CN112800962B - Stroke writing direction detection method and device, medium and electronic equipment - Google Patents
Stroke writing direction detection method and device, medium and electronic equipment Download PDFInfo
- Publication number
- CN112800962B CN112800962B CN202110120728.8A CN202110120728A CN112800962B CN 112800962 B CN112800962 B CN 112800962B CN 202110120728 A CN202110120728 A CN 202110120728A CN 112800962 B CN112800962 B CN 112800962B
- Authority
- CN
- China
- Prior art keywords
- stroke
- detected
- vector
- determining
- detection
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/32—Digital ink
- G06V30/333—Preprocessing; Feature extraction
- G06V30/347—Sampling; Contour coding; Stroke extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/32—Digital ink
- G06V30/36—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The present disclosure relates to a stroke writing direction detection method, apparatus, medium, and electronic device, the method comprising: receiving stroke information of a stroke to be detected, wherein the stroke information comprises position information of a plurality of key points corresponding to the stroke to be detected and sequence information corresponding to the key points; performing gradient color rendering on the strokes to be detected according to the position information and the sequence information to generate detection images corresponding to the stroke information; recognizing the strokes to be detected, and determining the type corresponding to the strokes to be detected; and determining the writing direction corresponding to the stroke to be detected according to the detection image and the stroke characteristic information corresponding to the type. Therefore, the comprehensiveness and accuracy of the characteristics of the strokes to be detected during the writing direction detection can be improved, so that the method can be applied to the writing scenes of complex characters, the application range of the method is widened, and the accuracy and robustness of the writing direction identification of the strokes to be detected are improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a medium, and an electronic device for detecting a writing direction of a stroke.
Background
In the experience of practicing calligraphy, children often appear the condition that the stroke is write in reverse, usually detect through the initial position of detecting the stroke sampling point among the prior art. However, because the strokes of the Chinese characters are complex, the accuracy and robustness of the characters written in complex forms are not sufficient when the detection is performed by the method for detecting the sampling points.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
In a first aspect, the present disclosure provides a method for detecting a writing direction of a stroke, the method including:
receiving stroke information to be detected, wherein the stroke information comprises position information of a plurality of key points corresponding to the stroke to be detected and sequence information corresponding to the key points;
performing gradient color rendering on the strokes to be detected according to the position information and the sequence information to generate detection images corresponding to the stroke information;
recognizing the strokes to be detected, and determining the type corresponding to the strokes to be detected;
and determining the writing direction corresponding to the stroke to be detected according to the detection image and the stroke characteristic information corresponding to the type.
In a second aspect, there is provided a stroke writing direction detecting apparatus, the apparatus including:
the stroke information comprises position information of a plurality of key points corresponding to the stroke to be detected and sequence information corresponding to the key points;
the rendering module is used for performing gradient color rendering on the strokes to be detected according to the position information and the sequence information to generate a detection image corresponding to the stroke information;
the recognition module is used for recognizing the strokes to be detected and determining the type corresponding to the strokes to be detected;
and the first determining module is used for determining the writing direction corresponding to the stroke to be detected according to the detection image and the stroke characteristic information corresponding to the type.
In a third aspect, a computer-readable medium is provided, on which a computer program is stored which, when being executed by a processing device, carries out the steps of the method of the first aspect.
In a fourth aspect, an electronic device is provided, comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to carry out the steps of the method of the first aspect.
In the technical scheme, stroke information to be detected is received, gradient color rendering is carried out on the strokes to be detected according to position information of a plurality of key points corresponding to the strokes to be detected and the sequence information corresponding to the key points, the strokes to be detected are contained in the stroke information, detection images corresponding to the stroke information are generated, the strokes to be detected are identified, the types corresponding to the strokes to be detected are determined, and therefore the writing directions corresponding to the strokes to be detected can be determined according to the detection images and the stroke characteristic information corresponding to the types. Therefore, according to the technical scheme, when the writing direction of the stroke to be detected is detected, the stroke to be detected is not directly detected based on the sequence of sampling points, but is subjected to gradient color rendering, so that the writing direction of the stroke to be detected can be represented according to the gradient color characteristics, when the detection of the writing direction is carried out based on the detection image, the detection image not only contains the writing direction characteristics, but also contains the corresponding color characteristics to carry out another dimensionality representation on the writing direction, the comprehensiveness and the accuracy of the characteristics when the writing direction of the stroke to be detected is detected are improved, the method can be suitable for the writing scene of complex characters, the application range of the method is widened, and the accuracy and the robustness of the recognition of the writing direction of the stroke to be detected are improved. In addition, accurate data support can be provided for prompting the user in the subsequent character writing process, and the use experience of the user is improved.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale. In the drawings:
FIG. 1 is a flow chart of a stroke writing direction detection method provided according to one embodiment of the present disclosure;
fig. 2A and 2B are rendering diagrams of strokes to be detected provided according to an embodiment of the present disclosure;
FIG. 3 is a block diagram of a stroke writing direction detection apparatus provided in accordance with one embodiment of the present disclosure;
FIG. 4 shows a schematic structural diagram of an electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "including" and variations thereof as used herein is intended to be open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
Fig. 1 is a flowchart illustrating a stroke writing direction detection method according to an embodiment of the present disclosure, where as shown in fig. 1, the method includes:
in step 11, stroke information to be detected is received, where the stroke information includes position information of a plurality of key points corresponding to the stroke to be detected and sequence information corresponding to the plurality of key points. The stroke information can be triggered and generated when a user writes in the writing board, and therefore the stroke information is obtained. For example, the keypoint samples can be taken during the writing process, so that the position information of a plurality of keypoints and the sequence information corresponding to the plurality of keypoints can be obtained. As shown in FIG. 2A, points 1-5 are key points of stroke information corresponding to user written strokes, left falling down.
