Ink chronology analysis detection method
By segmenting and converting the red and black images, and analyzing the pixel frequency to draw histograms, the errors and limitations of existing detection methods are solved, and efficient and accurate red and black time sequence judgment is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-07
- Publication Date
- 2026-03-27
AI Technical Summary
Existing methods for detecting the timing of ink and vermilion ink are subject to human error and limitations, making it difficult to accurately determine the order in which seals and characters were formed.
The red and black ink time sequence analysis detection method is adopted. By segmenting the red and black ink image, converting the image from RGB mode to CIELab mode, analyzing the frequency of pixel points in the a and b channels, drawing histograms, and judging the red and black ink time sequence based on the distribution trend curve.
It reduces human error, improves the accuracy and versatility of testing, does not rely on professional instruments and human experience, and simplifies the testing process.
Smart Images
Figure CN117115838B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of ink image analysis, in particular to a kind of ink time sequence analysis detection method. BACKGROUND
[0002] In the litigation process, many written evidence such as contracts, IOUs, receipts, etc. need to determine the order of the formation of the seal, signature or handprint to play a proof role. By testing the order of the seal or handprint on the file with the seal or handprint and the handwriting or printed text, it is determined whether it is "first print and then word" or "first word and then print". The seal ink or handprint ink is usually red, commonly known as "red". The printed text or handwritten text strokes intersecting the seal ink are usually black, commonly known as "black". Therefore, the order of the handwriting and the print is also called ink time sequence. This is a common means to determine the validity of the contract.
[0003] Generally, such cases are contracts that are modified by using blank spaces with pre-applied seals or fingerprints (stolen seals, etc.), which are often difficult to distinguish and can easily cause disputes, because the seals and fingerprints are real, but the content is not fair or one party is not aware. In the litigation process, many file evidence (written evidence) such as IOUs, receipts, wills, agreements, contracts, etc. need to determine the order of the formation of the seal to identify the authenticity of the file. The identification is generally performed by testing and analyzing the ink distribution state and physical and chemical properties of the intersection part of the seal (usually seal ink and fingerprint) and text (usually handwritten text formed by various writing tools and printed text formed by printing and copying tools) in the file system elements, to determine the order of their formation.
[0004] Currently, the main test methods for ink time sequence are microscopic method, fluorescence method and spectroscopic method. Regardless of which method, there are certain limitations. The microscopic method has high dependence on human experience and is easily disturbed by human error factors. Moreover, in modern times, most seal inks use photosensitive seal ink and atomic seal ink, so that the physical characteristics of the seal and the text at the overlapping part of the ink are not obvious in most cases, resulting in insufficient detection efficiency of this method. For the fluorescence method and the spectroscopic method, since not every color has obvious fluorescence or spectral characteristics, this detection method also has obvious limitations. SUMMARY
[0005] The technical problem to be solved by the present application is that the existing detection methods have human error and limitations. Therefore, the present application provides an ink time sequence analysis detection method, which can reduce errors and has strong versatility.
[0006] The technical solution adopted by the present application to solve the technical problem is: an ink time sequence analysis detection method, comprising:
[0007] S1, collect a to-be-detected ink image;
[0008] S2, perform segmentation processing on the ink image to obtain a plurality of sample images, the sample images including an ink-ink cross image, a pure ink image, and a pure ink image;
[0009] S3, convert the sample image from an RGB mode to a CIELab mode;
[0010] S4, analyze the frequency P1 of the pixel points of the ink-ink cross image in the a channel and the b channel, and draw a histogram according to the frequency P1;
[0011] S5, analyze the frequency P2 of the pixel points of the pure ink image in the a channel and the b channel, and draw a histogram according to the frequency P2;
[0012] S6, analyze the frequency P3 of the pixel points of the pure ink image in the a channel and the b channel, and draw a histogram according to the frequency P3;
[0013] S7, draw a distribution trend curve of the three histograms respectively, and determine the ink-ink time sequence of the ink image according to the distribution trend curve.
[0014] Further, if the distribution trend curve of the histogram of the ink-ink cross image is a sharp main peak distribution, it indicates that the ink is after the ink; if the distribution trend curve of the histogram of the ink-ink cross image is a multi-peak distribution, it indicates that the ink is before the ink.
[0015] Further, the CIELab mode includes an L channel, an a channel, and a b channel, wherein the L channel represents color brightness, the a channel represents color change from red to dark green, and the b channel represents color change from blue to yellow.
