Anesthesia cabinet application method based on fingerprint recognition and anesthesia cabinet

Abstract

The present invention belongs to the field of fingerprint recognition technology, and proposes an anesthesia cabinet application method and anesthesia cabinet based on fingerprint recognition, the method comprising the following steps: obtaining a fingerprint image through an optical fingerprint sensor; graying the fingerprint image to obtain a fingerprint grayscale image; obtaining a distance feature line according to the fingerprint grayscale image; obtaining a ridge-valley feature distance measurement value and a ridge-valley feature anomaly through the distance feature line, and storing the ridge-valley feature distance measurement value and the ridge-valley feature anomaly; when the anesthesia cabinet needs to be opened, obtaining the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified, and judging whether to open the anesthesia cabinet according to the stored ridge-valley feature distance measurement value and the ridge-valley feature anomaly. According to the recognition method of the embodiment of the present invention, even if there are factors that affect fingerprint imaging such as sweat, glove marks, and drug residues on the hands of medical staff, it is possible to accurately identify whether the fingerprint characteristics of the medical staff are consistent with the stored fingerprint characteristics.

Description

Technical Field

[0001] The invention belongs to the technical field of fingerprint recognition, and in particular relates to an anesthesia cabinet application method based on fingerprint recognition and an anesthesia cabinet. Background Art

[0002] At present, in medical environments, especially in operating rooms or emergency situations, the fingerprint images of medical staff are often degraded due to hand sweat, glove marks or drug residues, making them difficult to accurately identify. Traditional fingerprint recognition technology mainly relies on overall image matching or absolute matching of detail feature points (such as endpoints and bifurcation points). These methods require high clarity and consistency of fingerprint images, and even a slight deviation may lead to recognition failure. However, in medical scenarios, since the surface of the finger is often affected by various uncontrollable factors, traditional technologies are often unable to adapt to these changes, resulting in a significant reduction in the success rate of recognition, affecting the rapid and accurate identity verification of medical staff in emergency situations, and may delay critical medical operations. Therefore, the medical environment places higher requirements on fingerprint recognition, requiring stronger fault tolerance and robustness to cope with complex fingerprint changes and ensure efficient and reliable identity recognition in various situations. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the first object of the present invention is to propose an application method of an anesthesia cabinet based on fingerprint recognition, which can accurately identify whether the fingerprint characteristics of medical staff are consistent with the stored fingerprint characteristics in an operating room or in an emergency, even if there are factors that affect fingerprint imaging such as sweat, glove marks, and drug residues on the hands of medical staff;

[0004] The second object of the present invention is to provide an anesthesia cabinet.

[0005] To achieve the above object, a first embodiment of the present invention provides an anesthesia cabinet application method based on fingerprint recognition, the method comprising the following steps:

[0006] S100, obtains fingerprint images through optical fingerprint sensor;

[0007] S200, graying the fingerprint image to obtain a fingerprint grayscale image;

[0008] S300, obtaining a distance feature line according to the fingerprint grayscale image;

[0009] S400, obtaining a ridge-valley feature distance measurement value and a ridge-valley feature anomaly through a distance feature line, and storing the ridge-valley feature distance measurement value and the ridge-valley feature anomaly.

[0010] S500, when it is necessary to open the anesthesia cabinet, obtain the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified, and determine whether to open the anesthesia cabinet based on the stored ridge-valley feature distance measurement value and the ridge-valley feature anomaly.

[0011] According to the identification method of the embodiment of the present invention, accurate identification of fingerprints can be achieved.

[0012] Furthermore, in step S100, obtaining a fingerprint image through an optical fingerprint sensor includes: using an optical fingerprint sensor, the optical fingerprint sensor includes an optical scanning module and an image sensor; the optical sensor captures the fingerprint image by projecting light onto the fingerprint and detecting reflected light, the user places the finger on the sensor, and the sensor collects the image of the fingerprint through an optical method to generate an original fingerprint image.

[0013] In step S200, the process of graying the fingerprint image to obtain a fingerprint grayscale image includes:

[0014] The fingerprint image is grayed, and the grayed fingerprint image is referred to as the first gray image. The Canny edge detection algorithm is used to detect the edges in the image, highlight the ridges and valleys of the fingerprint, and identify and fill the connected areas in the gray image to determine the main feature areas of the fingerprint. The process of identifying and filling the connected areas in the gray image includes: scanning the image line by line, finding each connected area, and assigning a unique label to each connected area, wherein the connected area is usually an area with the same pixel value in the gray image. By filling all pixels in the connected area with a specific value (such as black or white), these areas are highlighted; wherein the area filling method includes: FloodFill algorithm, starting from an initial point, recursively filling adjacent pixels until the area boundary; after edge detection and area filling processing, a feature area set containing fingerprint ridges and valleys is obtained, and these fingerprint ridges and valleys The feature areas represent the key details in the fingerprint image and are helpful for subsequent fingerprint analysis and matching.

