CN110263636A - A kind of lossless person's handwriting restoring method and system - Google Patents

Abstract

Technical solution of the present invention includes kind of a lossless person's handwriting restoring method and system; it is characterized in that; this method comprises: S10, is acquired the handwriting image data write based on writing device, wherein the image data acquired is the coordinate of collection point, pressure sensitivity coefficient and apart from the upper time；The data of each stroke in handwriting image data are grouped by S20；S30, coordinate data and pressure sensitivity coefficient based on each stroke collection point calculate the derivative point of corresponding first edge and the derivative point of second edge, and the derivative point in each group of multiple edges is attached, and generate person's handwriting file；S40 is handled using Bezier algorithm by point is derived per two adjacent edges in person's handwriting file, obtains final person's handwriting.The invention has the benefit that the person's handwriting for improving accuracy rate and generation that person's handwriting identifies is more life-like.

Description

A kind of non-destructive handwriting restoration method and system

technical field

The invention relates to a lossless handwriting restoration method and system, belonging to the field of computers.

Background technique

At present, in the banking, telecommunications and other service industries, paperless services have become the norm, and all places that required handwritten signatures in the past need to be electronically handwritten signatures. When writing naturally, the strength of the strokes and the fluency of writing all affect the authenticity of the signature and handwriting. Therefore, in the paperless service, an algorithm is needed that can accurately restore the real handwriting, and can enlarge it without distortion, so as to compare the details. At present, the more common practice is to collect the points passed by the stroke during the writing process, and record the coordinate position and pressure sensitivity coefficient of each point in the stroke. When restoring, the coordinates of each point are taken as the center of the circle, and the pressure sensitivity coefficient is the radius/diameter. Dots of different sizes form visual lines through the aggregation of dots. The handwriting formed by such "points and lines" method, after magnifying a certain number of times, the details of the lines, especially the corners of the lines, will show obvious traces of connection, resulting in local distortion of the lines. And for handwriting with dense signature lines, the concentration of dots makes the lines indistinguishable.

SUMMARY OF THE INVENTION

The present invention provides a lossless handwriting restoration method and system, which are used to solve the deficiencies of the prior art.

The technical solution of the present invention includes a non-destructive handwriting restoration method, which is characterized in that the method includes: S10, collecting handwriting image data written based on a writing device, wherein the collected image data is the coordinates of the collection point, the pressure sensitivity coefficient and the The time from the previous point; S20, group the data of each stroke in the handwriting image data; S30, calculate the corresponding first edge derivative point and the second edge derivative point based on the coordinate data of each stroke collection point and the pressure sensitivity coefficient point, to generate a handwriting file; S40, use the Bessel algorithm to process every two adjacent edge-derived points in the handwriting file to obtain the final handwriting.

According to the non-destructive handwriting restoration method, S10 specifically includes: using a writing device with a collection function to collect the handwriting image data input by the user, and the collection points include abscissa, ordinate and pressure-sensitive data; Stroke is drawn as a stroke image.

According to the non-destructive handwriting restoration method, the stroke image is an SVG vector diagram.

According to the non-destructive handwriting restoration method, S20 specifically includes: taking the continuous collection point as a complete stroke based on the time from the previous point, and starting the action beyond the preset time as a new stroke, and further using the continuous collection point as a new stroke. points as a set of data.

According to the non-destructive handwriting restoration method, S30 includes: calculating the first edge derivative point and the second edge derivative point of the collection point according to the coordinate data and the pressure sensitivity coefficient of the connected collection points, and specifically includes: S31, according to any connected collection point. The two collection points (x ₁ , y ₁ ) and (x ₂ , y ₂ ) of , calculate the sin value and cos value of the angle a between the straight line formed by the two collection points and the abscissa; S32, take (x ₁ , y ₁ ) as the starting point, with (x ₂ , y ₂ ) as the end point, according to the sin value, cos value and pressure sensitivity coefficient of the angle a between the straight line and the abscissa, calculate the rotation length r, and further perform the reverse-time and clockwise steps respectively. Rotate 90° to obtain the corresponding first edge derived point and second edge derived point; S33, sequentially mark the first edge derived point of each collection point of the same group of strokes, and then reversely mark the second edge derived point of each collection point. Edge derived points form edge point markers for a full stroke.