In step 12, performing gradient color rendering on the stroke to be detected according to the position information and the sequence information, and generating a detection image corresponding to the stroke information.
The data set for rendering the gradient color can be generated by utilizing online data of the CASIA in advance, so that gradient color rendering is carried out on the strokes based on the data set, and the detection image can be generated based on the stroke information of the strokes to be detected. For example, a gradient color rendering may be performed according to the position information and the forward direction corresponding to the sequence information to obtain the detection image, that is, a transition from a starting point of the stroke to be detected to an end point of the stroke to be detected in the detection image is performed through a gradient color. As shown in fig. 2A, the forward direction corresponding to the sequence information is a direction with a point 1 as a starting point and a point 5 as an end point, wherein the sequence information can be rendered in a gradient color from white to black, i.e., the point 1 corresponds to white and the point 5 corresponds to black. The manner of performing the gradient color rendering may adopt a general rendering algorithm, which is not limited in this disclosure.
In step 13, the strokes to be detected are identified, and the type corresponding to the strokes to be detected is determined. Wherein the recognition may be based on stroke recognition models commonly used in the art or by comparison with standard strokes of various types.
In step 14, according to the detected image and the stroke feature information corresponding to the type, the writing direction corresponding to the stroke to be detected is determined.
Illustratively, the standard color image corresponding to the stroke characteristic information corresponding to the type is an image obtained by performing gradient color rendering on key points obtained based on a forward writing sequence corresponding to the type, then the detection image and the standard color image corresponding to the stroke to be detected can be input into an image detection model, when an output result of the image detection model shows that the detection image and the standard color image are similar, the writing direction corresponding to the stroke to be detected is determined to be a forward direction, and when an output result of the image detection model shows that the detection image and the standard color image are not similar, the writing direction corresponding to the stroke to be detected is determined to be a reverse direction.
In the technical scheme, stroke information to be detected is received, gradient color rendering is performed on the stroke to be detected according to position information of a plurality of key points corresponding to the stroke to be detected and the sequence information corresponding to the key points, which are contained in the stroke information, to be detected, a detection image corresponding to the stroke information is generated, the stroke to be detected is identified, the type corresponding to the stroke to be detected is determined, and therefore the writing direction corresponding to the stroke to be detected can be determined according to the detection image and the stroke characteristic information corresponding to the type. Therefore, according to the technical scheme, when the writing direction of the stroke to be detected is detected, the stroke to be detected is not directly detected based on the sequence of sampling points, but is subjected to gradient color rendering, so that the writing direction of the stroke to be detected can be represented according to the gradient color characteristics, when the detection of the writing direction is carried out based on the detection image, the detection image not only contains the writing direction characteristics, but also contains the corresponding color characteristics to carry out another dimensionality representation on the writing direction, the comprehensiveness and the accuracy of the characteristics when the writing direction of the stroke to be detected is detected are improved, the method can be suitable for the writing scene of complex characters, the application range of the method is widened, and the accuracy and the robustness of the recognition of the writing direction of the stroke to be detected are improved. In addition, accurate data support can be provided for prompting the user in the subsequent character writing process, and the use experience of the user is improved.
In order to make those skilled in the art more understand the technical solutions provided by the embodiments of the present invention, the following detailed descriptions are provided for the above steps.
In a possible embodiment, forward sampling may be performed in advance for each type of standard stroke to obtain position information of a key point corresponding to the standard stroke and sequence information corresponding to the plurality of key points, so that gradient color rendering may be performed on the standard stroke according to the position information and the sequence information of the key point corresponding to the standard stroke, thereby obtaining a color image corresponding to the standard stroke. Stroke characteristic information characterizing the standard stroke may then be extracted from the color image. The mode of generating the color image corresponding to the standard stroke is similar to the mode of generating the detection image corresponding to the stroke to be detected, and the implementation mode of the specific step is not repeated.
