Calligraphy handwriting analysis method and system based on mobile terminal

Abstract

The invention discloses a calligraphy handwriting analysis method and system based on a mobile terminal, and the method comprises the steps: obtaining a response instruction of calligraphy handwriting analysis, and carrying out the corresponding operation based on the obtained response instruction: obtaining an inputted complete handwriting image if the obtained instruction is a first response instruction; if the acquisition instruction is a second response instruction, acquiring a shot handwriting image; matching the handwriting image with a handwriting database image, and if the matching degree of the handwriting image and the handwriting database image is detected to be not less than an analysis threshold value, marking that the acquired handwriting image input information is qualified; otherwise, marking unqualified products. The invention discloses a calligraphy handwriting analysis method based on a mobile terminal, which applies a current popular mobile terminal portable tool and automatically evaluates calligraphy handwriting based on intelligent equipment so as to obtain a calligraphy handwriting analysis result with high accuracy and assist a user in improving the calligraphy writing level.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to a calligraphy handwriting analysis method and system based on a mobile terminal. Background Art

[0002] In real-life applications, users often practice calligraphy using copybooks and writing pads to improve their handwriting. Practicing with copybooks and other methods requires evaluation of the calligraphy quality by professional calligraphers to obtain a final evaluation result. This conventional method is often limited by objective factors such as the inability of professional calligraphers to provide timely evaluation of calligraphy works and the varying opinions of different calligraphers on calligraphy works, which in turn affects the user's true evaluation of the calligraphy level.

[0003] In view of the shortcomings of the existing technology, there is an urgent need to design a calligraphy handwriting analysis method and system based on a mobile terminal to solve the above technical problems. Summary of the Invention

[0004] In order to solve the above-mentioned deficiencies in the prior art, the purpose of the present invention is to overcome the existing deficiencies and provide a calligraphy handwriting analysis method based on a mobile terminal, the method comprising:

[0005] Obtain a response instruction for calligraphy handwriting analysis, and perform corresponding operations based on the obtained response instruction:

[0006] If the acquisition instruction is the first response instruction, the input complete handwriting image is acquired;

[0007] If the acquisition instruction is the second response instruction, acquiring the photographed handwriting image;

[0008] The handwriting image is matched with the handwriting database image. If the matching degree between the detected handwriting image and the handwriting database image is not less than the analysis threshold, the acquired handwriting image entry information is marked as qualified; otherwise, it is marked as unqualified.

[0009] As a further optimization of the above solution, the method of matching the handwriting image with the handwriting database image includes the following:

[0010] Marking the recorded complete handwriting image and the photographed handwriting image as images to be analyzed, and setting the handwriting database image matched with the recorded complete handwriting image and the photographed handwriting image as a comparison image;

[0011] The text in the comparison image is used as the target template to obtain the pixel coverage area A of the target template; the handwriting of the text in the image to be analyzed is collected to obtain the pixel coverage area B of the target handwriting;

[0012] Calculating an intersection pixel coverage area C of the pixel coverage area A of the target template and the pixel coverage area B of the target handwriting;

[0013] If the cross pixel coverage area C is S C ≥S 标 , then the target handwriting is valid; where S 标 is the base effective area;

[0014] If the cross pixel coverage area C is S 标 >S C >0, the target handwriting is invalid;

[0015] If the cross pixel coverage area C is S C =0, the target handwriting is abnormal.

[0016] As a further optimization of the above solution, after detecting that the area of the cross pixel coverage area is not less than the reference effective area, the method of matching the handwriting image with the handwriting database image further includes the following:

[0017] Get all extreme endpoints of the target template;

[0018] With all the extreme endpoints as the center of the circle and R as the radius, the corresponding circular areas are constructed respectively, marked as the limit regular circle, and the area of the limit regular circle is denoted as S 圆 ;

[0019] Get the pixel coverage area A and pixel coverage area B within the limit regular circle area, and mark the overlapping area S of the limit regular circle and A 重 , the remaining limit regular circle area is S 分 ;

[0020] If the pixel coverage area B of the target handwriting does not exceed the first standard circle S 圆1 If the target handwriting is within, the target handwriting is valid; among them, the first standard circle S 圆1 <S 圆 ;

[0021] If the pixel coverage area B of the target handwriting exceeds S 圆 , then the target handwriting is invalid;

[0022] If the pixel coverage area B of the target handwriting is within S 圆1 and S 圆 Further testing is performed between:

[0023] Obtaining a straight line extending from the extreme endpoint exit direction of the target template, and obtaining an endpoint extending from the edge exit direction of the target handwriting;

[0024] Assume that the corresponding extreme endpoint is P, the exit point of the target handwriting from the edge of the target template is O, and the endpoint of the target handwriting extending from the edge of the target template is Q.

