CN116959004A - Handwritten signature recognition methods, devices, electronic equipment and computer program products - Google Patents

Abstract

This application relates to the field of data processing technology and provides a handwritten signature recognition method, device, electronic equipment and computer program products. The method includes: extracting a vector image object of the file to be recognized based on the file format of the file to be recognized, where the vector image object includes characteristic information of a handwritten signature; and constructing a path object based on the vector image object, where the path object is To characterize the path or contour of the image; draw the path object, and cut the drawn path object to obtain a handwritten signature picture. The embodiment of this application obtains a handwritten signature picture by extracting vector image objects, constructing, drawing, and clipping path objects based on the vector image objects. Based on this, when there is a watermark on the background of the handwritten signature, or there are other interfering factors such as other text on the superimposed document document At this time, the intercepted handwritten signature picture has strong anti-interference, which improves the audit accuracy and the accuracy of handwritten signature recognition.

Description

Handwritten signature recognition methods, devices, electronic equipment and computer program products

Technical field

This application relates to the field of data processing technology, specifically to a handwritten signature recognition method, device, electronic equipment and computer program product.

Background technique

In the audit business of paperless electronic documents of the operator's business, the location, identification, extraction and preservation of the customer's handwritten electronic signature in the business document is related to the identification of the customer subject of the document business. It is the entrance to the business audit, so it is important in the entire operation. It is particularly important and critical in the business of paperless document audit.

Currently, there are three main ways to extract and save handwritten signatures on electronic documents: intercepting signatures based on coordinates, intercepting signatures based on picture elements, and using AI to identify signature areas and intercept them.

Regarding the method of intercepting signatures by coordinates: When there is a watermark on the background of the signature, or other text on part of the document is superimposed, the intercepted signature image will cause a certain degree of interference for manual recognition and program recognition. Regarding the method of intercepting signatures based on picture elements: the PDF document file contains multiple picture elements, and it is impossible to clearly distinguish which one is the signature picture based on size and color. If the signature picture is not stored in the PDF document file in image form, it cannot be obtained. Signed picture. Regarding the method of using AI to identify signature areas and intercept them: a large number of samples are required for training, and a large amount of annotation work is required, and the accuracy rate cannot reach 100%.

Based on this, existing methods for identifying handwritten signatures on electronic documents are inaccurate.

Contents of the invention

Embodiments of the present application provide a handwritten signature recognition method, device, electronic equipment and computer program product to solve the technical problem of inaccurate handwritten signature recognition.

In a first aspect, embodiments of the present application provide a handwritten signature recognition method, including:

Based on the file format of the file to be recognized, extract a vector image object of the file to be recognized, where the vector image object includes characteristic information of a handwritten signature;

Based on the vector image object, construct a path object, which is used to represent the path or contour of the image;

The path object is drawn, and the drawn path object is cropped to obtain a handwritten signature picture.

In one embodiment, constructing a path object based on the vector image object includes:

The path object is constructed based on the characteristic information of the handwritten signature of the vector image object and at least one path construction operator.

In one embodiment, the step of drawing the path object and cropping the drawn path object to obtain a handwritten signature picture includes:

Using a path drawing operator, stroke and fill the path object to draw the path object on the canvas;

A path clipping operator is used to cross-process the drawn path object and the clipping area to clip the path object outside the clipping area to obtain the handwritten signature picture.

In one embodiment, extracting the vector image object of the file to be identified based on the file format of the file to be identified includes:

Based on the signature page identification, determine the signature page of the document to be identified;

identifying the content of the signature page based on the file format;

The vector image object is extracted from the recognized content of the signature page.

In one embodiment, identifying the content of the signature page based on the file format includes:

Based on the file format, the signature page is parsed and rendered to obtain the content of the signature page.

In one embodiment, extracting the vector image object from the recognized content of the signature page includes: extracting a target element from the content of the signature page, and performing text processing on the target element to obtain the target Text; based on the characteristics of the vector image object, extract the vector image object in the target text.

In one embodiment, after drawing the path object, cropping the drawn path object, and obtaining a handwritten signature image, the method includes: converting the handwritten signature image into a raster image, and storing the raster image. .

In a second aspect, embodiments of the present application provide a handwritten signature recognition device, including:

An extraction module, configured to extract a vector image object of the file to be recognized based on the file format of the file to be recognized, where the vector image object includes characteristic information of a handwritten signature;

A construction module, configured to construct a path object based on the vector image object, where the path object is used to represent the path or contour of the image;

Obtaining a module for drawing the path object, cropping the drawn path object, and obtaining a handwritten signature picture.

In a third aspect, embodiments of the present application provide an electronic device, including a processor and a memory storing a computer program. When the processor executes the program, the steps of the handwritten signature recognition method described in the first aspect are implemented.

In a fourth aspect, embodiments of the present application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the handwritten signature recognition method of the first aspect.

The handwritten signature recognition method, device, electronic equipment and computer program product provided by the embodiments of the present application extract the vector image object of the file to be recognized based on the file format of the file to be recognized, and the vector image object includes the characteristics of the handwritten signature. information; based on the vector image object, construct a path object, the path object is used to represent the path or outline of the image; draw the path object, and cut the drawn path object to obtain a handwritten signature picture. The embodiment of this application obtains a handwritten signature picture by extracting vector image objects, constructing, drawing, and clipping path objects based on the vector image objects. Based on this, when there is a watermark on the background of the handwritten signature, or there are other interfering factors such as other text on the superimposed document document At this time, the intercepted handwritten signature picture has strong anti-interference, which improves the audit accuracy and the accuracy of handwritten signature recognition.

Description of the drawings

In order to explain the technical solutions in this application or the prior art more clearly, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are of the present invention. For some embodiments of the application, those of ordinary skill in the art can also obtain other drawings based on these drawings without exerting creative efforts.

Figure 1 is a schematic flow chart of a handwritten signature recognition method provided by an embodiment of the present application;

Figure 2 is a schematic structural diagram of a handwritten signature recognition device provided by an embodiment of the present application;

Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are part of this application. Examples, not all examples. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

Figure 1 is a schematic flowchart of a handwritten signature recognition method provided by an embodiment of the present application. Referring to Figure 1, an embodiment of the present application provides a handwritten signature recognition method, which may include:

S100, based on the file format of the file to be recognized, extract the vector image object of the file to be recognized. The vector image object includes the characteristic information of the handwritten signature;

The document to be identified is an electronic document of the operator's business, and the document to be identified has the customer's handwritten signature.

The electronic document in the embodiment of this application is in PDF format, and the file format includes the PDF structure of the file. PDF structure includes: file header, cross-reference table, directory, object, page, font, annotation, image, etc. Different PDF files can have different structures and contents.

The vector image object is a vector image containing characteristic information of a handwritten signature, such as a signature. Vector images are a type of image described using mathematical formulas and geometric elements, corresponding to pixel images (bitmaps). Vector images represent images by defining properties such as geometric shapes, paths, curves, and colors, rather than through arrays of pixels.

Based on the PDF structure of the file to be identified, by analyzing the PDF structure, the customer's handwritten signature is located, the target element in the PDF file to be identified is located, and the vector image object is further extracted from the target element to obtain the customer's handwritten signature.

S200, based on the vector image object, construct a path object, which is used to represent the path or contour of the image;

Determine the key parameters of the vector image object in the PDF file to be recognized. Based on the key parameters, establish the mapping relationship between the graphic elements of the handwritten signature and the raster graphic within the PDF structure, and clarify the conversion logic from the graphic elements of the handwritten signature to the raster graphic.

Construct a path object of the vector image object based on the key parameters of the vector image object; for example, extract the line shape and number of the vector image object, and construct a path object with the same line shape and number based on the line shape and number of the vector image object.

S300: Draw a path object, crop the drawn path object, and obtain a handwritten signature image.

Draw the constructed path object and draw the path object on a canvas. Crop the path object area in the canvas to obtain a handwritten signature image. For example, a cropping shape is set in advance, such as a rectangular frame or a circular frame, the drawn path object is placed in the cropping shape, and the path object and the surrounding area are cropped according to the cropping shape to obtain a handwritten signature image.

The embodiment of the present application extracts the vector image object of the file to be recognized based on the file format of the file to be recognized. The vector image object includes the characteristic information of the handwritten signature; based on the vector image object, a path object is constructed, and the path object is used to characterize the path or path of the image. Contour; draw the path object, crop the drawn path object, and obtain the handwritten signature picture. The embodiment of this application obtains a handwritten signature picture by extracting vector image objects, constructing, drawing, and clipping path objects based on the vector image objects. Based on this, when there is a watermark on the background of the handwritten signature, or there are other interfering factors such as other text on the superimposed document document At this time, the intercepted handwritten signature picture has strong anti-interference, which improves the audit accuracy and the accuracy of handwritten signature recognition.

Based on the above embodiment, based on the vector image object, a path object is constructed, including:

S210: Construct a path object based on the feature information of the handwritten signature of the vector image object and at least one path construction operator.

Feature information includes the geometric shape of the handwritten signature, such as straight lines, curves, diagonal lines, etc. The path construction operator is an operator for constructing path objects.

Construct a path object from the geometry of the handwritten signature using at least one path construction operator, for example, using a path construction operator such as Move To, Line To, Quadratic Bezier Curve to ( QuadraticBezier Curve To) and other operations to construct the shape and outline of the path object. Use these operators to create paths based on the handwritten signature style and shape; for example, when the geometry of the handwritten signature is a curve shape, a cubic Bezier curve is used, where the expression of the cubic Bezier curve is:

R(t)＝(1-t) ³ ×P ₀ +3t×(1-t) ² ×P ₁ +3t ² ×(1-t)P ₂ +t ³ ×P ₃ ;

Among them, P ₀ is the starting point, P ₁ and P ₂ are control points, P ₃ is the end point, R(t) is the cubic Bezier curve, and t is the position of a specific point.

Through different parameter values t, the positions of different points on the curve can be calculated, thereby drawing the entire cubic Bezier curve. t represents the position of a point on the curve in a cubic Bezier curve, which determines the shape of the curve between the starting point and the end point. When the value of t is between 0 and 1, it represents the position from the starting point to the end point of the curve. When t approaches 0, the points on the curve will approach the starting point P ₀ ; when t approaches 1, the points on the curve will approach the end point P ₃ .

The embodiment of the present application constructs a path object through feature information and a path construction operator, thereby improving the accuracy of constructing a path object.

Based on the above embodiment, the path object is drawn and the drawn path object is cropped to obtain a handwritten signature image, including:

S310, use a path drawing operator to stroke and fill the path object to draw the path object on the canvas;

S320: Use a path clipping operator to cross-process the drawn path object and the clipping area to clip the path object outside the clipping area to obtain a handwritten signature image.

Path drawing operators are operators that describe how to construct and draw paths, where paths include straight lines, curves, closed paths, etc.

There can be multiple path objects in the embodiment of this application. The number of path objects is determined by the number of words in the handwritten signature. For example, if the handwritten signature is "Zhang Xiaoming", then the number of words in the handwritten signature is 3, and the number of corresponding path objects is 3. .

Draw each path object in order from front to back. For example, first find the path object of "Zhang" and draw "Zhang"; then find the path object of "Small" and draw "Small"; finally find the path of "Ming" Object, drawn "Ming".

The drawing of each path object includes stroking and filling the path object on the canvas. Stroking can add color and line style to the outline of the path, and filling can add color and texture to the interior of the path. When drawing the next path object, the drawing process of the previous path object will be considered, such as the coordinate position, color settings, etc. of the previous path object.

When you need to clip a path object into a specific shape, use the path clipping operator. By performing an intersection operation on the path object and the clipping area, only the part of the path object within the clipping area is retained to achieve the clipping effect on the path object.

Embodiments of the present application implement drawing and clipping of path objects by using path drawing operators and path clipping operators, thereby obtaining handwritten signatures and improving the accuracy of handwritten signature recognition.

Based on the above embodiment, based on the file format of the file to be recognized, extracting the vector image object of the file to be recognized includes:

S110, based on the signature page identification, determine the signature page of the file to be identified;

S120, based on the file format, identify the content of the signature page;

S130: Extract vector image objects from the recognized content of the signature page.

The signature page mark is a mark or mark used to identify and locate the signature position in the document to provide users with an area to clearly locate the signature, such as "Party A or Party A's guardian", "My signature", "Handling person" Signature" etc. The signature page identification can be one of the following forms:

(1) Signature line: Reserve a line of space for a signature in a form or document, usually with the words "Signature" or "Signature" above or below the line. (2) Signature box: Define a rectangular area in the document for placing signatures. This rectangle is usually marked with a dashed line or other special style. (3) Signature label: Use text or icons to mark the location where a signature is required in the document, such as using the words "Sign Here" or an indicator arrow. (4) Handwritten signature area: A blank handwritten area is reserved in the electronic document. Users can use input devices such as touch screens, digital pads, or mice to directly handwrite signatures in this area.

When an operator's business electronic document has many pages, for example, more than 20 pages, the signature page can be quickly located through the signature page identification. Traverse the content of each page of the PDF file to be identified, and identify the signature page based on the signature page identification. Identify and extract target elements from the content of the signature page, and identify vector graphic objects based on the target elements.

Optionally, directly identify the content of the page to be identified without identifying the signature page, for example, directly traverse the PDF page elements of each page in the file to be identified to obtain the content of the page to be identified. Identify and extract target elements from the content of the page to be identified, and identify vector graphics objects based on the target elements.

The embodiment of the present application improves the efficiency of handwritten signature recognition by identifying the content of the signature page and then extracting vector image objects.

Based on the above embodiment, based on the file format, identifying the content of the signature page includes:

S121: Based on the file format, parse and render the signature page to obtain the content of the signature page.

Parsing and rendering engines include: PyMuPDF, MuPDF, etc. The embodiment of this application takes PyMuPDF as an example for description.

PyMuPDF is a powerful and flexible PDF processing library that can read, write and process PDF files. PyMuPDF can parse PDF files and extract text, images, fonts and other objects.

Use PyMuPDF to traverse the pages of the PDF signature page, obtain the page content, detect the text and images in the page, and then identify the content of the signature page.

Optionally, use PyMuPDF to traverse all pages of the file to be identified to obtain the page content, detect the text and images in the page, and then identify the content of the file to be identified.

The application embodiment uses a parsing and rendering engine to identify the content of the signature page, thereby improving the efficiency of handwritten signature recognition.

Based on the above embodiment, vector image objects are extracted from the recognized content of the signature page, including:

S131, extract the target element from the content of the signature page, and perform text processing on the target element to obtain the target text;

S132. Based on the characteristics of the vector image object, extract the vector image object in the target text.

The target element is a complete stream type element. In a PDF file, an element of stream type is an object type used to store and transmit data. Stream type elements are used to store various types of data, such as text content, image data, font data, etc.

The characteristics of the vector image object include the storage location and structure characteristics of the vector image.

List the recognized contents of the signature page to obtain a recognized content list. Optionally, list the recognized contents of the files to be recognized to obtain a recognized content list.

The identification content list in the embodiment of this application includes a cross-reference table (Cross-Reference Table, XRef). The XRef list can record the location and number information of the identified content. Find the complete stream type element based on the XRef list. Then the external object (XObject) in the stream type element is text-processed to obtain the target text. The XObject object is a type used to represent embedded images, forms, vector graphics and other elements. Detect and analyze the instruction sequence in some bytes in the target text of each XObject object, such as the instruction sequence in the first 40 bytes; obtain the storage location and structure of the XObject object. Compare the storage location and structure of the analyzed XObject object with the storage location and structure of the vector image object (handwritten signature), and then determine whether the XObject object is a vector image object.

For example, if the first 40 bytes of the target text of an XObject object start with [1J1j/DeviceRGB CS 0.000.00 0.00SCN] or [Q\nq\nq\n0 0 0RG], then find the graphics status of the XObject object Based on the operation instructions, color space instructions, and instructions to save and restore the graphics state, the storage location and structure of the XObject object are analyzed based on the above instructions, and then whether the XObject object is a vector image object is determined.

Collect in advance a variety of electronic documents of operator services containing handwritten signatures, analyze the handwritten signatures in the electronic documents of the operator's services, and summarize the storage location and structure of vector image objects (handwritten signatures) as a means to identify vector image objects. basis.

Based on the above method, all vector image objects are extracted.

The embodiment of the present application improves the efficiency of handwritten signature recognition by extracting target elements and performing text processing on the target elements to obtain vector image objects.

Based on the above embodiment, the path object is drawn, the drawn path object is cropped, and the handwritten signature image is obtained, including:

S330: Convert the handwritten signature image into a raster image, and store the raster image.

Raster images include bitmaps or pixel images, which are images composed of pixels. Raster pictures are represented in matrix form, where each pixel has its own color value and position. The color value of each pixel represents the color and brightness information of the image at that location. Raster images can be saved in a variety of file formats, such as Joint PhotographicExperts Group (JPG), Portable Network Graphics (PNG), etc. Different file formats have different characteristics and uses, such as JPEG for photos and PNG for when images require transparency.

Save the handwritten signature image in PNG format: save the path information in the handwritten signature image, leave the non-path information in the handwritten signature image blank, and obtain a transparent handwritten signature signature trajectory map. The PNG format has lossless compression characteristics, can preserve the quality and details of the image, and supports transparency.

Optionally, save the signature trajectory map in PNG format as JPG format.

Optionally, save the handwritten signature image directly in JPG format.

In the embodiment of this application, by first saving the handwritten signature image in PNG format and then converting it into JPG format, the file size and compression rate can be controlled while retaining higher quality, transparency, and clarity of lines and text, thereby improving handwriting. Accuracy of signature recognition.

In order to further analyze and explain the handwritten signature recognition method provided by the embodiments of this application, the following embodiments will be specifically described:

Step 1: Input the PDF file, traverse the content of each page of the PDF file, and find the signature page based on the signature page identifier;

Step 2: Use PyMuPDF to load the content of the PDF signature page and obtain the XRef list of the signature page;

Step 3: Traverse the XRef list, find the complete Streams type element for the XRef index in each XRef list, textualize the XObject object in the Streams type element to obtain the target text, detect and analyze each XObject object The instruction sequence in the first 40 bytes of the target text; judge each XObject object according to the characteristics of the vector image object, and then find the vector image object;

Step 4: Analyze the path elements of the vector image object, use the path construction operator to construct the path elements of the vector image, and obtain the path object; specifically, it includes setting line width instructions, drawing straight line instructions, and drawing Bezier instructions;

Step 5: Draw the path object: Use the path drawing operator to stroke and fill the path object on the canvas;

Step 6: Clipping the path object: Use the path clipping operator to clip the drawn path object to obtain the handwritten signature image.

Step 7: Save the handwritten signature image in PNG format: save only the path information and leave the non-path information blank to get a transparent signature track map.

Step 8: Save the handwritten signature image in PNG format to JPG format.

The embodiment of this application analyzes the file structure of the electronic document of the operator's business in PDF file format, locates the vector path type element of the corresponding graphic element in the PDF for the handwritten customer signature, and directly extracts this part of the vector path element. , and then redraw this part of the vector path and save it as a raster image. The biggest advantage of the embodiment of this application is that there are no interference factors, and the signature layer can be obtained directly. When there are watermarks in the background of the signature, or other interference factors such as other text on part of the document are superimposed, the intercepted signature image has strong anti-interference, which is greatly Improved accuracy in recognizing handwritten signatures.

The handwritten signature recognition device provided by the embodiment of the present application is described below. The handwritten signature recognition device described below and the handwritten signature recognition method described above can be mutually referenced. Referring to Figure 2, Figure 2 is a schematic structural diagram of a handwritten signature recognition device provided by an embodiment of the present application. A handwritten signature recognition device, including:

The extraction module 201 is used to extract the vector image object of the file to be recognized based on the file format of the file to be recognized, where the vector image object includes characteristic information of the handwritten signature;

The construction module 202 is used to construct a path object based on the vector image object. The path object is used to represent the path or outline of the image;

The obtaining module 203 is used to draw a path object, crop the drawn path object, and obtain a handwritten signature picture.

The handwritten signature recognition device provided by the embodiment of the present application extracts the vector image object of the file to be recognized based on the file format of the file to be recognized. The vector image object includes the characteristic information of the handwritten signature; based on the vector image object, a path object is constructed, and the path object Used to characterize the path or outline of an image; draw the path object and crop the drawn path object to obtain a handwritten signature image. The embodiment of this application obtains a handwritten signature picture by extracting vector image objects, constructing, drawing, and clipping path objects based on the vector image objects. Based on this, when there is a watermark on the background of the handwritten signature, or there are other interfering factors such as other text on the superimposed document document At this time, the intercepted handwritten signature picture has strong anti-interference, which improves the audit accuracy and the accuracy of handwritten signature recognition.

In one embodiment, the construction module 202 is configured to: construct a path object based on the feature information of the handwritten signature of the vector image object and at least one path construction operator.

In one embodiment, the obtaining module 203 is used to: use a path drawing operator to stroke and fill the path object to draw the path object on the canvas; use a path cutting operator to combine the drawn path object with the cut The area is intersected to clip the path object outside the clipping area to obtain the handwritten signature image.

In one embodiment, the extraction module 201 is configured to: determine the signature page of the file to be recognized based on the signature page identifier; identify the content of the signature page based on the file format; and extract vector image objects from the recognized content of the signature page.

In one embodiment, the extraction module 201 is configured to parse and render the signature page based on the file format to obtain the content of the signature page.

In one embodiment, the extraction module 201 is used to: extract target elements from the content of the signature page, perform text processing on the target elements to obtain target text; and extract vector image objects in the target text based on the characteristics of the vector image objects.

In one embodiment, the obtaining module 203 is also configured to: convert the handwritten signature image into a raster image, and store the raster image.

Figure 3 illustrates a schematic diagram of the physical structure of an electronic device. As shown in Figure 3, the electronic device may include: a processor (processor) 310, a communication interface (Communication Interface) 320, a memory (memory) 330 and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 complete communication with each other through the communication bus 340. The processor 310 can call the computer program in the memory 330 to perform the steps of the handwritten signature recognition method, for example, including:

Based on the file format of the file to be recognized, the vector image object of the file to be recognized is extracted. The vector image object includes the characteristic information of the handwritten signature; based on the vector image object, a path object is constructed. The path object is used to represent the path or contour of the image; the path object is Draw and crop the drawn path object to obtain a handwritten signature image.

In addition, the above-mentioned logical instructions in the memory 330 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code. .

On the other hand, embodiments of the present application also provide a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. The computer program is executed by a processor. When , the computer can perform the steps of the handwritten signature recognition method provided by the above embodiments, including, for example:

Based on the file format of the file to be recognized, the vector image object of the file to be recognized is extracted. The vector image object includes the characteristic information of the handwritten signature; based on the vector image object, a path object is constructed. The path object is used to represent the path or contour of the image; the path object is Draw and crop the drawn path object to obtain a handwritten signature image.

On the other hand, embodiments of the present application also provide a processor-readable storage medium that stores a computer program. The computer program is used to cause the processor to execute the handwritten signature provided in the above embodiments. The steps of the identification method include, for example:

Based on the file format of the file to be recognized, the vector image object of the file to be recognized is extracted. The vector image object includes the characteristic information of the handwritten signature; based on the vector image object, a path object is constructed. The path object is used to represent the path or contour of the image; the path object is Draw and crop the drawn path object to obtain a handwritten signature image.

The processor-readable storage medium may be any available media or data storage device that the processor can access, including but not limited to magnetic storage (such as floppy disks, hard disks, tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor memories (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid state drive (SSD)), etc.

The device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in One location, or it can be distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Persons of ordinary skill in the art can understand and implement the method without any creative effort.

Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the part of the above technical solution that essentially contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., including a number of instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent substitutions are made to some of the technical features; however, these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions in the embodiments of the present application.

Claims (10)

1. A method of handwriting signature recognition, comprising:

extracting a vector image object of a file to be identified based on a file format of the file to be identified, wherein the vector image object comprises characteristic information of a handwriting signature;

constructing a path object based on the vector image object, wherein the path object is used for representing a path or a contour of an image;

and drawing the path object, and cutting the drawn path object to obtain a handwritten signature picture.

2. The handwritten signature recognition method according to claim 1, wherein said constructing a path object based on said vector image object comprises:

and constructing the path object based on the characteristic information of the handwritten signature of the vector image object and at least one path construction operator.

3. The method for recognizing a handwritten signature according to claim 1, wherein the drawing the path object, cutting the drawn path object to obtain a handwritten signature picture, includes:

drawing and filling the path object by adopting a path drawing operator so as to draw the path object on a canvas;

and adopting a path clipping operator to perform cross processing on the drawn path object and a clipping region so as to clip the path object outside the clipping region, thereby obtaining the handwritten signature picture.

4. The handwritten signature recognition method according to claim 1, wherein the extracting a vector image object of a file to be recognized based on a file format of the file to be recognized includes:

determining a signature page of the file to be identified based on the signature page identification;

identifying content of the signature page based on the file format;

and extracting the vector image object from the content of the signature page obtained by recognition.

5. The handwritten signature recognition method according to claim 4, wherein the recognition of the content of the signature page based on the file format includes:

and analyzing and rendering the signature page based on the file format to obtain the content of the signature page.

6. The handwritten signature recognition method according to claim 4, wherein said extracting the vector image object from the content of the signature page obtained by the recognition includes:

extracting target elements from the content of the signature page, and performing text processing on the target elements to obtain target texts;

extracting the vector image object in the target text based on the characteristics of the vector image object.

7. The method for recognizing a handwritten signature according to claim 1, wherein the steps of drawing the path object, cutting the drawn path object to obtain a handwritten signature picture, and then:

and converting the handwritten signature picture into a grid picture, and storing the grid picture.

8. A handwritten signature recognition apparatus, comprising:

the extraction module is used for extracting a vector image object of the file to be identified based on the file format of the file to be identified, wherein the vector image object comprises characteristic information of a handwriting signature;

a construction module for constructing a path object based on the vector image object, the path object being used for characterizing a path or a contour of an image;

and the obtaining module is used for drawing the path object, cutting the drawn path object, and obtaining a handwritten signature picture.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the handwritten signature recognition method according to any one of claims 1 to 7 when the program is executed.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the handwritten signature recognition method as claimed in any one of claims 1 to 7.