Oil outlet grade analysis method and device based on oil detection surface paper

Abstract

The invention relates to an oil production grade analysis method based on oil-measuring surface paper, which comprises the following steps: acquiring a to-be-analyzed image of the oil-measuring surface paper; performing preprocessing operation on the to-be-analyzed image to obtain a preprocessed image; performing edge detection on the preprocessed image to obtain an edge image, and performing tilt correction on the edge image to obtain an image to be subjected to area analysis; performing oil outlet range determination on the image to be subjected to area analysis to obtain a preliminary oil outlet range; performing noise correction on the preliminary oil outlet range based on a preset floating value to obtain an accurate oil outlet range; and marking the accurate oil outlet range in the image to be subjected to area analysis, visualizing the marked image to be subjected to area analysis, and pushing the visualized image to a user terminal interface. According to the method, the finally obtained accurate oil outlet range can be accurate as much as possible, and finally the accurate oil outlet range is visually displayed to the user, so that the user can conveniently know the product use condition of the user, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field related to image processing, and in particular to an oil level analysis method and device based on oil measuring paper. Background Art

[0002] Oil-absorbing facial tissue is a thin paper or tissue with strong absorbency for sebum. In existing facial care products, people usually use this oil-absorbing facial tissue to absorb excess oil on the face to prevent facial pimples, while keeping the facial skin clean and refreshing.

[0003] At present, the oil-absorbing facial tissues on the market often require users to judge the oil-producing location based on their visual perception after use, and then take corresponding measures based on the judgment results. This method is not convenient for users to use and is greatly affected by subjective factors. If the oil-producing area analysis is performed through image analysis, the traces of the oil-absorbing facial tissue may cause more interference items and lead to inaccurate analysis results.

[0004] In the field of facial care, oil-absorbing facial tissue is widely used as an effective oil absorption tool to control facial oil secretion and keep the skin fresh. After using traditional oil-absorbing facial tissue, users usually rely on visual assessment to judge the location and extent of oil secretion, which has obvious limitations and subjectivity. The user's visual assessment is not only affected by personal perception differences, but also difficult to accurately quantify the oil secretion area and amount of oil, which limits the in-depth understanding and effective management of the oil secretion situation.

[0005] In addition, existing image analysis technology often uses a point measurement method when processing oil-absorbing facial tissue, which can only measure the oiliness of a fixed small area, but cannot accurately and comprehensively evaluate the oiliness of the face and the differences in parts.

[0006] It is difficult to accurately analyze the oil-discharging area due to the complex background and interference caused by the traces of use. These technologies usually lack fine control over image preprocessing and edge detection, resulting in inaccurate analysis results. Therefore, the existing technologies have the following major defects in the analysis of the oil-discharging area of ​​oil-absorbing facial tissue:

[0007] Highly subjective: Users’ visual assessments are highly dependent on personal experience and perception, lacking objectivity and repeatability.

[0008] The test is one-sided: The test is based on point measurements, such as the cheeks, forehead, etc., and lacks an assessment method for the overall facial oiliness level.

[0009] Insufficient precision: It is impossible to accurately quantify the oil secretion area, resulting in the inability to conduct detailed analysis and management of oil secretion.

[0010] Poor anti-interference ability: Existing image analysis technology has difficulty in accurately identifying the oily areas and levels of different people's faces when faced with complex backgrounds and interference items. Summary of the invention

[0011] The purpose of the present invention is to solve at least one of the deficiencies of the prior art and to provide an oil level analysis method and device based on oil measuring paper.

[0012] In order to achieve the above object, the present invention adopts the following technical solutions:

[0013] Specifically, a method for analyzing oil level based on oil measuring paper is proposed, including the following:

[0014] Obtain the image to be analyzed of the oil testing paper;

[0015] Performing a preprocessing operation on the image to be analyzed to obtain a preprocessed image;

[0016] Performing edge detection on the preprocessed image to obtain an edge image, and performing tilt correction on the edge image to obtain an image to be analyzed for the area;

[0017] Determining the oil-discharging range of the image to be analyzed in the area to obtain a preliminary oil-discharging range;

[0018] Based on the preset floating value, the noise of the preliminary oil output range is corrected to obtain the precise oil output range;

[0019] Obtaining the oil level analysis result according to the area ratio of the precise oil yield range in the image to be analyzed in accordance with the preset rules;

[0020] The precise oil yield range is marked in the image to be analyzed for the area, and the marked image to be analyzed for the area is visualized and pushed to the user terminal interface together with the oil yield level analysis result.

[0021] Further, specifically, performing a preprocessing operation on the image to be analyzed to obtain a preprocessed image includes:

[0022] The image to be analyzed is subjected to brightness and contrast adjustment, noise removal and grayscale conversion to obtain a preprocessed image.

[0023] Further, specifically, performing tilt correction on the edge image to obtain the image to be analyzed in the area includes:

[0024] Finding straight lines in the edge image by using Hough transform;

[0025] Assume that there are two points A(x1, y1) and B(x2, y2) in any straight line, calculate its slope slope = (y2-y1) / (x2-x1);

[0026] The slope slope is converted into the inclination angle angle of the line through angle = np.degrees(np.arctan(slope));

[0027] The inclination angles of all straight lines in the edge image are averaged to obtain average_angle=np.mean(angles);

[0028] Rotate the edge image based on average_angle to achieve tilt correction;

[0029] The blank edge area generated after rotation is cropped to obtain the image to be analyzed.

[0030] Further, specifically, determining the oil-discharge range of the image to be analyzed to obtain a preliminary oil-discharge range includes:

[0031] Binarizing the image to be analyzed for area to obtain a first image;

[0032] Detecting connected regions of the first image through connectedComponents to obtain multiple connected regions;

[0033] The area of ​​each connected region is calculated by cv2.findContours;

[0034] Calculate the average area of ​​all connected regions at this time to get the first mean;

[0035] Subtract the preset floating value from the first mean value to obtain the first discrimination value;

[0036] At this time, the connected regions whose areas are lower than the first discrimination value are eliminated from all the connected regions, and the remaining connected regions are the preliminary oil production range.

[0037] Further, specifically, based on the preset floating value, the preliminary oil output range is subjected to noise correction to obtain the precise oil output range, including:

[0038] Calculate the ratio P of the number of connected areas removed to the number of all connected areas;

[0039] Determine whether the ratio P is lower than a ratio threshold,

[0040] If it is lower than the ratio threshold, the average area of ​​the preliminary oil-producing range is calculated to obtain a second mean value, and the second mean value is subtracted from the preset floating value to obtain a second judgment value, and the connected areas in the preliminary oil-producing range that are lower than the second judgment value are removed to obtain a precise oil-producing range;

[0041] If it is not lower than the ratio threshold, the area average of the preliminary oil-producing range is calculated to obtain the second mean, and the second mean is directly used as the second discrimination value. The connected areas in the preliminary oil-producing range that are lower than the second discrimination value are eliminated to obtain the precise oil-producing range.

[0042] Further, specifically, the visualization operation includes:

[0043] After the precise oil-producing range is marked in the image to be analyzed for area, the precise oil-producing range is rendered in color and the area of ​​each connected region in the precise oil-producing range is marked.

[0044] Further, specifically, edge detection is performed on the preprocessed image using an edge detection algorithm based on a Canny operator to obtain an edge image.

[0045] Furthermore, the method further comprises:

[0046] The user's APP login information on the mobile terminal is obtained. After each analysis of the image to be analyzed of the oil-testing facial paper is completed, the pre-analysis data and the post-analysis data are associated and stored with the user's personal information, and then a user sample library is formed based on all registered users.

[0047] The present invention also proposes an oil level analysis device based on oil measuring paper, comprising the following:

[0048] A data acquisition module, used to acquire the image to be analyzed of the oil testing paper;

[0049] A preprocessing module, used for performing a preprocessing operation on the image to be analyzed to obtain a preprocessed image;

[0050] An edge detection module is used to perform edge detection on the preprocessed image to obtain an edge image, and to perform tilt correction on the edge image to obtain an image to be analyzed for area;

[0051] A first correction module is used to determine the oil-discharge range of the image to be analyzed to obtain a preliminary oil-discharge range;

[0052] A second correction module is used to perform noise correction on the preliminary oil delivery range based on a preset floating value to obtain a precise oil delivery range;

[0053] An oil yield level analysis module is used to obtain an oil yield level analysis result according to a preset rule based on the area ratio of the precise oil yield range in the image to be analyzed;

[0054] The visualization module is used to mark the precise oil output range in the image to be analyzed for area, and visualize the marked image to be analyzed for area and push it to the user terminal interface.

[0055] The beneficial effects of the present invention are:

[0056] The present invention provides an oil output level analysis method based on oil measuring facial paper. First, the image to be analyzed of the oil measuring facial paper is preprocessed to reduce preliminary interference items as much as possible. Then, the image after edge detection is tilted and corrected to ensure subsequent area analysis. When performing area analysis, some interference items are first removed to obtain a preliminary oil output range. Then, the intensity of the second interference item removal is determined according to the removal status of the interference items, so as to make the final precise oil output range as accurate as possible. Finally, the precise oil output range is visualized to the user, so that the user can understand his or her own product usage and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The above and other features of the present disclosure will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present disclosure represent the same or similar output voltages. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings:

[0058] Figure 1 Shown is a flow chart of an oil level analysis method based on oil measuring facial paper of the present invention;

[0059] Figure 2 The figure shows a schematic diagram of a management interface of an oil level analysis method based on oil measuring facial paper when establishing a user sample library according to the present invention;

[0060] Figure 3 The figure shows a schematic diagram of an APP interface of an oil level analysis method based on oil measuring facial paper according to the present invention when establishing a user sample library. DETAILED DESCRIPTION

[0061] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other without conflict. The same reference numerals used throughout the drawings indicate the same or similar parts.

[0062] Reference Figure 1 , Embodiment 1, the present invention proposes an oil level analysis method based on oil measuring facial paper, comprising the following,

[0063] Step 110, obtaining the image to be analyzed of the oil testing paper;

[0064] Step 120: performing a preprocessing operation on the image to be analyzed to obtain a preprocessed image;

[0065] Step 130, performing edge detection on the preprocessed image to obtain an edge image, and performing tilt correction on the edge image to obtain an image to be analyzed for area;

[0066] Step 140, determining the oil-discharging range of the image to be analyzed to obtain a preliminary oil-discharging range;

[0067] Step 150, performing noise correction on the preliminary oil output range based on the preset floating value to obtain the precise oil output range;

[0068] Step 160, obtaining the oil yield level analysis result according to the preset rules based on the area ratio of the precise oil yield range in the area analysis image; here, a mapping relationship between the preset range of the area ratio value and the oil yield level can be established, and the oil yield level can be obtained by reading the area ratio value and then mapping.

[0069] Step 170: annotate the precise oil yield range in the image to be analyzed for the area, visualize the annotated image to be analyzed for the area, and push it together with the oil yield level analysis result to the user terminal interface.

[0070] In this embodiment 1, the image to be analyzed of the oil-testing facial tissue is first preprocessed to reduce the initial interference items as much as possible, and then the image after edge detection is tilted and corrected to ensure the subsequent area analysis. When performing the area analysis, some interference items are first removed to obtain a preliminary oil-release range, and then the intensity of the second interference item removal is determined based on the removal of the interference items, so as to make the final precise oil-release range as accurate as possible. Finally, the precise oil-release range is visualized to the user, so that the user can understand his or her own product usage and improve the user experience.

[0071] As a preferred embodiment of the present invention, specifically, performing a preprocessing operation on the image to be analyzed to obtain a preprocessed image includes:

[0072] The image to be analyzed is subjected to brightness and contrast adjustment, noise removal and grayscale conversion to obtain a preprocessed image.

[0073] In this preferred embodiment, preprocessing the image to be analyzed in the above manner can facilitate the subsequent area analysis process.

[0074] As a preferred embodiment of the present invention, specifically, performing tilt correction on the edge image to obtain the image to be analyzed in the area includes:

[0075] Finding straight lines in the edge image by using Hough transform;

[0076] Assume that there are two points A(x1, y1) and B(x2, y2) in any straight line, calculate its slope slope = (y2-y1) / (x2-x1);

[0077] The slope slope is converted into the inclination angle angle of the line through angle = np.degrees(np.arctan(slope));

[0078] The inclination angles of all straight lines in the edge image are averaged to obtain average_angle=np.mean(angles);

[0079] Rotate the edge image based on average_angle to achieve tilt correction;

[0080] The blank edge area generated after rotation is cropped to obtain the image to be analyzed.

[0081] In this preferred embodiment, through the tilt correction in the above process, the edge image can be prevented from tilting as much as possible, which facilitates the subsequent area analysis process.

[0082] As a preferred embodiment of the present invention, specifically, determining the oil-discharge range of the image to be analyzed to obtain a preliminary oil-discharge range includes:

[0083] Binarizing the image to be analyzed for area to obtain a first image;

[0084] Detecting connected regions of the first image through connectedComponents to obtain multiple connected regions;

[0085] The area of ​​each connected region is calculated by cv2.findContours;

[0086] Calculate the average area of ​​all connected regions at this time to get the first mean;

[0087] Subtract the preset floating value from the first mean value to obtain the first discrimination value;

[0088] At this time, the connected regions whose areas are lower than the first discrimination value are eliminated from all the connected regions, and the remaining connected regions are the preliminary oil production range.

[0089] In this preferred embodiment, the above method can eliminate some interference items with smaller areas to obtain a preliminary oil output range. In addition, the following is a practical application code of a preferred embodiment.

[0090] import cv2

[0091] import numpy as np

[0092] #Read the image

[0093] image=cv2.imread('path_to_image',cv2.IMREAD_GRAYSCALE)

[0094] # Binarization

[0095] _,binary_image=cv2.threshold(image,0,255,cv2.THRESH_BINARY+

[0096] cv2.THRESH_OTSU)

[0097] #Use connectedComponents to detect connected areas

[0098] num_labels,labels,stats,centroids=cv2.connectedComponentsWithStats(binary_image,connectivity=8)

[0099] # Calculate the area of ​​the connected region

[0100] areas=stats[:,cv2.CC_STAT_AREA]

[0101] for i in range(1,num_labels):

[0102] print(f"The area of ​​region {i} is: {areas[i]}")

[0103] #Use findContours to detect connected areas

[0104] contours,hierarchy=cv2.findContours(binary_image,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)

[0105] # Calculate the area of ​​the connected region

[0106] for i,contour in enumerate(contours):

[0107] area=cv2.contourArea(contour)

[0108] print(f"The area of ​​region {i} is: {area}").

[0109] As a preferred embodiment of the present invention, specifically, the noise correction is performed on the preliminary oil output range based on the preset floating value to obtain the precise oil output range, including:

[0110] Calculate the ratio P of the number of connected areas removed to the number of all connected areas;

[0111] Determine whether the ratio P is lower than a ratio threshold,

[0112] If it is lower than the ratio threshold, the average area of ​​the preliminary oil-producing range is calculated to obtain a second mean value, and the second mean value is subtracted from the preset floating value to obtain a second judgment value, and the connected areas in the preliminary oil-producing range that are lower than the second judgment value are removed to obtain a precise oil-producing range;

[0113] If it is not lower than the ratio threshold, the area average of the preliminary oil-producing range is calculated to obtain the second mean, and the second mean is directly used as the second discrimination value. The connected areas in the preliminary oil-producing range that are lower than the second discrimination value are eliminated to obtain the precise oil-producing range.

[0114] In this preferred embodiment, through the preliminary proposed proportion of the number of connected areas, if the proportion is too large, it is considered that there are too many interference items. At this time, the second mean is directly used for screening. If the proportion is not large, it is considered that there are not many interference items. At this time, the second mean is floated downward, that is, the floating value is subtracted to obtain the second judgment value and screened. In this way, the precise oil production range can be obtained more accurately.

[0115] As a preferred embodiment of the present invention, specifically, the visualization operation includes:

[0116] After the precise oil-producing range is marked in the image to be analyzed for area, the precise oil-producing range is rendered in color and the area of ​​each connected region in the precise oil-producing range is marked.

[0117] As a preferred implementation manner of the present invention, specifically, edge detection is performed on the preprocessed image by an edge detection algorithm based on a Canny operator to obtain an edge image.

[0118] In this preferred embodiment, considering that the Canny operator detects edges through multi-step processing (including Gaussian smoothing, gradient calculation, non-maximum suppression and dual threshold linking), this method can effectively reduce the influence of noise and improve the accuracy of edge detection. Using a Gaussian filter to pre-process the image helps to smooth the image before edge detection and reduce the influence of noise on the edge detection results. The Canny operator ensures the accuracy of edge positioning through non-maximum suppression technology. This method can find the most significant points on the edge, thereby improving the accuracy of edge detection. By adjusting the standard deviation of the Gaussian filter, the scale of edge detection can be adjusted so that the Canny operator can adapt to the detection requirements of edge features of different sizes. Therefore, the Canny operator is selected for edge detection.

[0119] As a preferred embodiment of the present invention, refer to Figure 2 as well as Figure 3 , the method further comprises,

[0120] The user's APP login information on the mobile terminal is obtained. After each analysis of the image to be analyzed of the oil-testing facial paper is completed, the pre-analysis data and the post-analysis data are associated and stored with the user's personal information, and then a user sample library is formed based on all registered users.

[0121] In this preferred embodiment, establishing a user sample library in the above manner has the following advantages:

[0122] 1. Based on the oil-testing facial paper, a large amount of consumer comparison data before and after using the product can be collected to establish a consumer sample library (skin status research database, this brand has 20 million users, so data can be collected simply and conveniently)

[0123] 2. Based on the area analysis of skin sebum, the corresponding relationship between oil secretion and sebum data is established (CK testing instrument), and a new evaluation method standard is established

[0124] 3. After establishing a database of product evaluation and consumer oil secretion data, we can study different products and formulas and raw materials to regulate consumers' sebum status.

[0125] 4. In the later stage, we can match the corresponding products to consumers according to the data of oily facial tissues

[0126] 5. Oil-absorbing facial tissue can absorb consumers' sebum, and samples can be taken later to analyze the sebum composition model.

[0127] 6. According to different product types, you can collect and evaluate consumers' usage in different periods, make before-and-after comparisons, and obtain oil control data.

[0128] The present invention also proposes an oil level analysis device based on oil measuring paper, comprising the following:

[0129] A data acquisition module, used to acquire the image to be analyzed of the oil testing paper;

[0130] A preprocessing module, used for performing a preprocessing operation on the image to be analyzed to obtain a preprocessed image;

[0131] An edge detection module is used to perform edge detection on the preprocessed image to obtain an edge image, and to perform tilt correction on the edge image to obtain an image to be analyzed for area;

[0132] A first correction module is used to determine the oil-discharge range of the image to be analyzed to obtain a preliminary oil-discharge range;

[0133] A second correction module is used to perform noise correction on the preliminary oil delivery range based on a preset floating value to obtain a precise oil delivery range;

[0134] An oil yield level analysis module is used to obtain an oil yield level analysis result according to a preset rule based on the area ratio of the precise oil yield range in the image to be analyzed;

[0135] The visualization module is used to mark the precise oil output range in the image to be analyzed for area, and visualize the marked image to be analyzed for area and push it to the user terminal interface.

[0136] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

[0137] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0138] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0139] Although the description of the present invention has been quite detailed and specifically describes several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims in view of the prior art by reference to the appended claims, thereby effectively covering the intended scope of the present invention. In addition, the above description of the present invention is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that have not yet been foreseen may still represent equivalent changes to the present invention.

[0140] The above is only a preferred embodiment of the present invention. The present invention is not limited to the above implementation. As long as the technical effect of the present invention is achieved by the same means, it should belong to the protection scope of the present invention. Within the protection scope of the present invention, its technical scheme and / or implementation method can have various modifications and changes.

Claims

1. A method for analyzing oil level based on oil measuring paper, characterized in that: Including the following, Obtain the image to be analyzed of the oil testing paper; Performing a preprocessing operation on the image to be analyzed to obtain a preprocessed image; Performing edge detection on the preprocessed image to obtain an edge image, and performing tilt correction on the edge image to obtain an image to be analyzed for the area; Determining the oil-discharging range of the image to be analyzed in the area to obtain a preliminary oil-discharging range; Based on the preset floating value, the noise of the preliminary oil output range is corrected to obtain the precise oil output range; Obtaining the oil level analysis result according to the area ratio of the precise oil yield range in the image to be analyzed in accordance with the preset rules; The precise oil yield range is marked in the image to be analyzed for the area, and the marked image to be analyzed for the area is visualized and pushed to the user terminal interface together with the oil yield level analysis result.

2. The oil level analysis method based on oil measuring paper according to claim 1, characterized in that: Specifically, performing a preprocessing operation on the image to be analyzed to obtain a preprocessed image includes: The image to be analyzed is subjected to brightness and contrast adjustment, noise removal and grayscale conversion to obtain a preprocessed image.

3. The oil level analysis method based on oil measuring paper according to claim 2 is characterized in that: Specifically, the edge image is tilt-corrected to obtain the image to be analyzed in the area, including: Finding straight lines in the edge image by using Hough transform; Assume that there are two points A(x1, y1) and B(x2, y2) in any straight line, calculate its slope slope = (y2-y1) / (x2-x1); The slope slope is converted into the inclination angle angle of the line through angle = np.degrees(np.arctan(slope)); The inclination angles of all straight lines in the edge image are averaged to obtain average_angle=np.mean(angles); Rotate the edge image based on average_angle to achieve tilt correction; The blank edge area generated after rotation is cropped to obtain the image to be analyzed.

4. The oil level analysis method based on oil measuring paper according to claim 3 is characterized in that: Specifically, determining the oil-discharge range of the image to be analyzed to obtain a preliminary oil-discharge range includes: Binarizing the image to be analyzed for area to obtain a first image; Detecting connected regions of the first image through connectedComponents to obtain multiple connected regions; The area of ​​each connected region is calculated by cv2.findContours; Calculate the average area of ​​all connected regions at this time to get the first mean; Subtract the preset floating value from the first mean value to obtain the first discrimination value; At this time, the connected regions whose areas are lower than the first discrimination value are eliminated from all the connected regions, and the remaining connected regions are the preliminary oil production range.

5. The oil level analysis method based on oil measuring paper according to claim 4 is characterized in that: Specifically, based on the preset floating value, the noise correction is performed on the preliminary oil output range to obtain the precise oil output range, including: Calculate the ratio P of the number of connected areas removed to the number of all connected areas; Determine whether the ratio P is lower than a ratio threshold, If it is lower than the ratio threshold, the average area of ​​the preliminary oil-producing range is calculated to obtain a second mean value, and the second mean value is subtracted from the preset floating value to obtain a second judgment value, and the connected areas in the preliminary oil-producing range that are lower than the second judgment value are removed to obtain a precise oil-producing range; If it is not lower than the ratio threshold, the area average of the preliminary oil-producing range is calculated to obtain the second mean, and the second mean is directly used as the second discrimination value. The connected areas in the preliminary oil-producing range that are lower than the second discrimination value are eliminated to obtain the precise oil-producing range.

6. The oil level analysis method based on oil measuring paper according to claim 1, characterized in that: Specifically, the visualization operation includes: After the precise oil-producing range is marked in the image to be analyzed for area, the precise oil-producing range is rendered in color and the area of ​​each connected region in the precise oil-producing range is marked.

7. The oil level analysis method based on oil measuring paper according to claim 1, characterized in that: Specifically, edge detection is performed on the preprocessed image using an edge detection algorithm based on the Canny operator to obtain an edge image.

8. The oil level analysis method based on oil measuring paper according to claim 1, characterized in that: The method further comprises, The user's APP login information on the mobile terminal is obtained. After each analysis of the image to be analyzed of the oil-testing facial paper is completed, the pre-analysis data and the post-analysis data are associated and stored with the user's personal information, and then a user sample library is formed based on all registered users.

9. An oil level analysis device based on oil measuring paper, characterized in that: Includes the following: A data acquisition module, used to acquire the image to be analyzed of the oil testing paper; A preprocessing module, used for performing a preprocessing operation on the image to be analyzed to obtain a preprocessed image; An edge detection module is used to perform edge detection on the preprocessed image to obtain an edge image, and to perform tilt correction on the edge image to obtain an image to be analyzed for area; A first correction module is used to determine the oil-discharge range of the image to be analyzed to obtain a preliminary oil-discharge range; A second correction module is used to perform noise correction on the preliminary oil delivery range based on a preset floating value to obtain a precise oil delivery range; An oil yield level analysis module is used to obtain an oil yield level analysis result according to a preset rule based on the area ratio of the precise oil yield range in the image to be analyzed; The visualization module is used to mark the precise oil output range in the image to be analyzed for area, and visualize the marked image to be analyzed for area and push it to the user terminal interface.

Images