An online query method and system for a biological standardized fossil database

Abstract

The application discloses a kind of biological standardization fossil database online query method and system, belong to biological fossil identification processing technical field.The method includes the following steps: according to the light condition data of the fossil image to be identified and the glossiness of the fossil to be identified, the light effect reduction processing is carried out to the fossil image to be identified;According to the crack intensity parameter of the light effect reduction processing after the fossil image to be identified, the crack area of the light effect reduction processing after the fossil image to be identified is subjected to crack effect reduction processing;The crack effect reduction processing after the fossil image to be identified is compared with each biological standardization fossil image in biological standardization fossil database Similarity evaluation is carried out, and the fossil species to be identified is classified according to the similarity evaluation result, reduces the interference of crack to image analysis and feature extraction, so that the image feature can truly reflect the structure of fossil itself, and the accuracy of query result is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of biological fossil identification and processing, and in particular to an online query method and system for a biological standard fossil database. Background Art

[0002] The online query method of the biological standard fossil database is a digital tool established to conveniently access and analyze fossil data. By collecting and organizing a large amount of fossil specimen information, it provides important support for research in fields such as paleontology and geology.

[0003] The existing online query method for biological standard fossil databases systematically stores and manages the relevant information of fossil specimens by building a centralized digital platform, using standardized data formats and a unified identification system. Users can quickly retrieve the required fossil data through various query methods such as keyword search, species classification, geographic location, stratigraphic age, etc., and use modern database technology and network interfaces to ensure data accuracy, accessibility and efficiency.

[0004] For example, the invention patent with announcement number CN113128335B discloses a method, system and application for detecting, classifying and discovering microfossil images, including: formulating microfossil image acquisition standards and capturing microfossil images; constructing a data set with simulated microfossils; building an SSD network; adjusting the aspect ratio of the pre-selected box; loading the original weight file of the pre-trained model and training the network model for microfossil image detection; inputting the image to be detected into the trained network model and using the non-maximum suppression algorithm to screen out appropriate detection results; and making special records of the detection results of artificial simulated fossil categories that are different from the original known microfossils.

[0005] For example, the patent application with publication number CN116524243A discloses a method and device for classifying graptolite fossil images, which includes: preparing a graptolite fossil image dataset; building and training a metadata embedding classification model, which includes two parts: an embedding model and a classification layer model; building and training a graptolite fossil single image classifier; inputting the graptolite fossil single image and the corresponding metadata in the test set into the graptolite fossil single image classifier and the metadata embedding classification model respectively, and fusing the outputs of the two to obtain the graptolite fossil single image category prediction result.

[0006] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the prior art, when querying the type of fossils to be identified using a biological standard fossil database, the fossils to be identified may have cracks that affect the surface state of the fossils to be identified, resulting in a decrease in the image quality of the fossils to be identified when scanned or photographed, making it impossible to accurately identify and extract effective morphological information. This results in a problem of low accuracy in querying fossils to be identified using a biological standard fossil database. Summary of the Invention

[0008] The present invention provides an online query method and system for a biological standard fossil database, thereby solving the problem in the prior art of low accuracy in querying fossils to be identified using a biological standard fossil database, when querying the species of the fossil to be identified using the biological standard fossil database, because the fossil to be identified may have cracks that affect the surface state of the fossil to be identified, resulting in a decrease in image quality when scanned or photographed, and the inability to accurately identify and extract effective morphological information. The goal of improving the accuracy of fossil species query is achieved.

[0009] The present invention provides an online query method for a biological standard fossil database, comprising the following steps: dividing a fossil image to be identified into a crack area and a non-crack area; performing illumination influence reduction processing on the fossil image to be identified according to light condition data of the fossil image to be identified and the glossiness of the fossil to be identified, wherein the illumination influence reduction processing is used to reduce the influence of illumination differences on the accuracy of feature extraction of the fossil image to be identified; performing crack influence reduction processing on the crack area of ​​the fossil image to be identified after the illumination influence reduction processing according to a crack intensity parameter of the fossil image to be identified after the illumination influence reduction processing, wherein the crack influence reduction processing is used to reduce the influence of crack differences on similarity evaluation of the fossil image to be identified; performing similarity evaluation on the fossil image to be identified after the crack influence reduction processing and each biological standard fossil image in a biological standard fossil database, and classifying the fossils to be identified according to the similarity evaluation results.

[0010] The present invention provides an online query system for a biological standard fossil database, comprising a light impact reduction processing module, a crack impact reduction processing module, an online query module, and a fossil query database; wherein the light impact reduction processing module is used to divide a fossil image to be identified into a crack area and a non-crack area, and perform light impact reduction processing on the fossil image to be identified according to light condition data of the fossil image to be identified and the glossiness of the fossil to be identified, wherein the light impact reduction processing is used to reduce the influence of light differences on the accuracy of feature extraction of the fossil image to be identified; the crack impact reduction processing module is used to perform crack impact reduction processing on the crack area of ​​the fossil image to be identified after the light impact reduction processing according to the crack intensity parameter of the fossil image to be identified after the light impact reduction processing, wherein the crack impact reduction processing is used to reduce the influence of crack differences on similarity evaluation of the fossil image to be identified; the online query module is used to perform similarity evaluation on the fossil image to be identified after the crack impact reduction processing and each biological standard fossil image in the biological standard fossil database, and classify the fossils to be identified according to the similarity evaluation results.

[0011] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0012] 1. The present invention provides an online query method and system for a biological standard fossil database, thereby reducing the impact of illumination on the fossil image to be identified. Based on the crack intensity parameters after the illumination impact is reduced, the interference of the crack area is further reduced. By performing similarity assessment with the biological standard fossil images in the biological standard fossil database, the types of fossils to be identified can be more accurately classified, thereby achieving an efficient and more accurate fossil query and identification process.