According to the lossless handwriting restoration method, S31 specifically includes: dividing the distance of the ordinate axis by the distance of two points to obtain the sin value of a, and the calculation method is sina=(y ₂ -y ₁ )/R; Divide the distance of the abscissa axis by the distance of the two points to obtain the cos value of a, which is calculated as cosa=(x ₂ -x ₁ )/R.

According to the lossless handwriting restoration method, S32 includes: calculating the first edge derived point and the second edge derived point through the left transformation, and rotating 90 degrees counterclockwise through the coordinate geometric transformation formula to calculate the first edge Derived point (x1 _A , y1 _A ) x1 _A =x1-rsin(a-90)=x1+rcosa, y1 _A =y1-rcos(a-90)=y1-rsina; through the coordinate geometric transformation formula, rotate clockwise 90 degrees, calculate the second edge derived point (x1 _B , y1 _B ), x1 _A = x1-rsin(a-90)=x1+rcosa, y1 _A =y1-rcos(a-90)=y1-rsina .

According to the non-destructive handwriting restoration method, S40 includes: processing the first edge derived point and the second edge derived point using a Bezier curve algorithm, including calculating a Bezier curve for the collection points connected to each collection point The control points of , and the optimized Bezier curve is generated according to the control points.

According to the lossless handwriting restoration method, calculating the Bezier curve control point specifically includes: calculating the first control point, specifically: PA(n)_x=x(n)+(x(n+1)-x(n -1))*0.15, PA(n)_y=y(n)+(y(n+1)-y(n-1))*0.15, where 0.15 is the smoothing coefficient; calculate the second control point, specifically : pB(n)_x=x(n+1)-(x(n+2)-x(n))*0.15, pB(n)_y=y(n+1)+(y(n+2) -y(n))*0.15; According to the obtained first control point and second control point, the Sebel curve of each collection point is generated, and the optimization of each stroke is completed.

The calculation scheme of the present invention also includes a non-destructive handwriting restoration system according to any of the above-mentioned methods, characterized in that the system includes: a stroke collection module for collecting handwriting image data written by a writing device, wherein the collected image data are the coordinates of the collection point, the pressure sensitivity coefficient and the time from the previous point; the stroke grouping module is used to group the data of each stroke in the handwriting image data; the derived point calculation module is used to collect the points based on each stroke. The coordinate data and the pressure sensitivity coefficient calculate the corresponding first edge derived point and the second edge derived point, and connect multiple edge derived points in each group to generate a handwriting file; The edge-derived points are processed using the Bezier algorithm to obtain the final handwriting.

The beneficial effects of the invention are as follows: the accuracy of handwriting recognition is improved, and the generated handwriting is more realistic, natural, and enlarged without distortion.

Description of drawings

Figure 1 shows an overall flow chart according to an embodiment of the present invention;

Figure 2 shows a system block diagram according to an embodiment of the present invention;

Figures 3a, 3b, and 3c show handwriting restoration diagrams according to embodiments of the present invention;

Figures 4a and 4b are respectively a handwriting diagram of a signature and an enlarged diagram of a part according to an embodiment of the present invention.

Detailed ways

The concept, specific structure and technical effects of the present invention will be clearly and completely described below in conjunction with the embodiments and the accompanying drawings, so as to fully understand the purpose, solutions and effects of the present invention.

It should be noted that, unless otherwise specified, when a feature is called "fixed" or "connected" to another feature, it can be directly fixed or connected to another feature, or it can be indirectly fixed or connected to another feature. on a feature. In addition, descriptions such as upper, lower, left, right, etc. used in the present disclosure are only relative to the mutual positional relationship of each component of the present disclosure in the accompanying drawings. As used in this disclosure, the singular forms "a," "the," and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. Also, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. The terms used in the specification herein are for the purpose of describing specific embodiments only, and not for the purpose of limiting the present invention. As used herein, the term "and/or" includes any combination of one or more of the associated listed items.

It will be understood that, although the terms first, second, third, etc. may be used in this disclosure to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish elements of the same type from one another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present disclosure. The use of any and all examples or exemplary language ("for example," "such as," etc.) provided herein is intended only to better illustrate embodiments of the invention and does not impose limitations on the scope of the invention unless otherwise claimed .