In the embodiment of the present disclosure, the standard strokes corresponding to each type may be subjected to feature extraction in advance by the above manner, and a standard vector is obtained as stroke feature information, so that each extracted stroke feature information may be stored in advance. Correspondingly, after the type corresponding to the stroke to be detected is determined, the stroke characteristic information corresponding to the type of the stroke to be detected can be directly determined from the pre-stored stroke characteristic information according to the type, so that the detection efficiency of the writing direction can be improved to a certain extent.
Accordingly, an exemplary implementation manner of determining the stroke writing direction corresponding to the stroke to be detected according to the detection image in step 13 is as follows, and the step may include:
extracting the characteristics of the detection image to obtain a characteristic vector corresponding to the detection image;
and determining the stroke writing direction corresponding to the stroke to be detected according to the characteristic vector and the stroke characteristic information.
Therefore, by the technical scheme, the feature extraction can be carried out based on the detection image, so that more comprehensive and accurate features corresponding to the strokes to be detected are obtained, the stroke writing direction is determined by combining the feature vector and the stroke feature information for analysis, the stroke writing feature and the visual color feature can be combined simultaneously when the writing direction is detected, the global feature of the strokes to be detected can be effectively represented by the color feature, the use range and the robustness of the method can be improved, the error of detection only according to the sequence of sampling points in the prior art is avoided, and the use experience of a user is improved.
In a possible embodiment, an exemplary implementation manner of performing feature extraction on the detected image to obtain a feature vector corresponding to the detected image is as follows, and the step may include:
and inputting the detection image into a character recognition model, and determining the characteristic vector according to the output of a characteristic layer of the character recognition model.
The character recognition model can be implemented by training based on a neural network model, and illustratively, the Resnet 50 model can be used for training. There are multiple feature layers in the model, for example, after the training of the model is finished, the output of one of the feature layers of the model may be used as the feature vector, where the feature layer may be set according to an actual usage scenario, for example, the output of the 4 th layer may be extracted as the feature vector. As another example, it may also be specified that outputs of partial feature layers of the plurality of feature layers are weighted and combined, thereby obtaining the feature vector.
Wherein the character recognition model is determined by:
and aiming at the characters written in the standard way, performing gradient color rendering on each stroke of the characters to generate training images corresponding to the characters. The method comprises the steps of obtaining a plurality of strokes of a character, and obtaining a training image corresponding to the character by rendering the strokes according to position information and sequence information of key points of the strokes in the character. The manner in which the gradient color rendering is performed for each stroke is described in detail above and will not be described in detail here.
And then, taking the training image as the input of a model, taking the identification result of the character as the output of the model, and training the model to obtain the character recognition model.
For example, for a character "permanent" written in a standard manner, the identification result of the character is the text itself, and then the training image corresponding to the character "permanent" may be input into the model, so as to obtain the output of the model. Thereafter, a loss value of the model may be determined based on the output of the model and the identification result, and parameters of the model may be adjusted based on the loss value. And repeating iteration through the process, and determining that the model training is finished to obtain the character recognition model under the condition that the loss value is smaller than the preset threshold value.
In this embodiment, in the process of recognizing the characters in the input training image by the character recognition model, the feature layer in the middle of the model needs to perform feature extraction on the input training image to obtain the features of the characters corresponding to the training image, so that in the present disclosure, the feature vectors included in the image can be obtained by the feature layer of the character recognition model, the training process of the model for performing feature extraction can be simplified, and the matching degree between the extracted feature vectors and the characters can be ensured, so that the accuracy of the feature vectors extracted based on the model can be provided for accurate data support for the subsequent determination of the writing direction.
In a possible embodiment, the exemplary implementation manner of performing gradient color rendering on the stroke to be detected according to the position information and the sequence information to generate the detection image corresponding to the stroke information is as follows, and the step may include:
and performing gradient color rendering according to the position information and the forward direction corresponding to the sequence information to generate a forward direction color image.
And performing gradient color rendering according to the position information and the reverse direction corresponding to the sequence information to generate a reverse color image, wherein the detection image comprises the forward color image and the reverse color image.
In this embodiment, two detection images may be generated based on the stroke information. Illustratively, as described above, fig. 2A shows a color image obtained by performing the gradient color rendering in the forward direction based on the order information. In this embodiment, the detection image may also be obtained by performing gradient color rendering according to the position information and the reverse direction corresponding to the sequence information, that is, performing gradient color rendering with the point 5 as a starting point and the point 1 as an end point, as shown in fig. 2B, where the point 1 corresponds to black and the point 5 corresponds to white.
Therefore, two detection images can be generated based on the stroke information through the technical scheme so as to perform visual color representation on the forward characteristic and the reverse characteristic of the stroke information, and therefore more comprehensive and accurate data support can be provided for the subsequent writing direction detection process.