[0013] 2. The present invention adaptively reduces the impact of illumination according to the illumination conditions of the image, thereby reducing the influence of illumination according to different deviation illumination disturbance assessment indices, enhancing image details, and further realizing precise optimization processing of fossil images according to different illumination conditions, thereby improving image quality during the fossil identification process.

[0014] 3. The present invention quantifies the impact of cracks on the image of the fossil to be identified after illumination reduction processing based on the crack intensity parameter, obtains a crack intensity index, and compares it with a preset threshold value. Different filling and repair methods are adopted according to the range of different crack intensity indices, thereby achieving precise repair of the crack area, improving image quality, making the identification of fossils more accurate, and reducing the situation where the cracks are too large to be identified.

[0015] 4. The present invention reduces the impact of cracks by extracting the edge contours, surface textures and high-dimensional feature vectors of the image of the fossil to be identified after processing, and performs similarity evaluation with images in the biological standard fossil database, thereby quantifying the similarity between the fossil to be identified and the images of each biological standard fossil. Furthermore, by comparing the maximum correlation score coefficient with a preset threshold, the type of the fossil to be identified can be accurately determined, thereby avoiding misjudgment and improving the accuracy of fossil identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flowchart of a method for online querying a biological standard fossil database provided in an embodiment of the present application.

[0017] Figure 2 A crack strength index variation diagram of an online query method for a biological standard fossil database provided in an embodiment of the present application.

[0018] Figure 3 This is a schematic diagram of the structure of an online query system for a biological standard fossil database provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The embodiment of the present application provides an online query method and system for a biological standard fossil database, which solves the problem in the prior art that when querying the type of a fossil to be identified using a biological standard fossil database, the fossil to be identified may have cracks, which may affect the surface state of the fossil to be identified, resulting in a decrease in the image quality of the fossil to be identified when scanned or photographed, and the inability to accurately identify and extract effective morphological information. This problem leads to low accuracy in querying the fossil to be identified using a biological standard fossil database. By dividing the image of the fossil to be identified into crack areas and non-crack areas, the image of the fossil to be identified is illuminated according to the light condition data of the image of the fossil to be identified and the glossiness of the fossil to be identified. Impact reduction processing, the said illumination impact reduction processing is used to reduce the influence of illumination differences on the accuracy of feature extraction of the fossil image to be identified; crack impact reduction processing is performed on the crack area of ​​the fossil image to be identified after the illumination impact reduction processing according to the crack intensity parameters of the fossil image to be identified after the illumination impact reduction processing, and the said crack impact reduction processing is used to reduce the influence of crack differences on the similarity assessment of the fossil image to be identified; the fossil image to be identified after the crack impact reduction processing is evaluated for similarity with the images of each biological standard fossil in the biological standard fossil database, and the fossil species to be identified are divided according to the similarity assessment results, thereby achieving the goal of improving the accuracy of fossil species query.

[0020] The technical solution in the embodiments of the present application is to solve the problem of low accuracy in querying the type of fossils to be identified using a biological standard fossil database, because the fossils to be identified may have cracks that affect the surface condition of the fossils to be identified, resulting in a decrease in the image quality of the fossils to be identified when scanned or photographed, making it impossible to accurately identify and extract effective morphological information. The overall idea is as follows:

[0021] By using light condition data and fossil gloss to reduce the impact of illumination on the image, the interference of illumination differences on the feature extraction of fossil images is reduced; by performing crack impact reduction processing on the crack area, the interference of crack differences on the similarity assessment is reduced; by performing similarity assessment on the image after crack impact reduction processing and each standard fossil image in the biological standard fossil database, the similarity between the fossil to be identified and the fossil images in the database can be accurately compared. According to the similarity assessment results, the types of fossils to be identified can be effectively divided, thereby improving the accuracy and automation level of fossil identification.

[0022] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0023] like Figure 1 As shown, it is a flow chart of a biological standard fossil database online query method provided by an embodiment of the present application, the method comprising the following steps: dividing the fossil image to be identified into crack areas and non-crack areas, performing illumination effect reduction processing on the fossil image to be identified based on the light condition data of the fossil image to be identified and the glossiness of the fossil to be identified, the illumination effect reduction processing is used to reduce the influence of illumination differences on the accuracy of feature extraction of the fossil image to be identified, the light condition data includes the ratio of highlight pixels, the standard grayscale difference and the shadow coverage, the ratio of highlight pixels indicates the ratio of pixels whose RGB value of each pixel point in the fossil image to be identified is greater than a preset RGB threshold The standard grayscale difference represents the standard deviation of the grayscale value of each pixel in the fossil image to be identified and the average grayscale value, and the shadow coverage rate represents the proportion of the shadow area in the fossil image to be identified to the total area; according to the crack intensity parameter of the fossil image to be identified after the illumination effect reduction treatment, the crack area of ​​the fossil image to be identified after the illumination effect reduction treatment is subjected to crack influence reduction treatment, and the crack influence reduction treatment is used to reduce the influence of crack differences on the similarity evaluation of the fossil image to be identified; the fossil image to be identified after the crack influence reduction treatment is subjected to similarity evaluation with the images of each biological standard fossil in the biological standard fossil database, and the types of the fossils to be identified are divided according to the similarity evaluation results.

[0024] In this embodiment, the present invention is applied to the processing of images of fossils to be identified prior to online querying of a biological standard fossil database. By processing cracked and non-cracked areas in an image separately, the impact of cracks on image quality can be more accurately identified, and targeted repairs can be performed in subsequent processing, reducing the interference of cracks on the overall image feature extraction, thereby improving the accuracy of morphological information extraction. By performing illumination impact reduction processing on the image based on lighting conditions and glossiness, the impact of illumination differences can be eliminated or reduced, ensuring that image feature extraction remains accurate under different lighting conditions, thereby improving the quality of the fossil image to be identified. Cracks in the fossil to be identified may affect surface features, rendering traditional image similarity assessment methods ineffective. By performing specialized crack impact reduction processing on the cracked area, the impact of cracks on the image matching process can be reduced.

