Oxidation kinetics-based pen and ink aging degree detection method and system

Abstract

The invention discloses a pen and ink aging degree detection method and system based on oxidation kinetics, and relates to the field of pen and ink detection, and the method comprises the steps: dividing a target handwriting to obtain a plurality of handwriting regions, and carrying out the spectral parameter collection and image collection to obtain a spectral parameter and a handwriting image array; performing aging prediction on the spectrum parameter array to obtain a spectrum aging parameter array, identifying the handwriting image array to obtain a handwriting structure parameter array, and performing classification to obtain an image aging parameter array; performing relative error analysis and global error analysis to obtain relative and global error coefficients, and performing sample error analysis according to the target handwriting to obtain a sample error coefficient; and calculating to obtain the ink aging parameter, and performing error compensation to obtain the compensated ink aging parameter interval as the ink aging degree detection result, thereby solving the technical problems of strong subjectivity and insufficient accuracy and reliability in ink aging degree detection.

Description

Technical Field

[0001] The present invention relates to the field of pen and ink detection, and particularly to a method and system for detecting the aging degree of pen and ink based on oxidation kinetics. Background Art

[0002] In the fields of cultural relic protection, forensic identification, file management, etc., accurately judging the aging degree of pen and ink is crucial. The aging degree of pen and ink not only affects the preservation status and value assessment of cultural relics, but also directly relates to the accuracy of forensic identification and the reliability of files. However, most traditional methods for detecting the aging degree of pen and ink rely on manual observation and empirical judgment. This method is not only time-consuming and laborious, but also easily affected by human factors, resulting in greater subjectivity and uncertainty in the detection results. Pen and ink will age due to reasons such as oxidation kinetics, specifically the volatilization of pen and ink components and penetration into the paper. With the passage of time and environmental changes, the aging process of pen and ink presents complex and variable characteristics. Traditional detection methods often have difficulty accurately capturing these subtle changes, thus unable to provide accurate aging degree information and affecting the stability and reliability of detection. Summary of the Invention

[0003] In view of the technical problems of strong subjectivity, insufficient accuracy and reliability in detecting the aging degree of pen and ink in the prior art, the present invention provides a method and system for detecting the aging degree of pen and ink based on oxidation kinetics to solve these problems.

[0004] The technical solutions of the present invention for solving the above technical problems are as follows: In the first aspect, the present invention provides a method for detecting the aging degree of pen and ink based on oxidation kinetics, the method comprising: dividing a target handwriting to obtain a plurality of handwriting regions, collecting spectral parameters and images for the plurality of handwriting regions to obtain a spectral parameter array and a handwriting image array; performing aging prediction on the spectral parameter array to obtain a spectral aging parameter array, performing identification on the handwriting image array to obtain a handwriting structure parameter array, and classifying to obtain an image aging parameter array; performing relative error analysis and global error analysis according to the spectral aging parameter array and the image aging parameter array to obtain a relative error coefficient and a global error coefficient, performing sample error analysis according to the target handwriting to obtain a sample error coefficient, calculating according to the spectral aging parameter array and the image aging parameter array to obtain a pen and ink aging parameter, and performing error compensation according to the relative error coefficient, the global error coefficient and the sample error coefficient to obtain a compensated pen and ink aging parameter interval as the detection result of the aging degree of pen and ink.

[0005] Second aspect, the present invention provides an ink aging degree detection system based on oxidation kinetics. The system includes: a handwriting division module for dividing a target handwriting to obtain multiple handwriting regions, collecting spectral parameters and image collection for the multiple handwriting regions to obtain a spectral parameter array and a handwriting image array; a parameter array acquisition module for performing aging prediction on the spectral parameter array to obtain a spectral aging parameter array, identifying the handwriting image array to obtain a handwriting structure parameter array, and classifying to obtain an image aging parameter array; a sample error analysis module for performing relative error analysis and global error analysis based on the spectral aging parameter array and the image aging parameter array to obtain a relative error coefficient and a global error coefficient, and performing sample error analysis based on the target handwriting to obtain a sample error coefficient; a detection result generation module for calculating based on the spectral aging parameter array and the image aging parameter array to obtain an ink aging parameter, and performing error compensation based on the relative error coefficient, the global error coefficient, and the sample error coefficient to obtain a compensated ink aging parameter interval as the ink aging degree detection result.

[0006] The beneficial effects of the present invention are: by collecting the spectral parameters and image information of the handwriting, combining aging prediction and recognition technologies, spectral aging parameters and image aging parameters are obtained. Further, through relative error analysis, global error analysis, and sample error analysis, error compensation is performed on the obtained parameters, and finally an accurate ink aging parameter interval is obtained as the detection result, effectively improving the accuracy and reliability of ink aging degree detection. Description of the Drawings

[0007] Figure 1 It is a flowchart of the ink aging degree detection method based on oxidation kinetics provided by the present invention.

[0008] Figure 2 It is a structural diagram of the ink aging degree detection system based on oxidation kinetics provided by the present invention.

[0009] Description of the reference numerals: handwriting division module 11, parameter array acquisition module 12, sample error analysis module 13, detection result generation module 14. Detailed Embodiments

[0010] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0011] In the description of the present invention, the terms "first" and "second" are used only for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0012] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. The following description is provided to enable any person skilled in the art to implement and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0013] Embodiment 1: As Figure 1 shown, the embodiment of the present invention provides a method for detecting the aging degree of pen and ink based on oxidation kinetics, and the method includes: S10: Divide the target handwriting to obtain a plurality of handwriting regions, collect spectral parameters and images for the plurality of handwriting regions, and obtain a spectral parameter array and a handwriting image array.

[0014] S20: Perform aging prediction on the spectral parameter array to obtain a spectral aging parameter array, identify the handwriting image array to obtain a handwriting structure parameter array, and classify to obtain an image aging parameter array.

[0015] S30: Perform relative error analysis and global error analysis based on the spectral aging parameter array and the image aging parameter array to obtain a relative error coefficient and a global error coefficient, and perform sample error analysis based on the target handwriting to obtain a sample error coefficient.

[0016] S40: Calculate based on the spectral aging parameter array and the image aging parameter array to obtain a pen and ink aging parameter, and perform error compensation based on the relative error coefficient, the global error coefficient, and the sample error coefficient to obtain a compensated pen and ink aging parameter interval as the detection result of the aging degree of pen and ink.

[0017] Exemplarily, oxidation kinetics mainly refers to the rate and mechanism of the aging process of ink materials under the action of oxidation over time. During this process, the ink materials react with oxygen in the surrounding environment, resulting in changes in their chemical and physical properties, which in turn affect the appearance and performance of the ink. By analyzing the kinetic process of this oxidative aging, the aging degree of the ink can be more accurately evaluated. Thus, a method for detecting the aging degree of ink based on oxidation kinetics is proposed.

[0018] Specifically, when processing the target handwriting to evaluate its aging degree, the handwriting of the entire character is first carefully divided into multiple small handwriting regions. This step is similar to dividing a complex painting into several detailed parts for more precise analysis. Then, spectral parameter collection is performed on these divided handwriting regions. This process is completed by a specific spectral instrument, which can capture the absorption characteristics of the handwriting materials under different wavelengths of light. When the handwriting ages over time, subtle changes occur in its spectral absorption characteristics, which reflect the degree of reaction between the ink components and oxygen. At the same time, microscopic image collection is performed on these handwriting regions to obtain an array of handwriting images. Microscopic images can reveal the fine structure of the handwriting, including the distribution of ink particles, the diffusion of the handwriting edge, etc. Handwriting with different aging degrees will show different degrees of diffusion under the microscope, and this diffusion is caused by the gradual penetration of the ink materials into the paper fibers over time. By comparing the spectral parameters and microscopic images of different handwriting regions, the aging condition of the handwriting can be more comprehensively understood, including the uniformity of aging and the degree of aging differences in different regions. This comprehensive analysis method provides a more accurate and detailed means for evaluating the aging of handwriting.

[0019] Furthermore, an advanced aging prediction algorithm is used to predict the aging of the spectral parameter array. This algorithm can infer the aging trend of handwriting over time based on the absorption characteristics of the handwriting material under different spectra, and then generate a spectral aging parameter array. The spectral aging parameter array not only reflects the degree of handwriting aging, but also reveals the changing law of spectral characteristics during the aging process. Next, the handwriting image array is deeply identified. Through high-precision image processing technology, the subtle structural features of the handwriting, such as the distribution of ink, the width of the line, and the blurriness of the handwriting edge, can be extracted. These features are integrated into the handwriting structural parameter array. Subsequently, these structural parameters are classified and analyzed using a machine learning algorithm to distinguish the characteristics of handwriting images with different aging degrees. The key to this step is to identify subtle changes in the handwriting image caused by aging, such as the diffusion of ink and the breakage of lines, so as to generate an image aging parameter array. The combination of the spectral aging parameter array and the image aging parameter array can provide a more comprehensive understanding of the aging status of the handwriting. These parameters not only provide time clues for handwriting aging, but also reveal the complex mechanism of the interaction between the ink material and the paper during the aging process. By comparing different parameter arrays, the approximate aging time of handwriting can be more accurately inferred, providing a strong scientific basis for subsequent handwriting identification, cultural relics protection and other work.

[0020] Optionally, an error analysis method is adopted during the process of handwriting aging assessment to ensure the accuracy of the assessment results. First, relative error analysis and global error analysis are performed based on the spectral aging parameter array and the image aging parameter array. The core of this step lies in recognizing that there may be certain errors in the spectral aging parameters and image aging parameters of different handwriting regions, which may be caused by factors such as the uneven distribution of ink materials, the slight differences in the paper surface, or the technical limitations during the acquisition process. At the same time, even within the same handwriting region, there may be errors between the spectral aging parameters and the image aging parameters, which reflects the inherent differences between the two assessment methods. The proportion of these differences, that is, the relative error coefficient, is calculated through relative error analysis to quantify the error degree between different handwriting regions or different assessment methods within the same handwriting region. The global error analysis, on the other hand, considers the overall error situation of all handwriting regions and assessment methods, generating a global error coefficient to comprehensively evaluate the accuracy of the entire handwriting aging assessment process. In addition, sample error analysis is performed on the target handwriting. The starting point of this step is to recognize that when identifying the text within the handwriting, factors such as the writing habits, frequencies, and forces used during writing of different texts may all affect the aging degree and pattern of the ink. At the same time, differences in the sample data volume during model training using machine learning algorithms may also lead to biases in the assessment results. Therefore, through detailed sample error analysis of the target handwriting, the sample error coefficient is calculated to quantify the impact of these factors on the handwriting aging assessment results. This step not only helps to more accurately understand the complex mechanism of handwriting aging but also provides a more reliable assessment basis for subsequent handwriting identification, cultural relic protection, and other work.

[0021] Finally, calculations and error compensation are carried out in the final stage of handling handwriting aging assessment to obtain accurate detection results of the degree of pen and ink aging. First, comprehensive calculations are performed based on the spectral aging parameter array and the image aging parameter array, and preliminary pen and ink aging parameters are obtained by calculating the mean or weighted average of these two parameters. This step integrates the advantages of spectral analysis and image analysis and provides a comprehensive assessment of the degree of handwriting aging. However, due to the influence of various factors, there may be certain errors in these preliminary parameters. Therefore, error compensation is then carried out according to the relative error coefficient, global error coefficient, and sample error coefficient calculated previously. These three coefficients respectively reflect the errors between different handwriting regions, the errors between different evaluation methods within the same handwriting region, and the errors caused by sample data differences. Corresponding adjustments are made by combining these error coefficients with the preliminary pen and ink aging parameters to obtain more accurate pen and ink aging parameters. Specifically, these error coefficients can be regarded as an adjustment factor for defining the upper and lower limits of the preliminary parameters. For example, if the preliminary calculated pen and ink aging parameter is 1 (assuming this is a dimensionless standardized parameter), and the relative error coefficient, global error coefficient, and sample error coefficient all indicate that the error range is within ±5%, then the final pen and ink aging parameter can be defined as an interval, that is, 0.95 to 1.05 (i.e., 1 ± 5%). This interval not only includes the result of the preliminary calculation but also takes into account the possible error range, thus providing a more reliable and comprehensive detection result of the degree of pen and ink aging. Through this series of calculation and error compensation steps, the degree of handwriting aging can be evaluated more accurately, providing strong support for subsequent handwriting identification, cultural relic protection, and other work.

[0022] In a preferred embodiment, the target handwriting is divided to obtain multiple handwriting regions, and spectral parameter collection and image collection are performed on the multiple handwriting regions to obtain a spectral parameter array and a handwriting image array, including: dividing the target handwriting according to a preset division window to obtain multiple handwriting regions; using a spectrometer to collect the spectral parameters of the multiple handwriting regions to obtain a spectral parameter array; collecting the images of the multiple handwriting regions to obtain a handwriting image array.

[0023] Optionally, during the process of processing the target handwriting, the target handwriting is first carefully divided according to a preset division window. The purpose of this step is to split the handwriting into multiple independent handwriting regions so that the spectral parameters and images of each region can be collected separately. The size and shape of the preset division window are usually determined according to the complexity of the handwriting, the size of the paper, and the specific requirements of the analysis to ensure the rationality and accuracy of the division. For example, it is a rectangular window of 2mm * 2mm, and the target handwriting is divided into multiple rectangular regions. Each handwriting region includes a partial region of the handwriting, such as the region of a certain stroke. Subsequently, a professional spectrometer is used to collect the spectral parameters of each handwriting region. The spectrometer can measure the reflection or absorption characteristics of the pen ink at different wavelengths, thereby generating a series of spectral data. By collecting the spectral data of multiple handwriting regions, a spectral parameter array is constructed. This array contains the spectral characteristics of each handwriting region, providing key information for subsequent pen ink aging analysis. At the same time, the image of each handwriting region is also collected to obtain a handwriting image array. This step uses a high-resolution image acquisition device, which can capture features such as the fine structure of the handwriting, the thickness of the lines, and the distribution of the ink marks. The handwriting image array and the spectral parameter array complement each other and jointly constitute a comprehensive description of the target handwriting. Through this series of steps, not only is the target handwriting successfully divided into multiple handwriting regions convenient for analysis, but also the spectral parameters and image information of each region are collected, laying a foundation for subsequent pen ink aging analysis.

[0024] In a preferred embodiment, aging prediction is performed on the spectral parameter array to obtain a spectral aging parameter array, including: according to the pen ink aging detection data within the historical time, collecting the sample spectral parameter set of the sample handwriting, and collecting the actual aging time of the sample handwriting as the sample spectral aging parameter set; using the sample spectral parameter set and the sample spectral aging parameter set as training data and test data, and based on deep learning, training and testing to obtain a qualified spectral aging predictor; inputting the multiple spectral parameters in the spectral parameter array into the spectral aging predictor, predicting and outputting multiple spectral aging parameters to obtain the spectral aging parameter array.

[0025] Exemplarily, in the process of processing the spectral parameter array to predict the aging degree of the writing ink, the writing ink aging detection data within the historical time is reviewed, and representative sample handwriting is selected therefrom. For these sample handwritings, a spectrometer is used to collect spectral parameters, and a sample spectral parameter set is constructed. At the same time, the actual aging time of these sample handwritings is also recorded as the sample spectral aging parameter set. This step ensures that the training data contains both the spectral characteristics of the writing ink and their associated aging times, providing a solid foundation for the subsequent prediction model. Next, using these sample spectral parameter sets and sample spectral aging parameter sets as training data and test data, based on deep learning techniques, the spectral aging predictor is trained. The deep learning model can learn complex mapping relationships from a large amount of data, so it is very suitable for predicting the aging degree of the writing ink. During the training process, the parameters of the model are continuously adjusted to improve the accuracy of its prediction. When the performance of the model on the test data reaches the preset qualified standard, it is considered that the spectral aging predictor has been trained. Finally, multiple spectral parameters in the spectral parameter array to be analyzed are input into this trained spectral aging predictor. The predictor will output the corresponding spectral aging parameters according to these spectral parameters. Through this step, a spectral aging parameter array is obtained, and each parameter in this array represents the predicted value of the aging degree of the corresponding handwriting area. In summary, through the collection of historical data, the training of the deep learning model, and the application of the predictor, the aging prediction of the spectral parameter array is successfully achieved, providing strong support for the subsequent analysis of the writing ink aging.

[0026] In a preferred embodiment, the handwriting image array is identified to obtain a handwriting structure parameter array, and the image aging parameter array is classified, including: according to the writing ink aging detection data within the historical time, a sample handwriting image set of the sample handwriting is collected, and the actual diffusion distance of the sample handwriting is collected and labeled as the sample handwriting structure parameter set; using the sample handwriting image set and the sample handwriting structure parameter set as training data and test data, based on the convolutional neural network, a qualified handwriting structure recognizer is trained and tested; multiple handwriting images in the handwriting image array are input into the handwriting structure recognizer, and multiple handwriting structure parameters are recognized and output to obtain the handwriting structure parameter array; according to the multiple handwriting structure parameters, multiple image aging parameters are classified to obtain the image aging parameter array.

[0027] Specifically, relying on the ink aging detection data within a historical time period, a series of sample handwriting is selected, and a set of sample handwriting images of them is obtained using a high-resolution image acquisition device. At the same time, the diffusion distance of the ink during the actual aging process of these sample handwritings is measured, and these data are organized into a set of sample handwriting structure parameters. This step ensures that the training data includes both the image features of the handwriting and their structural changes during the actual aging process, providing strong support for the subsequent recognition model. Next, using these sets of sample handwriting images and sample handwriting structure parameters as training data and test data, based on the powerful image recognition ability of the convolutional neural network (CNN), the handwriting structure recognizer is trained. The CNN model can automatically extract features from the image data and learn the complex relationships between these features and the handwriting structure parameters. During the training process, the parameters of the model are continuously adjusted to improve its recognition accuracy and generalization ability. When the performance of the model on the test data reaches the preset qualified standard, it is considered that this handwriting structure recognizer has been trained. Then, multiple handwriting images in the handwriting image array to be analyzed are input into this trained handwriting structure recognizer. The recognizer will output the corresponding handwriting structure parameters according to these image features. Through this step, an array of handwriting structure parameters is obtained, and each parameter in this array represents the structural features of the corresponding handwriting area. Finally, the image aging parameter array is further classified based on these handwriting structure parameters. This step utilizes the internal relationship between the handwriting structure parameters and the degree of image aging, and converts the handwriting structure parameters into specific image aging parameters through a classification algorithm. These parameters not only reflect the aging degree of the handwriting image but also provide important reference information for the subsequent ink aging analysis. In summary, through the collection of historical data, the training of the CNN model, the application of the handwriting structure recognizer, and the classification of image aging parameters, the in-depth analysis and processing of the handwriting image array are successfully achieved, providing strong support for the subsequent ink aging research.

[0028] In a preferred embodiment, classifying a plurality of image aging parameters according to the plurality of handwriting structure parameters to obtain an image aging parameter array includes: collecting a set of sample handwriting structure parameters of sample handwriting and obtaining the average aging time of the sample handwriting under different sample handwriting structure parameters to obtain a set of sample image aging parameters; constructing a mapping relationship between the set of sample handwriting structure parameters and the set of sample image aging parameters to obtain an image aging classifier; and inputting the plurality of handwriting structure parameters into the image aging classifier respectively, and classifying and outputting a plurality of image aging parameters to obtain an image aging parameter array.

[0029] Specifically, a set of sample handwriting structure parameters of sample handwriting is collected from historical data, and these parameters record in detail the structural characteristics of different sample handwriting. At the same time, for each sample handwriting structure parameter, the average aging time of the corresponding sample handwriting is measured and calculated, so as to obtain a set of sample image aging parameters. This step ensures that the data contains both the structural information of the handwriting and its time characteristics during the actual aging process, providing a solid foundation for the subsequent classification model. Next, a mapping relationship between these sets of sample handwriting structure parameters and sample image aging parameters is constructed. This step is the key to constructing the image aging classifier, which enables the classifier to predict and output the corresponding image aging parameters according to the input handwriting structure parameters. To achieve this goal, machine learning algorithms are adopted, and by training and optimizing the model parameters, a qualified image aging classifier is finally obtained. Finally, multiple handwriting structure parameters to be analyzed are respectively input into this trained image aging classifier. The classifier will classify and output the corresponding image aging parameters according to these handwriting structure parameters and using the previously learned mapping relationship. Through this step, an array of image aging parameters is obtained, and each parameter in this array represents the predicted value of the aging degree of the corresponding handwriting image. In summary, through the collection of sample data, the construction of the mapping relationship, and the application of the image aging classifier, the classification processing of multiple handwriting structure parameters is successfully realized, and an array of image aging parameters is obtained. This process not only improves the accuracy and efficiency of the ink aging analysis, but also provides strong support for the subsequent ink research and application.

[0030] In a preferred embodiment, relative error analysis and global error analysis are performed according to the spectral aging parameter array and the image aging parameter array to obtain a relative error coefficient and a global error coefficient, including: randomly extracting two spectral aging parameters from the spectral aging parameter array, calculating the error magnitude as the first spectral global error coefficient; continuing to randomly extract multiple groups of spectral aging parameters, calculating multiple error magnitudes and calculating the mean value to obtain the spectral global error coefficient; performing global error analysis calculation according to the image aging parameter array to obtain the image global error coefficient, and combining the spectral global error coefficient to calculate the global error coefficient; combining the spectral aging parameters and the image aging parameters in the same handwriting area in the spectral aging parameter array and the image aging parameter array to obtain multiple groups of aging parameter combinations; respectively calculating the error magnitudes of the multiple groups of aging parameter combinations and calculating the mean value of the multiple error magnitudes to obtain the relative error coefficient.

[0031] Preferably, two spectral aging parameters are randomly selected from the spectral aging parameter array to calculate the error magnitude between them, and this value is used as a preliminary global error reference, that is, the first spectral global error coefficient. To more comprehensively evaluate the error situation of the spectral aging parameters, multiple groups of spectral aging parameters are further randomly selected, multiple groups of error magnitudes are calculated and their mean value is taken to obtain a more robust spectral global error coefficient. Next, a global error analysis is performed on the image aging parameter array, and an image global error coefficient is obtained through a specific calculation method. This step provides an independent evaluation of the accuracy of the image aging parameters. To obtain a comprehensive global error coefficient, the spectral global error coefficient and the image global error coefficient are combined, and a global error coefficient that takes into account both spectral and image information is obtained through an appropriate weighting or averaging method. In addition, to deeply explore the relationship between the spectral aging parameters and the image aging parameters, the aging parameters corresponding to the same handwriting area in both are paired and combined to form multiple groups of aging parameter combinations. For each group of combinations, the error magnitude between the spectral aging parameter and the image aging parameter is calculated, and the mean value of these error magnitudes is calculated to obtain a relative error coefficient. This coefficient reflects the degree of consistency or difference between the two aging parameters in describing the aging degree of the same handwriting. In summary, through in-depth error analysis of the spectral aging parameter array and the image aging parameter array, not only the global error coefficients of the spectrum and the image are obtained, but also the correlation and consistency between the two aging parameters are revealed through the calculation of the relative error coefficient. These error analysis results provide an important basis for the accuracy and reliability evaluation of subsequent ink aging research.

[0032] In a preferred embodiment, according to the target handwriting, a sample error analysis is performed to obtain a sample error coefficient, including: identifying and obtaining the text content of the target handwriting; retrieving and obtaining the writing proficiency coefficient of the text content; obtaining the average text appearance rate of different sample text contents within the sample handwriting; obtaining the average accuracy rates of spectral aging parameter prediction and handwriting structure parameter recognition, and calculating to obtain an error rate; and correcting and calculating the error rate according to the ratio of the average text appearance rate and the writing proficiency coefficient to obtain a sample error coefficient.

[0033] Exemplarily, the text content of the target handwriting is identified and obtained, which is the basis of the analysis. Subsequently, for the proficiency of writing the text content, 10,000 words in the files are randomly retrieved, and the proportion of the occurrence of the text content of the target handwriting is counted to obtain the writing proficiency coefficient. For example, if the text content is "I", and the proportion of the occurrence of the word "I" in 10,000 files is 10%, it is used as the writing proficiency coefficient. The larger this coefficient, the more stable the handwriting, the richer the sample data, and theoretically the smaller the error rate. Next, the average text occurrence rate of different sample text contents in the sample handwriting is calculated. This step is to count the occurrence rate of each character (or each type of text content) based on the sample handwriting in the training data, and then calculate its average value to obtain the average text occurrence rate. This value reflects the universality and representativeness of various text contents in the sample handwriting. At the same time, the average accuracy rates of spectral aging parameter prediction and handwriting structure parameter recognition are also obtained, and the error rate is calculated accordingly. For example, using 1 minus the average accuracy rates of spectral aging parameter prediction and handwriting structure parameter recognition, if it is 90%, the error rate is 10%. This error rate preliminarily reflects the possible deviation in the prediction and recognition process. In order to more accurately evaluate the sample error, a correction calculation method is adopted. Specifically, the ratio of the average text occurrence rate to the writing proficiency coefficient is used as the correction factor, and it is directly multiplied by the preliminarily calculated error rate to obtain the sample error coefficient. For example, assuming the average text occurrence rate is 0.05 (i.e., 5% of the text content appears frequently in the sample), the writing proficiency coefficient is 0.10 (indicating that the text content is relatively proficient for most people to write, and the occurrence rate of writing times is 10%), and the preliminary error rate is 10%, then the corrected sample error coefficient is 0.05 / 0.10×10% = 5%. This correction process takes into account the influence of the universality of the text content and the proficiency of the writer on the error rate, making the final sample error coefficient closer to the actual situation. In summary, through the text content recognition of the target handwriting, the retrieval of the writing proficiency coefficient, the calculation of the average text occurrence rate, the acquisition of the error rate, and the correction calculation, a comprehensive and accurate sample error coefficient is obtained, providing an important reference basis for subsequent handwriting analysis and research.

[0034] In a preferred embodiment, calculations are performed based on the spectral aging parameter array and the image aging parameter array to obtain the pen and ink aging parameter. Error compensation is performed based on the relative error coefficient, the global error coefficient, and the sample error coefficient to obtain a compensated pen and ink aging parameter interval as the pen and ink aging degree detection result, including: calculating the mean value based on the spectral aging parameter array and the image aging parameter array to obtain the pen and ink aging parameter; calculating to obtain an error compensation coefficient according to the relative error coefficient, the global error coefficient, and the sample error coefficient; using the error compensation coefficient to perform error compensation calculation on the pen and ink aging parameter to obtain a compensated pen and ink aging parameter interval as the pen and ink aging degree detection result.

[0035] Specifically, in the process of detecting the pen and ink aging degree, the information of the spectral aging parameter array and the image aging parameter array is first combined. By calculating the mean value of the parameters in these two arrays, the pen and ink aging parameter is comprehensively obtained. This step makes full use of the advantages of spectral analysis and image processing and provides a preliminary evaluation of the pen and ink aging degree. To further improve the accuracy of the detection result, various error sources are considered, and the relative error coefficient, the global error coefficient, and the sample error coefficient are calculated. These coefficients respectively reflect the relative difference between the spectral and image aging parameters, the error level of the overall data set, and the error characteristics of a specific sample. Subsequently, using these error coefficients, an error compensation coefficient is calculated through a specific weighting or combination method. This coefficient aims to comprehensively consider various error factors in order to correct the initially obtained pen and ink aging parameter. Finally, the error compensation coefficient is used to perform error compensation calculation on the pen and ink aging parameter. This step adjusts the value of the initial parameter to obtain a more accurate and reliable compensated pen and ink aging parameter interval. This interval not only contains the estimated value of the pen and ink aging degree but also reflects the possible fluctuation range due to the existence of errors. Therefore, it can be used as the final detection result of the pen and ink aging degree. In summary, by combining the spectral and image aging parameters, calculating the error coefficients, and performing error compensation, an accurate and reliable pen and ink aging degree detection result is obtained, providing strong support for subsequent pen and ink research and applications.

[0036] The method for detecting the pen and ink aging degree based on oxidation kinetics provided by the embodiment of the present invention has at least the following technical effects: 1. By combining the spectral parameter array and the handwriting image array, multi-dimensional detection of the pen and ink aging degree is achieved. The spectral parameters provide direct evidence of the chemical composition change of the pen and ink, while the handwriting image reflects the physical form change of the pen and ink on the paper. By fusing these two different-dimensional data and performing comprehensive analysis using technologies such as deep learning, the aging degree of the pen and ink can be evaluated more accurately, avoiding the one-sidedness that may be brought by single-dimensional data.

[0037] 2. Considering various error sources that may exist in the actual detection process, multiple error indicators such as relative error coefficient, global error coefficient, and sample error coefficient are innovatively introduced, and an error compensation coefficient is calculated based on these indicators. By applying this error compensation coefficient to the preliminarily calculated pen and ink aging parameters, precise compensation for errors can be achieved, thereby greatly improving the accuracy and reliability of the detection results.

[0038] 3. Intelligent technical means such as deep learning and convolutional neural networks are adopted to achieve automatic acquisition, recognition, and analysis of spectral parameters and handwriting images. This not only greatly improves the detection efficiency but also reduces errors caused by human intervention. In addition, this method also has the function of automatically calculating the error compensation coefficient and generating the interval of compensated pen and ink aging parameters, making the entire detection process more convenient and efficient.

[0039] Embodiment 2: As Figure 2 shown, based on the same inventive concept as the method for detecting the aging degree of pen and ink based on oxidation kinetics provided in Embodiment 1, the present invention embodiment also provides a system for detecting the aging degree of pen and ink based on oxidation kinetics. The system includes: A handwriting division module 11, configured to divide the target handwriting to obtain multiple handwriting regions, collect spectral parameters and images for the multiple handwriting regions, and obtain a spectral parameter array and a handwriting image array.

[0040] A parameter array acquisition module 12, configured to perform aging prediction on the spectral parameter array to obtain a spectral aging parameter array, identify the handwriting image array to obtain a handwriting structure parameter array, and classify to obtain an image aging parameter array.

[0041] A sample error analysis module 13, configured to perform relative error analysis and global error analysis based on the spectral aging parameter array and the image aging parameter array to obtain a relative error coefficient and a global error coefficient, and perform sample error analysis based on the target handwriting to obtain a sample error coefficient.

[0042] A detection result generation module 14, configured to calculate based on the spectral aging parameter array and the image aging parameter array to obtain pen and ink aging parameters, perform error compensation based on the relative error coefficient, global error coefficient, and sample error coefficient, and obtain an interval of compensated pen and ink aging parameters as the detection result of the pen and ink aging degree.

[0043] Furthermore, the handwriting division module 11 is further configured to perform the following steps: Divide the target handwriting according to a preset division window to obtain multiple handwriting regions; use a spectrometer to collect the spectral parameters of the multiple handwriting regions to obtain a spectral parameter array, and collect images of the multiple handwriting regions to obtain a handwriting image array.

[0044] Furthermore, the parameter array acquisition module 12 is further configured to perform the following steps: According to the ink aging detection data within a historical time, collect the sample spectral parameter set of the sample handwriting, and collect the actual aging time of the sample handwriting as the sample spectral aging parameter set; use the sample spectral parameter set and the sample spectral aging parameter set as training data and test data, and based on deep learning, train and test to obtain a qualified spectral aging predictor; input the multiple spectral parameters in the spectral parameter array into the spectral aging predictor, and predict and output multiple spectral aging parameters to obtain a spectral aging parameter array.

[0045] Furthermore, the parameter array acquisition module 12 is further configured to perform the following steps: According to the ink aging detection data within a historical time, collect the sample handwriting image set of the sample handwriting, and collect the actual diffusion distance of the sample handwriting, which is marked as the sample handwriting structure parameter set; use the sample handwriting image set and the sample handwriting structure parameter set as training data and test data, and based on a convolutional neural network, train and test to obtain a qualified handwriting structure recognizer; input the multiple handwriting images in the handwriting image array into the handwriting structure recognizer, and recognize and output multiple handwriting structure parameters to obtain a handwriting structure parameter array; classify multiple image aging parameters according to the multiple handwriting structure parameters to obtain an image aging parameter array.

[0046] Furthermore, the parameter array acquisition module 12 is further configured to perform the following steps: Collect the sample handwriting structure parameter set of the sample handwriting, and obtain the average aging time of the sample handwriting under different sample handwriting structure parameters to obtain the sample image aging parameter set; construct the mapping relationship between the sample handwriting structure parameter set and the sample image aging parameter set to obtain an image aging classifier; input the multiple handwriting structure parameters into the image aging classifier respectively, and classify and output multiple image aging parameters to obtain an image aging parameter array.

[0047] Furthermore, the sample error analysis module 13 is further configured to perform the following steps: Randomly select two spectral aging parameters from within the spectral aging parameter array, calculate the error margin, and use it as the first spectral global error coefficient; continue to randomly select multiple sets of spectral aging parameters, calculate multiple error margins and calculate the mean value to obtain the spectral global error coefficient; perform global error analysis and calculation based on the image aging parameter array to obtain the image global error coefficient, and combine it with the spectral global error coefficient to calculate and obtain the global error coefficient; combine the spectral aging parameters and image aging parameters of the same handwriting area within the spectral aging parameter array and the image aging parameter array to obtain multiple sets of aging parameter combinations; calculate the error margins of the multiple sets of aging parameter combinations respectively, and calculate the mean value of the multiple error margins to obtain the relative error coefficient.

[0048] Furthermore, the sample error analysis module 13 is further configured to perform the following steps: Identify and obtain the text content of the target handwriting; retrieve and obtain the writing proficiency coefficient of the text content; obtain the average text appearance rate of different sample text contents within the sample handwriting; obtain the average accuracy rates of spectral aging parameter prediction and handwriting structure parameter recognition, and calculate and obtain the error rate; perform correction calculation on the error rate according to the ratio of the average text appearance rate and the writing proficiency coefficient to obtain the sample error coefficient.

[0049] Furthermore, the detection result generation module 14 is further configured to perform the following steps: Calculate the mean value based on the spectral aging parameter array and the image aging parameter array to obtain the ink aging parameter; calculate and obtain the error compensation coefficient according to the relative error coefficient, the global error coefficient, and the sample error coefficient; use the error compensation coefficient to perform error compensation calculation on the ink aging parameter to obtain the compensated ink aging parameter interval as the ink aging degree detection result.

[0050] Through the foregoing detailed description of the method for detecting the ink aging degree based on oxidation kinetics in this specification, those skilled in the art can clearly know the system for detecting the ink aging degree based on oxidation kinetics in this embodiment. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0051] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An ink aging degree detection method based on oxidation kinetics, characterized in that The method includes: Dividing the target handwriting to obtain multiple handwriting regions, collecting spectral parameters and images of the multiple handwriting regions to obtain a spectral parameter array and a handwriting image array; Performing aging prediction on the spectral parameter array to obtain a spectral aging parameter array, performing recognition on the handwriting image array to obtain a handwriting structure parameter array, and classifying to obtain an image aging parameter array; Performing relative error analysis and global error analysis based on the spectral aging parameter array and the image aging parameter array to obtain a relative error coefficient and a global error coefficient, and performing sample error analysis based on the target handwriting to obtain a sample error coefficient; Calculating based on the spectral aging parameter array and the image aging parameter array to obtain a pen and ink aging parameter, and performing error compensation based on the relative error coefficient, the global error coefficient, and the sample error coefficient to obtain a compensated pen and ink aging parameter interval as the pen and ink aging degree detection result.

2. The method for detecting the aging degree of pen ink based on oxidation kinetics according to claim 1, wherein Dividing the target handwriting to obtain multiple handwriting regions, collecting spectral parameters and images of the multiple handwriting regions to obtain a spectral parameter array and a handwriting image array, including: Dividing the target handwriting according to a preset division window to obtain multiple handwriting regions; Using a spectrometer to collect the spectral parameters of the multiple handwriting regions to obtain a spectral parameter array; Collecting images of the multiple handwriting regions to obtain a handwriting image array.

3. The method for detecting the aging degree of pen ink based on oxidation kinetics according to claim 1, characterized in that, Performing aging prediction on the spectral parameter array to obtain a spectral aging parameter array, including: According to the pen and ink aging detection data within the historical time, collecting a sample spectral parameter set of the sample handwriting, and collecting the actual aging time of the sample handwriting as the sample spectral aging parameter set; Using the sample spectral parameter set and the sample spectral aging parameter set as training data and test data, and training and testing based on deep learning to obtain a qualified spectral aging predictor; Inputting the multiple spectral parameters in the spectral parameter array into the spectral aging predictor, and predicting and outputting multiple spectral aging parameters to obtain a spectral aging parameter array.

4. The method for detecting the aging degree of pen ink based on oxidation kinetics according to claim 1, wherein Performing recognition on the handwriting image array to obtain a handwriting structure parameter array, and classifying to obtain an image aging parameter array, including: According to the pen and ink aging detection data within the historical time, collecting a sample handwriting image set of the sample handwriting, and collecting the actual diffusion distance of the sample handwriting, and labeling it as the sample handwriting structure parameter set; Using the sample handwriting image set and the sample handwriting structure parameter set as training data and test data, and training and testing based on a convolutional neural network to obtain a qualified handwriting structure recognizer; Inputting the multiple handwriting images in the handwriting image array into the handwriting structure recognizer, and recognizing and outputting multiple handwriting structure parameters to obtain a handwriting structure parameter array; Classifying multiple image aging parameters according to the multiple handwriting structure parameters to obtain an image aging parameter array.

5. The method for detecting the aging degree of pen ink based on oxidation kinetics according to claim 4, characterized in that Classifying multiple image aging parameters according to the multiple handwriting structure parameters to obtain an image aging parameter array, including: Collecting a sample handwriting structure parameter set of the sample handwriting, and obtaining the average aging time of the sample handwriting under different sample handwriting structure parameters to obtain a sample image aging parameter set; Construct the mapping relationship between the set of sample handwriting structure parameters and the set of sample image aging parameters to obtain an image aging classifier; Input the multiple handwriting structure parameters into the image aging classifier respectively, and classify and output multiple image aging parameters to obtain an image aging parameter array.

6. The method for detecting the aging degree of pen ink based on oxidation kinetics according to claim 1, wherein Conduct relative error analysis and global error analysis based on the spectral aging parameter array and the image aging parameter array to obtain a relative error coefficient and a global error coefficient, including: Randomly extract two spectral aging parameters from the spectral aging parameter array, calculate the error magnitude, and use it as the first spectral global error coefficient; Continue to randomly extract multiple groups of spectral aging parameters, calculate multiple error magnitudes and calculate the mean value to obtain the spectral global error coefficient; Conduct global error analysis and calculation based on the image aging parameter array to obtain the image global error coefficient, and combine it with the spectral global error coefficient to calculate and obtain the global error coefficient; Combine the spectral aging parameters and image aging parameters in the same handwriting area in the spectral aging parameter array and the image aging parameter array to obtain multiple groups of aging parameter combinations; Calculate the error magnitudes of the multiple groups of aging parameter combinations respectively, and calculate the mean value of the multiple error magnitudes to obtain the relative error coefficient.

7. The method for detecting the aging degree of pen ink based on oxidation kinetics according to claim 1, characterized in that Conduct sample error analysis based on the target handwriting to obtain a sample error coefficient, including: Identify and obtain the text content of the target handwriting; Retrieve and obtain the writing proficiency coefficient of the text content; Obtain the average text appearance rate of different sample text contents in the sample handwriting; Obtain the average accuracy rate of spectral aging parameter prediction and handwriting structure parameter recognition, and calculate and obtain the error rate; According to the ratio of the average text appearance rate and the writing proficiency coefficient, conduct correction calculation on the error rate to obtain the sample error coefficient.

8. The method for detecting the aging degree of ink based on oxidation kinetics according to claim 1, characterized in that Conduct calculation based on the spectral aging parameter array and the image aging parameter array to obtain the ink aging parameter, and conduct error compensation based on the relative error coefficient, the global error coefficient and the sample error coefficient to obtain the compensated ink aging parameter interval as the ink aging degree detection result, including: Calculate the mean value based on the spectral aging parameter array and the image aging parameter array to obtain the ink aging parameter; Calculate and obtain the error compensation coefficient according to the relative error coefficient, the global error coefficient and the sample error coefficient; Use the error compensation coefficient to conduct error compensation calculation on the ink aging parameter to obtain the compensated ink aging parameter interval as the ink aging degree detection result.

9. An ink aging degree detection system based on oxidation kinetics, characterized in that For implementing the ink aging degree detection method based on oxidation kinetics according to any one of claims 1-8, the system includes: A handwriting division module, configured to divide the target handwriting to obtain multiple handwriting areas, collect spectral parameters and images for the multiple handwriting areas to obtain a spectral parameter array and a handwriting image array; A parameter array acquisition module, configured to conduct aging prediction on the spectral parameter array to obtain a spectral aging parameter array, identify the handwriting image array to obtain a handwriting structure parameter array, and classify to obtain an image aging parameter array; A sample error analysis module is used to perform relative error analysis and global error analysis based on the spectral aging parameter array and the image aging parameter array to obtain a relative error coefficient and a global error coefficient, and perform sample error analysis based on the target handwriting to obtain a sample error coefficient; A detection result generation module is used to perform calculations based on the spectral aging parameter array and the image aging parameter array to obtain pen and ink aging parameters, perform error compensation based on the relative error coefficient, global error coefficient, and sample error coefficient to obtain a compensated pen and ink aging parameter interval as the pen and ink aging degree detection result.

Images