[0025] If ∠POQ≤θ, the target handwriting is valid; if ∠POQ>θ, the target handwriting is invalid.

[0026] As a further optimization of the above scheme, based on the matching results between the handwriting image and the handwriting database image, a matching degree calculation expression f is constructed:

[0027] f=α×a+β×b+γ×c(1)

[0028] Construct the matching degree analysis function F based on the matching degree calculation expression f:

[0029]

[0030] Among them, the cross pixel coverage area C is S 标 >S C >0 The number of events is a, and the pixel coverage area B of the target handwriting exceeds S 圆 The number of events is b, and the pixel coverage area B of the target handwriting is in S 圆1 and S 圆 The number of events between them is c, α, β, γ are the corresponding event weights, μ is the analysis threshold, F = 0 means unqualified, otherwise it is qualified.

[0031] As a further optimization of the above solution, the step of obtaining the input complete handwriting image specifically includes the following:

[0032] After obtaining the first response instruction, a timing trigger point is set;

[0033] If no handwriting input is captured within the unit time t1 after the timing trigger point is triggered, the first response instruction currently triggered is closed; otherwise, the handwriting is continuously recorded and input;

[0034] After completing the handwriting input of this round, the handwriting input end instruction is activated to generate a handwriting image, which is marked as the input complete handwriting image.

[0035] As a further optimization of the above solution, the method for activating the handwriting input end instruction specifically includes the following:

[0036] During the continuous recording and input of handwriting, a response interval is set;

[0037] Within the response interval T1, any handwriting input is captured, recorded and input;

[0038] If no handwriting input is captured within the response interval T1, the handwriting input end instruction is activated.

[0039] As a further optimization of the above solution, the method for obtaining the photographed handwriting image specifically includes the following:

[0040] After obtaining the second response instruction, performing handwriting detection on the target handwriting based on a text recognition algorithm;

[0041] If the target handwriting is detected based on the text recognition algorithm and the recognition result is fed back, the first recognition instruction is activated:

[0042] If a confirmation instruction is obtained, the current text recognition result is saved and a comparison image is generated;

[0043] If a non-confirmation instruction is obtained, the activation state of the first recognition instruction is canceled and the target handwriting detection is performed again.

[0044] If no recognized text is fed back after the target handwriting is detected based on the text recognition algorithm, the handwriting detection end instruction is activated.

[0045] As a further optimization of the above solution, after generating the comparison image, the method for obtaining the photographed handwriting image also includes the following:

[0046] Based on the recognition results of the text contained in the generated comparison image, the center of the text is used as the center point of the comparison image to obtain the extreme position of the recognized text in the comparison image, and the extreme positions in four directions are used as references to construct a minimum rectangle containing the recognized text, and the minimum rectangle is marked as the recognition box;

[0047] Adjust the shooting distance of the mobile terminal until the target handwriting is completely contained in the recognition frame, and mark the current state as obtaining the photographed handwriting image.

[0048] A computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, which, when executed by a computing device, cause the computing device to perform any one of the above methods.

[0049] A computing device, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0050] The present invention adopts the above technical solution, which has the following beneficial effects compared with the prior art:

[0051] 1. The present invention discloses a calligraphy handwriting analysis method based on a mobile terminal. It applies the currently popular mobile terminal portable tool and automatically evaluates calligraphy handwriting based on smart devices, thereby obtaining calligraphy handwriting analysis results with high accuracy, helping users improve their calligraphy writing skills.

[0052] 2. The present invention designs a calibration method for the limiting regular circle to specifically describe and evaluate the writing format and writing quality of any stroke of the target handwriting, thereby greatly improving the accuracy of calligraphy handwriting identification, so as to reduce the error caused by the structure of the text, such as tight in the middle and loose near the periphery, and ensure that both the center and periphery positions of the calligraphy handwriting are taken into account, thereby obtaining accurate quality of the written text.

[0053] 3. Based on the calibration method of the limiting regular circle, the present invention further accurately determines the position of the stroke ends of the target handwriting. When the prerequisites are met, a specific angle calibration is adopted to standardize the direction and position of the actual stroke starting or ending, so as to ensure that the final target handwriting is infinitely close to the standard text.

[0054] 4. The present invention greatly improves the accuracy of stroke position detection of calligraphy handwriting and records problems by accurately describing the display information of calligraphy handwriting and adopting the method of extreme regular circle and angle calibration; at the same time, it adopts a quantitative solution to combine problem events with event weights to obtain the matching degree, and then compares it with the analysis threshold to finally obtain an accurate description of the calligraphy handwriting, which helps to improve the user's calligraphy writing standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0056] Figure 1 It is a schematic diagram of the process of the present invention;

[0057] Figure 2 is another flow chart of the present invention;

[0058] Figure 3 It is another flow chart of the present invention. DETAILED DESCRIPTION

[0059] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] like Figure 1-3 As shown, the embodiment of the present invention discloses a calligraphy handwriting analysis method based on a mobile terminal, which specifically includes the following steps:

[0061] Get the response instruction of calligraphy handwriting analysis and perform corresponding operations based on the response instruction:

[0062] If the acquisition instruction is the first response instruction, the input complete handwriting image is acquired;

[0063] If the acquisition instruction is the second response instruction, acquiring the photographed handwriting image;

[0064] Match the handwriting image with the handwriting database image. If the matching degree between the detected handwriting image and the handwriting database image is not less than the analysis threshold, the acquired handwriting image entry information is marked as qualified; otherwise, it is marked as unqualified.

[0065] In actual life applications, users usually use copybooks, writing books, etc. to practice calligraphy in order to improve their calligraphy skills. When practicing with copybooks and other methods, the quality of the calligraphy needs to be evaluated by professional calligraphers in order to obtain the final evaluation results of the calligraphy handwriting. This conventional method is often limited by objective factors such as professional calligraphers being unable to comment on calligraphy handwriting in a timely manner, or different calligraphers having different views on calligraphy works, thereby affecting the user's true calligraphy level evaluation. In this regard, the present invention discloses a calligraphy handwriting analysis method based on a mobile terminal, which applies the currently popular mobile terminal portable tool and automatically evaluates calligraphy handwriting based on smart devices, thereby obtaining calligraphy handwriting analysis results with high accuracy, and assisting users in improving their calligraphy writing skills. It should be noted that the mobile terminal mentioned in the present invention is a portable mobile device that supports handwritten stroke entry and photo taking and has network connection functions, including but not limited to smart phones, tablets and other devices.

[0066] Specifically, the method of matching the handwriting image with the handwriting database image includes the following:

[0067] Mark the recorded complete handwriting image and the photographed handwriting image as images to be analyzed, and set the handwriting database image that is matched with the recorded complete handwriting image and the photographed handwriting image as a comparison image;

[0068] The text in the comparison image is used as the target template to obtain the pixel coverage area A of the target template; the handwriting of the text in the image to be analyzed is collected to obtain the pixel coverage area B of the target handwriting;

[0069] Calculating the intersection pixel coverage area C of the pixel coverage area A of the target template and the pixel coverage area B of the target handwriting;

[0070] If the cross pixel coverage area C is S C ≥S 标 , then the target handwriting is valid; where S 标 is the base effective area;

[0071] If the cross pixel coverage area C is S 标 >S C >0, the target handwriting is invalid;

[0072] If the cross pixel coverage area C is S C =0, the target handwriting is abnormal.

[0073] More specifically, the present invention uses images generated by handwriting input on a mobile terminal and images obtained by taking photos as images to be analyzed, and uses images in a handwriting database that match the calligraphy handwriting contained in the image to be analyzed as comparison images for accurate analysis;

[0074] The present invention specifically calculates the values of pixel coverage areas A and B and provides a reference effective area, which is used to evaluate whether the writing of the image to be analyzed meets the standard: when S C ≥S 标 , indicating that the pixel coverage areas A and B have a large overlap area, which can be used to verify the effective nature of the current calligraphy handwriting and the corresponding annotation results; when S 标 >S C >0, indicating that the overlapped area of pixel coverage areas A and B is small, which cannot meet the minimum standard for effective calligraphy handwriting identification, and the corresponding marking result is obtained; when S C = 0, indicating that pixel coverage areas A and B do not overlap at all, that is, due to the user's operational problems, the complete handwriting image recorded by the mobile terminal or the photographed handwriting image is not compliant or has not reached a state that can be used to evaluate the quality of calligraphy handwriting. This will not be described in detail here. It is particularly important to note that, in view of different calligraphy style requirements or characteristics, the S 标 Corresponding changes should be made to ensure the rationality of the analysis of calligraphy handwriting.

[0075] Specifically, after detecting that the area of the cross pixel coverage area is not less than the reference effective area, the method of matching the handwriting image with the handwriting database image further includes the following steps:

[0076] All extreme endpoints of the target template are obtained; more specifically, the target template is actually the text of the comparison image, that is, a standard calligraphy font. After the standard calligraphy font is magnified, the position between the two ends of any stroke of any character is regarded as a convex figure, and the positions of the two ends are respectively approximated as a semi-ellipse. Then, there must be an extreme endpoint, that is, the intersection position of the major semi-axis of the semi-ellipse and the edge of the semi-ellipse. By setting the extreme endpoints, the present invention accurately depicts all strokes of any character using mathematical methods, which facilitates subsequent calligraphy handwriting analysis and comparison;

[0077] With all the extreme endpoints as the center of the circle and R as the radius, the corresponding circular areas are constructed respectively, marked as the limit regular circle, and the area of the limit regular circle is denoted as S 圆 More specifically, the limit regular circle is used to circle calligraphy images that are infinitely close to the limit endpoint for easy comparative analysis.

[0078] Get the pixel coverage area A and pixel coverage area B within the limit regular circle area, and mark the overlapping area S of the limit regular circle and A 重 , the remaining limit regular circle area is S 分 ;

[0079] If the pixel coverage area B of the target handwriting does not exceed the first standard circle S 圆1 If the target handwriting is within, the target handwriting is valid; among them, the first standard circle S 圆1 <S 圆 ;

[0080] If the pixel coverage area B of the target handwriting exceeds S 圆 , then the target handwriting is invalid;

[0081] If the pixel coverage area B of the target handwriting is within S 圆1 and S 圆 Further testing is performed between:

[0082] Obtaining a straight line extending from the extreme endpoint exit direction of the target template, and obtaining an endpoint extending from the edge exit direction of the target handwriting;

[0083] Assume that the corresponding extreme endpoint is P, the exit point of the target handwriting from the edge of the target template is O, and the endpoint of the target handwriting extending from the edge of the target template is Q.

[0084] If ∠POQ≤θ, the target handwriting is valid; if ∠POQ>θ, the target handwriting is invalid.

[0085] More specifically, the present invention provides an embodiment in which a 2×4 target template, i.e., an ideal text interval, is set at the middle position of a 6×6 comparison image; C ≥S 标 Under the premise of further setting S 圆 =S 重 +S 分 , when the pixel coverage area B≤the first standard circle S 圆1 , indicating that the actual calligraphy handwriting to be analyzed has a lot of overlap with the target template's font stroke ends, but the pixel coverage area B exceeds the target template edge and extends to S 分 At this time, the first standard circle S is further set 圆1 , used to calibrate the actual calligraphy stroke end position; in this embodiment, the pixel coverage area B does not exceed the first standard circle S 圆1 Assume that the coordinates of the 6×6 contrast image are (0,0), (0,1), ... (6,6), and make the first standard circle S with the coordinate position (5,3) as the center and the radius as 1. 圆1 , with a radius of 2, make a limiting regular circle S 圆 ; When pixel coverage area B crosses S 重 , but not crossing S 圆1 , mark the target handwriting as valid; when the pixel coverage area B crosses S 圆, marking the target handwriting is invalid; the present invention, by designing a calibration method for the limit regular circle, specifically describes and evaluates the writing format and writing quality of any stroke of the target handwriting, greatly improving the accuracy of calligraphy handwriting identification, so as to reduce the error caused by the structure of the text, such as being close to the center and loose to the periphery, and ensure that both the center and the periphery positions of the calligraphy handwriting are taken into account, thereby obtaining accurate writing quality; it should be noted that, with respect to the Chinese language and characters, the center refers to the connection between the upper and lower structures, the left and right structures, and the inside of the internal and external structures;

[0086] When the pixel coverage area B crosses S 圆1 , not crossing S 圆 , further detection is performed, specifically through angle range judgment; respectively take the straight line extending from the target template in the direction of the extreme endpoint exit and the endpoint extending from the target template edge exit, wherein the straight line extending from the target template in the direction of the extreme endpoint exit is perpendicular to the tangent direction of the endpoint; obtain and calculate the angle formed by the extreme endpoint, the target handwriting from the target template edge exit point and the endpoint extending from the target template edge exit, if ∠POQ≤θ, it indicates that there are defects in the stroke writing of the current calligraphy handwriting, but within the allowable error range, the marking target handwriting is valid; based on the calibration method of the extreme regular circle, the present invention further accurately judges the position of the stroke end of the target handwriting, and adopts specific angle calibration when the prerequisites are met to standardize the direction and position of the actual writing stroke starting or ending, so as to ensure that the final target handwriting is infinitely close to the standard text.

[0087] Specifically, based on the matching results between the handwriting image and the handwriting database image, a matching degree calculation expression f is constructed:

[0088] f=α×a+β×b+γ×c(1)

[0089] Construct the matching degree analysis function F based on the matching degree calculation expression f:

[0090]

[0091] Among them, the cross pixel coverage area C is S 标 >S C >0 The number of events is a, and the pixel coverage area B of the target handwriting exceeds S 圆 The number of events is b, and the pixel coverage area B of the target handwriting is in S 圆1 and S 圆 The number of events between them is c, α, β, γ are the corresponding event weights, μ is the analysis threshold, F = 0 means unqualified, otherwise it is qualified.

[0092] More specifically, the present invention provides an embodiment in which α is set to 0.3, β is set to 0.6, γ is set to 0.1, and μ is set to 1.2, thereby obtaining the allowable error event of F. It should be noted that the requirements for calligraphy handwriting vary based on different calligraphy formats or characteristics, and therefore μ is adaptively adjusted.

[0093] The present invention greatly improves the detection accuracy of stroke positions of calligraphy handwriting and records problems by accurately describing the display information of calligraphy handwriting and adopting the method of extreme regular circle and angle calibration. At the same time, a quantitative solution is adopted to combine problem events with event weights to obtain the matching degree, which is then compared with the analysis threshold to finally obtain an accurate description of the calligraphy handwriting, which helps to improve the user's calligraphy writing standards.

[0094] Specifically, obtaining the input complete handwriting image includes the following steps:

[0095] After obtaining the first response instruction, a timing trigger point is set; the timing trigger point designed by the present invention is used to accurately record the response time of the user during the first handwriting input;

[0096] If no handwriting input is captured within the unit time t1 after the timing trigger point is triggered, the first response instruction of the current trigger is closed; otherwise, the handwriting is continuously recorded and input;

[0097] After completing the current round of handwriting input, the handwriting input completion instruction is activated to generate a handwriting image, which is marked as the completed handwriting image. It is particularly important to note that the present invention's activation of the handwriting input completion instruction specifically involves setting a shortcut key. Clicking "Confirm" completes the current round of calligraphy handwriting input and outputs the corresponding handwriting image for subsequent comparative analysis.

[0098] Specifically, the method for activating the handwriting end input instruction includes the following:

[0099] During the continuous recording and input of handwriting, a response interval is set; the response interval designed by the present invention is used to accurately record the pause time of the user during handwriting input, thereby avoiding evaluation errors caused by sudden interruptions in the writing process;

[0100] Within the response interval T1, any handwriting input is captured, recorded and input;

[0101] If no handwriting input is captured within the response interval T1, the handwriting input end instruction is activated.

[0102] Specifically, the method for obtaining the photographed handwriting image includes the following:

[0103] After obtaining the second response instruction, performing handwriting detection on the target handwriting based on a text recognition algorithm;

[0104] If the target handwriting is detected based on the text recognition algorithm and the recognition result is fed back, the first recognition instruction is activated:

[0105] If a confirmation instruction is obtained, the current text recognition result is saved and a comparison image is generated. It should be noted that the text recognition result data of the present invention comes from the handwriting database image, and the text recognition algorithm used refers to transcribing the image text into data that can be recognized by the mobile terminal. This algorithm is an existing conventional technology and will not be described in detail here.

[0106] If a non-confirmation instruction is obtained, the activation state of the first recognition instruction is canceled and the target handwriting detection is performed again.

[0107] If no recognized text is fed back after the target handwriting is detected based on the text recognition algorithm, the handwriting detection end instruction is activated.

[0108] Specifically, after generating the comparison image, the method for obtaining the photographed handwriting image also includes the following steps:

[0109] Based on the recognition results of the text contained in the generated comparison image, the center of the text is used as the center point of the comparison image to obtain the extreme position of the recognized text in the comparison image, and the extreme positions in four directions are used as references to construct the minimum rectangle containing the recognized text. The minimum rectangle is marked as the recognition box;

[0110] Adjust the shooting distance of the mobile terminal until the target handwriting is completely contained in the recognition frame, and mark the current state as obtaining the photographed handwriting image.

[0111] More specifically, the pole positions mentioned in this invention are specifically represented by the points corresponding to the top, bottom, left, and right ends of the text, respectively, as the pole positions, using the recognized text results as the calibration reference. The rectangles constructed based on the pole positions serve as the minimum rectangular unit area that can fully describe the recognized text. The center of the text is specifically represented as the center position of the text recognition box. This invention uses detailed calibration of the comparative image position of the recognized text to accurately mark the recognition range of the target handwriting, facilitating subsequent data processing and analysis.

[0112] It should be noted that an embodiment of the present invention is a calligraphy handwriting analysis system based on a mobile terminal, and its implementation technical means are the same as a calligraphy handwriting analysis method based on a mobile terminal, so it will not be described in detail here.

[0113] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions to enable a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0115] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0116] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0117] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A calligraphy handwriting analysis method based on a mobile terminal, characterized in that: The method comprises: Obtain a response instruction for calligraphy handwriting analysis, and perform corresponding operations based on the obtained response instruction: If the acquisition instruction is the first response instruction, the input complete handwriting image is acquired; If the acquisition instruction is the second response instruction, acquiring the photographed handwriting image; The handwriting image is matched with the handwriting database image. If the matching degree between the detected handwriting image and the handwriting database image is not less than the analysis threshold, the acquired handwriting image entry information is marked as qualified; otherwise, it is marked as unqualified.

2. The calligraphy handwriting analysis method based on a mobile terminal according to claim 1, characterized in that: Methods for matching handwriting images with handwriting database images include the following: Marking the recorded complete handwriting image and the photographed handwriting image as images to be analyzed, and setting the handwriting database image matched with the recorded complete handwriting image and the photographed handwriting image as a comparison image; The text in the comparison image is used as the target template to obtain the pixel coverage area A of the target template; the handwriting of the text in the image to be analyzed is collected to obtain the pixel coverage area B of the target handwriting; Calculating an intersection pixel coverage area C of the pixel coverage area A of the target template and the pixel coverage area B of the target handwriting; If the cross pixel coverage area C is S C ≥S 标 , then the target handwriting is valid; where S 标 is the base effective area; If the cross pixel coverage area C is S 标 >S C >0, the target handwriting is invalid; If the cross pixel coverage area C is S C =0, the target handwriting is abnormal.

3. The calligraphy handwriting analysis method based on a mobile terminal according to claim 2, characterized in that: After detecting that the area of the cross pixel coverage area is not less than the reference effective area, the method for matching the handwriting image with the handwriting database image further includes the following steps: Get all extreme endpoints of the target template; With all the extreme endpoints as the center of the circle and R as the radius, the corresponding circular areas are constructed respectively, marked as the limit regular circle, and the area of the limit regular circle is denoted as S 圆 ; Get the pixel coverage area A and pixel coverage area B within the limit regular circle area, and mark the overlapping area S of the limit regular circle and A 重 , the remaining limit regular circle area is S 分 ; If the pixel coverage area B of the target handwriting does not exceed the first standard circle S 圆1 If the target handwriting is within, the target handwriting is valid; among them, the first standard circle S 圆1 <S 圆 ; If the pixel coverage area B of the target handwriting exceeds S 圆 , then the target handwriting is invalid; If the pixel coverage area B of the target handwriting is within S 圆1 and S 圆 Further testing is performed between: Obtaining a straight line extending from the extreme endpoint exit direction of the target template, and obtaining an endpoint extending from the edge exit direction of the target handwriting; Assume that the corresponding extreme endpoint is P, the exit point of the target handwriting from the edge of the target template is O, and the endpoint of the target handwriting extending from the edge of the target template is Q. If ∠POQ≤θ, the target handwriting is valid; if ∠POQ>θ, the target handwriting is invalid.

4. The calligraphy handwriting analysis method based on a mobile terminal according to claim 3, characterized in that: Based on the matching results between the handwriting image and the handwriting database image, the matching degree calculation expression f is constructed: f=α×a+β×b+γ×c (1) Construct the matching degree analysis function F based on the matching degree calculation expression f: Among them, the cross pixel coverage area C is S 标 >S C >0 The number of events is a, and the pixel coverage area B of the target handwriting exceeds S 圆 The number of events is b, and the pixel coverage area B of the target handwriting is in S 圆1 and S 圆 The number of events between them is c, α, β, γ are the corresponding event weights, μ is the analysis threshold, F = 0 means unqualified, otherwise it is qualified.

5. The calligraphy handwriting analysis method based on a mobile terminal according to claim 1, characterized in that: The acquisition of the input complete handwriting image specifically includes the following steps: After obtaining the first response instruction, a timing trigger point is set; If no handwriting input is captured within the unit time t1 after the timing trigger point is triggered, the first response instruction currently triggered is closed; Otherwise, continue to record and enter handwriting; After completing the handwriting input of this round, the handwriting input end instruction is activated to generate a handwriting image, which is marked as the input complete handwriting image.

6. The calligraphy handwriting analysis method based on a mobile terminal according to claim 5, characterized in that: The method for activating the handwriting end input instruction specifically includes the following steps: During the continuous recording and input of handwriting, a response interval is set; Within the response interval T1, any handwriting input is captured, recorded and input; If no handwriting input is captured within the response interval T1, the handwriting input end instruction is activated.

7. The calligraphy handwriting analysis method based on a mobile terminal according to claim 6, characterized in that: The method for obtaining the photographed handwriting image specifically includes the following steps: After obtaining the second response instruction, performing handwriting detection on the target handwriting based on a text recognition algorithm; If the target handwriting is detected based on the text recognition algorithm and the recognition result is fed back, the first recognition instruction is activated: If a confirmation instruction is obtained, the current text recognition result is saved and a comparison image is generated; If a non-confirmation instruction is obtained, the activation state of the first recognition instruction is canceled and the target handwriting detection is performed again; If no recognized text is fed back after the target handwriting is detected based on the text recognition algorithm, the handwriting detection end instruction is activated.

8. The calligraphy handwriting analysis method based on a mobile terminal according to claim 7, characterized in that: After generating the comparison image, the method for obtaining the photographed handwriting image further includes the following steps: Based on the recognition results of the text contained in the generated comparison image, the center of the text is used as the center point of the comparison image to obtain the extreme position of the recognized text in the comparison image, and the extreme positions in four directions are used as references to construct a minimum rectangle containing the recognized text, and the minimum rectangle is marked as the recognition box; Adjust the shooting distance of the mobile terminal until the target handwriting is completely contained in the recognition frame, and mark the current state as obtaining the photographed handwriting image.

9. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any one of the methods according to claims 1 to 8.

10. A computing device, characterized in that The method comprises one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any one of the methods according to claims 1 to 8.

Images