[0025] In addition, the fossil query database is used to store relevant data based on the online query method of the biological standard fossil database, including: the light disturbance assessment threshold corresponding to each gloss value, the highlight pixel influencing factor, the critical highlight pixel ratio, the critical standard grayscale difference and the critical shadow coverage rate, etc. The data in the fossil query database can be obtained through cooperation with scientific research organizations such as the Chinese Society of Paleontology, or through queries in public databases such as the Paleontological Site Protection Database.

[0026] Furthermore, the step of performing a light effect reduction process on the image of the fossil to be identified based on the light condition data and the glossiness of the fossil to be identified includes:

[0027] First, the glossiness of the fossil to be identified is matched with the light disturbance assessment threshold corresponding to each glossiness value in the preset fossil query database to obtain the light disturbance assessment threshold corresponding to the glossiness of the fossil to be identified.

[0028] Then, the influence of light on the quality of the fossil image to be identified is quantified based on the light condition data of the fossil image to be identified, and the light disturbance evaluation index is obtained. The specific process is: obtain the light condition data reference data from the preset fossil query database, including: critical highlight pixel ratio, critical standard grayscale difference and critical shadow coverage; perform proportion approximation operation on the highlight pixel ratio, standard grayscale difference and shadow coverage respectively with the critical highlight pixel ratio, critical standard grayscale difference and critical shadow coverage, and then weight the proportion approximation operation results and couple them with the light condition data compensation value to obtain the light disturbance evaluation index. The light condition data compensation value includes the highlight pixel influence factor, the standard grayscale difference influence factor and the shadow coverage influence factor. The light disturbance evaluation index represents the quantitative data of the degree of influence of the highlight pixel ratio, standard grayscale difference and shadow coverage on the quality of the fossil image to be identified. The light disturbance evaluation index is obtained as follows:

[0029]

[0030] Where LI represents the illumination disturbance evaluation index, μ1 represents the highlight pixel impact factor, μ2 represents the standard grayscale difference impact factor, μ3 represents the shadow coverage impact factor, HP1 represents the highlight pixel ratio, HP0 represents the critical highlight pixel ratio, GD1 represents the standard grayscale difference, GD0 represents the critical standard grayscale difference, SC1 represents the shadow coverage, and SC0 represents the critical shadow coverage.

[0031] μ1, μ2, and μ3 are respectively the compensation values ​​corresponding to the highlight pixel ratio, standard grayscale difference, and shadow coverage ratio preset in the fossil query database, respectively representing the numerical values ​​of the degree of influence of the highlight pixel ratio, standard grayscale difference, and shadow coverage ratio on the light disturbance assessment index, and can be directly obtained from the fossil query database when used. For example, the highlight pixel ratio and the compensation values ​​corresponding to the highlight pixel ratio preset in the fossil query database form a mapping set, and the compensation values ​​corresponding to the highlight pixel ratio are obtained by inputting the mapping set according to the highlight pixel ratio; the standard grayscale difference and the compensation values ​​corresponding to the standard grayscale difference preset in the fossil query database form a mapping set, and the compensation values ​​corresponding to the standard grayscale difference are obtained by inputting the mapping set according to the standard grayscale difference; the shadow coverage ratio and the compensation values ​​corresponding to the shadow coverage ratio preset in the fossil query database form a mapping set, and the compensation values ​​corresponding to the shadow coverage ratio are obtained by inputting the mapping set according to the shadow coverage ratio, wherein the mapping relationship is a many-to-one or one-to-one relationship, and the compensation value range of the compensation value in this embodiment is between 0 and 1.

[0032] Finally, the illumination disturbance assessment index is compared with the illumination disturbance assessment threshold. If the illumination disturbance assessment index is less than or equal to the illumination disturbance assessment threshold, no additional operation is performed. Otherwise, the illumination impact of the fossil image to be identified is reduced according to the deviation illumination disturbance assessment index. The deviation illumination disturbance assessment index represents the deviation between the illumination disturbance assessment index and the illumination disturbance assessment threshold.

[0033] In the present embodiment, the glossiness value can be measured by using a glossiness meter on the surface of the fossil. The instrument emits multiple light rays at specific angles (for example, 20°, 60°, and 85°), receives the reflected light, and obtains the average value of the reflected intensity by calculation. Among them, the light disturbance evaluation threshold represents the critical point at which the light source conditions have a significant impact on the glossiness of the fossil, which can be directly obtained from the fossil query database. For example, in the fossil query database, the glossiness value and the light disturbance evaluation threshold are one-to-one corresponding to form a mapping relationship table, which records each glossiness value and its corresponding light disturbance evaluation threshold. These relationships can be one-to-one or many-to-one. When obtaining the light disturbance evaluation threshold, only the glossiness value needs to be input into the mapping relationship table, and the fossil query database can quickly locate and return the light disturbance evaluation threshold corresponding to the glossiness value. The light influence reduction processing can retain more details of the fossil surface by reducing the reflection of too strong or uneven light. Through light influence reduction processing, the negative impact of light on image quality can be reduced, the real features of the fossil can be highlighted, and the morphology and characteristics of the fossil can be accurately analyzed during subsequent identification.

[0034] In addition, the three indicators of high light pixel ratio, standard gray difference, and shadow coverage rate are related to each other. For example, the greater the standard gray difference, the higher the shadow coverage rate may be. If the high light area ratio in the image is larger, and the standard gray difference is large, the image may have strong light influence, which may cause the loss of fossil details or overexposure. By combining these three indicators, the light influence on the fossil image to be identified can be more comprehensively evaluated, and the light disturbance evaluation index obtained by comprehensive analysis can accurately determine the degree of influence of the image in terms of light, thereby evaluating the quality of the fossil image to be identified.

[0035] Furthermore, the step of reducing the illumination influence on the fossil image to be identified according to the deviation illumination disturbance evaluation index includes: obtaining a first deviation illumination disturbance evaluation threshold and a second deviation illumination disturbance evaluation threshold from a preset fossil query database; comparing the deviation illumination disturbance evaluation index with the first deviation illumination disturbance evaluation threshold and the second deviation illumination disturbance evaluation threshold respectively; if the deviation illumination disturbance evaluation index is less than the first deviation illumination disturbance evaluation threshold, restrictive histogram equalization is turned on, and at the same time, the contrast of the crack area is enhanced according to the deviation illumination disturbance evaluation index, specifically: pre-setting a threshold to limit the number of pixels of a single gray level in the histogram, the part exceeding the threshold is truncated and evenly distributed to other gray levels, and then the image is divided into several small blocks, for each Histogram equalization is performed independently on small blocks, and the shadow area is enhanced using the Retinex shadow enhancement technology; if the deviation illumination perturbation evaluation index is greater than or equal to the first deviation illumination perturbation evaluation threshold and less than the second deviation illumination perturbation evaluation threshold, the non-subsampled contourlet transform technology is used to decompose the fossil image to be identified into high-frequency components and low-frequency components, homomorphic filtering is applied to the low-frequency components, and adaptive threshold denoising is performed on the high-frequency components; if the deviation illumination perturbation evaluation index is greater than or equal to the second deviation illumination perturbation evaluation threshold, the multi-scale Gaussian surround solution is used to separate the illumination and reflection components, and the reflection component is eliminated from the fossil image to be identified while enabling adaptive homomorphic filtering (dynamically adjusting the cutoff frequency and gain of the V channel in the HSV space to suppress low-frequency illumination while retaining high-frequency cracks).

[0036] Among them, the step of enhancing the contrast of the crack area according to the deviation light disturbance assessment index includes: obtaining the contrast enhancement value corresponding to each deviation light impact area from a preset fossil query database; matching the deviation light disturbance assessment index with each deviation light impact area to obtain each deviation light impact area corresponding to the deviation light disturbance assessment index, thereby obtaining the contrast enhancement value corresponding to the deviation light disturbance assessment index; processing the contrast of the fossil image to be identified according to the contrast enhancement value; the contrast enhancement values ​​include 10, 15 and 20.

[0037] In this embodiment, by obtaining and comparing the deviation illumination disturbance assessment index with a preset threshold, the system can perform adaptive processing according to the specific illumination interference of the image, avoiding a one-size-fits-all processing approach, thereby retaining more details and reducing invalid or over-correction; by turning on restrictive histogram equalization processing, the brightness and contrast of the image can be effectively improved, and the details of the fossil surface, especially important features such as cracks, can be enhanced; the processing of low-frequency components by homomorphic filtering helps to reduce the brightness changes caused by uneven ambient illumination, making the illumination of the fossil image more balanced, and the adaptive denoising of high-frequency components can effectively remove noise while retaining the detailed structure in the image, making the details of the fossil more prominent; for images that are severely disturbed by reflection, the system will separate the illumination and reflection components in the image and eliminate the reflection component, which helps to remove the interference caused by gloss and specular reflection, making the true surface structure of the fossil clearer, and adaptive homomorphic filtering helps to dynamically adjust the image under different lighting conditions, especially for images with more significant reflection components. Adaptive filtering can flexibly adjust the filter intensity according to changes in image content and illumination distribution, thereby maintaining the details and texture of the image.

[0038] The contrast enhancement value reflects the degree of image contrast enhancement and can be directly obtained from the fossil query database. For example, in the fossil query database, each deviation light-affected region is mapped to a contrast enhancement value, forming a one-to-one mapping table. The table records each deviation light-affected region and its corresponding contrast enhancement value. These relationships are one-to-one. To obtain the contrast enhancement value, simply input the deviation light perturbation assessment index into the mapping table. The fossil query database can then quickly locate the deviation light-affected region corresponding to the deviation light perturbation assessment index and return the corresponding contrast enhancement value for the deviation light-affected region. The contrast enhancement value setting can flexibly respond to different lighting conditions, ensuring that cracks and important feature areas remain clearly presented despite the influence of deviation light. This targeted enhancement ensures image consistency and reliability under different lighting environments. When processing fossil images for identification based on the contrast enhancement value, the sum of the image contrast and the contrast enhancement value can be directly used as the contrast value of the current image.

[0039] Further, the step of performing the crack influence reduction processing on the crack area of the fossil image to be identified after the illumination influence reduction processing according to the crack intensity parameter of the fossil image to be identified after the illumination influence reduction processing includes: a first step, according to the crack intensity parameter, the influence of the crack on the fossil image to be identified after the illumination influence reduction processing is quantified, and the crack intensity index is obtained, wherein the crack intensity parameter includes the crack area ratio, the crack depth ratio and the crack number, the crack area ratio represents the proportion of the total area of the crack area in the image to the total area of the image, the crack depth ratio represents the ratio of the maximum depth of the crack to the maximum depth of the detected fossil, and the crack number represents the total number of cracks identified in the image. The parameters are related to each other, for example, if the crack area ratio is large and the crack number is large, it usually means that the object surface damage is serious and more dispersed, and the damage degree is complex; if the crack area ratio is large and the crack depth ratio is also high, it usually indicates that the object is seriously damaged, there are large area cracks and deep cracks, which may affect the structural stability of the object. The crack intensity index obtained by comprehensive analysis can reflect the damage of the object to be identified, evaluate the severity of the crack and the integrity of the object, so as to judge the influence of the distribution, depth and number of cracks on the fossil image to be identified.

[0040] The method for obtaining the crack intensity index is: obtaining crack intensity parameter reference data from a preset fossil query database, including: critical crack area ratio, critical crack depth ratio and critical crack number; the crack area ratio, the crack depth ratio and the crack number are respectively compared with the critical crack area ratio, the critical crack depth ratio and the critical crack number to perform the ratio proximity operation, and then the ratio proximity operation results are respectively processed by weighting and coupling through the crack intensity parameter compensation value to obtain the crack intensity index. The crack intensity parameter compensation value includes the crack area ratio influence factor, the crack depth ratio influence factor and the crack number influence factor, and the crack intensity index represents the quantitative data of the influence degree of the crack area ratio, the crack depth ratio and the crack number on the crack area of the fossil image to be identified after the illumination influence reduction processing.

[0041] The crack intensity index is obtained as follows:

[0042]

[0043] In the formula, CS represents the crack intensity index, μ4 represents the crack area ratio influence factor, μ5 represents the crack depth ratio influence factor, μ6 represents the crack number influence factor, CN1 represents the crack number influence factor, CA1 represents the crack area ratio, CA0 represents the critical crack area ratio, CD1 represents the crack depth ratio, CD0 represents the critical crack depth ratio, CN1 represents the crack number, and CN0 represents the critical crack number.

[0044] μ4, μ5, and μ6 are respectively the compensation values ​​corresponding to the crack area ratio, crack depth ratio, and number of cracks preset in the fossil query database, which respectively represent the numerical values ​​of the degree of influence of the crack area ratio, crack depth ratio, and number of cracks on the crack strength index, and can be directly obtained from the fossil query database when used. For example, the crack area ratio and the compensation values ​​corresponding to the crack area ratio preset in the fossil query database form a mapping set, and the compensation value corresponding to the crack area ratio is obtained by inputting the mapping set according to the crack area ratio; the crack depth ratio and the compensation values ​​corresponding to the crack depth ratio preset in the fossil query database form a mapping set, and the compensation value corresponding to the crack depth ratio is obtained by inputting the mapping set according to the crack depth ratio; the number of cracks and the compensation values ​​corresponding to the number of cracks preset in the fossil query database form a mapping set, and the compensation value corresponding to the number of cracks is obtained by inputting the mapping set according to the number of cracks, wherein the mapping relationship is a many-to-one or one-to-one relationship, and the compensation value in this embodiment ranges from 0 to 1.

[0045] The second step is to obtain the first threshold value and the second threshold value of the crack intensity index from the preset fossil query database; compare the crack intensity index with the first threshold value and the second threshold value of the crack intensity index respectively; if the crack intensity index is less than the first threshold value, the crack area of ​​the fossil image to be identified is filled and repaired after the illumination effect is reduced according to the adjacent pixels of each crack area; if the crack intensity index is greater than or equal to the first threshold value of the crack intensity index and less than the second threshold value of the crack intensity index, the crack area of ​​the fossil image to be identified is filled and repaired after the illumination effect is reduced by extracting texture features and pixel information from around the crack area; if the crack intensity index is greater than or equal to the second threshold value of the crack intensity index, it is prompted that the cracks of the fossil to be identified need to be repaired and cannot be identified.

[0046] In this embodiment, the crack intensity index is compared with the preset first and second thresholds to classify the cracks according to their severity. For example, a crack intensity index less than the first threshold may correspond to a slight crack, a crack intensity index greater than or equal to the first threshold but less than the second threshold corresponds to a medium crack, and a crack intensity index greater than or equal to the second threshold corresponds to a severe crack. This can guide the selection of subsequent repair processing. For slight cracks, the method will fill and repair based on the information of neighboring pixels around the crack area, and repair the area with slight cracks by using methods such as the mean or weighted average of the neighborhood pixels to make it blend naturally with the surrounding area as much as possible to reduce visual disharmony; for medium cracks, a texture synthesis method is used to extract texture features from around the crack area and apply them to the crack area to restore the natural texture of the area. For cracks, a non-local mean algorithm is used to calculate the pixel information of similar areas in the image to fill the crack area, and a partial differential equation repair method is used to protect the edge information of the crack area; for severe cracks, the method will prompt that the crack cannot be effectively repaired and recommends repair. This graded repair method adjusts the treatment according to the severity of the crack, resulting in a more subtle and natural-looking repair.

[0047] The crack area ratio influence factor was set to 0.4, the crack depth ratio influence factor was set to 0.4, the crack number influence factor was set to 0.2, the crack area ratio was set to 30%, the critical crack area ratio was set to 20%, the crack depth ratio was set to 40%, the critical crack depth ratio was set to 20%, and the critical number of cracks was set to 3. The crack strength index was calculated under the condition of increasing crack number. This is shown in Table 1, a crack strength index data table for an online query method for a biological standard fossil database.

[0048] Table 1 Crack strength index data of a biological standard fossil database online query method

[0049] serial number CN1 (one) CS 1 1 1.467 2 2 1.533 3 3 1.6 4 4 1.667 5 5 1.733

[0050] like Figure 2 As shown in Table 1 and Figure 2 It can be seen that when the influencing factors of crack area ratio, crack depth ratio, crack number ratio, crack area ratio, critical crack area ratio, crack depth ratio, critical crack depth ratio and critical crack number remain unchanged, and the number of cracks continues to increase, the crack intensity index also continues to increase.

[0051] Furthermore, the steps of performing similarity evaluation on the image of the fossil to be identified after the crack effect reduction processing and each biological standard fossil image in the biological standard fossil database, and classifying the fossil to be identified into types according to the similarity evaluation results include:

[0052] First, the image features of the fossil to be identified and the image features of each biological standard fossil after crack reduction processing are extracted. The image features include the fossil edge contour point set, fossil surface texture and high-dimensional feature vector. The edge contour correlation score coefficient is obtained based on the fossil edge contour point set. The specific process is: the contour point set is extracted using the Canny edge detection technology, the Hu moment vector is calculated respectively, and then the cosine similarity is used to calculate the coefficient. The central moment calculation formula is: Where μ p,q Represents the central moment of the image, I(x, y) is the pixel value of the image at point (x, y), and is the center position of the image. After normalizing the central moment, the normalized second-order and third-order central moments are combined to obtain seven Hu invariant moments. The calculation formula of cosine similarity is: Where A and B are the Hu moment feature vectors of the two images, A·B is the dot product of vector A and vector B, ‖A‖ and ‖B‖ are the norms of vector A and B respectively. The texture correlation score coefficient is obtained according to the fossil surface texture. The specific process is: the fossil surface texture features are extracted using local binary patterns, and then calculated using histogram intersection. The calculation formula of local binary pattern (LBP) is: Where, P c is the gray value of the center pixel, P a is the gray value of the ith neighborhood pixel, s(x) is the sign function, defined as The LBP histogram calculation formula is: Where H(j) is the frequency of LBP value j in the histogram, ‖LBP(x, y) = j is an indicator function that is 1 when LBP(x, y) = j and 0 otherwise, and (x, y) are the pixel coordinates in the image. The formula for calculating histogram intersection is: Where M is the total number of LBP values, H1(i) and H2(i) are the i-th elements of the LBP histograms in the two images, respectively. A high-dimensional feature correlation score coefficient is obtained based on the high-dimensional feature vector. The specific process is: using a pre-trained CNN model to extract the high-dimensional feature vector and then calculating it using cosine similarity. The three are interrelated. For example, edges reflect the macroscopic shape and outline of an object, while texture reflects the microscopic structure of the object's surface. The combination of the two can provide more accurate information about the object's structure and surface. Edge features provide the basic outline of the image, while high-dimensional features comprehensively consider more complex abstract features. Texture features reflect the surface microscopic information of the image, while high-dimensional features include the deeper feature expression of this microscopic information. The correlation score coefficient obtained from this comprehensive analysis can provide a comprehensive similarity assessment between the biological reference fossil image and the fossil image to be identified, reflecting the degree of similarity between the images in terms of shape, surface texture, and high-level features.

[0053] Then, the similarity between the image of the fossil to be identified after the crack influence reduction treatment and the images of each biological standard fossil in the biological standard fossil database is quantified based on the edge contour correlation score coefficient, texture correlation score coefficient and high-dimensional feature correlation score coefficient, and the correlation score coefficient of each biological standard fossil image is obtained. The specific process is: the edge contour correlation score coefficient, texture correlation score coefficient and high-dimensional feature correlation score coefficient of each biological standard fossil image are weighted and coupled using the similarity compensation value to obtain the correlation score coefficient of each biological standard fossil image. The similarity compensation value includes the edge contour similarity influencing factor, the texture similarity influencing factor and the high-dimensional feature similarity influencing factor. The correlation score coefficient of each biological standard fossil image represents the quantitative data of the influence of the edge contour correlation score coefficient, the texture correlation score coefficient and the high-dimensional feature correlation score coefficient on the similarity between the fossil to be identified and each biological standard fossil. The correlation score coefficient of each biological standard fossil image is obtained as follows:

[0054] SE i =μ7×EC 1i +μ8×Te 1i +μ9×HF 1i ;

[0055] Where, SE i represents the correlation score coefficient of the i-th biological standard fossil image, μ7 represents the edge contour similarity influencing factor, μ8 represents the texture similarity influencing factor, μ9 represents the high-dimensional feature similarity influencing factor, EC1 represents the edge contour correlation score coefficient, Te 1i Represents the texture correlation score coefficient, HF 1irepresents a high-dimensional feature correlation score coefficient, wherein i is the number of each biological standardized fossil image, i = 1, 2, 3,..., N, and N is the total number of biological standardized fossil images.

[0056] μ7, μ8 and μ9 are respectively preset compensation values of edge contour similarity, texture similarity and high-dimensional feature similarity in the fossil query database, and represent the numerical values of the influence degree of edge contour similarity, texture similarity and high-dimensional feature similarity on the correlation score coefficient, which can be directly obtained from the fossil query database when used. For example, the edge contour similarity and the preset compensation value of the edge contour similarity in the fossil query database form a mapping set, and the compensation value corresponding to the edge contour similarity is obtained by inputting the mapping set according to the edge contour similarity; the texture similarity and the preset compensation value of the texture similarity in the fossil query database form a mapping set, and the compensation value corresponding to the texture similarity is obtained by inputting the mapping set according to the texture similarity; the high-dimensional feature similarity and the preset compensation value of the high-dimensional feature similarity in the fossil query database form a mapping set, and the compensation value corresponding to the high-dimensional feature similarity is obtained by inputting the mapping set according to the high-dimensional feature similarity, wherein the mapping relationship is a many-to-one or one-to-one relationship, and the value range of the compensation value in the embodiment is between 0 and 1.

[0057] Finally, the correlation score coefficients of each biological standardized fossil image are sorted from large to small to obtain the maximum correlation score coefficient; the maximum correlation score threshold is obtained from the preset fossil query database; the maximum correlation score coefficient is compared with the maximum correlation score threshold, if the maximum correlation score coefficient is less than the maximum correlation score threshold, it is prompted that there is no similar fossil in the biological standardized fossil database, if the maximum correlation score coefficient is greater than or equal to the maximum correlation score threshold, the biological standardized fossil corresponding to the maximum correlation score coefficient is taken as the fossil species to be identified.

[0058] In the embodiment, through multi-dimensional feature extraction, the key information of the fossil can be comprehensively and carefully extracted, the influence caused by image cracks or other interference factors can be effectively reduced, and the accuracy and reliability of the fossil identification are improved; by comparing with the maximum correlation score threshold in the preset fossil query database, the judgment standard of similarity can be dynamically adjusted in each identification, when the maximum similarity of the fossil to be identified is higher than the threshold, the method automatically prompts the similar fossil type; when it is lower than the threshold, the method will prompt that no matching fossil species is found in the database, and such feedback mechanism ensures the flexibility and accuracy of the evaluation process.