As described above, in a possible embodiment, the detection image is rendered according to the writing order of the strokes to be detected, that is, according to the forward direction corresponding to the order information of the strokes to be detected.
Correspondingly, the stroke feature information comprises a standard forward vector and a standard reverse vector, wherein the standard forward vector is extracted from an image obtained by performing gradient color rendering on the forward writing direction of the standard stroke, and the standard reverse vector is extracted from an image obtained by performing gradient color rendering on the reverse writing direction of the standard stroke. The exemplary implementation manner for determining the stroke writing direction corresponding to the stroke to be detected according to the feature vector and the stroke feature information may include:
and calculating the similarity according to the standard forward vector and the feature vector to serve as a first similarity parameter, and calculating the similarity according to the standard reverse vector and the feature vector to serve as a second similarity parameter, so that the corresponding stroke writing direction can be determined according to the first similarity parameter and the second similarity parameter.
In one possible embodiment, the detection image may include a forward color image and a reverse color image, the stroke feature information includes a normal forward vector and a normal reverse vector, and the feature vector may include a detection forward vector and a detection reverse vector. The detection forward vector is a feature vector extracted from the forward color image and used for representing features corresponding to the actual writing sequence of the strokes to be detected, and the detection reverse vector is a feature vector extracted from the reverse color image and used for representing features corresponding to the reverse direction of the actual writing sequence of the strokes to be detected.
Correspondingly, the exemplary implementation manner for determining the stroke writing direction corresponding to the stroke to be detected according to the feature vector and the stroke feature information may include the following steps:
and determining a first similar parameter and a second similar parameter corresponding to the stroke to be detected according to the standard forward vector, the standard backward vector, the detection forward vector and the detection backward vector.
The first similar parameter can be used for representing the possibility that the writing direction of the stroke to be detected is the same as the standard writing direction, and the second similar parameter can be used for representing the possibility that the writing direction of the stroke to be detected is opposite to the standard writing direction.
The exemplary implementation manner of determining the first similar parameter and the second similar parameter corresponding to the stroke to be detected according to the standard forward vector, the standard backward vector, the detected forward vector and the detected backward vector may include:
and determining the sum of the similarity parameters corresponding to the standard forward vector and the detection forward vector and the similarity parameters corresponding to the standard reverse vector and the detection reverse vector as the first similarity parameter.
In this embodiment, the writing directions corresponding to the standard forward vector and the detection forward vector may be the same to some extent by adding the detection backward vector, and the writing directions corresponding to the standard backward vector and the detection backward vector may also be the same to some extent by adding the detection backward vector, so that in this embodiment, the two cases may be considered at the same time, and thus the accuracy of the determined first similar parameter may be ensured.
And determining the similarity parameter corresponding to the standard forward vector and the detected backward vector and the sum of the similarity parameters corresponding to the standard backward vector and the detected forward vector as the second similarity parameter.
Similarly, when the standard reverse vector and the detected forward vector are similar, the writing directions corresponding to the standard reverse vector and the detected forward vector may be different to some extent.
The similarity parameter may be a distance between two vectors or a cosine value of an included angle corresponding to the two vectors, which is not limited by the present disclosure.
In this embodiment, when the writing direction of the stroke to be detected is detected, the characteristics corresponding to the stroke to be detected in the writing direction can be combined with the reverse characteristics of the stroke to be detected, and the characteristics of the stroke to be detected in two directions are analyzed, so that the accuracy of the determined similar parameters can be improved. Meanwhile, by analyzing the characteristics of the strokes to be detected from the multiple directions, errors caused by one-sidedness of direction recognition of the single direction of the strokes to be detected can be avoided, the recognition accuracy of the method in a complex character writing scene is further improved, accurate data support is provided for subsequent direction prompt and the like, and the method is convenient for users to use.
Then, the stroke writing direction can be determined according to the first similarity parameter and the second similarity parameter.
For example, the determining the stroke writing direction according to the first similarity parameter and the second similarity parameter may include:
determining the writing direction of the stroke to be detected as the forward direction under the condition that the similarity level corresponding to the first similarity parameter is higher than the similarity level corresponding to the second similarity parameter;
and under the condition that the similarity level corresponding to the first similar parameter is lower than the similarity level corresponding to the second similar parameter, determining that the writing direction of the stroke to be detected is reverse.
If the first similar parameter and the second similar parameter are the distance between vectors, the smaller the similarity parameter is, the higher the corresponding similarity level is; if the first similar parameter and the second similar parameter are cosine values of included angles between vectors, the larger the similarity parameter is, the higher the corresponding similarity level is.