[0015] In a medical environment, especially in an operating room or in an emergency, medical staff may have sweat, glove marks, drug residues, etc. on their hands, which may make it difficult to accurately identify their fingerprints. Traditional fingerprint recognition usually relies on overall image matching or absolute matching of simple detail feature points (such as endpoints and bifurcation points). This absolute matching will greatly reduce the success rate of medical staff identification in a medical environment and make it impossible to obtain correct fingerprint recognition. In order to solve the above problems, the embodiments of the present invention propose the following steps.

[0016] In step S300, a distance characteristic line is obtained according to the fingerprint grayscale image;

[0017] S301, zj(j) is used to represent the grayscale value of the grid in the feature area of ​​the j-th fingerprint ridge, and the value range of j is [1, K], where K is the number of grids in the feature area of ​​the fingerprint ridge; zg(g) represents the grayscale value of the grid in the feature area of ​​the g-th fingerprint valley, and the value range of g is [1, H], where H is the number of grids in the feature area of ​​the fingerprint valley, and the grayscale value of the grid is the average grayscale value of all pixels in the grid; the grid in the feature area of ​​the fingerprint ridge with the largest grayscale value is recorded as zjxu, and the grayscale value of zjxu is recorded as zjxp; the grid in the feature area of ​​the fingerprint valley with the largest grayscale value is recorded as zgxu, and the grayscale value of zgxu is recorded as zgxp;

[0018] S302, define an integer variable k, set its initial value to 1, and create two variables HDzh1 and HDzh2, which are initially zero, for subsequent calculation and comparison.

[0019] S303, performing grayscale feature analysis on the grayscale values ​​of the grids in the characteristic area of ​​the fingerprint ridges and the grids in the characteristic area of ​​the fingerprint valleys, and creating two blank sequences HDa and HDb.

[0020] S304, calculate the values ​​of HDzh1 and HDzh2, where: the calculation formula of HDzh1 is zjxp−zj(k), and the calculation formula of HDzh2 is zgxp−zg(k); compare the values ​​of HDzh1 and HDzh2: if HDzh1 is greater than HDzh2, add the grid number where zj(j) is located to the sequence HDa. If HDzh1 is less than or equal to HDzh2, add the grid number where zg(g) is located to the sequence HDb.

[0021] S305, determine whether the grayscale feature analysis is completed; if the current variable k is less than K or less than H, increase k by 1 and return to step S303 to continue the grayscale feature analysis; if the current variable k is not less than K or not less than H, it means that the grayscale feature analysis has been processed.

[0022] S306, obtaining the grayscale value of the grid corresponding to the grid number in the sequence HDa as the median of the grayscale values ​​of all grid numbers in the sequence HDa, and recording the grid as zjx; obtaining the grayscale value of the grid corresponding to the grid number in the sequence HDb as the median of the grayscale values ​​of all grid numbers in the sequence HDb, and recording the grid as zgx;

[0023] The beneficial effects of this step are as follows: since sweat will form a thin film on the skin surface, the shape of the finger will expand when pressed, causing the ridges and valleys in the fingerprint image to expand or shrink and become blurred, and since water has a high reflectivity, it will reflect more light back to the camera or sensor compared to dry skin, so the grayscale values ​​of these areas are much higher than the actual grayscale values. When the finger is wet, the water covers the surface of the finger, changing the optical properties of the fingerprint. The water part will reflect more light, thus appearing as a brighter area in the grayscale image, and the grayscale value of the wet part will become larger; By screening out the HDa sequence and the HDb sequence, the grid numbers that are not related to the maximum grayscale value grid in the fingerprint ridge feature area and the fingerprint valley feature area can be obtained. These grids represent the obvious texture in the fingerprint image and the area that is not blurred by sweat, and can identify the fingerprint well. Through such a cycle process and grayscale analysis, the system can avoid the abnormal increase of the grayscale value of the fingerprint image grid caused by factors such as sweat, and effectively extract and screen out the fingerprint area that is not affected by interference factors and has stability and importance, thereby improving the reliability and accuracy of the fingerprint recognition system in the medical environment.

[0024] S307, obtaining the distance between the grids of the characteristic regions of all fingerprint ridges, wherein the distance between the grids is the length of the line segment connecting the center points of the grids, and recording the shortest distance between the grid of the characteristic region of one fingerprint ridge and the grids of the characteristic regions of all other fingerprint ridges as the shortest neighbor distance; zjk(j) is used to represent the shortest neighbor distance of the grid of the characteristic region of the jth fingerprint ridge; calculating the difference between the shortest neighbor distances of each grid and the adjacent grid, obtaining the grid with the largest shortest neighbor distance difference, recording the grid with the largest shortest neighbor distance difference as the distance grid zjt, and recording the grid of the characteristic region of the fingerprint ridge that is the shortest distance from the distance grid zjt as the distance grid zjp;

[0025] Specifically, ridges and valleys are the main structural features in fingerprints, and their grayscale values ​​can reflect the local details and texture changes of fingerprints. By comparing the grayscale values ​​of different grids, the ridge feature areas and valley feature areas with the largest grayscale values ​​are found. These areas are the key feature points in the fingerprint and are the basis for analyzing fingerprints.

[0026] Furthermore, the shortest neighbor distance can reflect the density and relative position of the ridges and is used to understand the overall structure of the fingerprint.