[0059] As Figure 3As shown, it is a structural schematic diagram of an online query system for a biological standard fossil database provided by an embodiment of the present application. The online query system for a biological standard fossil database provided by an embodiment of the present application includes: an illumination effect reduction processing module, a crack effect reduction processing module, an online query module and a fossil query database; wherein, the illumination effect reduction processing module is used to divide the fossil image to be identified into a crack area and a non-crack area, and perform illumination effect reduction processing on the fossil image to be identified according to the light condition data of the fossil image to be identified and the glossiness of the fossil to be identified, and the illumination effect reduction processing is used to reduce the influence of illumination difference on the accuracy of feature extraction of the fossil image to be identified; the crack effect reduction processing module is used to perform crack effect reduction processing on the crack area of ​​the fossil image to be identified after illumination effect reduction processing according to the crack intensity parameter of the fossil image to be identified after illumination effect reduction processing, and the crack effect reduction processing is used to reduce the influence of crack difference on the similarity evaluation of the fossil image to be identified; the online query module is used to perform similarity evaluation on the fossil image to be identified after crack effect reduction processing with each biological standard fossil image in the biological standard fossil database, and classify the fossils to be identified according to the similarity evaluation results.

[0060] In summary, the embodiments of the present application perform illumination impact reduction processing on images through light condition data and fossil gloss, thereby reducing the interference of illumination differences on fossil image feature extraction; perform crack impact reduction processing on crack areas, thereby reducing the interference of crack differences on similarity assessment; perform similarity assessment on images after crack impact reduction processing and each standard fossil image in the biological standard fossil database, and accurately compare the similarity between the fossil to be identified and the fossil images in the database. According to the similarity assessment results, the types of fossils to be identified can be effectively divided, thereby improving the accuracy and automation level of fossil identification.

[0061] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0062] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0063] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0064] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0065] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0066] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for online querying of a biological standard fossil database, characterized in that: The following steps are involved: Dividing the image of the fossil to be identified into a crack area and a non-crack area, and performing a light impact reduction process on the image of the fossil to be identified based on the light condition data of the image of the fossil to be identified and the glossiness of the fossil to be identified, wherein the light impact reduction process is used to reduce the influence of light differences on the accuracy of feature extraction of the image of the fossil to be identified; performing crack influence reduction processing on the crack region of the fossil image to be identified after the illumination influence reduction processing according to the crack intensity parameter of the fossil image to be identified after the illumination influence reduction processing, wherein the crack influence reduction processing is used to reduce the influence of crack differences on the similarity evaluation of the fossil image to be identified; The image of the fossil to be identified after crack reduction treatment is evaluated for similarity with the images of various biological standard fossils in the biological standard fossil database, and the type of fossil to be identified is divided according to the similarity evaluation results; The step of performing a light influence reduction process on the fossil image to be identified based on the light condition data and the glossiness of the fossil to be identified comprises: Matching the glossiness of the fossil to be identified with the light disturbance assessment threshold corresponding to each glossiness value in the preset fossil query database to obtain the light disturbance assessment threshold corresponding to the glossiness of the fossil to be identified; quantifying the influence of light on the quality of the image of the fossil to be identified based on the light condition data of the image of the fossil to be identified, and obtaining a light disturbance evaluation index; Comparing the light disturbance assessment index with the light disturbance assessment threshold; if the light disturbance assessment index is less than or equal to the light disturbance assessment threshold, no additional operation is performed; otherwise, the fossil image to be identified is subjected to light impact reduction processing according to the deviation light disturbance assessment index, where the deviation light disturbance assessment index represents the deviation between the light disturbance assessment index and the light disturbance assessment threshold; The step of performing crack influence reduction processing on the crack region of the fossil image to be identified after the illumination influence reduction processing according to the crack intensity parameter of the fossil image to be identified after the illumination influence reduction processing comprises: The crack intensity parameter is used to quantify the effect of cracks on the image of the fossil to be identified after the illumination effect is reduced, and the crack intensity index is obtained; Obtaining a first threshold value of a crack strength index and a second threshold value of a crack strength index from a preset fossil query database; The crack intensity index is compared with the first crack intensity index threshold and the second crack intensity index threshold respectively. If the crack intensity index is less than the first crack intensity index threshold, the crack area of ​​the fossil image to be identified after the illumination effect reduction processing is performed based on the adjacent pixels of each crack area. If the crack intensity index is greater than or equal to the first crack intensity index threshold and less than the second crack intensity index threshold, the crack area of ​​the fossil image to be identified after the illumination effect reduction processing is performed by extracting texture features and pixel information from around the crack area to fill and repair the crack area. If the crack intensity index is greater than or equal to the second crack intensity index threshold, it is prompted that the crack of the fossil to be identified cannot be identified. The steps of performing similarity evaluation on the image of the fossil to be identified after the crack effect reduction process and each biological standard fossil image in the biological standard fossil database, and classifying the fossil to be identified into types according to the similarity evaluation results include: Extracting image features of the fossil to be identified and image features of each biological standard fossil after crack effect reduction processing, wherein the image features include fossil edge contour point sets, fossil surface textures, and high-dimensional feature vectors; The edge contour correlation score coefficient is obtained based on the fossil edge contour point set; The texture correlation score coefficient was obtained based on the fossil surface texture; Obtain high-dimensional feature correlation score coefficients based on high-dimensional feature vectors; The similarity between the image of the fossil to be identified and the images of each biological standard fossil in the biological standard fossil database after the crack influence reduction treatment is quantified based on the edge contour correlation score coefficient, texture correlation score coefficient and high-dimensional feature correlation score coefficient, and the correlation score coefficient of each biological standard fossil image is obtained; Sort the correlation score coefficients of each biological standard fossil image from large to small to obtain the maximum correlation score coefficient; Obtaining a maximum relevance score threshold from a pre-set fossil query database; The maximum correlation score coefficient is compared with the maximum correlation score threshold. If the maximum correlation score coefficient is less than the maximum correlation score threshold, it indicates that there is no similar fossil in the biological reference fossil database. If the maximum correlation score coefficient is greater than or equal to the maximum correlation score threshold, the biological reference fossil corresponding to the maximum correlation score coefficient is used as the fossil species to be identified.

2. The online query method for a biological standard fossil database according to claim 1, characterized in that: The lighting condition data includes the ratio of highlight pixels, standard grayscale difference, and shadow coverage; The step of quantifying the influence of light on the quality of the fossil image to be identified based on the light condition data of the fossil image to be identified to obtain the light disturbance evaluation index comprises: Obtain light condition data reference from the preset fossil query database, including: critical highlight pixel ratio, critical standard grayscale difference, and critical shadow coverage; The highlight pixel ratio, standard grayscale difference and shadow coverage are respectively subjected to ratio approximation calculation with the critical highlight pixel ratio, critical standard grayscale difference and critical shadow coverage, and then the ratio approximation calculation results are weighted and coupled with the light condition data compensation value to obtain the light disturbance assessment index. The light condition data compensation value includes the highlight pixel impact factor, the standard grayscale difference impact factor and the shadow coverage impact factor. The light disturbance assessment index represents the quantitative data of the degree of influence of the highlight pixel ratio, standard grayscale difference and shadow coverage on the quality of the fossil image to be identified.

3. The online query method for a biological standard fossil database according to claim 1, characterized in that: The step of performing illumination influence reduction processing on the fossil image to be identified according to the deviation illumination disturbance evaluation index comprises: Obtaining a first deviation light disturbance assessment threshold and a second deviation light disturbance assessment threshold from a preset fossil query database; The deviation light disturbance evaluation index is compared with the first deviation light disturbance evaluation threshold and the second deviation light disturbance evaluation threshold respectively. If the deviation light disturbance evaluation index is less than the first deviation light disturbance evaluation threshold, restrictive histogram equalization is turned on, and the contrast of the crack area is enhanced according to the deviation light disturbance evaluation index. If the deviation light disturbance evaluation index is greater than or equal to the first deviation light disturbance evaluation threshold and less than the second deviation light disturbance evaluation threshold, the fossil image to be identified is decomposed into high-frequency components and low-frequency components, homomorphic filtering is applied to the low-frequency components, and adaptive threshold denoising is performed on the high-frequency components. If the deviation light disturbance evaluation index is greater than or equal to the second deviation light disturbance evaluation threshold, the illumination and reflection components are separated, the reflection component is eliminated from the fossil image to be identified, and adaptive homomorphic filtering is turned on.

4. The online query method for a biological standard fossil database according to claim 3, characterized in that: The step of enhancing the contrast of the crack area according to the deviation illumination disturbance evaluation index includes: Obtain the contrast enhancement value corresponding to each deviation light-affected area from a preset fossil query database; Matching the deviation light disturbance evaluation index with each deviation light influence area to obtain each deviation light influence area corresponding to the deviation light disturbance evaluation index, thereby obtaining a contrast enhancement value corresponding to the deviation light disturbance evaluation index; The contrast of the fossil image to be identified is processed according to the contrast enhancement value to reduce the influence of illumination on the quality of the crack area of ​​the fossil image to be identified.

5. The online query method for a biological standard fossil database according to claim 1, characterized in that: The crack strength parameters include crack area ratio, crack depth ratio and number of cracks; The step of quantifying the effect of the cracks on the image of the fossil to be identified after the illumination effect reduction treatment according to the crack strength parameter to obtain the crack strength index comprises: Obtain reference data for crack strength parameters from a preset fossil query database, including: critical crack area ratio, critical crack depth ratio, and critical crack number; The crack area ratio, crack depth ratio and number of cracks are respectively subjected to ratio approximation calculation with the critical crack area ratio, critical crack depth ratio and critical crack number, and then the ratio approximation calculation results are weighted and coupled by the crack intensity parameter compensation value to obtain the crack intensity index. The crack intensity parameter compensation value includes the crack area ratio influencing factor, the crack depth ratio influencing factor and the crack number influencing factor. The crack intensity index represents the quantitative data of the degree of influence of the crack area ratio, the crack depth ratio and the crack number on the crack area of ​​the fossil image to be identified after the illumination influence is reduced.

6. The online query method for a biological standard fossil database according to claim 1, characterized in that: The step of quantifying the similarity between the image of the fossil to be identified and the images of each biological standard fossil in the biological standard fossil database after the crack influence reduction treatment based on the edge contour correlation score coefficient, the texture correlation score coefficient and the high-dimensional feature correlation score coefficient to obtain the correlation score coefficient of each biological standard fossil image comprises: The edge contour correlation score coefficient, texture correlation score coefficient and high-dimensional feature correlation score coefficient of each biological standard fossil image are weighted and coupled using the similarity compensation value to obtain the correlation score coefficient of each biological standard fossil image. The similarity compensation value includes the edge contour similarity influencing factor, the texture similarity influencing factor and the high-dimensional feature similarity influencing factor. The correlation score coefficient of each biological standard fossil image represents the quantitative data of the influence of the edge contour correlation score coefficient, the texture correlation score coefficient and the high-dimensional feature correlation score coefficient on the similarity between the fossil to be identified and each biological standard fossil.

7. An online query system for a biological standard fossil database, used to execute the method according to any one of claims 1 to 6, characterized in that: It includes a light impact reduction processing module, a crack impact reduction processing module, an online query module and a fossil query database; The illumination effect reduction processing module is used to divide the fossil image to be identified into crack areas and non-crack areas, and perform illumination effect reduction processing on the fossil image to be identified based on the light condition data of the fossil image to be identified and the glossiness of the fossil to be identified. The illumination effect reduction processing is used to reduce the impact of illumination differences on the accuracy of feature extraction of the fossil image to be identified. The crack influence reduction processing module is used to perform crack influence reduction processing on the crack area of ​​the fossil image to be identified after the illumination influence reduction processing according to the crack intensity parameter of the fossil image to be identified after the illumination influence reduction processing, and the crack influence reduction processing is used to reduce the influence of crack differences on the similarity evaluation of the fossil image to be identified; The online query module is used to evaluate the similarity between the image of the fossil to be identified after the crack effect reduction processing and the images of each biological standard fossil in the biological standard fossil database, and classify the fossil to be identified into types according to the similarity evaluation results.

Images