Therefore, in this embodiment, the writing direction is detected by determining the similarity levels corresponding to the first similarity parameter and the second similarity parameter, where the first similarity parameter and the second similarity parameter are respectively used to represent the similarities between the writing direction of the stroke to be detected and the forward direction and the reverse direction of the standard stroke, and then the direction indicated by the similarity parameter with the high similarity level may be determined as the writing direction. In the embodiment, when the writing party is detected, the judgment threshold value is not required to be set, so that the influence on the writing direction detection caused by the inaccurate judgment threshold value can be effectively avoided, the accuracy of the determined writing direction can be improved, and the workload of a user can be saved.
The present disclosure also provides a device for detecting a writing direction of a stroke, as shown in fig. 3, the device 10 includes:
the receiving module 100 is configured to receive stroke information to be detected, where the stroke information includes position information of a plurality of key points corresponding to the stroke to be detected and sequence information corresponding to the plurality of key points;
the rendering module 200 is configured to perform gradient color rendering on the stroke to be detected according to the position information and the sequence information, and generate a detection image corresponding to the stroke information;
the recognition module 300 is configured to recognize the stroke to be detected, and determine a type corresponding to the stroke to be detected;
and a first determining module 400, configured to determine, according to the detection image, a writing direction corresponding to the stroke to be detected.
Optionally, the rendering module comprises:
the first rendering submodule is used for performing gradient color rendering according to the forward direction corresponding to the position information and the sequence information to generate a forward direction color image;
and the second rendering submodule is used for performing gradient color rendering according to the position information and the reverse direction corresponding to the sequence information to generate a reverse color image, wherein the detection image comprises the forward color image and the reverse color image.
Optionally, the first determining module includes:
the extraction submodule is used for extracting the characteristics of the detection image to obtain a characteristic vector corresponding to the detection image;
and the first determining submodule is used for determining the stroke writing direction corresponding to the stroke to be detected according to the characteristic vector and the stroke characteristic information.
Optionally, the detection image comprises a forward color image and a reverse color image, the stroke feature information comprises a standard forward vector and a standard reverse vector, the feature vector comprises a detection forward vector corresponding to the forward color image and a detection reverse vector corresponding to the reverse color image;
the first determination submodule includes:
the second determining submodule is used for determining a first similar parameter and a second similar parameter corresponding to the stroke to be detected according to the standard forward vector, the standard reverse vector, the detection forward vector and the detection reverse vector;
and the third determining submodule is used for determining the stroke writing direction according to the first similarity parameter and the second similarity parameter.
Optionally, the second determining sub-module includes:
a fourth determining submodule, configured to determine, as the first similarity parameter, a sum of similarity parameters corresponding to the standard forward vector and the detected forward vector and similarity parameters corresponding to the standard reverse vector and the detected reverse vector;
and the fifth determining submodule is used for determining the similarity parameter corresponding to the standard forward vector and the detection backward vector and the sum of the similarity parameters corresponding to the standard backward vector and the detection forward vector as the second similarity parameter.
Optionally, the third determining submodule includes:
a sixth determining submodule, configured to determine that the writing direction of the stroke to be detected is the forward direction when the similarity level corresponding to the first similarity parameter is higher than the similarity level corresponding to the second similarity parameter;
and the seventh determining submodule is used for determining that the writing direction of the stroke to be detected is reverse under the condition that the similarity level corresponding to the first similarity parameter is lower than the similarity level corresponding to the second similarity parameter.
Optionally, the extracting sub-module includes:
an eighth determining submodule, configured to input the detection image into a character recognition model, and determine the feature vector according to an output of a feature layer of the character recognition model;
wherein the character recognition model is determined by:
aiming at a character written in a standard way, performing gradient color rendering on each stroke of the character to generate a training image corresponding to the character;
and taking the training image as the input of a model, taking the identification result of the character as the output of the model, and training the model to obtain the character recognition model.
Referring now to FIG. 4, a block diagram of an electronic device 600 suitable for use in implementing embodiments of the present disclosure is shown. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 4, the electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, magnetic tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, the processes described above with reference to the flow diagrams may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: receiving stroke information to be detected, wherein the stroke information comprises position information of a plurality of key points corresponding to the stroke to be detected and sequence information corresponding to the key points; performing gradient color rendering on the strokes to be detected according to the position information and the sequence information to generate detection images corresponding to the stroke information; recognizing the strokes to be detected, and determining the type corresponding to the strokes to be detected; and determining the writing direction corresponding to the stroke to be detected according to the detected image and the stroke characteristic information corresponding to the type.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, smalltalk, C + +, and including conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. The name of a module does not constitute a limitation to the module itself in some cases, and for example, a receiving module may also be described as a "module that receives stroke information to be detected".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems on a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Example 1 provides a stroke writing direction detection method according to one or more embodiments of the present disclosure, wherein the method includes:
receiving stroke information to be detected, wherein the stroke information comprises position information of a plurality of key points corresponding to the stroke to be detected and sequence information corresponding to the key points;
performing gradient color rendering on the strokes to be detected according to the position information and the sequence information to generate detection images corresponding to the stroke information;
recognizing the strokes to be detected, and determining the type corresponding to the strokes to be detected;
and determining the writing direction corresponding to the stroke to be detected according to the detection image and the stroke characteristic information corresponding to the type.
Example 2 provides the method of example 1, wherein the performing, according to the position information and the sequence information, gradient color rendering on the stroke to be detected to generate a detection image corresponding to the stroke information includes:
performing gradient color rendering according to the position information and the forward direction corresponding to the sequence information to generate a forward direction color image;
and performing gradient color rendering according to the position information and the reverse direction corresponding to the sequence information to generate a reverse color image, wherein the detection image comprises the forward color image and the reverse color image.
Example 3 provides the method of example 2, wherein the determining, according to the detection image and the stroke feature information corresponding to the type, a writing direction corresponding to the stroke to be detected includes:
extracting the characteristics of the detection image to obtain a characteristic vector corresponding to the detection image;
and determining the stroke writing direction corresponding to the stroke to be detected according to the characteristic vector and the stroke characteristic information.
Example 4 provides the method of example 3, wherein the detection image includes a forward color image and a reverse color image, the standard vectors include a standard forward vector and a standard reverse vector, and the stroke feature information includes a detected forward vector corresponding to the forward color image and a detected reverse vector corresponding to the reverse color image;
the determining the stroke writing direction corresponding to the stroke to be detected according to the feature vector and the standard vector comprises:
determining a first similar parameter and a second similar parameter corresponding to the stroke to be detected according to the standard forward vector, the standard backward vector, the detection forward vector and the detection backward vector;
and determining the stroke writing direction according to the first similarity parameter and the second similarity parameter.
Example 5 provides the method of example 4, wherein the determining, according to the standard forward vector, the standard backward vector, the detected forward vector, and the detected backward vector, the first similarity parameter and the second similarity parameter corresponding to the stroke to be detected includes:
determining the sum of similarity parameters corresponding to the standard forward vector and the detection forward vector and the similarity parameters corresponding to the standard reverse vector and the detection reverse vector as the first similarity parameter;
and determining the similarity parameter corresponding to the standard forward vector and the detected backward vector and the sum of the similarity parameters corresponding to the standard backward vector and the detected forward vector as the second similarity parameter.
Example 6 provides the method of example 4 or example 5, wherein the determining the stroke writing direction according to the first similarity parameter and the second similarity parameter includes:
determining the writing direction of the stroke to be detected as the forward direction under the condition that the similarity level corresponding to the first similarity parameter is higher than the similarity level corresponding to the second similarity parameter;
and under the condition that the similarity level corresponding to the first similar parameter is lower than the similarity level corresponding to the second similar parameter, determining that the writing direction of the stroke to be detected is reverse.
Example 7 provides the method of example 3, wherein the extracting features of the detected image to obtain a feature vector corresponding to the detected image includes:
inputting the detection image into a character recognition model, and determining the characteristic vector according to the output of a characteristic layer of the character recognition model;
wherein the character recognition model is determined by:
aiming at the characters written in a standard way, performing gradient color rendering on each stroke of the characters to generate training images corresponding to the characters;
and taking the training image as the input of a model, taking the identification result of the character as the output of the model, and training the model to obtain the character recognition model.
Example 8 provides a stroke writing direction detection apparatus, according to one or more embodiments of the present disclosure, the apparatus including:
the stroke information comprises position information of a plurality of key points corresponding to the stroke to be detected and sequence information corresponding to the key points;
the rendering module is used for performing gradient color rendering on the strokes to be detected according to the position information and the sequence information to generate a detection image corresponding to the stroke information;
the recognition module is used for recognizing the strokes to be detected and determining the type corresponding to the strokes to be detected;
and the first determining module is used for determining the writing direction corresponding to the stroke to be detected according to the detection image and the stroke characteristic information corresponding to the type.
Example 9 provides a computer readable medium having stored thereon a computer program that, when executed by a processing apparatus, performs the steps of the method of any one of examples 1-7, in accordance with one or more embodiments of the present disclosure.