Figure 1 shows an overall flow diagram according to an embodiment of the present invention. S10, collecting the handwriting image data written based on the writing device, wherein the collected image data is the coordinates of the collection point, the pressure sensitivity coefficient and the time from the previous point; S20, grouping the data of each stroke in the handwriting image data S30, calculate the corresponding first edge derived point and the second edge derived point based on the coordinate data of each stroke collection point and the pressure sensitivity coefficient, and connect the multiple edge derived points of each group to generate a handwriting file; S40, The Bezier algorithm is used to process every two adjacent edge-derived points in the handwriting file to obtain the final handwriting.

Figure 2 shows a system block diagram according to an embodiment of the present invention. The system includes: a stroke collection module for collecting handwriting image data written by a writing device, wherein the collected image data is the coordinates of the collection point, the pressure sensitivity coefficient and the time from the previous point; the stroke grouping module is used for handwriting The data of each stroke in the image data is grouped; the derived point calculation module is used to calculate the corresponding first edge derived point and the second edge derived point based on the coordinate data and pressure sensitivity coefficient of each stroke collection point, and calculate the corresponding first edge derived point and the second edge derived point. Groups of multiple edge-derived points are connected to generate a handwriting file; the optimization module uses the Bezier algorithm to process every two adjacent edge-derived points in the handwriting file to obtain the final handwriting.

3a, 3b, and 3c are diagrams illustrating restoration of handwriting according to an embodiment of the present invention.

Let's first look at the pressure-sensitive data collected by a set of handwriting tablets:

166.8158,71.54401,0.049804688,0;

166.69043,71.54401,0.14550781,5;

166.43958,71.54401,0.19824219,4;

166.06342,71.54401,0.23046875,5;

165.6872,71.54401,0.25,4;

......

......

Each row of the above data group contains 4 data, which are the data of the collection point.

x, y, pressure sensitivity coefficient, time from the previous point

Now we need to generate an image of handwriting based on the above collection points.

The characteristic of svg vector graphics is that it is enlarged without distortion. In order to achieve the effect, the generated handwriting image needs to be drawn by "stroke", that is, according to the thickness of the writing, the outline of the stroke is depicted, as shown in the stroke image below:

Referring to Figure 3a, in order to achieve this effect, the collected data needs to be processed. First of all, we need to group the strokes, take a continuous point as a complete stroke, pay attention to the fourth value of each group of data: the time from the previous point, we can consider it as a new stroke if the distance from the previous point exceeds 90 To start, build an array of strokes. For each point within the stroke, calculate the two edge points derived from that point.

The black point is the collection point, the line is the length calculated according to the third data - pressure sensitivity coefficient, and the gray point is the derived edge point.

Referring to Figure 3b, according to the two collection points x1, y1, x2, y2, the sin and cos values of the angle a between the straight line formed by the two points and the x-coordinate axis can be calculated:

Divide the distance on the y-axis by the distance between the two points to get the sine of a

sin a=(y2-y1)/R

Divide the distance on the x-axis by the distance between the two points to get the cosine of a

cos a=(x2-x1)/R

The two derived blue dots can be obtained by rotating 90 degrees forward and backward in time respectively, using the length r calculated from the starting point of x1 and y1 as the pressure-sensitive system in the two-point straight line, as shown in Figure 3c below:

Therefore, the two derived points are (note that the y-axis direction in the computer is opposite to that of the Cartesian coordinate system in the figure):

Through the coordinate geometric transformation formula, rotate 90 degrees counterclockwise, and calculate the first edge derived point (x1, y1)

x1_a=x1-rsin(a-90)=x1+rcos a

y1_a=y1-rcos(a-90)=y1-rsin a

Through the coordinate geometric transformation formula, rotate 90 degrees clockwise to calculate the second edge derived point (x1, y1)

x1_b=x1-rsin(a+90)=x1-rcos a

y1_b=y1-rcos(a+90)=y1+rsin a

Then connect the sequence of the same group of strokes to the derivative point 1, and then connect the derivative point 2 in reverse order to form the following svg

