency in the candidate characters;
acquiring at least one drawing track corresponding to each character;
acquiring characteristic information of each drawing track;
and training the characteristic information of each character and each drawing track by using a classification algorithm to obtain the recognition model.
The above aspect and any possible implementation manner further provide an implementation manner, where the recognizing the first track by using a recognition model to obtain at least two characters included in the first track includes:
segmenting the first track to obtain at least two second tracks contained in the first track;
and identifying each second track by using the identification model to obtain characters contained in each second track.
The above-mentioned aspect and any possible implementation manner further provide an implementation manner, where the recognizing, by using the recognition model, each of the second tracks to obtain characters included in each of the second tracks includes:
obtaining characteristic information of each second track;
and according to the characteristic information of each second track, matching is carried out in the recognition model so as to obtain at least one character matched with the characteristic information of each second track, and the character is used as the character contained in each second track.
The above aspect and any possible implementation manner further provide an implementation manner, where obtaining a target text according to at least two characters included in the first trajectory includes:
splicing at least two characters contained in the first track into a character string according to the position of each second track in the first track;
directly taking the character string as the target character; and/or matching in at least one candidate character according to the character string to obtain at least one candidate character matched with the character string as the target character.
In one aspect of the embodiments of the present invention, an apparatus for acquiring a text includes:
the track acquisition unit is used for acquiring a first track input by a user;
the track recognition unit is used for recognizing the first track by using a recognition model so as to obtain at least two characters contained in the first track;
the character processing unit is used for obtaining target characters according to at least two characters contained in the first track;
and the information output unit is used for outputting the target characters.
The above-described aspects and any possible implementations further provide an implementation, where the apparatus further includes:
the model generating unit is used for acquiring at least one character with the largest occurrence frequency in the candidate text, acquiring at least one drawing track corresponding to each character, acquiring characteristic information of each drawing track, and training each character and the characteristic information of each drawing track by using a classification algorithm to obtain the recognition model.
The above-mentioned aspect and any possible implementation manner further provide an implementation manner, where the trajectory identification unit is specifically configured to:
segmenting the first track to obtain at least two second tracks contained in the first track;
and identifying each second track by using the identification model to obtain characters contained in each second track.
The above-mentioned aspect and any possible implementation manner further provide an implementation manner, where the trajectory recognition unit is configured to, when recognizing each second trajectory by using the recognition model to obtain a character included in each second trajectory, specifically:
obtaining characteristic information of each second track;
and according to the characteristic information of each second track, matching is carried out in the recognition model so as to obtain at least one character matched with the characteristic information of each second track, and the character is used as the character contained in each second track.
The above-mentioned aspect and any possible implementation manner further provide an implementation manner, where the character processing unit is specifically configured to:
splicing at least two characters contained in the first track into a character string according to the position of each second track in the first track;
directly taking the character string as the target character; and/or matching in at least one candidate character according to the character string to obtain at least one candidate character matched with the character string as the target character.
According to the technical scheme, the embodiment of the invention has the following beneficial effects:
according to the technical scheme provided by the embodiment of the invention, the target characters can be automatically acquired and output according to the track input by the user, so that the user can be prevented from manually screening and searching the characters needing to be input from a large number of characters. Therefore, the technical scheme provided by the embodiment of the invention can reduce the operation cost for acquiring the color characters and improve the acquisition efficiency of the color characters.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a schematic flow chart of a method for acquiring a text and a color according to an embodiment of the present invention;
FIG. 2 is an exemplary diagram of a first trace of user input in an embodiment of the present invention;
FIG. 3 is an exemplary diagram of trace slicing provided by embodiments of the present invention;
fig. 4 is a functional block diagram of an apparatus for acquiring a text message according to an embodiment of the present invention.
[ detailed description ] embodiments
For better understanding of the technical solutions of the present invention, the following detailed descriptions of the embodiments of the present invention are provided with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be understood that although the terms first, second, etc. may be used to describe the tracks in embodiments of the present invention, these keywords should not be limited to these terms. These terms are only used to distinguish the tracks from each other. For example, a first trajectory may also be referred to as a second trajectory, and similarly, a second trajectory may also be referred to as a first trajectory without departing from the scope of embodiments of the present invention.
The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
Example one
An embodiment of the present invention provides a method for acquiring a color word, please refer to fig. 1, which is a schematic flow chart of the method for acquiring a color word according to the embodiment of the present invention, and as shown in the figure, the method includes the following steps:
s101, acquiring a first track input by a user.
S102, recognizing the first track by using a recognition model to obtain at least two characters contained in the first track.
S103, obtaining a target character according to at least two characters contained in the first track.
And S104, outputting the target color characters.
It is understood that the alphabets refer to patterns formed by characters such as english alphabets and punctuation marks, and are part of American Standard Code for Information Interchange (ASCII) Art, and some very simple face patterns can be formed by punctuation marks and english words on the terminal. At present, common characters such as ": -)" represent smiling face, ": - (" represents unhappy, ": P" represents tongue spitting, "@ _ @ represents confusion or head-sick turn," (< lambda > O ^)/"represents happy, etc.
It should be noted that, the embodiment of the present invention is illustrated only by the color text, but is not limited to the color text, and the technical solution provided by the embodiment of the present invention is also applicable to other named expressions.
It should be noted that the terminal according to the embodiment of the present invention may include, but is not limited to, a Personal Computer (PC), a Personal Digital Assistant (PDA), a wireless handheld device, a Tablet Computer (Tablet Computer), a mobile phone, an MP3 player, an MP4 player, and the like.
It should be noted that the execution subjects of S101 to S103 may be an apparatus for acquiring a text, and the apparatus may be located in an application of the local terminal, or may also be a functional unit such as a Software Development Kit (SDK) or a plug-in located in the application of the local terminal, or may also be located on the server side, which is not particularly limited in this embodiment of the present invention.
It should be understood that the application may be an application program (native app) installed on the terminal, or may also be a web page program (webApp) of a browser on the terminal, which is not limited in this embodiment of the present invention.
Example two
Based on the method for acquiring the text and the text provided in the first embodiment, the embodiment of the present invention specifically describes a method for acquiring the first trajectory input by the user in S101. The step may specifically include:
in the embodiment of the invention, the first track input by the user in the client can be obtained.
Preferably, the first trajectory input by the user may be a trajectory manually drawn by the user in the client.
Referring to fig. 2, which is an exemplary diagram of a first track input by a user in an embodiment of the present invention, as shown in fig. 2, the user may draw the track on an interface presented by a client by using a finger.
EXAMPLE III
Based on the method for acquiring the text characters provided in the first embodiment and the second embodiment, the embodiment of the present invention specifically describes a method for acquiring at least two characters included in the first trajectory by recognizing the first trajectory with a recognition model in S102. The step may specifically include:
in this embodiment of the present invention, before the first trajectory is identified by using an identification model to obtain at least two characters included in the first trajectory, the identification model may be generated in advance.
For example, in the embodiment of the present invention, the method for generating the recognition model may include, but is not limited to:
first, at least one character with the largest occurrence frequency in the candidate character is obtained. Then, at least one drawing track corresponding to each character is obtained, and characteristic information of each drawing track is obtained. And finally, training the characteristic information of each character and each drawing track by using a classification algorithm to obtain the recognition model.
In a specific implementation process, for each candidate character, a plurality of characters included in each candidate character may be acquired, for each character, the occurrence frequency of the character in all candidate characters may be counted, then all characters are sorted according to the order of the occurrence frequency from high to low, and then at least one character with the largest occurrence frequency is acquired, thereby implementing the collection of common characters in the candidate characters.
In a specific implementation process, for each of the characters, a drawing trace input by each of at least one user may be obtained as at least one drawing trace corresponding to the character, and each of the characters and the drawing traces input by the users are used as a training set.
For example, the method for acquiring the characteristic information of each drawing track may include, but is not limited to:
on one hand, a plurality of sampling points are obtained from the drawing track according to a preset sampling frequency, for each sampling point, a vector between the sampling point and the previous sampling point is obtained, and then projection information of the vector in 8 directions is obtained, wherein the projection information is a matrix of 8 x 1.
On the other hand, each drawing trace may be regarded as an image of 256 pixels by 256 pixels, and the drawing trace is equally divided into 8 blocks in each of the horizontal and vertical directions, so that the drawing trace is divided into 64 sections, and projection information of each section is acquired based on projection information of vectors included in each section. It should be noted that, if a certain portion includes projection information of at least two vectors, average projection information of the at least two pieces of projection information may be obtained as the projection information of the certain portion.
And finally, sequencing the projection information of each part from left to right and from top to bottom to obtain a sequencing result, wherein the sequencing result is used as the characteristic information of the drawing track.
It should be noted that, because each character may correspond to at least one drawing track, each character in the at least one character may correspond to at least one feature information by using the method.
Preferably, the 8 directions may include up, down, left, right, left-up, left-down, right-up, and right-down.
Preferably, the classification algorithm may include, but is not limited to: a K-Nearest Neighbor (KNN), a bayesian algorithm, or a Support Vector Machine (SVM) algorithm, etc.
It can be understood that after the recognition model is obtained in advance by using the above method, after the user inputs the first trajectory, the first trajectory may be recognized by using the recognition model to obtain the characters included in the first trajectory.
For example, in the embodiment of the present invention, the method for recognizing the first track by using the recognition model to obtain at least two characters included in the first track may include, but is not limited to:
firstly, the first track is segmented to obtain at least two second tracks contained in the first track. Then, each second track is identified by the identification model to obtain characters contained in each second track.
In a specific implementation process, a coordinate system is established for the first trajectory input by the user, and then the first trajectory is segmented according to a projection of the first trajectory on an X axis in the horizontal direction, so as to obtain at least two second trajectories included in the first trajectory.
For example, the method for recognizing each of the second tracks by using the recognition model to obtain the characters contained in each of the second tracks may include, but is not limited to:
first, feature information of each of the second tracks is obtained. Then, according to the feature information of each second track, matching is performed in the recognition model to obtain at least one character matched with the feature information of each second track, and the character is used as the character contained in each second track.
It can be understood that the feature information of each second track can be obtained by using the above method for obtaining the feature information of each drawing track, and the implementation method for obtaining the feature information of each second track is not described herein again.
In a specific implementation process, the obtained feature information of the second track may be used as an input of the recognition model, so that the recognition model performs matching according to the feature information of the second track, and then the recognition model may output at least one character matching the feature information of the second track, where the at least one character is used as a character included in the second track.
Example four
Based on the method for acquiring a color word, the second embodiment and the third embodiment provided in the first embodiment, the embodiment of the present invention specifically describes a method for acquiring a target color word according to at least two characters included in the first trajectory in S103. The step may specifically include:
for example, in the embodiment of the present invention, the method for obtaining the target text according to at least two characters included in the first track may include, but is not limited to:
firstly, according to the position of each second track in the first track, splicing at least two characters contained in the first track into a character string. Then, directly taking the character string as the target character; and/or matching in at least one candidate character according to the character string to obtain at least one candidate character matched with the character string as the target character.
In a specific implementation process, the at least two characters may be spliced according to a position of each of the second tracks in the first track and a character included in each of the at least two second tracks, so as to obtain a character string. Since there may be at least two characters per second trajectory, each character is stitched once to obtain a corresponding string.
In a specific implementation process, for a character string obtained by splicing, the character string may be directly used as the target text. Or, each character string obtained by splicing may be subjected to character string matching in at least one candidate color word to obtain a candidate color word with the highest similarity to the character string, which is used as a candidate color word matched with the character string, and these candidate color words are used as target color words in the embodiment of the present invention. Or, both the character string obtained by splicing and the candidate color word matched with the character string are used as the target color word in the embodiment of the present invention, which is not particularly limited in the embodiment of the present invention.
In addition, the character strings obtained by splicing are directly used as the target color words, so that the color words created by the user can be obtained, further, the target color words can be stored in a color word library, and the target color words can be shared with other users.
Referring to fig. 3, which is an exemplary diagram of a track splitting provided by the embodiment of the present invention, as shown in fig. 3, a first track input by a user shown in fig. 2 may be split into a track 1, a track 2, and a track 3 shown in fig. 3. Then, the feature information of the track 1, the feature information of the track 2 and the feature information of the track 3 are obtained, and the feature information of the three tracks is respectively input into the recognition model to obtain the character ": included in the track 1, the character" - "included in the track 2 and the character") "included in the track 3 output by the recognition model. Finally, the three characters are spliced to be output as the target color character ": -".
EXAMPLE five
Based on the method for acquiring the color word provided in the first embodiment and the second to fourth embodiments, the embodiment of the present invention specifically describes the method for outputting the target color word in S104. The step may specifically include:
in a specific implementation process, if the execution main bodies of S101 to S104 are located on the server side, the server may output the target text to the client after obtaining the target text, and the client may further display the target text to the user, so that the user can select which target text is used as the input target text. Or, if the execution main bodies of S101 to S104 are located at the client, the client may directly display the target color characters to the user to implement output of the target color characters, so that the user can select which one is used as the input target color character.
The embodiment of the invention further provides an embodiment of a device for realizing the steps and the method in the embodiment of the method.
Please refer to fig. 4, which is a functional block diagram of an apparatus for acquiring a text according to an embodiment of the present invention. As shown, the apparatus comprises:
a trajectory acquisition unit 401, configured to acquire a first trajectory input by a user;
a track recognition unit 402, configured to recognize the first track by using a recognition model to obtain at least two characters included in the first track;
a character processing unit 403, configured to obtain a target text according to at least two characters included in the first trajectory;
and an information output unit 404, configured to output the target text.
Optionally, the apparatus further comprises:
the model generating unit 405 is configured to obtain at least one character with the largest occurrence frequency in the candidate text, obtain at least one drawing track corresponding to each character, obtain feature information of each drawing track, and train the feature information of each character and each drawing track by using a classification algorithm to obtain the recognition model.
Preferably, the track recognition unit 402 is specifically configured to:
segmenting the first track to obtain at least two second tracks contained in the first track;
and identifying each second track by using the identification model to obtain characters contained in each second track.
Preferably, the track recognition unit 402 is configured to, when recognizing each second track by using the recognition model to obtain characters included in each second track, specifically:
obtaining characteristic information of each second track;
and according to the characteristic information of each second track, matching is carried out in the recognition model so as to obtain at least one character matched with the characteristic information of each second track, and the character is used as the character contained in each second track.
Preferably, the character processing unit 403 is specifically configured to:
splicing at least two characters contained in the first track into a character string according to the position of each second track in the first track;
directly taking the character string as the target character; and/or matching in at least one candidate character according to the character string to obtain at least one candidate character matched with the character string as the target character.
Since each unit in the present embodiment can execute the method shown in fig. 1, reference may be made to the related description of fig. 1 for a part of the present embodiment that is not described in detail.
The technical scheme of the embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, the first track input by the user can be obtained; thus, the first track is identified by utilizing an identification model to obtain at least two characters contained in the first track; and then, according to at least two characters contained in the first track, obtaining a target character and outputting the target character.
According to the technical scheme provided by the embodiment of the invention, the target characters can be automatically acquired and output according to the track input by the user, so that the user can be prevented from manually screening and searching the characters needing to be input from a large number of characters. Therefore, the technical scheme provided by the embodiment of the invention can reduce the operation cost for acquiring the color characters and improve the acquisition efficiency of the color characters.
In addition, in the embodiment of the invention, the obtained target characters can be used as the characters created by the user for storage or sharing, so that the threshold of creating the characters by the user is reduced, the creation interest of the characters is improved, and good experience is brought to the user.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions in actual implementation, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a Processor (Processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. A method for acquiring a text, the method comprising:
acquiring a first track input by a user;
identifying the first track by using an identification model to obtain at least two characters contained in the first track;
obtaining a character string according to at least two characters contained in the first track; directly taking the character string as a target character; and/or matching in at least one candidate character according to the character string to obtain at least one candidate character matched with the character string as a target character;
outputting the target text;
the identification model is generated in the following mode:
acquiring at least one character with the largest occurrence frequency in the candidate characters;
acquiring at least one drawing track corresponding to each character;
acquiring characteristic information of each drawing track;
training the characteristic information of each character and each drawing track by using a classification algorithm to obtain the recognition model;
wherein acquiring characteristic information of each of the drawing traces includes:
acquiring a plurality of sampling points from the drawing track according to a preset sampling frequency, acquiring a vector between each sampling point and the last sampling point, and taking projection information of each vector in each direction as characteristic information of the drawing track; or,
equally dividing the dialog track into a plurality of blocks in the horizontal and vertical directions to obtain a plurality of parts, obtaining projection information of each part according to projection information of vectors contained in each part, sequencing the projection information of each part according to a preset sequence, and taking a sequencing result as feature information of the painting track.
2. The method of claim 1, wherein the recognizing the first track by using a recognition model to obtain at least two characters contained in the first track comprises:
segmenting the first track to obtain at least two second tracks contained in the first track;
and identifying each second track by using the identification model to obtain characters contained in each second track.
3. The method according to claim 2, wherein the recognizing each of the second tracks by using the recognition model to obtain the characters contained in each of the second tracks comprises:
obtaining characteristic information of each second track;
and according to the characteristic information of each second track, matching is carried out in the recognition model so as to obtain at least one character matched with the characteristic information of each second track, and the character is used as the character contained in each second track.
4. The method according to claim 2 or 3, wherein obtaining a character string according to at least two characters contained in the first track comprises:
and splicing at least two characters contained in the first track into a character string according to the position of each second track in the first track.
5. An apparatus for acquiring a text, the apparatus comprising:
the track acquisition unit is used for acquiring a first track input by a user;
the model generating unit is used for acquiring at least one character with the largest occurrence frequency in candidate characters, acquiring at least one drawing track corresponding to each character, acquiring characteristic information of each drawing track, and training each character and the characteristic information of each drawing track by using a classification algorithm to obtain a recognition model;
the track recognition unit is used for recognizing the first track by using a recognition model so as to obtain at least two characters contained in the first track;
the character processing unit is used for obtaining a character string according to at least two characters contained in the first track; directly taking the character string as a target character; and/or matching in at least one candidate character according to the character string to obtain at least one candidate character matched with the character string as a target character;
the information output unit is used for outputting the target characters;
wherein acquiring characteristic information of each of the drawing traces includes:
acquiring a plurality of sampling points from the drawing track according to a preset sampling frequency, acquiring a vector between each sampling point and the last sampling point, and taking projection information of each vector in each direction as characteristic information of the drawing track; or,
equally dividing the dialog track into a plurality of blocks in the horizontal and vertical directions to obtain a plurality of parts, obtaining projection information of each part according to projection information of vectors contained in each part, sequencing the projection information of each part according to a preset sequence, and taking a sequencing result as feature information of the painting track.
6. The apparatus according to claim 5, wherein the trajectory recognition unit is specifically configured to:
segmenting the first track to obtain at least two second tracks contained in the first track;
and identifying each second track by using the identification model to obtain characters contained in each second track.
7. The apparatus according to claim 6, wherein the trajectory recognition unit, when recognizing each of the second trajectories by using the recognition model to obtain the characters included in each of the second trajectories, is specifically configured to:
obtaining characteristic information of each second track;
and according to the characteristic information of each second track, matching is carried out in the recognition model so as to obtain at least one character matched with the characteristic information of each second track, and the character is used as the character contained in each second track.
8. The apparatus according to claim 6 or 7, wherein the character processing unit is specifically configured to:
and splicing at least two characters contained in the first track into a character string according to the position of each second track in the first track.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510418501.6A CN105094544B (en) | 2015-07-16 | 2015-07-16 | Method and device for acquiring characters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510418501.6A CN105094544B (en) | 2015-07-16 | 2015-07-16 | Method and device for acquiring characters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105094544A CN105094544A (en) | 2015-11-25 |
| CN105094544B true CN105094544B (en) | 2020-03-03 |
Family
ID=54575129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510418501.6A Active CN105094544B (en) | 2015-07-16 | 2015-07-16 | Method and device for acquiring characters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105094544B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111722726B (en) * | 2019-03-20 | 2024-06-07 | 北京搜狗科技发展有限公司 | Method and device for determining pigment and text |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739118A (en) * | 2008-11-06 | 2010-06-16 | 大同大学 | Video handwriting character inputting device and method thereof |
| CN101853126A (en) * | 2010-05-12 | 2010-10-06 | 中国科学院自动化研究所 | Real-time identification method for on-line handwriting sentences |
| CN102520790A (en) * | 2011-11-23 | 2012-06-27 | 中兴通讯股份有限公司 | Character input method based on image sensing module, device and terminal |
| CN103577843A (en) * | 2013-11-22 | 2014-02-12 | 中国科学院自动化研究所 | Identification method for handwritten character strings in air |
| CN104049831A (en) * | 2013-03-12 | 2014-09-17 | 百度国际科技（深圳）有限公司 | Method and device for inputting emotion icon |
| CN104205126A (en) * | 2012-03-23 | 2014-12-10 | 微软公司 | Rotation-free recognition of handwritten characters |
| CN104504412A (en) * | 2014-11-28 | 2015-04-08 | 苏州大学 | Method and system for extracting and identifying handwriting stroke features |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7174043B2 (en) * | 2003-02-25 | 2007-02-06 | Evernote Corp. | On-line handwriting recognizer |
| US20100246941A1 (en) * | 2009-03-24 | 2010-09-30 | Microsoft Corporation | Precision constrained gaussian model for handwriting recognition |
-
2015
- 2015-07-16 CN CN201510418501.6A patent/CN105094544B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739118A (en) * | 2008-11-06 | 2010-06-16 | 大同大学 | Video handwriting character inputting device and method thereof |
| CN101853126A (en) * | 2010-05-12 | 2010-10-06 | 中国科学院自动化研究所 | Real-time identification method for on-line handwriting sentences |
| CN102520790A (en) * | 2011-11-23 | 2012-06-27 | 中兴通讯股份有限公司 | Character input method based on image sensing module, device and terminal |
| CN104205126A (en) * | 2012-03-23 | 2014-12-10 | 微软公司 | Rotation-free recognition of handwritten characters |
| CN104049831A (en) * | 2013-03-12 | 2014-09-17 | 百度国际科技（深圳）有限公司 | Method and device for inputting emotion icon |
| CN103577843A (en) * | 2013-11-22 | 2014-02-12 | 中国科学院自动化研究所 | Identification method for handwritten character strings in air |
| CN104504412A (en) * | 2014-11-28 | 2015-04-08 | 苏州大学 | Method and system for extracting and identifying handwriting stroke features |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105094544A (en) | 2015-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109614944B (en) | Mathematical formula identification method, device, equipment and readable storage medium | |
| CN111625635A (en) | Question-answer processing method, language model training method, device, equipment and storage medium | |
| CN111381751A (en) | Text processing method and device | |
| US20180300542A1 (en) | Drawing emojis for insertion into electronic text-based messages | |
| CN112396049A (en) | Text error correction method and device, computer equipment and storage medium | |
| US20150154176A1 (en) | Handwriting input support apparatus and method | |
| CN102750552B (en) | Handwriting recognition method and system as well as handwriting recognition terminal | |
| CN104866308A (en) | Scenario image generation method and apparatus | |
| CN110610180A (en) | Method, device and equipment for generating recognition set of wrongly-recognized words and storage medium | |
| CN112559800A (en) | Method, apparatus, electronic device, medium, and product for processing video | |
| CN113627439A (en) | Text structuring method, processing device, electronic device and storage medium | |
| WO2015161823A1 (en) | Handwriting recognition method and device | |
| CN110532415A (en) | Picture search processing method, device, equipment and storage medium | |
| CN112926300A (en) | Image searching method, image searching device and terminal equipment | |
| CN112149680A (en) | Wrong word detection and identification method and device, electronic equipment and storage medium | |
| KR20220038477A (en) | Extract line of text | |
| CN115101069A (en) | Voice control method, device, equipment, storage medium and program product | |
| CN113869063A (en) | Data recommendation method and device, electronic equipment and storage medium | |
| US9418281B2 (en) | Segmentation of overwritten online handwriting input | |
| CN113220125A (en) | Finger interaction method and device, electronic equipment and computer storage medium | |
| CN105022480A (en) | Input method and terminal | |
| CN105094544B (en) | Method and device for acquiring characters | |
| CN104850819B (en) | Information processing method and electronic equipment | |
| CN112840622B (en) | Pushing method and related product | |
| US10127478B2 (en) | Electronic apparatus and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |