CN112464767A

CN112464767A - Scribble identification method, scribble identification device and electronic equipment

Info

Publication number: CN112464767A
Application number: CN202011288739.9A
Authority: CN
Inventors: 顾在旺; 程骏; 庞建新
Original assignee: Ubtech Robotics Corp
Current assignee: Ubtech Robotics Corp
Priority date: 2020-11-17
Filing date: 2020-11-17
Publication date: 2021-03-09

Abstract

The application discloses a graffiti identification method, a graffiti identification device, electronic equipment and a computer-readable storage medium. The doodling identification method comprises the following steps: determining an object to be drawn; receiving a doodle track input by a user on a screen based on the object to be drawn; carrying out graffiti identification on the graffiti track to obtain an identification result; and if the identification result is matched with the object to be drawn, determining that the user scribbles and is drawn successfully. Through this application scheme, can promote the efficiency of scribble discernment to a certain extent.

Description

Scribble identification method, scribble identification device and electronic equipment

Technical Field

The application belongs to the technical field of human-computer interaction, and particularly relates to a graffiti identification method, a graffiti identification device, electronic equipment and a computer-readable storage medium.

Background

In recent years, man-machine interaction modes are more flexible and various, and one of the modes is to identify a line drawing (also called graffiti) drawn by a user, specifically: the front end gives keywords, such as cat; next, the user draws an image of the cat on the interface displayed at the front end; and finally, predicting whether the user correctly draws the keywords given at the beginning of the front end by a background algorithm according to the image drawn by the user. At present, above-mentioned in-process, the user draws the back front end that finishes and needs to transmit the image of drawing the gained to the backstage and discern, when the size of this image is great, leads to transmission speed slower easily to influence the efficiency of scribble discernment.

Disclosure of Invention

The application provides a scribble identification method, a scribble identification device, an electronic device and a computer readable storage medium, which can improve the efficiency of scribble identification to a certain extent.

In a first aspect, the present application provides a graffiti identification method, including:

determining an object to be drawn;

carrying out graffiti recognition on a graffiti track input by a user on the basis of the object to be drawn on a screen to obtain a recognition result;

and if the identification result is matched with the object to be drawn, determining that the user scrawling drawing is successful.

In a second aspect, the present application provides a graffiti identification device comprising:

a determination unit for determining an object to be drawn;

the identification unit is used for carrying out graffiti identification on a graffiti track input by a user on the basis of the object to be drawn on a screen to obtain an identification result;

and the matching unit is used for determining that the user scrawling drawing is successful if the identification result is matched with the object to be drawn.

In a third aspect, the present application provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect when executing the computer program.

In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the first aspect.

In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by one or more processors, performs the steps of the method of the first aspect as described above.

It is from top to bottom, through this application embodiment, at the in-process of scribble discernment, no longer carry out the scribble discernment based on this whole of image that the user drawn, but only carry out the scribble discernment based on the scribble orbit that the user drawn, this can make the data volume that the front end transmitted for the backstage significantly reduce to reduce data transmission's consuming time, can promote the efficiency of scribble discernment to a certain extent. It is understood that the beneficial effects of the second aspect to the fifth aspect can be referred to the related description of the first aspect, and are not described herein again.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

FIG. 1 is a schematic flow chart illustrating an implementation of a graffiti recognition method provided by an embodiment of the present application;

fig. 2 is a schematic flowchart illustrating a specific implementation of step 102 in the graffiti identification method provided in the embodiment of the present application;

fig. 3 is an exemplary diagram of a vertical line drawn by a user in a drawing process according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a graffiti recognition network provided by an embodiment of the present application;

FIG. 5-1 is an exemplary diagram of a first drawing performed by a user during a drawing process according to an embodiment of the present application;

FIG. 5-2 is an exemplary diagram of a second pen drawing during a drawing process by a user according to an embodiment of the present application;

5-3 are exemplary diagrams of a third pen drawing during a drawing process by a user provided by the embodiment of the application;

FIG. 6 is a block diagram of a graffiti recognition device provided by an embodiment of the present application;

fig. 7 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

The following describes a graffiti recognition method provided by an embodiment of the present application. Referring to fig. 1, the method for identifying graffiti in the embodiment of the present application includes:

step 101, determining an object to be drawn;

in the embodiment of the present application, an object to be drawn by a user needs to be determined first, that is, an object to be drawn needs to be determined. It should be noted that the object to be drawn should generally have a physical image, that is, the object to be drawn is an object that can be imaged. For example, the object to be drawn may be a cat, a flower, a car, or the like, and is not limited herein.

In some embodiments, a developer may preset a system lexicon, and configure at least one name of an object that can be expressed by graffiti, that is, configure at least one name of an object that can be liked. For example, the system lexicon may be configured with: kittens, puppies, ponies, flowers, trees, leaves, cars, bicycles, houses, and the like, without limitation. Then step 101 may be embodied as: determining an object to be drawn in the system word stock; namely, a name word is randomly selected in the system word stock to be used as the object to be drawn.

In some embodiments, if the user is in a double doodle game, the object determined by another user may be the object to be drawn. For example, if the user a is performing a doodle game with the user B, the user a may issue questions for the user B, and the user B may issue questions for the user a; that is, the user a determines the object to be drawn of the user B, and the user B determines the object to be drawn of the user a. For example, after the user a inputs a character "car" in an interface displayed by the user terminal and checks and determines that the character input by the user a is indeed the name of an object capable of being expressed by graffiti in the background, the character "car" input by the user a can be transmitted to the user B, so as to inform the user B that an object to be drawn by the user B (i.e., an object to be drawn by the user B) is currently the "car"; or, a question may be made for another user in a manner that the user selects from the system lexicon, for example, the user B refers to the system lexicon in an interface displayed by the user terminal of the user B, and selects an object "kitten" from the system lexicon, that is, the object "kitten" selected by the user B may be transmitted to the user a, so as to inform the user a that the object to be drawn (that is, the object to be drawn of the user a) is "kitten".

And 102, carrying out graffiti recognition on a graffiti track input by a user on the screen based on the object to be drawn to obtain a recognition result.

In the embodiment of the application, after knowing an object to be drawn (i.e., an object to be drawn), a user can start to draw a scribble on an interface displayed by a user terminal of the user. Generally speaking, a user terminal may display a canvas with a preset size on a display interface, where the canvas defines a range of drawings that the user can draw, that is, the user can only draw on the canvas. In the present application, in order to reduce the amount of data transmitted to the background, the user does not pay attention to the whole image drawn by the user, but only to the line drawn by the user, that is, the graffiti track. For example, the prior art focuses on the whole of the drawn image, and after the user finishes drawing, a lot of blank areas on the canvas are also part of the drawn image, which results in a lot of useless data in the data transmitted to the background. And in this application, the blank region on the canvas will not be transmitted to the backstage, only the lines that the user drawn, also the scribble orbit that the user drawn itself will be transmitted to the backstage, so, the data bulk of the data that can significantly reduce and transmit to the backstage. After obtaining the doodle track input by the user, the background can identify the doodle track to obtain an identification result.

Illustratively, a graffiti track may be represented by the coordinates and states of the various track points that make up the graffiti track. Referring to fig. 2, the step 102 includes:

step 1021, receiving a graffiti track input by a user on the screen based on the object to be drawn.

And step 1022, obtaining a track point set according to the scrawling track.

In the embodiment of the present application, the elements included in the trace point set are all trace points constituting the graffiti trace. Specifically, the information of a track point includes not only the coordinates of the track point, but also a state identifier of the track point, where the state identifier is used to represent the state of the track point in the track, including a starting state, an intermediate state, and an end state. Here, the start point state may be represented by a value "0", the intermediate state may be represented by a value "1", and the end point state may be represented by a value "2". For example, a user currently wants to draw a rectangle, generally speaking, the drawing order is: the first pen draws the vertical line on the left (from the top down), the second pen draws the horizontal line on the top (from the left to the right), the third pen draws the vertical line on the right (from the top down), and the fourth pen draws the horizontal line on the bottom (from the left to the right). Referring to FIG. 3, FIG. 3 shows an example of the first stroke, i.e., drawing a vertical line:

in the first drawing, three points are selected for explanation, which are respectively the starting points P₀A certain intermediate point P₁And end point P₂(ii) a Note that in fig. 3, these three dots are reinforced in the form of black small dots. In the actual drawing process, a pen drawn by the user is usually a broken line, a line segment or a curve with uniform thickness.

For the starting point P₀In other words, the starting pointP₀Except for the coordinates (x) in two-dimensional space₀，y₀) In addition, there is an identifier representing the state, i.e. state identifier 0, for representing P₀The starting point for the drawing (i.e., the starting point for the scribble), then the final starting point P₀Represented as (x) in the set of trace points₀，y₀，0)；

For the middle point P₁In other words, the intermediate point P₁Except for the coordinates (x) in two-dimensional space₁，y₁) In addition, there is an identifier representing the state, namely state identifier 1, for representing P₁The intermediate point drawn for the stroke (i.e. the intermediate point of the scribble), the final intermediate point P₁Represented as (x) in the set of trace points₁，y₁，1)；

For end point P₂In other words, the end point P₂Except for the coordinates (x) in two-dimensional space₂，y₂) In addition, there is an identifier representing the state, namely state identifier 2, for representing P₂The end point drawn for the stroke (i.e., the end point of the scribble), then the final end point P₂Represented as (x) in the set of trace points₂，y₂，2)。

Through the expression of the information of above-mentioned track point, can be so that electronic equipment learns fast that when the user draws a section of lines, the drawing order of each point on this line to the better recognition of doodling is carried out to track point set of convenient doodling recognition network, helps promoting the recognition accuracy of doodling recognition network to a certain extent.

And 1023, performing scrawling identification on the track point set to obtain an identification result of the track point set.

In the embodiment of the application, a graffiti recognition network can be trained in advance based on a plurality of existing trajectory point sets of graffiti trajectories. The graffiti recognition network can be a combination of a Convolutional Neural Network (CNN) and a long-term memory mechanism (LSTM), and belongs to a classification network. Moreover, research and development personnel can optimize the combination of the CNN and the LSTM to obtain a lightweight doodle identification network, and the identification delay can be reduced.

Referring to fig. 4, fig. 4 shows a possible structural schematic of the graffiti recognition network, which specifically includes: the method comprises the following steps of 2 layers of convolution layers, 3 layers of LSTM layers and 1 layer of Softmax layer, wherein the convolution layers and the LSTM layers are used for extracting low-order features, and the LSTM layers are used for extracting high-order features. In the graffiti recognition network, input data of each layer is output data of the previous layer, input data of the 1 st convolutional layer is a track point set, output data of the Softmax layer is a recognition result of the track point set, and the recognition result is an object type to which the track point set recognized by the graffiti recognition network (namely a graffiti track input by a user) belongs.

In some embodiments, considering that an average user may not have a high drawing level, the graffiti recognition network outputs a predetermined number of recognition results based on the input set of trace points, the predetermined number being a positive integer greater than 1. For convenience of illustration, the predetermined number may be denoted as N. That is, after the user finishes drawing, the graffiti recognition network can output N object categories to which the graffiti trajectory most probably belongs, specifically: a plurality of object categories are preset in the graffiti identification network; through the processing of each layer in the scrawling recognition network, the score of each object category can be finally obtained, and the score is used for representing the probability that a track point set (namely the scrawling track input by a user) belongs to the corresponding object category; the top N (e.g., 5) object categories with the highest scores are used as recognition results, that is, the N recognition results may be finally output.

In some embodiments, the graffiti recognition network may be trained based on back propagation, specifically: calculating the output value of each neuron in a forward direction; reversely calculating the value of an error term of each neuron; the gradient of each weight is calculated according to the corresponding error term. Finally, the graffiti recognition network can accurately recognize the object type of the graffiti track represented by the track point set.

And 103, if the identification result is matched with the object to be drawn, determining that the user scrawling drawing is successful.

In the embodiment of the application, if the identified identification result is matched with the object to be drawn, the user is considered to have correctly drawn the object to be drawn, that is, it is determined that the user has successfully drawn the graffiti. On the contrary, if the identified identification result is not matched with the object to be drawn, the user is considered to fail to correctly draw the object to be drawn, that is, the user can be determined to have a graffiti drawing failure. For example, if the object to be drawn is a "kitten" and the recognition result obtained based on the scribble trajectory input by the user is also a "kitten", the object to be drawn is considered to match the recognition result, and at this time, the user successfully draws the scribble and the next round of game can be started.

In some embodiments, if at least two recognition results are obtained in step 102, the user may be considered to have a successful drawing of the graffiti as long as any recognition result matches the object to be drawn; otherwise, if all the recognition results are not matched with the object to be drawn, the user can be considered to have a doodle drawing failure. For example, the object to be drawn is a "kitten", and three recognition results are obtained based on the scribble trajectory input by the user, namely, a "puppy" with the highest score, a "kitten" with the next highest score and a "bear" with the lowest score, and considering that the "kitten" is matched with the object to be drawn, at this time, the user successfully draws the scribble, and a next round of game can be started.

In some embodiments, a time for drawing by the user may be defined, and after the step 101, the method for identifying graffiti further comprises:

triggering a timer to start timing;

accordingly, the step 1021 can be embodied as:

and receiving a doodle track input by the user on the screen based on the object to be drawn in a preset time period, wherein the starting time of the preset time period is the time when the timer starts to time, and the ending time of the preset time period is the time when the timing time of the timer reaches a preset first time threshold value.

That is, in this case, once an object drawn by the user (an object to be drawn) is given, it can be considered that the game has started. At this point, a timer may be triggered to start counting from 0. The electronic device may preset a first time threshold, such as 20 seconds. The user can only draw on the canvas displayed by the user terminal within 20 seconds after the game starts. Once the timed time of the timer reaches the first time threshold of 20s, the user-drawn graffiti trace is no longer received. That is, after the timing time starts to be counted, only the graffiti trajectory drawn by the user in the time period (i.e., the preset time period) from 0 to 20s of the timing time is received, and the graffiti trajectory drawn by the user outside the preset time period is not taken into account by the electronic device.

In some embodiments, the recognizing may be performed each time the user completes a drawing, and the receiving a graffiti trajectory input by the user on the screen based on the object to be drawn may include:

monitoring the screen;

when the touch operation of the user on the screen is monitored, receiving and storing a doodle track input by the user on the screen based on the object to be drawn;

correspondingly, the above-mentioned trajectory point set that obtains based on above-mentioned scribble orbit includes:

and when the touch operation disappears, acquiring a track point set based on the currently stored doodle track.

That is, after the game starts, the electronic device may monitor the screen of the user terminal, and once the touch operation of the user on the screen is monitored, the user is considered to be drawing at the moment, and at the moment, a doodle track input by the user on the screen based on an object to be drawn is received and stored; once the touch operation of the user on the screen is monitored to disappear, the user is considered to have finished drawing, all scrawling tracks drawn by the user on a canvas displayed on the screen from the beginning of the game to the current moment are stored in the electronic equipment, a track point set is obtained based on the currently stored scrawling tracks, and the track point set is input to a scrawling recognition network for primary recognition. And if the recognition result output by the graffiti recognition network at the moment is not matched with the object to be drawn, continuing monitoring the screen to wait for the next drawing of the user and recognizing the graffiti again. In this embodiment, in order to avoid the user drawing time being too long, a time threshold may be set, which is recorded as a second time threshold, for example, 20 seconds. After the game starts, a timer needs to be triggered to start timing; and if the recognition result output by the graffiti recognition network is not matched with the object to be drawn after the user finishes one-time drawing, continuing to monitor the screen to wait for the next-time drawing of the user, and performing graffiti recognition again until the recognition result output by the graffiti recognition network is matched with the object to be drawn or the timing time of the timer reaches a preset second time threshold value.

To illustrate the above process, the following explanation and description are made with specific examples:

assuming that the object to be drawn is "house", the second time threshold is 20 seconds;

referring to fig. 5-1, in fig. 5-1, a user draws a first stroke based on the object to be drawn, the first stroke takes 2 seconds, the electronic device performs first real-time graffiti recognition based on the graffiti stroke, and if the recognition result is not "house", the electronic device waits for the user to continue drawing;

after the first drawing is finished for 0.5 second, the user continues drawing, please refer to fig. 5-2, where fig. 5-2 is a scribble trajectory obtained after the user draws a second pen based on the object to be drawn, the second drawing takes 1.5 seconds (4 seconds total time), at this time, the scribble trajectory stored by the electronic device includes the first drawing and the second drawing, the electronic device performs a second real-time scribble recognition based on the scribble trajectory, and the recognition result is not "house", and the electronic device waits for the user to continue drawing;

after the second drawing is finished for 0.5 second, the user continues to draw, please refer to fig. 5-3, where fig. 5-3 is a drawing track obtained after the user draws a third drawing based on the object to be drawn, the third drawing takes 1 second (total time consumption is 5.5 seconds), at this time, the drawing track stored by the electronic device includes the first drawing, the second drawing and the third drawing, the electronic device performs the third drawing recognition based on the drawing track, the recognition result is "house", at this time, it is confirmed that the user has drawn successfully, and the game is finished;

as can be seen from fig. 5-1 to 5-3, after each drawing is completed within a predetermined time (20 seconds), the user performs recognition in real time based on the currently existing scribble trajectory; until fig. 5-3, although the door of the house has not been drawn, the graffiti recognition network has been able to determine that the graffiti drawn by the user is "house," at which point the user can confirm that the user has drawn the graffiti successfully without having to make a fourth drawing to mend the door of the house. Through the process, once doodle recognition is carried out after one stroke of drawing is completed, and the efficiency of doodle recognition can be further improved.

It is thus clear that, through this application embodiment, at the in-process of scribble discernment, no longer carry out the scribble discernment based on this whole of image that the user drawn, but only carry out the scribble discernment based on the scribble orbit that the user drawn, this can make the data volume that the front end transmitted for the backstage significantly reduce to reduce data transmission's consuming time, can promote the efficiency of scribble discernment to a certain extent.

Corresponding to the graffiti identification method provided above, an embodiment of the present application further provides a graffiti identification device, which may be integrated in an electronic device, and referring to fig. 3, a graffiti identification device 600 in an embodiment of the present application includes:

a determination unit 601, configured to determine an object to be drawn;

the recognition unit 602 is configured to perform scribble recognition on a scribble trajectory input by a user on the screen based on the object to be drawn, so as to obtain a recognition result;

and the matching unit 603 determines that the user doodle drawing is successful if the identification result is matched with the object to be drawn.

Optionally, the identifying unit 602 includes:

the trajectory receiving subunit is used for receiving a doodle trajectory input by a user on the screen based on the object to be drawn;

the set acquisition subunit is used for acquiring a track point set according to the doodle track, wherein the track point set comprises all track points forming the doodle track;

and the graffiti identification subunit is used for performing graffiti identification on the track point set to obtain an identification result of the track point set.

Optionally, the graffiti recognition subunit is specifically configured to input the track point set to a trained graffiti recognition network, so as to obtain a preset number of recognition results output by the graffiti recognition network, where the preset number is a positive integer greater than 1;

correspondingly, the matching unit 603 is specifically configured to determine that the user has drawn the graffiti successfully if one recognition result matched with the object to be drawn exists in the preset number of recognition results.

Optionally, the graffiti recognition device 600 further comprises:

the timing trigger unit is used for triggering a timer to start timing after the object to be drawn is determined;

correspondingly, the track receiving subunit is specifically configured to receive, within a preset time period, a graffiti track input by the user on the screen based on the object to be drawn, where a start time of the preset time period is a time when the timer starts timing, and an end time of the preset time period is a time when the timing time of the timer reaches a preset first time threshold.

Optionally, the track receiving subunit includes:

the monitoring subunit is used for monitoring the screen;

the storage subunit is used for receiving and storing a doodle track input by the user on the screen based on the object to be drawn when the touch operation of the user on the screen is monitored;

correspondingly, the set acquisition subunit is specifically configured to, when it is monitored that the touch operation disappears, obtain a set of track points based on the currently stored scribble trajectory.

Optionally, the graffiti recognition device 600 further comprises:

correspondingly, after the scribble recognition subunit performs the scribble recognition on the track point set to obtain the recognition result of the track point set, if the recognition result is not matched with the object to be drawn, the execution of the monitoring subunit and other subsequent units is triggered back until the recognition result output by the scribble recognition network is matched with the object to be drawn or the timing time of the timer reaches a preset second time threshold.

Optionally, the determining unit 601 is specifically configured to randomly determine an object to be drawn in a preset system lexicon, where the system lexicon stores names of at least one object that can be expressed by graffiti.

It is thus clear that, through this application embodiment, at the in-process of scribble discernment, the scribble recognition device no longer carries out the scribble discernment based on this whole of image that the user drawn, but only carries out the scribble discernment based on the scribble orbit that the user drawn, and this can make the data volume that the front end transmitted for the backstage significantly reduce to reduce data transmission's consuming time, can promote the efficiency of scribble discernment to a certain extent.

Corresponding to the graffiti identification method provided above, the embodiment of the application further provides an electronic device. The electronic device may be a cloud server, or may be a user terminal used by a user, which is not limited herein. Referring to fig. 7, the electronic device 7 in the embodiment of the present application includes: a memory 701, one or more processors 702 (only one shown in fig. 7), and a computer program stored on the memory 701 and executable on the processors. Wherein: the memory 701 is used for storing software programs and modules, and the processor 702 executes various functional applications and data processing by running the software programs and units stored in the memory 701, so as to acquire resources corresponding to the preset events. Specifically, the processor 702 realizes the following steps by running the above-mentioned computer program stored in the memory 701:

determining an object to be drawn;

and if the identification result is matched with the object to be drawn, determining that the user scribbles and is drawn successfully.

Assuming that the foregoing is the first possible implementation manner, in a second possible implementation manner provided on the basis of the first possible implementation manner, the performing graffiti recognition on a graffiti trajectory input by a user on a screen based on the object to be drawn to obtain a recognition result includes:

receiving a doodle track input by a user on a screen based on the object to be drawn;

obtaining a track point set according to the scrawling track, wherein the track point set comprises all track points forming the scrawling track;

and carrying out graffiti identification on the track point set to obtain an identification result of the track point set.

In a third possible implementation manner provided on the basis of the second possible implementation manner, the performing graffiti recognition on the track point set to obtain a recognition result of the track point set includes:

inputting the track point set into a trained graffiti recognition network to obtain a preset number of recognition results output by the graffiti recognition network, wherein the preset number is a positive integer greater than 1;

correspondingly, if the recognition result is matched with the object to be drawn, determining that the user scribbles and is drawn successfully comprises the following steps:

and if one recognition result matched with the object to be drawn exists in the preset number of recognition results, determining that the user scrawling drawing is successful.

In a fourth possible implementation manner provided on the basis of the second possible implementation manner, after the determining of the object to be drawn, the processor 702, by executing the above computer program stored in the memory 701, implements the following steps:

triggering a timer to start timing;

correspondingly, the receiving of the doodle track input by the user on the screen based on the object to be drawn comprises:

and receiving a doodle track input by the user on the screen based on the object to be drawn within a preset time period, wherein the starting time of the preset time period is the time when the timer starts timing, and the ending time of the preset time period is the time when the timing time of the timer reaches a preset first time threshold value.

In a fifth possible implementation manner provided on the basis of the second possible implementation manner, the receiving a graffiti trajectory input by a user on a screen based on the object to be drawn includes:

monitoring the screen;

correspondingly, the obtaining of the track point set based on the doodle track comprises:

In a sixth possible implementation manner provided on the basis of the fifth possible implementation manner, after the determining the object to be drawn, the graffiti recognition method further includes:

triggering a timer to start timing;

correspondingly, after the scribble recognition is carried out on the track point set to obtain the recognition result of the track point set, the scribble recognition method further comprises the following steps:

and if the identification result is not matched with the object to be drawn, returning to execute the step of monitoring the screen and the subsequent steps until the identification result output by the graffiti identification network is matched with the object to be drawn or the timing time of the timer reaches a preset second time threshold value.

In a seventh possible implementation manner provided on the basis of the first possible implementation manner, the determining an object to be drawn includes:

and randomly determining an object to be drawn in a preset system word bank, wherein the name of at least one object capable of being expressed by scrawling is stored in the system word bank.

It should be understood that in the embodiments of the present Application, the Processor 702 may be a Central Processing Unit (CPU), and the Processor may be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Memory 701 may include both read-only memory and random access memory and provides instructions and data to processor 702. Some or all of memory 701 may also include non-volatile random access memory. For example, memory 701 may also store information of device types.

It is from top to bottom, through this application embodiment, at the in-process of scribble discernment, electronic equipment no longer carries out the scribble discernment based on this whole of image that the user drawn, but only carries out the scribble discernment based on the scribble orbit that the user drawn, and this can make the data volume that the front end transmitted for the backstage significantly reduce to reduce data transmission's consuming time, can promote the efficiency of scribble discernment to a certain extent.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned functions may be distributed as different functional units and modules according to needs, that is, the internal structure of the apparatus may be divided into different functional units or modules to implement all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art would appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of external device software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the above-described modules or units is only one logical functional division, and in actual implementation, there may be another division, for example, multiple 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.

The integrated unit may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer-readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. The computer program includes computer program code, and the computer program code may be in a source code form, an object code form, an executable file or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying the above-described computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer readable Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signal, telecommunication signal, software distribution medium, etc. It should be noted that the computer readable storage medium may contain other contents which can be appropriately increased or decreased according to the requirements of the legislation and the patent practice in the jurisdiction, for example, in some jurisdictions, the computer readable storage medium does not include an electrical carrier signal and a telecommunication signal according to the legislation and the patent practice.

The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims

1. A graffiti identification method is characterized by comprising the following steps:

determining an object to be drawn;

2. The graffiti recognition method as claimed in claim 1, wherein the graffiti recognition of a graffiti track input by a user on a screen based on the object to be drawn is performed to obtain a recognition result, and the method comprises the following steps:

3. The graffiti recognition method according to claim 2, wherein the graffiti recognition of the track point set to obtain a recognition result of the track point set comprises:

4. The graffiti identification method of claim 2, wherein after the determining an object to be drawn, the graffiti identification method further comprises:

triggering a timer to start timing;

5. The graffiti recognition method of claim 2, wherein receiving a graffiti trajectory entered by a user on a screen based on the object to be drawn comprises:

monitoring the screen;

6. The graffiti identification method of claim 5, wherein after the determining an object to be drawn, the graffiti identification method further comprises:

triggering a timer to start timing;

7. The graffiti identification method of claim 1, wherein said determining an object to be drawn comprises:

8. A graffiti identification device, comprising:

a determination unit for determining an object to be drawn;

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.