[0027] S308, obtaining distance characteristic lines, wherein the distance characteristic lines include a first distance characteristic line, a second distance characteristic line and a third distance characteristic line. Specifically, the midpoint P3 of the line segment between the center point of zgx and the center point of zjx is recorded; the center point of the distance special grid zjt is recorded as P4, the center point of the grid of the distance special neighboring grid zjp is recorded as P5, and the midpoint of the line segment between points P4 and P5 is recorded as P6; the line segment between points P3 and P6 is recorded as the first distance characteristic line L1, the line segment between P3 and P4 is recorded as the second distance characteristic line L2, and the line segment between P3 and P5 is recorded as the third distance characteristic line L3;

[0028] Among them, the distance feature lines L1, L2 and L3 respectively describe different geometric relationships in the fingerprint; the first distance feature line L1 provides the relative position relationship between the ridge lines and the valley lines, the second feature line L2 and the third distance feature line L3 describe the distance between the important structural features and other feature points in the fingerprint. These distance feature lines are used for fingerprint matching and identity authentication in subsequent steps. By comparing the lengths and relative positions of these feature lines, the similarities and differences between different fingerprints can be compared to enhance the accuracy of fingerprint recognition.

[0029] The beneficial effect of this step is: by calculating and analyzing the key geometric features in the fingerprint grayscale image, the distance feature lines of the ridges and valleys are extracted. These feature lines describe the details and structure of the fingerprint, providing an important basis for the accurate matching and identity authentication of the fingerprint. This process enhances the robustness and accuracy of the fingerprint recognition system, which helps to achieve efficient identity authentication.

[0030] S400, obtaining a ridge-valley characteristic distance measurement value and a ridge-valley characteristic anomaly through the distance characteristic line, and storing the ridge-valley characteristic distance measurement value and the ridge-valley characteristic anomaly;

[0031] The length of L1 is obtained and recorded as the ridge-valley characteristic distance measurement value lg; the length of L2 is recorded as the first characteristic length lka, and the length of L3 is recorded as the second characteristic length lkb; the ridge-valley characteristic anomaly ld is calculated, where ld=abs(lka-lkb), where abs is the absolute value function, that is, the ridge-valley characteristic anomaly ld is the absolute value of the direct difference between the first characteristic length lka and the second characteristic length lkb;

[0032] Specifically, by calculating the length of the distance feature line, the geometric features of the fingerprint can be accurately quantified. The ridge-valley feature distance measurement value lg, the first feature length lka, and the second feature length lkb provide the specific spatial relationship between the ridges and valleys in the fingerprint. Among them, the ridge-valley feature anomaly ld is the absolute difference between the first feature length lka and the second feature length lkb. This difference can help capture the subtle structural differences in the fingerprint, allowing the system to identify very detailed fingerprint features.

[0033] Furthermore, by calculating the ridge-valley feature deviation ld, a certain range of variation can be allowed during the fingerprint recognition process. Since actual fingerprints may vary slightly under different conditions (such as finger position, pressure, etc.), by calculating the ridge-valley feature deviation the system can still accurately recognize within these variation ranges.

[0034] Furthermore, the ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly ld are stored.

[0035] S500, when it is necessary to open the anesthesia cabinet, obtain the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified, and determine whether to open the anesthesia cabinet according to the stored ridge-valley feature distance measurement value and the ridge-valley feature anomaly;

[0036] Among them, the user to be identified is the user who needs to open the anesthesia cabinet;

[0037] When the ridge-valley feature distance measurement value of the user to be identified is equal to the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly and the ridge-valley feature anomaly ld of the user to be identified are equal, the anesthesia cabinet is opened and the recognition success is displayed; if the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified do not satisfy the ridge-valley feature distance measurement value of the user to be identified and the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly and the ridge-valley feature anomaly ld of the user to be identified are equal, the anesthesia cabinet is not opened and the recognition failure is displayed.

[0038] Due to factors that affect fingerprint imaging, such as sweat, glove marks, and drug residues on the hands of medical staff, there will be certain errors in the ridge-valley feature anomaly and the ridge-valley feature anomaly obtained in a medical environment. In order to avoid this error, it is necessary to further calculate the misalignment interval difference to avoid recognition failure due to slight deviations.

[0039] Among them, the misalignment interval difference is a fault-tolerant mechanism for handling small changes in fingerprint recognition. It allows a certain range of distance deviation. In actual applications, the ridges and valleys of the fingerprint may change slightly due to the angle, pressure or environmental factors of the finger, or there may be sweat, glove marks, drug residues and other factors on the hands of medical staff in a medical environment that affect fingerprint imaging. The misalignment interval difference allows the fingerprint characteristics to change within a certain range, which can improve the system's tolerance to these changes and enhance the robustness and accuracy of the fingerprint recognition system.

[0040] Preferably, when the ridge-valley feature distance measurement value of the user to be identified is equal to the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly and the ridge-valley feature anomaly ld of the user to be identified are equal, the anesthesia cabinet is opened and the recognition success is displayed; if the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified do not satisfy the ridge-valley feature distance measurement value of the user to be identified and the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly and the ridge-valley feature anomaly ld of the user to be identified are equal, the absolute value of the difference between the ridge-valley feature distance measurement value of the user to be identified and the ridge-valley feature distance measurement value lg is calculated and recorded as the misalignment interval difference; if the misalignment interval difference is less than the ridge-valley feature anomaly ld, the anesthesia cabinet is opened and the recognition success is displayed; if the misalignment interval difference is not less than the ridge-valley feature anomaly ld, the anesthesia cabinet is not opened and the recognition failure is displayed.

[0041] When the user's ridge-valley feature distance measurement value and the ridge-valley feature anomaly ld do not completely match, the misalignment interval difference can be calculated to further determine whether the anesthesia cabinet is allowed to be opened. This mechanism improves the system's fault tolerance and avoids recognition failures due to minor deviations.

[0042] Beneficial effects of this step: the method of the present invention does not rely on absolute matching, and by introducing the concept of misalignment interval difference, a certain deviation is allowed during identification. As long as this deviation is within the set fault tolerance range, it can still be regarded as a successful match; this fault tolerance mechanism is particularly suitable for slight identification deviations that may be caused by changes in angle, pressure or surface state of fingers, which improves the success rate of identification. In the operating room or in an emergency, even if there are sweat, glove marks, drug residues and other factors that affect fingerprint imaging on the hands of medical staff, it can accurately identify whether the fingerprint characteristics of medical staff are consistent with the stored fingerprint characteristics.

[0043] To achieve the above-mentioned purpose, the second aspect of the present invention further proposes an anesthesia cabinet, characterized in that the anesthesia cabinet is opened by identifying through an anesthesia cabinet application method based on fingerprint recognition; the anesthesia cabinet can be used in an operating room or in an emergency situation, even if the medical staff have sweat, glove marks, drug residues and other factors that affect fingerprint imaging on their hands, and it can accurately identify whether the fingerprint characteristics of the medical staff are consistent with the stored fingerprint characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 Shown is a flow chart of an anesthesia cabinet application method based on fingerprint recognition. DETAILED DESCRIPTION

[0045] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0046] Figure 1 Shown is a flow chart of an anesthesia cabinet application method based on fingerprint recognition.

[0047] Reference Figure 1 The present invention proposes an anesthesia cabinet application method based on fingerprint recognition, the method comprising the following steps:

[0048] S100, obtains fingerprint images through optical fingerprint sensor;

[0049] S200, graying the fingerprint image to obtain a fingerprint grayscale image;

[0050] S300, obtaining a distance feature line according to the fingerprint grayscale image;

[0051] S400, obtaining a ridge-valley feature distance measurement value and a ridge-valley feature anomaly through a distance feature line, and storing the ridge-valley feature distance measurement value and the ridge-valley feature anomaly.

[0052] S500, when it is necessary to open the anesthesia cabinet, obtain the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified, and determine whether to open the anesthesia cabinet based on the stored ridge-valley feature distance measurement value and the ridge-valley feature anomaly.

[0053] According to the identification method of the embodiment of the present invention, accurate identification of fingerprints can be achieved.

[0054] Furthermore, in step S100, obtaining a fingerprint image through an optical fingerprint sensor includes: using an optical fingerprint sensor, the optical fingerprint sensor includes an optical scanning module and an image sensor; the optical sensor captures the fingerprint image by projecting light onto the fingerprint and detecting reflected light, the user places the finger on the sensor, and the sensor collects the image of the fingerprint through an optical method to generate an original fingerprint image.

[0055] In step S200, the process of graying the fingerprint image to obtain a fingerprint grayscale image includes:

[0056] The fingerprint image is subdivided 8 to 32 times. After the subdivision process, the fingerprint image is divided into G sub-regions, kj(i) represents the i-th sub-region, the value range of i is [1, G], and G is the number of sub-regions.

[0057] The fingerprint image is grayed, and the grayed fingerprint image is referred to as the first gray image. The Canny edge detection algorithm is used to detect the edges in the image, highlight the ridges and valleys of the fingerprint, and identify and fill the connected areas in the gray image to determine the main feature areas of the fingerprint. The process of identifying and filling the connected areas in the gray image includes: scanning the image line by line, finding each connected area, and assigning a unique label to each connected area, wherein the connected area is usually an area with the same pixel value in the gray image. These areas are highlighted by filling all pixels in the connected area with a specific value (such as black or white); wherein the area filling method includes: FloodFill algorithm, starting from an initial point, recursively filling adjacent pixels until the area boundary. After edge detection and area filling processing, a set of feature areas containing fingerprint ridges and valleys is obtained. These feature areas of fingerprint ridges and valleys represent key details in the fingerprint image, which are helpful for subsequent fingerprint analysis and matching.

[0058] In a medical environment, especially in an operating room or in an emergency, medical staff may have sweat, glove marks, drug residues, etc. on their hands, which may make it difficult to accurately identify their fingerprints. Traditional fingerprint recognition usually relies on overall image matching or absolute matching of simple detail feature points (such as endpoints and bifurcation points). This absolute matching will greatly reduce the success rate of medical staff identification in a medical environment and make it impossible to obtain correct fingerprint recognition. In order to solve the above problems, the embodiments of the present invention propose the following steps.

[0059] In step S300, a distance characteristic line is obtained according to the fingerprint grayscale image;

[0060] S301, zj(j) is used to represent the grayscale value of the grid in the feature area of ​​the j-th fingerprint ridge, and the value range of j is [1, K], where K is the number of grids in the feature area of ​​the fingerprint ridge; zg(g) represents the grayscale value of the grid in the feature area of ​​the g-th fingerprint valley, and the value range of g is [1, H], where H is the number of grids in the feature area of ​​the fingerprint valley, and the grayscale value of the grid is the average grayscale value of all pixels in the grid; the grid in the feature area of ​​the fingerprint ridge with the largest grayscale value is recorded as zjxu, and the grayscale value of zjxu is recorded as zjxp; the grid in the feature area of ​​the fingerprint valley with the largest grayscale value is recorded as zgxu, and the grayscale value of zgxu is recorded as zgxp;

[0061] S302, define an integer variable k, set its initial value to 1, and create two variables HDzh1 and HDzh2, which are initially zero, for subsequent calculation and comparison.

[0062] S303, performing grayscale feature analysis on the grayscale values ​​of the grids in the characteristic area of ​​the fingerprint ridges and the grids in the characteristic area of ​​the fingerprint valleys, and creating two blank sequences HDa and HDb.

[0063] S304, calculate the values ​​of HDzh1 and HDzh2, where: the calculation formula of HDzh1 is zjxp−zj(k), and the calculation formula of HDzh2 is zgxp−zg(k); compare the values ​​of HDzh1 and HDzh2: if HDzh1 is greater than HDzh2, add the grid number where zj(j) is located to the sequence HDa. If HDzh1 is less than or equal to HDzh2, add the grid number where zg(g) is located to the sequence HDb.

[0064] S305, determine whether the grayscale feature analysis is completed; if the current variable k is less than K or less than H, increase k by 1 and return to step S303 to continue the grayscale feature analysis; if the current variable k is not less than K or not less than H, it means that the grayscale feature analysis has been processed.

[0065] S306, obtaining the grayscale value of the grid corresponding to the grid number in the sequence HDa as the median of the grayscale values ​​of all grid numbers in the sequence HDa, and recording the grid as zjx; obtaining the grayscale value of the grid corresponding to the grid number in the sequence HDb as the median of the grayscale values ​​of all grid numbers in the sequence HDb, and recording the grid as zgx;

[0066] The beneficial effects of this step are as follows: since sweat will form a thin film on the skin surface, the shape of the finger will expand when pressed, causing the ridges and valleys in the fingerprint image to expand or shrink and become blurred, and since water has a high reflectivity, it will reflect more light back to the camera or sensor compared to dry skin, so the grayscale values ​​of these areas are much higher than the actual grayscale values. When the finger is wet, the water covers the surface of the finger, changing the optical properties of the fingerprint. The water part will reflect more light, thus appearing as a brighter area in the grayscale image, and the grayscale value of the wet part will become larger; By screening out the HDa sequence and the HDb sequence, the grid numbers that are not related to the maximum grayscale value grid in the fingerprint ridge feature area and the fingerprint valley feature area can be obtained. These grids represent the obvious texture in the fingerprint image and the area that is not blurred by sweat, and can identify the fingerprint well. Through such a cycle process and grayscale analysis, the system can avoid the abnormal increase of the grayscale value of the fingerprint image grid caused by factors such as sweat, and effectively extract and screen out the fingerprint area that is not affected by interference factors and has stability and importance, thereby improving the reliability and accuracy of the fingerprint recognition system in the medical environment.

[0067] S307, obtaining the distance between the grids of the characteristic regions of all fingerprint ridges, wherein the distance between the grids is the length of the line segment connecting the center points of the grids, and recording the shortest distance between the grid of the characteristic region of one fingerprint ridge and the grids of the characteristic regions of all other fingerprint ridges as the shortest neighbor distance; zjk(j) is used to represent the shortest neighbor distance of the grid of the characteristic region of the jth fingerprint ridge; calculating the difference between the shortest neighbor distances of each grid and the adjacent grid, obtaining the grid with the largest shortest neighbor distance difference, recording the grid with the largest shortest neighbor distance difference as the distance grid zjt, and recording the grid of the characteristic region of the fingerprint ridge that is the shortest distance from the distance grid zjt as the distance grid zjp;

[0068] Specifically, ridges and valleys are the main structural features in fingerprints, and their grayscale values ​​can reflect the local details and texture changes of fingerprints. By comparing the grayscale values ​​of different grids, the ridge feature areas and valley feature areas with the largest grayscale values ​​are found. These areas are the key feature points in the fingerprint and are the basis for analyzing fingerprints.

[0069] Furthermore, the shortest neighbor distance can reflect the density and relative position of the ridges and is used to understand the overall structure of the fingerprint.

[0070] S308, obtain distance characteristic lines, wherein the distance characteristic lines include a first distance characteristic line, a second distance characteristic line and a third distance characteristic line. Specifically, record the midpoint P3 of the line segment between the center point of zgx and the center point of zjx; record the center point of the distance special grid zjt as P4, record the grid center point of the distance special neighboring grid zjp as P5, and record the midpoint of the line segment between points P4 and P5 as P6; record the line segment between points P3 and P6 as the first distance characteristic line L1, the line segment between P3 and P4 as the second distance characteristic line L2, and the line segment between P3 and P5 as the third distance characteristic line L3.

[0071] S400, obtaining a ridge-valley characteristic distance measurement value and a ridge-valley characteristic anomaly through the distance characteristic line, and storing the ridge-valley characteristic distance measurement value and the ridge-valley characteristic anomaly;

[0072] The length of L1 is obtained and recorded as the ridge-valley characteristic distance measurement value lg; the length of L2 is recorded as the first characteristic length lka, and the length of L3 is recorded as the second characteristic length lkb; the ridge-valley characteristic anomaly ld is calculated, where ld=abs(lka-lkb), where abs is the absolute value function, that is, the ridge-valley characteristic anomaly ld is the absolute value of the direct difference between the first characteristic length lka and the second characteristic length lkb;

[0073] Specifically, by calculating the length of the distance feature line, the geometric features of the fingerprint can be accurately quantified. The ridge-valley feature distance measurement value lg, the first feature length lka, and the second feature length lkb provide the specific spatial relationship between the ridges and valleys in the fingerprint. Among them, the ridge-valley feature anomaly ld is the absolute difference between the first feature length lka and the second feature length lkb. This difference can help capture the subtle structural differences in the fingerprint, allowing the system to identify very detailed fingerprint features.

[0074] Furthermore, by calculating the ridge-valley feature deviation ld, a certain range of variation can be allowed during the fingerprint recognition process. Since actual fingerprints may vary slightly under different conditions (such as finger position, pressure, etc.), by calculating the ridge-valley feature deviation the system can still accurately recognize within these variation ranges.

[0075] Furthermore, the ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly ld are stored.

[0076] S500, when it is necessary to open the anesthesia cabinet, obtain the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified, and determine whether to open the anesthesia cabinet according to the stored ridge-valley feature distance measurement value and the ridge-valley feature anomaly;

[0077] Among them, the user to be identified is the user who needs to open the anesthesia cabinet;

[0078] When the ridge-valley feature distance measurement value of the user to be identified is equal to the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly and the ridge-valley feature anomaly ld of the user to be identified are equal, the anesthesia cabinet is opened and the recognition success is displayed; if the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified do not satisfy the ridge-valley feature distance measurement value of the user to be identified and the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly and the ridge-valley feature anomaly ld of the user to be identified are equal, the anesthesia cabinet is not opened and the recognition failure is displayed.

[0079] Due to factors that affect fingerprint imaging, such as sweat, glove marks, and drug residues on the hands of medical staff, there will be certain errors in the ridge-valley feature anomaly and the ridge-valley feature anomaly obtained in a medical environment. In order to avoid this error, it is necessary to further calculate the misalignment interval difference to avoid recognition failure due to slight deviations.

[0080] Among them, the misalignment interval difference is a fault-tolerant mechanism for handling small changes in fingerprint recognition. It allows a certain range of distance deviation. In actual applications, the ridges and valleys of the fingerprint may change slightly due to the angle, pressure or environmental factors of the finger, or there may be sweat, glove marks, drug residues and other factors on the hands of medical staff in a medical environment that affect fingerprint imaging. The misalignment interval difference allows the fingerprint characteristics to change within a certain range, which can improve the system's tolerance to these changes and enhance the robustness and accuracy of the fingerprint recognition system.

[0081] Preferably, when the ridge-valley feature distance measurement value of the user to be identified is equal to the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly and the ridge-valley feature anomaly ld of the user to be identified are equal, the anesthesia cabinet is opened and the recognition success is displayed; if the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified do not satisfy the ridge-valley feature distance measurement value of the user to be identified and the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly and the ridge-valley feature anomaly ld of the user to be identified are equal, the absolute value of the difference between the ridge-valley feature distance measurement value of the user to be identified and the ridge-valley feature distance measurement value lg is calculated and recorded as the misalignment interval difference; if the misalignment interval difference is less than the ridge-valley feature anomaly ld, the anesthesia cabinet is opened and the recognition success is displayed; if the misalignment interval difference is not less than the ridge-valley feature anomaly ld, the anesthesia cabinet is not opened and the recognition failure is displayed.

[0082] When the user's ridge-valley feature distance measurement value and the ridge-valley feature anomaly ld do not completely match, the misalignment interval difference can be calculated to further determine whether the anesthesia cabinet is allowed to be opened. This mechanism improves the system's fault tolerance and avoids recognition failures due to minor deviations.

[0083] Beneficial effects of this step: the method of the present invention does not rely on absolute matching, and by introducing the concept of misalignment interval difference, a certain deviation is allowed during identification. As long as this deviation is within the set fault tolerance range, it can still be regarded as a successful match; this fault tolerance mechanism is particularly suitable for slight identification deviations that may be caused by changes in angle, pressure or surface state of fingers, which improves the success rate of identification. In the operating room or in an emergency, even if there are sweat, glove marks, drug residues and other factors that affect fingerprint imaging on the hands of medical staff, it can accurately identify whether the fingerprint characteristics of medical staff are consistent with the stored fingerprint characteristics.

[0084] The present invention also proposes an anesthesia cabinet, characterized in that the anesthesia cabinet is opened by identifying through an anesthesia cabinet application method based on fingerprint recognition; the anesthesia cabinet can accurately identify whether the fingerprint characteristics of medical staff are consistent with the stored fingerprint characteristics in an operating room or in an emergency situation, even if there are sweat, glove marks, drug residues and other factors that affect fingerprint imaging on the hands of medical staff.

[0085] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0086] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0087] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0088] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0089] In addition, the terms "first", "second", etc. used in the embodiments of the present invention are only used for descriptive purposes and should not be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in the present embodiment. Therefore, the features defined by the terms "first", "second", etc. in the embodiments of the present invention can explicitly or implicitly indicate that the embodiment includes at least one of the features. In the description of the present invention, the word "multiple" means at least two or two or more, such as two, three, four, etc., unless otherwise clearly and specifically defined in the embodiments.

[0090] In the present invention, unless otherwise clearly specified or limited in the embodiments, the terms "installed", "connected", "connected" and "fixed" etc. in the embodiments should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integrated connection. It can be understood that it can also be a mechanical connection, an electrical connection, etc.; of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements, or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific implementation situation.

[0091] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0092] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An application method of an anesthesia cabinet based on fingerprint recognition, characterized in that: The method comprises the following steps: S100, obtains fingerprint images through optical fingerprint sensor; S200, graying the fingerprint image to obtain a fingerprint grayscale image; S300, obtaining a distance feature line according to the fingerprint grayscale image, wherein S300 includes: S301, using zj(j) to represent the grayscale value of the grid of the feature area of ​​the j-th fingerprint ridge, the value range of j is [1, K], wherein K is the number of grids in the feature area of ​​the fingerprint ridge; zg(g) represents the grayscale value of the grid of the feature area of ​​the g-th fingerprint valley, the value range of g is [1, H], wherein H is the number of grids in the feature area of ​​the fingerprint valley, wherein the grayscale value of the grid is the average value of the grayscale values ​​of all pixels in the grid; the grid of the feature area of ​​the fingerprint ridge with the largest grayscale value is recorded as zjxu, the grayscale value of zjxu is recorded as zjxp, the grid of the feature area of ​​the fingerprint valley with the largest grayscale value is recorded as zgxu, the grayscale value of zgxu is recorded as zgxp; S302, define an integer variable k, set its initial value to 1, and create two variables HDzh1 and HDzh2, which are initially zero, for subsequent calculation and comparison; S303, performing grayscale feature analysis on the grayscale values ​​of the grids in the characteristic area of ​​the fingerprint ridges and the grids in the characteristic area of ​​the fingerprint valleys, and creating two blank sequences HDa and HDb; S304, calculate the values ​​of HDzh1 and HDzh2, where: the calculation formula of HDzh1 is zjxp−zj(k), and the calculation formula of HDzh2 is zgxp−zg(k); compare the values ​​of HDzh1 and HDzh2: if HDzh1 is greater than HDzh2, add the grid number where zj(j) is located to the sequence HDa; if HDzh1 is less than or equal to HDzh2, add the grid number where zg(g) is located to the sequence HDb; S305, judging whether the grayscale feature analysis is completed; if the current variable k is less than K or less than H, k is increased by 1, and the process returns to step S303 to continue the grayscale feature analysis; if the current variable k is not less than K or not less than H, it indicates that the grayscale feature analysis has been completed; S306, obtaining the grayscale value of the grid corresponding to the grid number in the sequence HDa as the median of the grayscale values ​​of all grid numbers in the sequence HDa, and recording the grid as zjx; obtaining the grayscale value of the grid corresponding to the grid number in the sequence HDb as the median of the grayscale values ​​of all grid numbers in the sequence HDb, and recording the grid as zgx; S307, obtaining the distance between the grids of the characteristic regions of all fingerprint ridges, wherein the distance between the grids is the length of the line segment connecting the center points of the grids, and recording the shortest distance between the grid of the characteristic region of one fingerprint ridge and the grids of the characteristic regions of all other fingerprint ridges as the shortest neighbor distance; zjk(j) is used to represent the shortest neighbor distance of the grid of the characteristic region of the jth fingerprint ridge; calculating the difference between the shortest neighbor distances of each grid and the adjacent grid, obtaining the grid with the largest shortest neighbor distance difference, recording the grid with the largest shortest neighbor distance difference as the distance grid zjt, and recording the grid of the characteristic region of the fingerprint ridge that is the shortest distance from the distance grid zjt as the distance grid zjp; S308, obtaining distance characteristic lines, wherein the distance characteristic lines include a first distance characteristic line, a second distance characteristic line and a third distance characteristic line. Specifically, the midpoint P3 of the line segment between zgx and zjx is recorded; the center point of the distance special grid zjt is recorded as P4, the center point of the grid of the distance special neighboring grid zjp is recorded as P5, and the midpoint of the line segment between points P4 and P5 is recorded as P6; the line segment between points P3 and P6 is recorded as the first distance characteristic line L1, the line segment between P3 and P4 is recorded as the second distance characteristic line L2, and the line segment between P3 and P5 is recorded as the third distance characteristic line L3; S400, obtaining the ridge-valley characteristic distance measurement value and the ridge-valley characteristic anomaly through the distance characteristic line, and storing the ridge-valley characteristic distance measurement value and the ridge-valley characteristic anomaly; wherein S400 includes: obtaining the length of the first distance characteristic line as the ridge-valley characteristic distance measurement value lg; the length of the second distance characteristic line as the first characteristic length lka, and the length of the third distance characteristic line as the second characteristic length lkb; calculating the ridge-valley characteristic anomaly ld, the ridge-valley characteristic anomaly ld is the absolute value of the direct difference between the first characteristic length lka and the second characteristic length lkb; S500, when it is necessary to open the anesthesia cabinet, obtain the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified, and determine whether to open the anesthesia cabinet based on the stored ridge-valley feature distance measurement value and the ridge-valley feature anomaly.

2. The anesthesia cabinet application method based on fingerprint recognition according to claim 1 is characterized in that: In step S100, obtaining a fingerprint image through an optical fingerprint sensor includes: using an optical fingerprint sensor, the optical fingerprint sensor includes an optical scanning module and an image sensor; the optical sensor captures the fingerprint image by projecting light onto the fingerprint and detecting reflected light, the user places the finger on the sensor, and the sensor collects the image of the fingerprint through an optical method to generate an original fingerprint image.

3. The anesthesia cabinet application method based on fingerprint recognition according to claim 1 is characterized in that: In step S200, the process of graying the fingerprint image to obtain a fingerprint grayscale image includes: The fingerprint image is grayed, and the grayed fingerprint image is referred to as the first gray image. The Canny edge detection algorithm is used to detect the edges in the image, highlight the ridges and valleys of the fingerprint, and identify and fill the connected areas in the gray image to determine the main feature areas of the fingerprint. The process of identifying and filling the connected areas in the gray image includes: scanning the image line by line, finding each connected area, and assigning a unique label to each connected area, wherein the connected area is usually an area with the same pixel value in the gray image; by filling all pixels in the connected area with a specific value, these areas are highlighted; wherein the area filling method includes: the FloodFill algorithm, starting from an initial point, recursively filling adjacent pixels until the area boundary; after edge detection and area filling processing, a set of feature areas including fingerprint ridges and valleys is obtained, and these feature areas of fingerprint ridges and valleys represent key details in the fingerprint image, which are helpful for subsequent fingerprint analysis and matching.

4. The fingerprint recognition-based anesthesia cabinet application method according to claim 1, characterized in that: In step S500, when the anesthesia cabinet needs to be opened, the ridge-valley feature distance measurement value and the ridge-valley feature anomaly value of the user to be identified are obtained, and the method for determining whether to open the anesthesia cabinet is based on the stored ridge-valley feature distance measurement value and the ridge-valley feature anomaly value. include: Among them, the user to be identified is the user who needs to open the anesthesia cabinet; When the ridge-valley feature distance measurement value of the user to be identified is equal to the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly and the ridge-valley feature anomaly ld of the user to be identified are equal, the anesthesia cabinet is opened and the recognition success is displayed; if the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified do not satisfy the ridge-valley feature distance measurement value of the user to be identified and the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly and the ridge-valley feature anomaly ld of the user to be identified are equal, the anesthesia cabinet is not opened and the recognition failure is displayed.

5. The anesthesia cabinet application method based on fingerprint recognition according to claim 1 is characterized in that: In step S500, when it is necessary to open the anesthesia cabinet, the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified are obtained, and the method for judging whether to open the anesthesia cabinet based on the stored ridge-valley feature distance measurement value and the ridge-valley feature anomaly also includes: when the ridge-valley feature distance measurement value of the user to be identified is equal to the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly of the user to be identified and the ridge-valley feature anomaly ld are equal, the anesthesia cabinet is opened and the recognition is successful; if the ridge-valley feature distance measurement value and the ridge-valley feature anomaly of the user to be identified are equal, When the feature anomaly does not satisfy that the ridge-valley feature distance measurement value of the user to be identified is equal to the stored ridge-valley feature distance measurement value lg and the ridge-valley feature anomaly value of the user to be identified and the ridge-valley feature anomaly value ld are equal, the absolute value of the difference between the ridge-valley feature distance measurement value of the user to be identified and the ridge-valley feature distance measurement value lg is calculated and recorded as the misalignment interval difference. If the misalignment interval difference is less than the ridge-valley feature anomaly value ld, the anesthesia cabinet is opened and the recognition is successful; if the misalignment interval difference is not less than the ridge-valley feature anomaly value ld, the anesthesia cabinet is not opened and the recognition failure is displayed.

Images