<path d="M x1_a y1_a L x2_a y2_a...L xn_a yn_a L xn_by yn_b...L x2_by2_b Lx1_b y1_b Z" style="stroke-width:1px;"/>

For the handwriting generated above, the dots are connected by straight lines. When enlarged, the handwriting edges displayed in the image will appear stiff and not smooth enough. Therefore, we use the Bezier curve algorithm to improve the generated edge points. For each two points, the adjacent two points of the front and rear endpoints are required to calculate the control points of the Bezier curve:

Control point 1pA(n)_x=x(n)+(x(n+1)-x(n-1))*0.15 0.15 is the smoother coefficient of the Bezier curve tested

pA(n)_y=y(n)+(y(n+1)-y(n-1))*0.15

Control point 2: pB(n)_x=x(n+1)-(x(n+2)-x(n))*0.15

pB(n)_y=y(n+1)-(y(n+2)-y(n))*0.15

Once the control points are obtained, the relevant Bezier curve can be formed:

<path M x1_a y1_a C pA(2)_x pA(2)_y pB(2)_x pB(2)_y x2_a y2_a….style="stroke-width:1px;"/>

After being improved by the Bezier algorithm, the edge of the handwriting curve is smooth and natural after being enlarged.

Figures 4a and 4b are respectively a handwriting diagram of a signature and an enlarged diagram of a part according to an embodiment of the present invention. Fig. 4a is the signature handwriting generated by the algorithm, and Fig. 4b is the partially enlarged handwriting, and there is no distortion such as blur and sawtooth when enlarged.

It should be appreciated that embodiments of the present invention may be implemented or implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in non-transitory computer readable memory. The method can be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the specific Methods and figures described in the Examples. Each program may be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, if desired, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.

Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes (or variations and/or combinations thereof) described herein can be performed under the control of one or more computer systems configured with executable instructions, and as code that executes collectively on one or more processors (eg, , executable instructions, one or more computer programs or one or more applications), implemented in hardware, or a combination thereof. The computer program includes a plurality of instructions executable by one or more processors.

Further, the methods may be implemented in any type of computing platform operably connected to a suitable, including but not limited to personal computer, minicomputer, mainframe, workstation, network or distributed computing environment, stand-alone or integrated computer platform, or communicate with charged particle tools or other imaging devices, etc. Aspects of the invention may be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optically read and/or written storage medium, RAM, ROM, etc., such that it can be read by a programmable computer, when a storage medium or device is read by a computer, it can be used to configure and operate the computer to perform the processes described herein. Furthermore, the machine-readable code, or portions thereof, may be transmitted over wired or wireless networks. The invention described herein includes these and other various types of non-transitory computer-readable storage media when such media includes instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein.

A computer program can be applied to input data to perform the functions described herein, transforming the input data to generate output data for storage to non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects produced on the display.

The above are only preferred embodiments of the present invention, and the present invention is not limited to the above-mentioned embodiments, as long as it achieves the technical effect of the present invention by the same means, all within the spirit and principle of the present invention, do Any modification, equivalent replacement, improvement, etc., should be included within the protection scope of the present invention. Various modifications and changes can be made to its technical solutions and/or implementations within the protection scope of the present invention.

Claims (10)

1. a kind of lossless person's handwriting restoring method, which is characterized in that this method comprises:

S10 is acquired the handwriting image data write based on writing device, wherein the image data acquired is collection point Coordinate, pressure sensitivity coefficient and apart from the upper time；

The data of each stroke in handwriting image data are grouped by S20；

S30, coordinate data and pressure sensitivity coefficient based on each stroke collection point calculate the derivative point of corresponding first edge and second Edge derives point, and the derivative point in each group of multiple edges is attached, and generates person's handwriting file；

S40 is handled using Bezier algorithm by point is derived per two adjacent edges in person's handwriting file, obtains final pen Mark.

2. lossless person's handwriting restoring method according to claim 1, which is characterized in that the S10 is specifically included:

The handwriting image data inputted using the writing device acquisition user for having acquisition function are acquired, and collection point includes Abscissa, ordinate and pressure sensitivity data；

Image data of identifying the handwriting, which carries out retouching side, is depicted as stroke image.