Example 10 provides, in accordance with one or more embodiments of the present disclosure, an electronic device comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to carry out the steps of the method of any one of examples 1-7.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Claims (8)
1. A stroke writing direction detection method is characterized by comprising the following steps:
receiving stroke information to be detected, wherein the stroke information comprises position information of a plurality of key points corresponding to the stroke to be detected and sequence information corresponding to the key points;
performing gradient color rendering on the strokes to be detected according to the position information and the sequence information to generate detection images corresponding to the stroke information;
recognizing the strokes to be detected, and determining the type corresponding to the strokes to be detected;
determining the writing direction corresponding to the stroke to be detected according to the detection image and the stroke characteristic information corresponding to the type;
the determining the writing direction corresponding to the stroke to be detected according to the detection image and the stroke characteristic information corresponding to the type comprises the following steps:
extracting the characteristics of the detection image to obtain a characteristic vector corresponding to the detection image;
determining the stroke writing direction corresponding to the stroke to be detected according to the feature vector and the stroke feature information;
the detection image comprises a forward color image and a reverse color image, the stroke feature information comprises a standard forward vector and a standard reverse vector, the feature vectors comprise a detection forward vector corresponding to the forward color image and a detection reverse vector corresponding to the reverse color image;
determining the stroke writing direction corresponding to the stroke to be detected according to the feature vector and the stroke feature information, wherein the determining comprises the following steps:
determining a first similar parameter and a second similar parameter corresponding to the stroke to be detected according to the standard forward vector, the standard backward vector, the detection forward vector and the detection backward vector;
determining the stroke writing direction according to the first similarity parameter and the second similarity parameter;
the first similar parameter is used for representing the possibility that the writing direction of the stroke to be detected is in the same direction as the standard writing direction, and the second similar parameter is used for representing the possibility that the writing direction of the stroke to be detected is in the opposite direction to the standard writing direction.
2. The method according to claim 1, wherein performing gradient color rendering on the stroke to be detected according to the position information and the sequence information to generate a detection image corresponding to the stroke information comprises:
performing gradient color rendering according to the position information and the forward direction corresponding to the sequence information to generate a forward direction color image;
and performing gradient color rendering according to the position information and the reverse direction corresponding to the sequence information to generate a reverse color image, wherein the detection image comprises the forward color image and the reverse color image.
3. The method according to claim 1, wherein the determining a first similarity parameter and a second similarity parameter corresponding to the stroke to be detected according to the standard forward vector, the standard backward vector, the detected forward vector and the detected backward vector comprises:
determining the sum of similarity parameters corresponding to the standard forward vector and the detection forward vector and the similarity parameters corresponding to the standard reverse vector and the detection reverse vector as the first similarity parameter;
and determining the similarity parameter corresponding to the standard forward vector and the detected backward vector and the sum of the similarity parameters corresponding to the standard backward vector and the detected forward vector as the second similarity parameter.
4. The method according to claim 1 or 3, wherein the determining the stroke writing direction according to the first similarity parameter and the second similarity parameter comprises:
determining the writing direction of the stroke to be detected as the forward direction under the condition that the similarity level corresponding to the first similarity parameter is higher than the similarity level corresponding to the second similarity parameter;
and under the condition that the similarity level corresponding to the first similarity parameter is lower than the similarity level corresponding to the second similarity parameter, determining that the writing direction of the stroke to be detected is reverse.
5. The method according to claim 1, wherein the performing feature extraction on the detected image to obtain a feature vector corresponding to the detected image comprises:
inputting the detection image into a character recognition model, and determining the characteristic vector according to the output of a characteristic layer of the character recognition model;
wherein the character recognition model is determined by:
aiming at the characters written in a standard way, performing gradient color rendering on each stroke of the characters to generate training images corresponding to the characters;
and taking the training image as the input of a model, taking the identification result of the character as the output of the model, and training the model to obtain the character recognition model.
6. A stroke writing direction detecting device, characterized in that the device comprises:
the stroke information comprises position information of a plurality of key points corresponding to the stroke to be detected and sequence information corresponding to the key points;
the rendering module is used for performing gradient color rendering on the strokes to be detected according to the position information and the sequence information to generate a detection image corresponding to the stroke information;
the recognition module is used for recognizing the strokes to be detected and determining the types corresponding to the strokes to be detected;
the first determining module is used for determining the writing direction corresponding to the stroke to be detected according to the detection image and the stroke characteristic information corresponding to the type;
the first determining module includes:
the extraction submodule is used for extracting the characteristics of the detection image to obtain a characteristic vector corresponding to the detection image;
the first determining submodule is used for determining the stroke writing direction corresponding to the stroke to be detected according to the feature vector and the stroke feature information;
the detection image comprises a forward color image and a reverse color image, the stroke feature information comprises a standard forward vector and a standard reverse vector, the feature vectors comprise a detection forward vector corresponding to the forward color image and a detection reverse vector corresponding to the reverse color image;
the first determination submodule includes:
the second determining submodule is used for determining a first similar parameter and a second similar parameter corresponding to the stroke to be detected according to the standard forward vector, the standard reverse vector, the detection forward vector and the detection reverse vector;
the third determining submodule is used for determining the stroke writing direction according to the first similarity parameter and the second similarity parameter;
the first similar parameters are used for representing the possibility that the writing direction of the stroke to be detected is the same as the standard writing direction, and the second similar parameters are used for representing the possibility that the writing direction of the stroke to be detected is opposite to the standard writing direction.
7. A computer-readable medium, on which a computer program is stored, characterized in that the program, when being executed by processing means, carries out the steps of the method of any one of claims 1 to 5.
