Intravenous injection processing method based on image recognition and related device

Abstract

The invention discloses an intravenous injection processing method based on image recognition and a related device. The method comprises the steps that a first size parameter of a needle of a to-be-injected injection tool is determined; acquiring a first image of a target part of the target object through a vein recognition module; performing vein line extraction on the first image to obtain a vein line graph; dividing the vein line graph into a plurality of sections to obtain a plurality of sections of vein line areas; determining the average width of each vein line area in the plurality of sections of vein line areas to obtain a plurality of average widths; determining the position of each vein line area in the plurality of sections of vein line areas to obtain a plurality of positions; evaluating each vein line region in the plurality of sections of vein line regions according to the plurality of average widths and the plurality of positions to obtain a plurality of score values; and selecting a maximum value in the plurality of score values, and determining a target vein line area corresponding to the maximum value. By adopting the embodiment of the invention, medical personnel can be quickly helped to find the intravenous injection position.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to an intravenous injection processing method and related devices based on image recognition. Background Art

[0002] With the rapid development of science and technology, electronic products are gradually changing people's lives. Electronic products can not only bring people joy, but also improve their work efficiency. Currently, in medical application scenarios, the inability to quickly find the intravenous injection site often reduces the work efficiency of medical staff. Therefore, how to quickly help medical staff find the intravenous injection site and assist them in completing the rapid injection problem needs to be solved. Summary of the Invention

[0003] The embodiments of the present application provide an intravenous injection processing method and related devices based on image recognition, which can quickly help medical personnel find the intravenous injection location to assist medical personnel in completing rapid injection.

[0004] In a first aspect, an embodiment of the present application provides an image recognition-based intravenous injection processing method, which is applied to a medical electronic device, wherein the medical electronic device includes a vein recognition module; the method includes:

[0005] determining a first size parameter of a needle of an injection device to be injected;

[0006] Acquiring a first image of a target part of a target object by the vein recognition module;

[0007] Extracting vein patterns from the first image to obtain a vein pattern map;

[0008] Dividing the venous pattern map into multiple segments to obtain multiple venous pattern regions; the length of each venous pattern region is greater than a first threshold, and the first threshold corresponds to the first size parameter;

[0009] determining an average width of each of the plurality of vein pattern regions to obtain a plurality of average widths;

[0010] determining a position of each of the plurality of vein pattern regions to obtain a plurality of positions;

[0011] Evaluate each of the plurality of vein pattern areas according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values;

[0012] A maximum value among the multiple scoring values is selected, a target vein pattern area corresponding to the maximum value is determined, and the target vein pattern area is marked.

[0013] In a second aspect, an embodiment of the present application provides an intravenous injection processing device based on image recognition, which is applied to a medical electronic device, wherein the medical electronic device includes a vein recognition module; the device includes: a determination unit, an acquisition unit, an extraction unit, a division unit, and an evaluation unit, wherein:

[0014] The determining unit is configured to determine a first size parameter of a needle of an injection device to be injected;

[0015] The acquisition unit is configured to acquire a first image of a target part of a target object through the vein recognition module;

[0016] The extraction unit is configured to extract vein patterns from the first image to obtain a vein pattern map;

[0017] The dividing unit is configured to divide the venous pattern map into multiple segments to obtain multiple venous pattern regions; the length of each venous pattern region is greater than a first threshold, and the first threshold corresponds to the first size parameter;

[0018] The determining unit is further configured to determine an average width of each of the plurality of vein pattern regions to obtain a plurality of average widths; and to determine a position of each of the plurality of vein pattern regions to obtain a plurality of positions.

[0019] The evaluation unit is configured to evaluate each of the plurality of vein pattern regions according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values;

[0020] The determining unit is further configured to select a maximum value among the multiple scoring values, determine a target vein pattern area corresponding to the maximum value, and mark the target vein pattern area.

[0021] In a third aspect, an embodiment of the present application provides a medical electronic device comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program comprises instructions for executing the steps in the first aspect of the embodiment of the present application.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the above-mentioned computer-readable storage medium stores a computer program for electronic data exchange, wherein the above-mentioned computer program enables a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application.

[0023] In a fifth aspect, embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

[0024] The implementation of the embodiments of the present application has the following beneficial effects:

[0025] It can be seen that the image recognition-based intravenous injection processing method and related device described in the embodiments of the present application are applied to medical electronic equipment, which includes a vein recognition module to determine a first size parameter of the needle of the injection device to be injected, obtain a first image of the target part of the target object through the vein recognition module, extract vein patterns from the first image to obtain a vein pattern map, divide the vein pattern map into multiple segments to obtain multiple segments of vein pattern areas; the length of each vein pattern area is greater than a first threshold, and the first threshold corresponds to the first size parameter, determine the average width of each vein pattern area in the multiple segments of vein pattern areas, and obtain multiple average widths, determine the position of each vein pattern area in the multiple segments of vein pattern areas, and obtain multiple positions, evaluate each vein pattern area in the multiple segments of vein pattern areas according to the multiple average widths and the multiple positions, and obtain multiple score values, select the maximum value of the multiple score values, and determine the target vein pattern area corresponding to the maximum value. , mark the target vein pattern area. First, the vein pattern extraction can be performed on the first image to obtain a vein pattern map. The vein pattern map is an image that only includes vein patterns. Therefore, the interference of the background area can be eliminated, which helps to improve the accuracy of vein position recognition. Second, the vein pattern map can be divided into multiple segments to obtain multiple vein pattern areas. The length of each vein pattern area is greater than the first threshold value. Therefore, a certain length of vein can be guaranteed for smooth insertion of the needle. Third, each vein pattern area in the multiple vein pattern areas can be evaluated based on the matching degree between the needle of the injection device and the vein, the effect of intravenous injection and the difficulty of the intravenous injection operation. That is, the optimal vein pattern area can be determined based on the evaluation results. Therefore, it can not only quickly help medical personnel find the intravenous injection position to assist medical personnel in completing rapid injection, but also ensure a high matching degree between the needle of the injection device and the vein, as well as a better effect of intravenous injection and reduce the difficulty of intravenous injection operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0027] Figure 1 This is a flow chart of an intravenous injection processing method based on image recognition provided in an embodiment of the present application;

[0028] Figure 2 This is a schematic structural diagram of a medical electronic device provided in an embodiment of the present application;

[0029] Figure 3 This is a schematic structural diagram of another medical electronic device provided in an embodiment of the present application;

[0030] Figure 4 This is a structural diagram of another medical electronic device provided in an embodiment of the present application;

[0031] Figure 5 This is a block diagram of the functional units of an intravenous injection processing device based on image recognition provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0033] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0034] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0035] The medical electronic device described in the embodiments of the present invention may include a specific medical device, or may also include an electronic device with a vein recognition module (that is, the electronic device can act as a medical electronic device). The electronic device may include a smart phone (such as an Android phone, an iOS phone, a Windows Phone phone, a Hongmeng phone, etc.), a tablet computer, a PDA, a driving recorder, a server, a laptop computer, a mobile Internet device (MID, Mobile Internet Devices) or a wearable device (such as a smart watch, a Bluetooth headset), etc. The above are only examples and not exhaustive, including but not limited to the above electronic devices.

[0036] In the embodiment of the present application, the vein recognition module can be understood as a module based on biometric recognition technology, which utilizes the property of hemoglobin in the blood to absorb near-infrared light and uses an infrared-sensitive camera to obtain vein images under near-infrared light (wavelength of 700nm-1000nm).

[0037] The following is a detailed introduction to the embodiments of the present application.

[0038] See also Figure 1 , Figure 1 This is a flow chart of an intravenous injection processing method based on image recognition provided in an embodiment of the present application, which is applied to a medical electronic device including a vein recognition module. The intravenous injection processing method based on image recognition includes:

[0039] 101. Determine a first size parameter of a needle of an injection device to be injected.

[0040] In the embodiments of the present application, different injection devices may correspond to different size parameters. Specifically, an injection task may be obtained through a medical system, and the first size parameter of the needle of the injection device to be injected may be obtained from the injection task. Different tasks may require different needles, and different needles may have different requirements for vein width. The injection task may be derived from a diagnostic report of a target subject.

[0041] Among them, such as Figure 2 As shown, the medical electronic device may include a vein recognition module, which is used to implement vein recognition.

[0042] 102. Acquire a first image of a target part of a target object through the vein recognition module.

[0043] In a specific implementation, the target object may be any object to be injected, and the target site may be the site to be injected on the target object.

[0044] In an embodiment of the present application, a first image of a target part of a target object can be acquired through a vein recognition module, and the first image can be used to identify the vein position to help medical personnel quickly find the optimal intravenous injection position.

[0045] Optionally, the medical electronic device includes a visible light camera, and the above step 102 of acquiring a first image of a target part of the target object through the vein recognition module can be implemented according to the following steps:

[0046] Acquiring a first physiological state parameter of the target object;

[0047] determining a first operating parameter corresponding to the first physiological state parameter;

[0048] determining a second image of the target part by using the visible light camera;

[0049] determining a first skin color parameter of the target part using the second image;

[0050] determining a first adjustment parameter corresponding to the first skin color parameter;

[0051] Adjust the first operating parameter according to the first adjustment parameter to obtain a second operating parameter;

[0052] The first image of the target part is acquired by the vein recognition module using the second working parameter.

[0053] In specific implementation, such as Figure 3 As shown, the medical electronic device may further include a visible light camera and a vein recognition module. The visible light camera can be used to recognize skin color, and different skin colors will affect the prominence of veins in the vein image to a certain extent.

[0054] The first physiological state parameter may include at least one of the following: height, weight, age, gender, blood pressure, blood lipids, blood sugar, blood temperature, heart rate, hemoglobin content, etc., without limitation herein. Because the first physiological state parameter reflects, to a certain extent, the infrared light absorption effect of hemoglobin, the operating parameters of the vein recognition module suitable for the target subject can be determined based on the first physiological state parameter to ensure effective vein recognition.

[0055] In the embodiment of the present application, the first physiological state parameter of the target subject can be obtained using the target subject's wearable device, or the first physiological state parameter of the target subject can be obtained through the target subject's blood test report or physical examination report. Generally, medical facilities often require blood tests to identify the patient's condition, and the first physiological state parameter of the target subject can also be obtained during the blood test process.

[0056] In a specific implementation, the operating parameters of the vein recognition module may include at least one of the following: operating current, operating voltage, operating power, operating mode, operating frequency, operating band, etc., which are not limited here. The first skin color parameter may include at least one of the following: skin color type, skin color, skin color degree, etc., which are not limited here.

[0057] Then, the mapping relationship between the preset physiological state parameters and the working parameters of the vein recognition module can be pre-stored, and then, the first working parameter corresponding to the first physiological state parameter can be determined based on the mapping relationship, and then the second image of the target part can be determined through the visible light camera, and then the first skin color parameter of the target part can be determined through the second image. Then, the mapping relationship between the preset skin color parameters and the adjustment parameters can be pre-stored, and then, the first adjustment parameter corresponding to the first skin color parameter can be determined based on the mapping relationship, and then part or all of the first working parameters can be adjusted according to the first adjustment parameter to obtain the second working parameter, for example, the second working parameter = (1 + first adjustment parameter) * first working parameter. Finally, the first image of the target part can be obtained with the second working parameter through the vein recognition module.

[0058] Therefore, on the one hand, since the first physiological state parameter reflects the effect of hemoglobin on absorbing infrared light to a certain extent, the working parameters of the corresponding vein recognition module can be preliminarily determined based on the actual situation of the target object. On the other hand, different skin colors will affect the degree of prominence of veins in the vein image to a certain extent. Based on the influence of skin color, the working parameters of the vein recognition module can be dynamically adjusted so that the depth of the vein image conforms to the intrinsic and extrinsic characteristics of the target object, thereby ensuring the efficiency of vein recognition.

[0059] 103. Extract vein patterns from the first image to obtain a vein pattern map.

[0060] In an embodiment of the present application, vein patterns can be extracted from the first image to obtain a vein pattern map. The vein pattern map is an image that only includes vein patterns, thereby eliminating interference from background areas and helping to improve the accuracy of vein position recognition.

[0061] In a specific implementation, target extraction can be performed on the first image, i.e., extracting the vein region to obtain a vein pattern map. For example, a target segmentation algorithm can be used to extract the target from the first image. The target segmentation algorithm can include any algorithm capable of performing target segmentation or target extraction. For example, the target segmentation algorithm can include a neural network model, a large model, etc., which are not limited here.

[0062] Optionally, the above step 103, extracting vein patterns from the first image to obtain a vein pattern map, can be implemented as follows:

[0063] Performing multi-scale decomposition on the first image to obtain a low-frequency component image and a high-frequency component image;

[0064] Determine a target area and a background area in the low-frequency component image to obtain a first target area and a first background area;

[0065] determining a first energy value of the first target area and a second energy value of the first background area;

[0066] Determine a target area and a background area in the high-frequency component image to obtain a second target area and a second background area;

[0067] determining a third energy value of the second target area and a fourth energy value of the second background area;

[0068] determining a first ratio between the third energy value and the first energy value;

[0069] determining a second ratio between the fourth energy value and the second energy value;

[0070] determining a fifth energy value of the low-frequency component image and a sixth energy value of the high-frequency component image;

[0071] determining a third ratio between the fifth energy value and the sixth energy value;

[0072] The vein pattern is extracted from the first image according to the first ratio, the second ratio, and the third ratio to obtain the vein pattern map.

[0073] In a specific implementation, a multi-scale decomposition algorithm can be used to decompose the first image into multiple scales to obtain a low-frequency component image and a high-frequency component image. The low-frequency component image represents the main body of the image, and the high-frequency component image represents the image details. Of course, both the low-frequency component image and the high-frequency component image also have a target area and a background area. In the embodiment of the present application, the target area is the area where the vein pattern is located, and the background area is the area other than the area where the vein pattern is located. The multi-scale decomposition algorithm can include at least one of the following: a wavelet transform algorithm, a non-subsampled contourlet transform algorithm, a shearlet transform algorithm, etc., which are not limited here.

[0074] Next, the target region and background region in the low-frequency component image can be determined to obtain a first target region and a first background region, and the energy value of the first target region can be determined to obtain a first energy value, and the energy value of the first background region can be determined to obtain a second energy value. Correspondingly, the target region and background region in the high-frequency component image can be determined to obtain a second target region and a second background region, and the energy value of the second target region can be determined to obtain a third energy value, and the energy value of the second background region can be determined to obtain a fourth energy value.

[0075] Next, a first ratio between the third energy value and the first energy value can be determined, the first ratio = third energy value / first energy value, and then a second ratio between the fourth energy value and the second energy value can be determined, that is, the second ratio = fourth energy value / second energy value. Determine the energy value of the low-frequency component image to obtain a fifth energy value and determine the energy value of the high-frequency component image to obtain a sixth energy value, then determine a third ratio between the fifth energy value and the sixth energy value, the third ratio = fifth energy value / sixth energy value. Finally, vein pattern extraction can be performed on the first image according to the first ratio, the second ratio and the third ratio to obtain a vein pattern map. In this way, since the first ratio represents the degree of association between the target area in the low-frequency component image and the target area in the high-frequency component image, and the second ratio represents the degree of association between the background area in the low-frequency component image and the background area in the high-frequency component image, the first ratio and the second ratio can be used to determine the depth correlation between the image body and the image details. That is, the algorithm parameters can be deeply optimized based on the depth correlation between the image body and the image details, so that the depth of the final vein pattern extraction effect conforms to the image characteristics, which is conducive to deep extraction of vein patterns, thereby ensuring that medical personnel can quickly find the intravenous injection position to assist medical personnel in completing rapid injection.

[0076] Optionally, the above step of extracting vein patterns from the first image according to the first ratio, the second ratio, and the third ratio to obtain the vein pattern map may be implemented as follows:

[0077] determining a first vein pattern extraction algorithm and a first algorithm parameter of the first vein pattern extraction algorithm corresponding to the third ratio;

[0078] determining a first normalized deviation between the first ratio and the second ratio;

[0079] determining a first optimization parameter corresponding to the first normalized deviation;

[0080] Optimizing the first algorithm parameters according to the first optimization parameters to obtain second algorithm parameters;

[0081] The vein pattern extraction is performed on the first image according to the first vein pattern extraction algorithm and the second algorithm parameters to obtain the vein pattern map.

[0082] Among them, the third ratio reflects the degree of association between the image main body and the image details. Furthermore, the mapping relationship between the preset ratio and the vein pattern extraction algorithm can be pre-stored. Furthermore, the first vein pattern extraction algorithm corresponding to the third ratio can be determined based on the mapping relationship, that is, the vein pattern extraction algorithm corresponding to the degree of association between the image main body and the image details can be determined.

[0083] Accordingly, a mapping relationship between a preset ratio and the algorithm parameters of the first vein pattern extraction algorithm can also be pre-stored. The algorithm parameters are used to control the algorithm effect of the first vein pattern extraction algorithm, such as the accuracy of vein recognition, the completeness of the contour of the vein area extraction, the speed of vein recognition, etc. Then, the first algorithm parameters corresponding to the third ratio can be determined based on the mapping relationship, and the algorithm parameters of the first vein pattern extraction algorithm with an appropriate degree of correlation between the image main body and the image details can be further determined, which helps to preliminarily ensure the vein extraction effect.

[0084] Then, the first normalized deviation between the first ratio and the second ratio can be determined, the first normalized deviation = (first ratio - second ratio) / (first ratio + second ratio), then, the mapping relationship between the preset normalized deviation and the optimization parameter can be pre-stored, and then, the first optimization parameter corresponding to the first normalized deviation can be determined based on the mapping relationship, that is, the first algorithm parameter can be optimized according to the first optimization parameter to obtain the second algorithm parameter, the second algorithm parameter = (1 + first optimization parameter) * first algorithm parameter, finally, the vein pattern extraction of the first image can be performed according to the first vein pattern extraction algorithm and the second algorithm parameter to obtain a vein pattern map.

[0085] Among them, since the first ratio represents the degree of correlation between the target area in the low-frequency component image and the target area in the high-frequency component image, and the second ratio represents the degree of correlation between the background area in the low-frequency component image and the background area in the high-frequency component image, the normalized deviation between the first ratio and the second ratio reflects the degree of depth correlation between the image subject and the image details. Furthermore, the algorithm parameters can be deeply optimized based on the degree of depth correlation between the image subject and the image details, so that the final vein pattern extraction effect depth conforms to the image characteristics, which is helpful for deep extraction of vein patterns, thereby ensuring that medical personnel can quickly find the intravenous injection position to assist medical personnel in completing rapid injection.

[0086] 104. Divide the venous pattern map into multiple segments to obtain multiple venous pattern regions; the length of each venous pattern region is greater than a first threshold, and the first threshold corresponds to the first size parameter.

[0087] Among them, the first threshold can be pre-set or system default, and the first threshold corresponds to the first size parameter. For example, the mapping relationship between the size parameter of the needle of the preset injection device and the threshold can be pre-stored, and then, the first threshold corresponding to the first size parameter can be determined based on the mapping relationship.

[0088] In a specific implementation, since the needle is inserted into the vein obliquely, the needle needs to go deep into the vein. Therefore, a certain length of vein needs to be ensured for smooth insertion of the needle.

[0089] In a specific implementation, the vein pattern map can be divided into multiple segments to obtain multiple vein pattern areas, and the length of each vein pattern area is greater than a first threshold, thereby ensuring that a certain length of vein is used for smooth needle insertion.

[0090] In a specific implementation, the number of branches of the vein pattern map can be determined, each branch corresponds to a segment of the original sub-vein pattern map, and then the length of each segment of the original sub-vein pattern map is determined. Based on the principle that the length of each segment of the original sub-vein pattern map and the length of each vein pattern area is greater than a first threshold, each segment of the original sub-vein pattern map is divided, thereby obtaining multiple segments of vein pattern areas.

[0091] 105. Determine an average width of each of the multiple segments of the vein pattern areas to obtain multiple average widths.

[0092] In the embodiment of the present application, the average width of each vein pattern area in the multiple vein pattern areas can be determined, and multiple average widths can be obtained. The area of each vein pattern area can be determined, and then the length of each vein pattern area can be determined. The ratio of the area to the length can be understood as the average width.

[0093] 106. Determine the position of each vein pattern area in the multiple vein pattern areas to obtain multiple positions.

[0094] In the specific implementation, the effect of intravenous injection and the difficulty of intravenous injection operation are different due to different positions. In addition, since each vein pattern area is known, the center position of each vein pattern area can be determined, and the center position can be used as the position of each vein pattern area to obtain multiple positions.

[0095] 107. Evaluate each of the plurality of vein pattern regions according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values.

[0096] In the embodiment of the present application, since the average width reflects the degree of matching between the needle of the injection device and the vein to a certain extent, the side also reflects the effect of intravenous injection and the difficulty of intravenous injection operation, and the effect of intravenous injection and the difficulty of intravenous injection operation are different in different positions, each vein pattern area in the multiple vein pattern areas can be evaluated based on the degree of matching between the needle of the injection device and the vein, the effect of intravenous injection and the difficulty of intravenous injection operation, and multiple score values can be obtained. The larger the score value, the better the intravenous injection position, and vice versa.

[0097] In a specific implementation, the first size parameter of the needle may include the needle width. Generally, it is necessary to ensure that the vein width is greater than the needle width. Of course, the greater the difference between the vein width and the needle width, the higher the degree of match between the needle of the injection device and the vein.

[0098] Optionally, the step 107 of evaluating each of the plurality of vein pattern regions according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values may be implemented as follows:

[0099] Determining a weight factor corresponding to each of the plurality of positions according to a preset mapping relationship between positions and weight factors, to obtain a plurality of weight factors;

[0100] Performing calculations based on the multiple average widths and the multiple weight factors to obtain multiple first widths;

[0101] According to a preset mapping relationship between widths and scoring values, a scoring value corresponding to each of the plurality of first widths is determined to obtain the plurality of scoring values.

[0102] In a specific implementation, a mapping relationship between preset positions and weight factors can be pre-stored. The value range of the weight factors can be pre-set or system default. For example, the value range of the weight factors can be 0 to 0.2. Then, according to the mapping relationship between the preset positions and weight factors, the weight factor corresponding to each of the multiple positions is determined to obtain multiple weight factors. Then, based on the multiple average widths and the multiple weight factors, multiple widths are obtained, where width = (1 + weight factor) * average width. This width reflects, to a certain extent, the degree of fit between the needle of the injection device and the vein, the effectiveness of the intravenous injection, and the difficulty of the intravenous injection operation.

[0103] Next, the mapping relationship between the preset width and the score value can be pre-stored, and then the score value corresponding to each width in the multiple weighted widths can be determined according to the mapping relationship between the preset width and the score value to obtain multiple score values. In this way, each vein pattern area in the multiple vein pattern areas can be evaluated based on the matching degree between the needle of the injection device and the vein, the effect of intravenous injection and the difficulty of the intravenous injection operation, thereby ensuring that the depth of the evaluation value is related to the matching degree between the needle of the injection device and the vein, the effect of intravenous injection and the difficulty of intravenous injection operation, which helps to help medical staff quickly find the best intravenous injection position.

[0104] 108. Select a maximum value among the multiple scoring values, determine a target vein pattern area corresponding to the maximum value, and mark the target vein pattern area.

[0105] In an embodiment of the present application, the maximum value among multiple scoring values can be selected, and the target venous pattern area corresponding to the maximum value can be determined, and the target venous pattern area can be marked. Thus, it can not only quickly help medical personnel find the intravenous injection position to assist medical personnel in completing rapid injection, but also ensure a high degree of matching between the needle of the injection device and the vein, as well as a better intravenous injection effect and reduce the difficulty of intravenous injection operation.

[0106] It can be seen that the intravenous injection processing method based on image recognition described in the embodiment of the present application is applied to medical electronic equipment, which includes a vein recognition module, determines a first size parameter of the needle of the injection device to be injected, obtains a first image of the target part of the target object through the vein recognition module, extracts vein patterns from the first image, obtains a vein pattern map, divides the vein pattern map into multiple segments, and obtains multiple segments of vein pattern areas; the length of each vein pattern area is greater than a first threshold, and the first threshold corresponds to the first size parameter, determines the average width of each vein pattern area in the multiple segments of vein pattern areas, and obtains multiple average widths, determines the position of each vein pattern area in the multiple segments of vein pattern areas, and obtains multiple positions, evaluates each vein pattern area in the multiple segments of vein pattern areas according to the multiple average widths and the multiple positions, and obtains multiple score values, selects the maximum value of the multiple score values, and determines the target vein pattern area corresponding to the maximum value, and marks Note the target vein pattern area. First, vein pattern extraction can be performed on the first image to obtain a vein pattern map. The vein pattern map is an image that only includes vein patterns. Therefore, the interference of the background area can be eliminated, which helps to improve the accuracy of vein position recognition. Second, the vein pattern map can be divided into multiple segments to obtain multiple vein pattern areas. The length of each vein pattern area is greater than the first threshold, so that a certain length of vein can be guaranteed for smooth insertion of the needle. Third, each vein pattern area in the multiple vein pattern areas can be evaluated based on the degree of matching between the needle of the injection device and the vein, the effect of intravenous injection and the difficulty of the intravenous injection operation. That is, the optimal vein pattern area can be determined based on the evaluation results. Therefore, it can not only quickly help medical personnel find the intravenous injection position to assist medical personnel in completing rapid injection, but also ensure a high degree of matching between the needle of the injection device and the vein, as well as a better effect of intravenous injection and reduce the difficulty of intravenous injection operation.

[0107] See also Figure 4 , Figure 4 1 is a schematic diagram of the structure of another medical electronic device provided in an embodiment of the present application. The medical electronic device includes a processor, a memory, a communication interface, and one or more programs. The one or more programs are stored in the memory and configured to be executed by the processor. The medical electronic device includes a vein recognition module. In the embodiment of the present application, the program includes instructions for executing the following steps:

[0108] determining a first size parameter of a needle of an injection device to be injected;

[0109] Acquiring a first image of a target part of a target object by the vein recognition module;

[0110] Extracting vein patterns from the first image to obtain a vein pattern map;

[0111] Dividing the venous pattern map into multiple segments to obtain multiple venous pattern regions; the length of each venous pattern region is greater than a first threshold, and the first threshold corresponds to the first size parameter;

[0112] determining an average width of each of the plurality of vein pattern regions to obtain a plurality of average widths;

[0113] Determining a position of each of the plurality of vein pattern regions to obtain a plurality of positions; evaluating each of the plurality of vein pattern regions according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values;

[0114] A maximum value among the multiple scoring values is selected, a target vein pattern area corresponding to the maximum value is determined, and the target vein pattern area is marked.

[0115] Optionally, in the aspect of evaluating each of the plurality of vein pattern regions according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values, the program includes instructions for executing the following steps:

[0116] Determining a weight factor corresponding to each of the plurality of positions according to a preset mapping relationship between positions and weight factors, to obtain a plurality of weight factors;

[0117] Performing calculations based on the multiple average widths and the multiple weight factors to obtain multiple first widths;

[0118] According to a preset mapping relationship between widths and scoring values, a scoring value corresponding to each of the plurality of first widths is determined to obtain the plurality of scoring values.

[0119] Optionally, the medical electronic device includes a visible light camera, and in acquiring the first image of the target part of the target object through the vein recognition module, the program includes instructions for performing the following steps:

[0120] Acquiring a first physiological state parameter of the target object;

[0121] determining a first operating parameter corresponding to the first physiological state parameter;

[0122] determining a second image of the target part by using the visible light camera;

[0123] determining a first skin color parameter of the target part using the second image;

[0124] determining a first adjustment parameter corresponding to the first skin color parameter;

[0125] Adjust the first operating parameter according to the first adjustment parameter to obtain a second operating parameter;

[0126] The first image of the target part is acquired by the vein recognition module using the second working parameter.

[0127] Optionally, in the aspect of extracting vein patterns from the first image to obtain a vein pattern map, the program includes instructions for executing the following steps:

[0128] Performing multi-scale decomposition on the first image to obtain a low-frequency component image and a high-frequency component image;

[0129] Determine a target area and a background area in the low-frequency component image to obtain a first target area and a first background area;

[0130] determining a first energy value of the first target area and a second energy value of the first background area;

[0131] Determine a target area and a background area in the high-frequency component image to obtain a second target area and a second background area;

[0132] determining a third energy value of the second target area and a fourth energy value of the second background area;

[0133] determining a first ratio between the third energy value and the first energy value;

[0134] determining a second ratio between the fourth energy value and the second energy value;

[0135] determining a fifth energy value of the low-frequency component image and a sixth energy value of the high-frequency component image;

[0136] determining a third ratio between the fifth energy value and the sixth energy value;

[0137] The vein pattern is extracted from the first image according to the first ratio, the second ratio, and the third ratio to obtain the vein pattern map.

[0138] Optionally, in the aspect of extracting vein patterns from the first image according to the first ratio, the second ratio, and the third ratio to obtain the vein pattern map, the program includes instructions for executing the following steps:

[0139] determining a first vein pattern extraction algorithm and a first algorithm parameter of the first vein pattern extraction algorithm corresponding to the third ratio;

[0140] determining a first normalized deviation between the first ratio and the second ratio;

[0141] determining a first optimization parameter corresponding to the first normalized deviation;

[0142] Optimizing the first algorithm parameters according to the first optimization parameters to obtain second algorithm parameters;

[0143] The vein pattern extraction is performed on the first image according to the first vein pattern extraction algorithm and the second algorithm parameters to obtain the vein pattern map.

[0144] It can be seen that the medical electronic device described in the embodiment of the present application includes a vein recognition module, which determines a first size parameter of the needle of the injection device to be injected, obtains a first image of the target part of the target object through the vein recognition module, extracts vein patterns from the first image to obtain a vein pattern map, divides the vein pattern map into multiple segments, and obtains multiple segments of vein pattern areas; the length of each vein pattern area is greater than a first threshold, and the first threshold corresponds to the first size parameter, determines the average width of each vein pattern area in the multiple segments of vein pattern areas, and obtains multiple average widths, determines the position of each vein pattern area in the multiple segments of vein pattern areas, and obtains multiple positions, evaluates each vein pattern area in the multiple segments of vein pattern areas according to the multiple average widths and the multiple positions, and obtains multiple score values, selects the maximum value of the multiple score values, and determines the target vein pattern area corresponding to the maximum value, and marks the target vein pattern area. First, vein patterns can be extracted from the first image to obtain a vein pattern map, which is an image that only includes vein patterns. Thus, the interference of the background area can be eliminated, which helps to improve the accuracy of vein position recognition. Second, the vein pattern map can be divided into multiple segments to obtain multiple vein pattern areas. The length of each vein pattern area is greater than the first threshold, thereby ensuring that a certain length of vein is used to smoothly insert the needle. Third, each vein pattern area in the multiple vein pattern areas can be evaluated based on the degree of matching between the needle of the injection device and the vein, the effect of intravenous injection, and the difficulty of the intravenous injection operation. That is, the optimal vein pattern area can be determined based on the evaluation results. Therefore, it can not only quickly help medical personnel find the intravenous injection position to assist medical personnel in completing rapid injection, but also ensure a high degree of matching between the needle of the injection device and the vein, as well as a better effect of intravenous injection and reduce the difficulty of intravenous injection operation.

[0145] Figure 5This is a functional unit block diagram of an intravenous injection processing device 500 based on image recognition involved in an embodiment of the present application. The intravenous injection processing device 500 based on image recognition is applied to medical electronic equipment, and the medical electronic equipment includes a vein recognition module; the intravenous injection processing device 500 based on image recognition includes: a determination unit 501, an acquisition unit 502, an extraction unit 503, a division unit 504 and an evaluation unit 505, wherein,

[0146] The determining unit 501 is used to determine a first size parameter of a needle of an injection device to be injected;

[0147] The acquisition unit 502 is configured to acquire a first image of a target part of a target object through the vein recognition module;

[0148] The extraction unit 503 is configured to extract vein patterns from the first image to obtain a vein pattern map;

[0149] The dividing unit 504 is configured to divide the venous pattern map into multiple segments to obtain multiple venous pattern regions; the length of each venous pattern region is greater than a first threshold, and the first threshold corresponds to the first size parameter;

[0150] The determining unit 501 is further configured to determine an average width of each of the plurality of venous pattern regions to obtain a plurality of average widths; and determine a position of each of the plurality of venous pattern regions to obtain a plurality of positions.

[0151] The evaluation unit 505 is configured to evaluate each of the plurality of vein pattern regions according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values;

[0152] The determining unit 501 is further configured to select a maximum value from the multiple scoring values, determine a target vein pattern area corresponding to the maximum value, and mark the target vein pattern area.

[0153] Optionally, in evaluating each of the plurality of vein pattern regions according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values, the evaluation unit 505 is specifically configured to:

[0154] Determining a weight factor corresponding to each of the plurality of positions according to a preset mapping relationship between positions and weight factors, to obtain a plurality of weight factors;

[0155] Performing calculations based on the multiple average widths and the multiple weight factors to obtain multiple first widths;

[0156] According to a preset mapping relationship between widths and scoring values, a scoring value corresponding to each of the plurality of first widths is determined to obtain the plurality of scoring values.

[0157] Optionally, the medical electronic device includes a visible light camera. In acquiring the first image of the target part of the target object through the vein recognition module, the acquiring unit 502 is specifically configured to:

[0158] Acquiring a first physiological state parameter of the target object;

[0159] determining a first operating parameter corresponding to the first physiological state parameter;

[0160] determining a second image of the target part by using the visible light camera;

[0161] determining a first skin color parameter of the target part using the second image;

[0162] determining a first adjustment parameter corresponding to the first skin color parameter;

[0163] Adjust the first operating parameter according to the first adjustment parameter to obtain a second operating parameter;

[0164] The first image of the target part is acquired by the vein recognition module using the second working parameter.

[0165] Optionally, in extracting the vein pattern from the first image to obtain the vein pattern map, the extraction unit 503 is specifically configured to:

[0166] Performing multi-scale decomposition on the first image to obtain a low-frequency component image and a high-frequency component image;

[0167] Determine a target area and a background area in the low-frequency component image to obtain a first target area and a first background area;

[0168] determining a first energy value of the first target area and a second energy value of the first background area;

[0169] Determine a target area and a background area in the high-frequency component image to obtain a second target area and a second background area;

[0170] determining a third energy value of the second target area and a fourth energy value of the second background area;

[0171] determining a first ratio between the third energy value and the first energy value;

[0172] determining a second ratio between the fourth energy value and the second energy value;

[0173] determining a fifth energy value of the low-frequency component image and a sixth energy value of the high-frequency component image;

[0174] determining a third ratio between the fifth energy value and the sixth energy value;

[0175] The vein pattern is extracted from the first image according to the first ratio, the second ratio, and the third ratio to obtain the vein pattern map.

[0176] Optionally, in extracting vein patterns from the first image according to the first ratio, the second ratio, and the third ratio to obtain the vein pattern map, the extraction unit 503 is specifically configured to:

[0177] determining a first vein pattern extraction algorithm and a first algorithm parameter of the first vein pattern extraction algorithm corresponding to the third ratio;

[0178] determining a first normalized deviation between the first ratio and the second ratio;

[0179] determining a first optimization parameter corresponding to the first normalized deviation;

[0180] Optimizing the first algorithm parameters according to the first optimization parameters to obtain second algorithm parameters;

[0181] The vein pattern extraction is performed on the first image according to the first vein pattern extraction algorithm and the second algorithm parameters to obtain the vein pattern map.

[0182] It can be seen that the intravenous injection processing device based on image recognition described in the embodiment of the present application is applied to medical electronic equipment, which includes a vein recognition module, determines a first size parameter of the needle of the injection device to be injected, obtains a first image of the target part of the target object through the vein recognition module, extracts vein patterns from the first image, obtains a vein pattern map, divides the vein pattern map into multiple segments, and obtains multiple segments of vein pattern areas; the length of each vein pattern area is greater than a first threshold, and the first threshold corresponds to the first size parameter, determines the average width of each vein pattern area in the multiple segments of vein pattern areas, and obtains multiple average widths, determines the position of each vein pattern area in the multiple segments of vein pattern areas, and obtains multiple positions, evaluates each vein pattern area in the multiple segments of vein pattern areas according to the multiple average widths and the multiple positions, and obtains multiple score values, selects the maximum value of the multiple score values, and determines the target vein pattern area corresponding to the maximum value, and marks Note the target vein pattern area. First, vein pattern extraction can be performed on the first image to obtain a vein pattern map. The vein pattern map is an image that only includes vein patterns. Therefore, the interference of the background area can be eliminated, which helps to improve the accuracy of vein position recognition. Second, the vein pattern map can be divided into multiple segments to obtain multiple vein pattern areas. The length of each vein pattern area is greater than the first threshold, so that a certain length of vein can be guaranteed for smooth insertion of the needle. Third, each vein pattern area in the multiple vein pattern areas can be evaluated based on the degree of matching between the needle of the injection device and the vein, the effect of intravenous injection and the difficulty of the intravenous injection operation. That is, the optimal vein pattern area can be determined based on the evaluation results. Therefore, it can not only quickly help medical personnel find the intravenous injection position to assist medical personnel in completing rapid injection, but also ensure a high degree of matching between the needle of the injection device and the vein, as well as a better effect of intravenous injection and reduce the difficulty of intravenous injection operation.

[0183] It can be understood that the functions of each program module of the image recognition-based intravenous injection processing device of this embodiment can be specifically implemented according to the method in the above method embodiment. The specific implementation process can refer to the relevant description of the above method embodiment and will not be repeated here.

[0184] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments.

[0185] The present application also provides a computer program product comprising a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package.

[0186] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0187] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0188] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0189] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0190] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0191] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0192] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0193] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for those skilled in the art, according to the idea of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An intravenous injection processing method based on image recognition, characterized in that: Applied to medical electronic equipment, the medical electronic equipment includes a vein recognition module; the method includes: determining a first size parameter of a needle of an injection device to be injected; Acquiring a first image of a target part of a target object by the vein recognition module; Extracting vein patterns from the first image to obtain a vein pattern map; Dividing the venous pattern map into multiple segments to obtain multiple venous pattern regions; the length of each venous pattern region is greater than a first threshold, and the first threshold corresponds to the first size parameter; determining an average width of each of the plurality of vein pattern regions to obtain a plurality of average widths; determining a position of each of the plurality of vein pattern regions to obtain a plurality of positions; Evaluate each of the plurality of vein pattern areas according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values; A maximum value among the multiple scoring values is selected, a target vein pattern area corresponding to the maximum value is determined, and the target vein pattern area is marked.

2. The method according to claim 1, characterized in that The step of evaluating each of the plurality of vein pattern regions according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values includes: Determining a weight factor corresponding to each of the plurality of positions according to a preset mapping relationship between positions and weight factors, to obtain a plurality of weight factors; Performing calculations based on the multiple average widths and the multiple weight factors to obtain multiple first widths; According to a preset mapping relationship between widths and scoring values, a scoring value corresponding to each of the plurality of first widths is determined to obtain the plurality of scoring values.

3. The method according to claim 1 or 2, characterized in that The medical electronic device includes a visible light camera, and acquiring a first image of a target part of a target object through the vein recognition module includes: Acquiring a first physiological state parameter of the target object; determining a first operating parameter corresponding to the first physiological state parameter; determining a second image of the target part by using the visible light camera; determining a first skin color parameter of the target part using the second image; determining a first adjustment parameter corresponding to the first skin color parameter; Adjust the first operating parameter according to the first adjustment parameter to obtain a second operating parameter; The first image of the target part is acquired by the vein recognition module using the second working parameter.

4. The method according to claim 1 or 2, characterized in that The extracting vein patterns from the first image to obtain a vein pattern map includes: Performing multi-scale decomposition on the first image to obtain a low-frequency component image and a high-frequency component image; Determine a target area and a background area in the low-frequency component image to obtain a first target area and a first background area; determining a first energy value of the first target area and a second energy value of the first background area; Determine a target area and a background area in the high-frequency component image to obtain a second target area and a second background area; determining a third energy value of the second target area and a fourth energy value of the second background area; determining a first ratio between the third energy value and the first energy value; determining a second ratio between the fourth energy value and the second energy value; determining a fifth energy value of the low-frequency component image and a sixth energy value of the high-frequency component image; determining a third ratio between the fifth energy value and the sixth energy value; The vein pattern is extracted from the first image according to the first ratio, the second ratio, and the third ratio to obtain the vein pattern map.

5. The method according to claim 4, characterized in that The extracting vein patterns from the first image according to the first ratio, the second ratio, and the third ratio to obtain the vein pattern map includes: determining a first vein pattern extraction algorithm and a first algorithm parameter of the first vein pattern extraction algorithm corresponding to the third ratio; determining a first normalized deviation between the first ratio and the second ratio; determining a first optimization parameter corresponding to the first normalized deviation; Optimizing the first algorithm parameters according to the first optimization parameters to obtain second algorithm parameters; The vein pattern extraction is performed on the first image according to the first vein pattern extraction algorithm and the second algorithm parameters to obtain the vein pattern map.

6. An intravenous injection processing device based on image recognition, characterized in that: Applicable to medical electronic equipment, the medical electronic equipment includes a vein recognition module; the device includes: a determination unit, an acquisition unit, an extraction unit, a division unit and an evaluation unit, wherein, The determining unit is configured to determine a first size parameter of a needle of an injection device to be injected; The acquisition unit is configured to acquire a first image of a target part of a target object through the vein recognition module; The extraction unit is configured to extract vein patterns from the first image to obtain a vein pattern map; The dividing unit is configured to divide the venous pattern map into multiple segments to obtain multiple venous pattern regions; the length of each venous pattern region is greater than a first threshold, and the first threshold corresponds to the first size parameter; The determining unit is further configured to determine an average width of each of the plurality of vein pattern regions to obtain a plurality of average widths; and to determine a position of each of the plurality of vein pattern regions to obtain a plurality of positions. The evaluation unit is configured to evaluate each of the plurality of vein pattern regions according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values; The determining unit is further configured to select a maximum value among the multiple scoring values, determine a target vein pattern area corresponding to the maximum value, and mark the target vein pattern area.

7. The device according to claim 6, characterized in that In the aspect of evaluating each of the plurality of vein pattern regions according to the plurality of average widths and the plurality of positions to obtain a plurality of scoring values, the evaluation unit is specifically configured to: Determining a weight factor corresponding to each of the plurality of positions according to a preset mapping relationship between positions and weight factors, to obtain a plurality of weight factors; Performing calculations based on the multiple average widths and the multiple weight factors to obtain multiple first widths; According to a preset mapping relationship between widths and scoring values, a scoring value corresponding to each of the plurality of first widths is determined to obtain the plurality of scoring values.

8. The aspect according to claim 6 or 7, characterized in that The medical electronic device includes a visible light camera. In acquiring a first image of a target part of a target object through the vein recognition module, the acquiring unit is specifically configured to: Acquiring a first physiological state parameter of the target object; determining a first operating parameter corresponding to the first physiological state parameter; determining a second image of the target part by using the visible light camera; determining a first skin color parameter of the target part using the second image; determining a first adjustment parameter corresponding to the first skin color parameter; Adjust the first operating parameter according to the first adjustment parameter to obtain a second operating parameter; The first image of the target part is acquired by the vein recognition module using the second working parameter.

9. A medical electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store one or more programs and is configured to be executed by the processor, wherein the programs include instructions for executing the steps of the method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 5.

Images