[0016] Further, the process of converting the sample image from the RGB mode to the CIELab mode includes: first converting the sample image from the RGB color space to the XYZ color space; and then converting from the XYZ color space to the CIELab color space.
[0017] Further, the conversion matrix from the RGB color space to the XYZ color space is:
[0018]
[0019] The conversion matrix of the XYZ color space to the CIELab color space is:
[0020]
[0021] wherein X n = 0.950456, Yn = 1, Z n = 1.088754,
[0022]
[0023] Further, the value range of a is [-128, 127], the value range of b is [-128, 127], and the value range of L is [0, 100].
[0024] Further, the pure ink image represents a trace image, the pure ink image represents a trace image, and the ink trace intersection image represents an intersection image of the trace and the ink.
[0025] The analysis and detection method of the present application is based on the ink image, and the frequency of the pixel points appearing in the a channel and the b channel is counted, so that the ink timing can be analyzed. BRIEF DESCRIPTION OF DRAWINGS
[0026] The present application will be further described below in combination with the drawings and examples.
[0027] Figure 1 The flow chart of the analysis and detection method of the ink timing of the present application.
[0028] Figure 2 The schematic diagram of the collected ink image of the present application.
[0029] Figure 3 The schematic diagram of the image segmentation of the present application.
[0030] Figure 4 The distribution curve trend diagram of the trace of the present application.
[0031] Figure 5 The distribution curve trend diagram of the trace of the present application.
[0032] Figure 6 The distribution curve trend diagram of the trace intersection of the present application. DETAILED DESCRIPTION
[0033] The present application will be further described below in combination with the drawings and examples. These drawings are simplified schematic diagrams, and only illustrate the basic structure of the present application in a schematic manner, and therefore only show the components related to the present application.
[0034] In the description of the present application, it needs to be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, the features defined as "first", "second" can be explicitly or implicitly included one or more features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.
[0035] In the description of the present application, it needs to be understood that unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood in a broad sense, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected, it can be mechanically connected, or it can be electrically connected, it can be directly connected, or indirectly connected through an intermediate medium, it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.
[0036] As Figure 1 shown, the ink timing analysis detection method of the present application comprises: S1, collecting the ink image to be detected; S2, segmenting the ink image to obtain a plurality of sample images, the sample image containing ink cross image, pure ink image and pure ink image; S3, converting the sample image from RGB mode to CIELab mode; S4, analyzing the frequency P1 of the pixel points in the cross section of the ink cross image appearing in a channel and b channel, and drawing a histogram according to the frequency P1; S5, analyzing the frequency P2 of the pixel points in the pure ink image appearing in a channel and b channel, and drawing a histogram according to the frequency P2; S6, analyzing the frequency P3 of the pixel points in the pure ink image appearing in a channel and b channel, and drawing a histogram according to the frequency P3; S7, drawing the distribution trend curve of the three histograms respectively, and judging the ink timing of the ink image according to the distribution trend curve.
[0037] In other words, the present application segments the ink image in the file, then converts the image mode, and then counts the histogram of the three kinds of images, and according to the distribution trend curve of the histogram, the order of the appearance of the ink can be judged. In this way, on the one hand, it does not need to rely on artificial experience, reduces human error, and is not limited by fluorescence or spectral characteristics; on the other hand, it can improve the universality of the detection method and reduce the dependence on the detection equipment.
[0038] Specifically, images of the vermilion ink to be detected can be obtained using digital camera photography or microscopic imaging (e.g., ...). Figure 2 (As shown). The Zhumo image to be detected is segmented manually, such as... Figure 3 As shown, a cross-image of vermilion and ink, a pure vermilion image, and a pure ink image are selected from the original vermilion and ink image. The pure vermilion image represents the imprint image, the pure ink image represents the handwriting image, and the cross-image of vermilion and ink represents the cross-image of imprint and handwriting. Multiple samples of each type can be selected. It should be noted that the RGB color mode consists of a red channel (R), a green channel (G), and a blue channel (B). The brightest red + the brightest green + the brightest blue = white; the darkest red + the darkest green + the darkest blue = black; and between the brightest and darkest, red of equal brightness + green of equal brightness + blue of equal brightness = gray. The CIELab mode is a color mode that includes all colors visible to the human eye, compensating for the shortcomings of the RGB and CMYK color modes. The CIELab mode includes an L channel, an a channel, and a b channel. The L channel represents color brightness, the a channel represents color variations from red to dark green, and the b channel represents color variations from blue to yellow. The value range of 'a' is [-128, 127], the value range of 'b' is [-128, 127], and the value range of 'L' is [0, 100]. In terms of color gamut representation, the CIELab mode is the most comprehensive, followed by the RGB mode, and the CMYK mode is the narrowest. In other words, the CIELab mode defines the most colors and is independent of lighting and device.
[0039] The process of converting a sample image from RGB mode to CIELab mode includes: first, converting the sample image from the RGB color space to the XYZ color space; and then transforming it from the XYZ color space to the CIELab color space. The transformation matrix from RGB color space to XYZ color space is as follows:
[0040]
[0041] The transformation matrix from XYZ color space to CIELab color space is as follows:
[0042]
[0043] Among them, X n =0.950456, Y n =1,Z n =1.088754,
[0044] After color mode conversion, the frequencies P1, P2 and P3 of the pixel points in the cross section of the ink and the colorant image, the pure ink image and the pure colorant image in the a channel and the b channel are calculated respectively, and the histograms are drawn according to the frequencies P1, P2 and P3 respectively. Figure 4 As shown in the distribution trend curve of the print part, the curve of the a channel and the curve of the b channel appear multiple sharp peaks. Figure 5 As shown in the distribution trend curve of the print part, the curve of the a channel and the curve of the b channel appear multiple sharp peaks. Figure 6 In other words, the printing or handwriting ink directly acts on the surface of the material, the ink particles are uniformly distributed, and the color channel should present a sharp peak distribution. If the printing material is first applied to another medium (such as the surface of the seal or the finger), and then applied to the surface of the material, the printing material particles are not uniformly distributed, and the color channel presents at least two or more multi-peak distribution characteristics.
[0045] In summary, the analysis and detection method of the present application is based on the ink and colorant image, and the frequencies of the pixel points in the a channel and the b channel are counted, so that the ink and colorant time sequence can be analyzed. The present application does not need to rely on professional analysis instruments or manual experience, has strong universality, and is very convenient.
[0046] Based on the above ideal embodiments according to the present application, through the above description, relevant personnel can make various changes and modifications without deviating from the technical idea of the present application. The technical scope of the present application is not limited to the contents of the specification, and must be determined by the scope of the claims.
Claims
1. A method of ink-maze timing analysis detection, the method comprising: The method comprises the following steps: S1, collecting a to-be-detected ink image; S2, performing segmentation processing on the ink image to obtain a plurality of sample images, the sample images including an ink-ink cross image, a pure ink image, and a pure ink image; S3, converting the sample images from an RGB mode to a CIELab mode; S4, analyzing a frequency P1 at which pixel points in a cross portion of the ink-ink cross image appear in an a channel and a b channel, and drawing a histogram according to the frequency P1; S5, analyzing a frequency P2 at which pixel points of the pure ink image appear in the a channel and the b channel, and drawing a histogram according to the frequency P2; S6, analyzing a frequency P3 at which pixel points of the pure ink image appear in the a channel and the b channel, and drawing a histogram according to the frequency P3; S7, drawing distribution trend curves of the three histograms respectively, and determining an ink-ink time sequence of the ink image according to the distribution trend curves; If the distribution trend curve of the histogram of the ink-ink cross image is a sharp main peak distribution, it indicates that ink is applied after ink; if the distribution trend curve of the histogram of the ink-ink cross image is a multi-peak distribution, it indicates that ink is applied before ink.
2. The ink timing analysis detection method of claim 1, wherein, The CIELab mode includes an L channel, an a channel, and a b channel, wherein the L channel represents color brightness, the a channel represents color change from red to dark green, and the b channel represents color change from blue to yellow.
3. The ink timing analysis detection method of claim 2, wherein, The process of converting the sample images from the RGB mode to the CIELab mode includes: first converting the sample images from an RGB color space to an XYZ color space; and then converting the XYZ color space to the CIELab color space.
4. The ink timing analysis detection method of claim 3, wherein, The conversion matrix for converting from the RGB color space to the XYZ color space is: The conversion matrix for converting from the XYZ color space to the CIELab color space is: wherein X n = 0.950456, Y n = 1, and Z n = 1.088754, 。 5. The ink timing analysis detection method of claim 2, wherein, The value range of a is [-128, 127], the value range of b is [-128, 127], and the value range of L is [0, 100].
6. The ink timing analysis detection method of claim 1, wherein, The pure ink image represents a print image, the pure ink image represents a handwriting image, and the ink-ink cross image represents a print-handwriting cross image.