3. lossless person's handwriting restoring method according to claim 2, which is characterized in that the stroke image is SVG polar plot.

4. lossless person's handwriting restoring method according to claim 1, which is characterized in that the S20 is specifically included:

Based on apart from the upper time using continuous collection point as a complete stroke, and be more than preset time conduct then Start as new stroke, further using continuous collection point as one group of data.

5. lossless person's handwriting restoring method according to claim 1, which is characterized in that the S30 includes:

The derivative point of first edge and second edge for calculating the collection point according to the coordinate data of connected collection point and pressure sensitivity coefficient Derivative point, specifically includes:

S31, according to two arbitrarily connected collection point (x₁,y₁) and (x₂,y₂), calculate the straight line and seat of the formation of two collection points The sin value and cos value of parameter x angle a；

S32, with (x₁,y₁) it is used as starting point, with (x₂,y₂) it is used as terminal, according to sin value, the cos value of straight line and abscissa angle a, Using default thickness value multiplied by pressure sensitivity coefficient as radius of turn r, the inverse time is further executed respectively and 90 ° of up time rotate, obtain pair The derivative point of the first edge answered and the derivative point of second edge；

The derivative point of the first edge of each collection point of same group of stroke is linked in sequence by S33, and the connection of another mistake sequence is each adopted The derivative point of the second edge of collection point forms the SVG of a complete stroke.

6. lossless person's handwriting restoring method according to claim 5, which is characterized in that the S31 is specifically included:

With the distance of reference axis y divided by the distance of two o'clock, the sin value of a is obtained, calculation is sina=(y₂-y₁)/R；

With the distance of reference axis x divided by the distance of two o'clock, the cos value of a is obtained, calculation is cosa=(x₂-x₁)/R。

7. lossless person's handwriting restoring method according to claim 5, which is characterized in that the S32 includes:

It is calculated, is converted by coordinate geometry public by left side transformation point derivative to first edge and the derivative point of second edge Formula is rotated by 90 ° counterclockwise, calculates the derivative point (x1 in first edge_A,y1_A)

x1_A=x1-rsin (a-90)=x1+rcosa,

y1_A=y1-rcos (a-90)=y1-rsina；

By coordinate geometry transformation for mula, 90 degree are rotated clockwise, calculates the derivative point (x1 in second edge_B,y1_B)

x1_A=x1-rsin (a-90)=x1+rcosa,

y1_A=y1-rcos (a-90)=y1-rsina.

8. lossless person's handwriting restoring method according to claim 1, which is characterized in that the S40 includes:

Point derivative to first edge and the derivative point of second edge are handled using Bezier algorithm, including to each acquisition The connected collection point of point calculates the control point of Bezier, generates the Bezier after optimization according to control point.

9. lossless person's handwriting restoring method according to claim 8, which is characterized in that it is specific to calculate Bezier control point Include:

The first control point is calculated, specifically:

PA (n) _ x=x (n)+(x (n+1)-x (n-1)) * 0.15,

PA (n) _ y=y (n)+(y (n+1)-y (n-1)) * 0.15, wherein 0.15 is smoothing factor；

The second control point is calculated, specifically:

PB (n) _ x=x (n+1)-(x (n+2)-x (n)) * 0.15,

PB (n) _ y=y (n+1)+(y (n+2)-y (n)) * 0.15；

The match Bell curve of each collection point is generated according to obtained the first control point and the second control point, is completed to each stroke Optimization.

10. a kind of lossless person's handwriting also original system of -9 any the methods according to claim 1, which is characterized in that the system packet It includes:

Stroke acquisition module, the handwriting image data for being write by writing device are acquired, wherein the picture number acquired According to coordinate, the pressure sensitivity coefficient and apart from the upper time for collection point；

Stroke groupings module, for being grouped the data of each stroke in handwriting image data；

A derivative point computing module, for based on each stroke collection point coordinate data and pressure sensitivity coefficient calculate corresponding first side The derivative point of edge and the derivative point of second edge are generated comprising the derivative point person's handwriting file in all edges；

Optimization module is handled using Bezier algorithm by point is derived per two adjacent edges in person's handwriting file, and described For SVG, final lossless person's handwriting is obtained.