8. An electronic device, comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to carry out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110120728.8A CN112800962B (en) | 2021-01-28 | 2021-01-28 | Stroke writing direction detection method and device, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110120728.8A CN112800962B (en) | 2021-01-28 | 2021-01-28 | Stroke writing direction detection method and device, medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112800962A CN112800962A (en) | 2021-05-14 |
| CN112800962B true CN112800962B (en) | 2023-02-28 |
Family
ID=75812562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110120728.8A Active CN112800962B (en) | 2021-01-28 | 2021-01-28 | Stroke writing direction detection method and device, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800962B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101253513A (en) * | 2005-08-29 | 2008-08-27 | 微软公司 | Style aware use of writing input |
| CN101764940A (en) * | 2008-11-04 | 2010-06-30 | 新奥特（北京）视频技术有限公司 | Subtitle rendering method based on pixel space mask matrix model |
| CN105700671A (en) * | 2014-11-26 | 2016-06-22 | 熊兆王 | Gesture control method and system |
| CN109147002A (en) * | 2018-06-27 | 2019-01-04 | 北京捷通华声科技股份有限公司 | A kind of image processing method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150088933A (en) * | 2014-01-24 | 2015-08-04 | 민수정 | Method for teaching an order of making strokes in writing characters using Gradation |
| JP2016114652A (en) * | 2014-12-11 | 2016-06-23 | 株式会社文溪堂 | Training aid for character learning |
| TWI676919B (en) * | 2018-08-02 | 2019-11-11 | 義守大學 | Computerized writing evaluation and training method |
-
2021
- 2021-01-28 CN CN202110120728.8A patent/CN112800962B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101253513A (en) * | 2005-08-29 | 2008-08-27 | 微软公司 | Style aware use of writing input |
| CN101764940A (en) * | 2008-11-04 | 2010-06-30 | 新奥特（北京）视频技术有限公司 | Subtitle rendering method based on pixel space mask matrix model |
| CN105700671A (en) * | 2014-11-26 | 2016-06-22 | 熊兆王 | Gesture control method and system |
| CN109147002A (en) * | 2018-06-27 | 2019-01-04 | 北京捷通华声科技股份有限公司 | A kind of image processing method and device |
Non-Patent Citations (2)
| Title |
|---|
| EasyFont: A style Learning-Based System to Easily Build Your Large-Scale Handwriting Fonts;Zhouhui Lian 等;《ACM Transactions on Graphics》;20181214;第38卷(第1期);第1-18页 * |
| 以笔画为研究对象的笔迹伪动态特征提取方法;王民 等;《计算机工程与应用》;20150605;第52卷(第18期);第179-182、207页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112800962A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298413B (en) | Image feature extraction method and device, storage medium and electronic equipment | |
| CN113313064A (en) | Character recognition method and device, readable medium and electronic equipment | |
| CN110826567B (en) | Optical character recognition method, device, equipment and storage medium | |
| CN112883968B (en) | Image character recognition method, device, medium and electronic equipment | |
| CN110659639B (en) | Chinese character recognition method and device, computer readable medium and electronic equipment | |
| CN112883967B (en) | Image character recognition method, device, medium and electronic equipment | |
| CN110188782B (en) | Image similarity determining method and device, electronic equipment and readable storage medium | |
| CN112800961B (en) | Stroke writing sequence detection method, device, medium and electronic equipment | |
| CN109829431B (en) | Method and apparatus for generating information | |
| CN112990176B (en) | Writing quality evaluation method and device and electronic equipment | |
| CN112883966B (en) | Image character recognition method, device, medium and electronic equipment | |
| CN114153959A (en) | Key value matching method and device, readable medium and electronic equipment | |
| CN110674813B (en) | Chinese character recognition method and device, computer readable medium and electronic equipment | |
| CN113191257B (en) | Order of strokes detection method and device and electronic equipment | |
| CN110765304A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| CN110705536A (en) | Chinese character recognition error correction method and device, computer readable medium and electronic equipment | |
| CN112800962B (en) | Stroke writing direction detection method and device, medium and electronic equipment | |
| CN114612909A (en) | Character recognition method and device, readable medium and electronic equipment | |
| CN114463768A (en) | Form recognition method and device, readable medium and electronic equipment | |
| CN114495080A (en) | Font identification method and device, readable medium and electronic equipment | |
| CN114758342A (en) | Text recognition method, device, medium and electronic equipment | |
| CN114429628A (en) | Image processing method and device, readable storage medium and electronic equipment | |
| CN114862720A (en) | Canvas restoration method and device, electronic equipment and computer readable medium | |
| CN110334763B (en) | Model data file generation method, model data file generation device, model data file identification device, model data file generation apparatus, model data file identification apparatus, and model data file identification medium | |
| CN113255812A (en) | Video frame detection method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |