A blood vessel feature recognition method and related device

Abstract

This application discloses a method and related apparatus for blood vessel feature recognition, relating to the field of image processing. It involves processing an acquired image of the sclera region based on a blood vessel segmentation algorithm to obtain a first blood vessel mask image of the sclera region. Then, the blood vessels in the first blood vessel mask image are refined to obtain a second blood vessel mask image. The blood vessel pixels in the second blood vessel mask image are identified using a neighborhood method and feature point recognition rules to obtain blood vessel feature points. Based on this, the feature information of the blood vessel contour is determined according to the coordinate information of each blood vessel feature point in the second blood vessel mask image. Compared to some existing deep learning techniques, this method does not require manual pre-annotation of nodes, has a fast recognition speed and high feature recognition accuracy, and is also interpretable.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method and related apparatus for blood vessel feature recognition. Background Technology

[0002] With the rapid development of artificial intelligence and optical imaging technology, intelligent analysis systems for human health status based on scleral images (referred to as eye diagnostic instruments) have gradually become widely used. As an intelligent device, it can objectively extract blood vessel features from scleral images, thus providing important assistance in judging human health. However, current eye diagnostic instruments still have shortcomings in the process of blood vessel feature recognition, and are prone to feature recognition errors, reducing the accuracy of feature recognition. Summary of the Invention

[0003] In view of the above problems, this application provides a blood vessel feature recognition method and related apparatus to improve the accuracy and efficiency of recognition. The specific solution is as follows:

[0004] The first aspect of this application provides a method for blood vessel feature recognition, including:

[0005] The obtained scleral region image is processed based on the blood vessel segmentation algorithm to obtain the first blood vessel mask image of the scleral region.

[0006] The blood vessels in the first blood vessel mask image are refined to obtain the second blood vessel mask image;

[0007] Based on the domain method and feature point recognition rules, the blood vein pixels in the second blood vein mask are identified to obtain blood vein feature points.

[0008] Based on the coordinate information of each blood vessel feature point in the second blood vessel mask image, the feature information of the blood vessel contour is determined.

[0009] In one possible implementation, before processing the acquired sclera region image based on the blood vessel segmentation algorithm to obtain the first blood vessel mask map of the sclera region, the following steps are also included:

[0010] The acquired eye image is masked to obtain an eye mask image;

[0011] Based on the shape of the sclera region in the eye mask image, the sclera region image is separated from the eye image.

[0012] In one possible implementation, the feature points include: the terminal points and nodes of the blood vessels. The process of identifying blood vessel pixels in the second blood vessel mask image based on the neighborhood method and feature point recognition rules to obtain blood vessel feature points includes:

[0013] Based on the eight-neighbor method, the blood vein pixels in the second blood vein mask image are identified to obtain the identification result data of the end point and the identification result data of the node.

[0014] The identification result data of the nodes is filtered based on the two-domain method, the four-domain method, and the feature point identification rules.

[0015] In one possible implementation, the node includes a branching point and an intersection point. The filtering process for the node identification result data based on the two-neighborhood method, the four-neighborhood method, and the feature point identification rules includes:

[0016] Y-shaped bifurcation points are filtered out from the node identification result data based on the two-neighborhood method.

[0017] Based on the four-domain method, T-shaped bifurcation points and cross-shaped intersection points are filtered out from the node identification result data.

[0018] In one possible implementation, the node includes a branching point and an intersection point, and the filtering process of the node identification result data based on the two-neighborhood method, the four-neighborhood method, and the feature point identification rule further includes:

[0019] If a target node exists in the node identification result data and the nodes adjacent to the target node are not on the same side, then the target node is determined as an intersection point. The target node is a node with no less than 4 adjacent nodes.

[0020] In one possible implementation, when filtering out T-shaped bifurcation points from the node identification result data based on the four-neighborhood method, if all adjacent pixels are identified as T-shaped bifurcation points, then the pixel with the smallest Harmanton distance to its adjacent pixels is determined as the T-shaped bifurcation point.

[0021] In one possible implementation, the blood vessel feature points include: end points and nodes. Based on the coordinate information of each of the blood vessel feature points in the second blood vessel mask image, feature information of the blood vessel contour is determined, including:

[0022] The distance from each terminal point to the nearest connected node is determined based on the search algorithm, and the length of each blood vessel branch is obtained.

[0023] The number of blood vessel bifurcations is determined based on the length threshold, the length of each blood vessel bifurcation, and the number of nodes.

[0024] Based on the minimum bounding rectangle of the blood vessel bifurcation, the angle between adjacent blood vessel bifurcations at the same node is determined.

[0025] A second aspect of this application provides a blood vessel feature recognition device, comprising:

[0026] The blood vessel image extraction module is used to process the acquired sclera region image based on the blood vessel segmentation algorithm to obtain the first blood vessel mask image of the sclera region.

[0027] The blood vessel image refinement module is used to refine the blood vessels in the first blood vessel mask image to obtain a second blood vessel mask image.

[0028] The feature point determination module is used to identify blood vein pixels in the second blood vein mask image based on the neighborhood method and feature point recognition rules to obtain blood vein feature points;

[0029] The feature information extraction module is used to determine the feature information of the blood vessel contour based on the coordinate information of each blood vessel feature point in the second blood vessel mask image.

[0030] A third aspect of this application provides a computer program product including computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the blood vessel feature recognition method described in the first aspect or any implementation thereof.

[0031] A fourth aspect of this application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0032] The memory is used to store computer programs;

[0033] The processor is used to execute the computer program so that the electronic device can implement the blood vessel feature recognition method of the first aspect or any implementation thereof.

[0034] The fifth aspect of this application provides a computer storage medium carrying one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the blood vessel feature recognition method described in the first aspect or any implementation thereof.

[0035] Using the above technical solution, the blood vessel feature recognition method provided in this application processes the acquired sclera region image based on a blood vessel segmentation algorithm to obtain a first blood vessel mask image of the sclera region. Then, the blood vessels in the first blood vessel mask image are refined to obtain a second blood vessel mask image. The blood vessel pixels in the second blood vessel mask image are identified using the neighborhood method and feature point recognition rules to obtain blood vessel feature points. Based on this, the feature information of the blood vessel contour is determined according to the coordinate information of each blood vessel feature point in the second blood vessel mask image. Compared with some existing deep learning techniques, this method does not require manual pre-annotation of nodes, has a fast recognition speed and high feature recognition accuracy, and is also interpretable. Attached Figure Description

[0036] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0037] Figure 1 An architecture diagram of a bloodline feature recognition system provided in this application;

[0038] Figure 2 An architecture diagram of a terminal provided in this application;

[0039] Figure 3 An architecture diagram of a server provided for this application;

[0040] Figure 4 A flowchart of a blood vessel feature recognition method provided in this application;

[0041] Figure 5 A mask image for the eye image provided in this application;

[0042] Figure 6 Images of the sclera region provided in this application;

[0043] Figure 7 The extracted blood vessel map provided in this application;

[0044] Figure 8 The blood vessel diagram provided for this application is a preliminary version.

[0045] Figure 9 The detailed blood vessel diagram provided for this application;

[0046] Figure 10 A pixel map of the T-shaped bifurcation point provided in this application;

[0047] Figure 11 A pixel map of the Y-shaped bifurcation point provided in this application;

[0048] Figure 12 A pixel map of the L-shaped bifurcation point provided in this application;

[0049] Figure 13 A pixel map of the cross-shaped intersection points provided in this application;

[0050] Figure 14 A pixel map of the X-shaped intersection points provided in this application;

[0051] Figure 15 The diagram showing the identification results of endpoints and nodes provided in this application;

[0052] Figure 16The recognition results of the rotating Y-shaped bifurcation and the rotating L-shaped bifurcation provided in this application are shown in the figure.

[0053] Figure 17 A diagram showing the node processing results of the four-domain method provided in this application;

[0054] Figure 18 The diagram showing the identification results of the intersection points of the eight-domain method provided in this application;

[0055] Figure 19 The blood vessel diagram provided for this application is a preliminary version.

[0056] Figure 20 Provide a detailed bloodline diagram for this application;

[0057] Figure 21 A diagram showing the effect of not merging the original bloodline mask image provided in this application;

[0058] Figure 22 The structural diagram of the circumscribed rectangle provided in this application;

[0059] Figure 23 This is a structural diagram of the blood vessel feature recognition device provided in this application;

[0060] Figure 24 A structural diagram of the electronic device provided in this application. Detailed Implementation

[0061] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0062] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0063] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0064] See Figure 1 , Figure 1 A schematic diagram of the architecture of a bloodline feature recognition system is shown. The system may include a terminal 100 and a server 200. The server 200 may include one or more servers (…). Figure 1 (The example includes a server) Server 200 can provide the blood vessel feature recognition method provided in the embodiments of this application to one or more terminals.

[0065] The terminal 100 may have a blood vessel feature recognition application installed. The application and webpage can provide an interface. The terminal 100 can receive the relevant human eye image input by the user on the blood vessel feature recognition interface and send the human eye image to the server 200. The server 200 can obtain the processing result based on the received human eye image and return the processing result to the terminal 100.

[0066] It should be understood that in some optional implementations, the terminal 100 can also complete the action of obtaining the processing result based on the received human eye image on its own, without the need for the server to cooperate. This application embodiment is not limited to this.

[0067] The following description Figure 1 The product form of the mid-terminal 100;

[0068] The terminal 100 in this application embodiment can be a mobile phone, tablet computer, wearable device, vehicle device, augmented reality (AR) / virtual reality (VR) device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), etc., and this application embodiment does not impose any restrictions on it.

[0069] Figure 2 A schematic diagram of one optional hardware structure for terminal 100 is shown.

[0070] refer to Figure 2 As shown, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), a headphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190, and other components. Those skilled in the art will understand that... Figure 2These are merely examples of terminals or multi-functional devices and do not constitute a limitation on terminals or multi-functional devices. They may include more or fewer components than shown in the illustration, or combine certain components, or use different components.

[0071] The input unit 130 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the portable multi-functional device. Specifically, the input unit 130 may include a touchscreen 131 (optional) and / or other input devices 132. The touchscreen 131 can collect touch operations performed by the user on or near it (such as operations performed by the user using fingers, knuckles, styluses, or any suitable object on or near the touchscreen), and drive the corresponding connection devices according to a pre-set program. The touchscreen can detect the user's touch actions, convert the touch actions into touch signals and send them to the processor 170, and can receive and execute commands sent by the processor 170; the touch signal includes at least touch point coordinate information. The touchscreen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition, various types of touchscreens, such as resistive, capacitive, infrared, and surface acoustic wave, can be used to implement the touchscreen. Besides the touchscreen 131, the input unit 130 may also include other input devices. Specifically, other input devices 132 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0072] Among them, the input device 132 can receive input data, etc.

[0073] The display unit 140 can be used to display information input by the user or information provided to the user, various menus of the terminal 100, interactive interfaces, file display, and / or playback of any multimedia file. In this embodiment, the display unit 140 can be used to display the interface for blood vessel feature recognition, processing results, etc.

[0074] The memory 120 can be used to store instructions and data. The memory 120 may primarily include an instruction storage area and a data storage area. The data storage area can store various types of data, such as multimedia files and text. The instruction storage area can store software units such as operating systems, applications, and instructions required for at least one function, or subsets or extended sets thereof. It may also include non-volatile random access memory. It provides the processor 170 with hardware, software, and data resources for managing the computing device, supporting control software and applications. It is also used for storing multimedia files, as well as storing running programs and applications.

[0075] The processor 170 is the control center of the terminal 100. It connects various parts of the terminal 100 via various interfaces and lines. By running or executing instructions stored in the memory 120 and calling data stored in the memory 120, it performs various functions and processes data of the terminal 100, thereby controlling the terminal device as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 170. In some embodiments, the processor and memory can be implemented on a single chip; in some embodiments, they can also be implemented separately on independent chips. The processor 170 can also be used to generate corresponding operation control signals, send them to the corresponding components of the computing processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that the various functional modules therein perform corresponding functions, thereby controlling the corresponding components to act according to the instructions.

[0076] The memory 120 can be used to store software code related to the blood vessel feature recognition method, and the processor 170 can execute the steps of the blood vessel feature recognition method, and can also schedule other units (such as the above-mentioned input unit 130 and display unit 140) to achieve the corresponding functions.

[0077] The radio frequency unit 110 (optional) can be used for receiving and transmitting signals during information transmission or calls. For example, it can receive downlink information from the base station and process it for the processor 170; additionally, it can transmit uplink data to the base station. Typically, the RF circuit includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier (LNA), a duplexer, etc. Furthermore, the radio frequency unit 110 can also communicate wirelessly with network devices and other devices. This wireless communication can use any communication standard or protocol, including but not limited to Global System for Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0078] In this embodiment of the application, the radio frequency unit 110 can send human eye images to the server 200 and receive blood vessel feature data sent by the server 200.

[0079] It should be understood that the radio frequency unit 110 is optional and can be replaced with other communication interfaces, such as a network port.

[0080] The terminal 100 also includes a power supply 190 (such as a battery) that supplies power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0081] Terminal 100 also includes an external interface 180, which can be a standard Micro USB interface or a multi-pin connector, which can be used to connect terminal 100 to other devices for communication or to connect a charger to charge terminal 100.

[0082] Although not shown, terminal 100 may also include a flash, a wireless fidelity (WiFi) module, a Bluetooth module, and sensors with various functions, which will not be elaborated here. Some or all of the methods described below can be applied to, for example... Figure 2 In the terminal 100 shown.

[0083] The following description Figure 1 The product form of the mid-range server 200;

[0084] Figure 3 A structural diagram of a server 200 is provided, as follows: Figure 3 As shown, server 200 includes bus 201, processor 202, communication interface 203, and memory 204. Processor 202, memory 204, and communication interface 203 communicate with each other via bus 201.

[0085] Bus 201 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0086] The processor 202 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0087] Memory 204 may include volatile memory, such as random access memory (RAM). Memory 204 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0088] The memory 204 can be used to store software code related to the blood vessel feature recognition method, and the processor 202 can execute the steps of the blood vessel feature recognition method of the chip, and can also schedule other units to achieve the corresponding functions.

[0089] It should be understood that the aforementioned terminal 100 and server 200 can be centralized or distributed devices. The processors (e.g., processor 170 and processor 202) in the aforementioned terminal 100 and server 200 can be hardware circuits (such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), general-purpose processors, digital signal processors (DSPs), microprocessors or microcontrollers, etc.) or combinations of these hardware circuits. For example, the processor can be a hardware system with instruction execution capabilities, such as a CPU or DSP, or a hardware system without instruction execution capabilities, such as an ASIC or FPGA, or a combination of the aforementioned hardware systems without instruction execution capabilities and hardware systems with instruction execution capabilities.

[0090] Reference Figure 4 , Figure 4 This is a flowchart illustrating a blood vessel feature recognition method provided in an embodiment of this application, as follows: Figure 4 As shown in the embodiment of this application, a blood vessel feature recognition method may include steps 401 to 404, which are described in detail below.

[0091] 401. The obtained sclera region image is processed based on the blood vessel segmentation algorithm to obtain the first blood vessel mask image of the sclera region.

[0092] Specifically, as shown in Figure 5, the mask image of the human eye obtained after masking the human eye image captured by the eye diagnostic instrument is shown. The masking process can be performed using algorithms such as Unet, which will not be elaborated here.

[0093] Based on the obtained eye mask image, the sclera region is extracted from the original image of the eye region. The sclera region image can be separated from the eye image based on the shape of the sclera region in the eye mask image (see reference). Figure 6 Image of the sclera region extracted from the original eye image.

[0094] Based on the obtained image of the sclera region, recognition algorithms such as FR-Unet can be used to process the image to obtain the first vein mask image of all veins in the sclera region image, referring to... Figure 7 As shown, for ease of explanation, only a partial bloodline mask is displayed here.

[0095] It is understood that those skilled in the art can also use processing algorithms to process the bloodline mask image, which will not be elaborated here.

[0096] 402. Refine the blood vessels in the first blood vessel mask image to obtain the second blood vessel mask image.

[0097] Specifically, to reduce the impact of vein width on morphological recognition, thinning algorithms (such as Guo-Hall) can be used to thin the vein according to the selected thinning type, as shown in the reference. Figure 8 This is the unrefined bloodline mask image after cropping. Figure 9 The image shown is the cropped and refined blood vessel mask. It is important to note that the image should be cropped after refining; otherwise, the refining effect at the edges may be poor after cropping.

[0098] 403. Based on the domain method and feature point recognition rules, the blood vein pixels in the second blood vein mask are identified to obtain blood vein feature points.

[0099] Specifically, the blood vessel feature points here can include: terminal points and nodes, where nodes can be further divided into bifurcation points and intersection points. For example, refer to... Figure 10 The T-shaped bifurcation point is shown in the area consisting of 9 squares on the left. Each square represents one pixel, and the middle square with 0 pixels represents the non-zero pixel to be judged (i.e., the middle square represents the entire T-shaped bifurcation point). The adjacent 128-pixel squares represent adjacent non-zero pixels, and the other 255-pixel blank squares represent zero pixels. Other types of intersections and bifurcation points are also distinguished by pixels according to the above rules. Since the shape formed by non-zero pixels resembles a T, for this type of bifurcation, the middle pixel is defined as the T-shaped bifurcation point. Figure 10 Patterns created by flipping, rotating, or combining flipping and rotating the pixels on the left also fall into this category. Subsequent patterns will be presented in this manner unless otherwise specified. Figure 10 The fork shown on the right is defined as a rotating T-shaped fork according to the pattern, and the middle pixel is also defined as a T-shaped fork point.

[0100] And so on, refer to Figure 11 The image shown, from left to right, represents the pixel diagram of the Y-shaped bifurcation point and the rotated Y-shaped bifurcation point. Figure 12 The image shown, from left to right, represents the pixel diagram of the L-shaped bifurcation point and the rotated L-shaped bifurcation point. Figure 13 The image shown is a pixel map of the cross-shaped intersection points. (Refer to...) Figure 14 The image shows pixel diagrams of X-shaped intersections and X-shaped intersections.

[0101] When identifying blood vessel feature points, the coordinate information of non-zero pixels in the blood vessel mask image is first obtained. Then, for terminal points, the eight-neighborhood method is used for judgment. This is done by calculating the number of non-zero pixels to be judged and their adjacent non-zero pixels. If there is only one adjacent non-zero pixel, then it is considered a terminal point. Figure 15 As shown in pixel 2, the middle pixel 1 is the identified bifurcation point. When using the eight-neighborhood method for judgment, there is a possibility of misjudgment, where adjacent non-zero pixels of the bifurcation point are identified as other types of bifurcation points. Figure 15 It can be seen that this bifurcation point should belong to a rotated Y-shaped bifurcation point. To address this situation, the Y-shaped bifurcation point is filtered out from the node identification results data using the two-neighborhood method. According to the two-neighborhood method, nodes with a neighboring pixel count of 2 are excluded, effectively eliminating false positives.

[0102] However, the two-neighborhood method obviously excludes T-shaped bifurcation points and cross-shaped intersection points. Therefore, we consider using the four-neighborhood method to filter out T-shaped bifurcation points and cross-shaped intersection points from the node identification results. When using the four-neighborhood method, a node is considered valid if the number of adjacent pixels is ≥3. (Refer to...) Figure 16 As shown, some of the non-zero pixel values ​​adjacent to pixel 3 are identified as bifurcation points. Here, only one bifurcation point is retained as needed. The rule for retaining the bifurcation point is to minimize the Harman Kardon distance between the bifurcation point and all its adjacent pixels. For example, refer to... Figure 17 As shown, pixel 4 is a T-shaped branch point, pixel 5 is a Y-shaped branch point, and pixel 6 is a Y-shaped branch point. Here, pixels 4, 5, and 6 are obtained by eliminating the rotation of L-shaped branch points.

[0103] The four-neighborhood method determines the value of a pixel by considering its four neighboring areas: the top, bottom, left, and right sides of the pixel, resulting in a total of four non-zero pixels.

[0104] Similar to the four-neighborhood rule, the two-neighborhood rule only considers two non-zero pixels in the horizontal (left-right) or vertical (up-down) direction.

[0105] It is understood that those skilled in the art can adjust and select the above-mentioned node determination scheme as needed, and no restrictions are imposed here.

[0106] 404. Based on the coordinate information of each blood vessel feature point in the second blood vessel mask image, determine the feature information of the blood vessel contour.

[0107] Specifically, the distance from each endpoint to the nearest connected node can be determined based on a search algorithm, thus obtaining the length of each bloodline bifurcation. For example, refer to... Figure 22 As shown, the mask image contains contours composed of three bloodline branches. The length from the end point to the nearest bifurcation point or intersection point in each contour is determined by the number of non-zero pixels connected between two pixels. Then, the length of all bifurcation bloodlines can be determined by the breadth-first search algorithm of the priority queue (min-heap).

[0108] Then, based on the length threshold, the length of each blood vessel bifurcation, and the number of nodes, the number of blood vessel bifurcations is determined. The number of blood vessel bifurcations can be determined by the number of nodes. Here, to avoid repeatedly calculating the same bifurcation, the nearest feature point is used to calculate a bifurcation. At the same time, the length threshold of the bifurcation blood vessels is determined as needed, and some shorter blood vessel bifurcations, especially those with spurs, can be removed.

[0109] Finally, based on the minimum bounding rectangle of the blood vessel bifurcation, the angle between adjacent blood vessel bifurcations at the same node is determined. See the attached diagram for details. Figure 22 The diagram shows a connected blood vessel formed by a bifurcation point or intersection point and an end point. The corresponding minimum bounding rectangle is calculated. The bifurcation angle can be calculated from the longer side of the minimum bounding rectangle corresponding to the two end points and the common bifurcation point or intersection point.

[0110] This blood vessel feature recognition method eliminates the need for manual pre-marking of bifurcation and intersection points. By combining terminal points and nodes, it can more accurately obtain information such as the number and angle of the main blood vessels and their bifurcations. It combines two-domain, four-domain, and eight-domain methods to remove falsely identified bifurcation and intersection points, thereby improving the accuracy and reliability of blood vessel feature recognition.

[0111] In some specific embodiments, when identifying feature points based on feature point recognition rules, the specific process of refining the blood vessel mask image is as follows: Figure 19 The image shown is the blood vessel mask before refinement. Figure 20 The refined blood vessel mask shows that at pixels 8 and 10, the refinement has resulted in two adjacent nodes. These can be merged as needed, as this does not affect the determination of the number of branches and can be handled on a case-by-case basis. At pixels 7 and 9, misjudged branching and termination points occur due to the refinement of thicker blood vessels. These can be excluded by setting a threshold based on the maximum blood vessel width.

[0112] Furthermore, when using the eight-neighborhood method to identify intersections, the criterion is that if there are more than four adjacent non-zero pixels, it can be identified as an intersection. However, referring to... Figure 18 As shown, the intersection of this shape does not satisfy this condition. Therefore, we can directly determine whether there are four branches that cannot be on the same side. That is, we can further classify whether it is a branching point or an intersection point based on the number of adjacent feature points of the node. If the number of adjacent feature points is ≥4, then paths with significant overlap between adjacent feature points can only be counted as one, and the node and its adjacent feature points are not on the same side, then it can be considered an intersection point; otherwise, it is a branching point. Figure 20As shown, pixel 9 is a typical intersection point. However, for intersection points that become two separate points due to thinning, such as pixels 8 and 10 (which are similar), merging is considered. To avoid misjudgment, merging is performed based on the characteristics of the intersection points. To demonstrate a general effect, as shown... Figure 21 As shown, this diagram illustrates the effect of blood vessel bifurcation recognition before refinement, without merging, under a more complex original blood vessel mask image.

[0113] The above describes a blood vessel feature recognition method provided by the embodiments of this application. The following describes the apparatus for performing the above blood vessel feature recognition method.

[0114] Please see Figure 23 , Figure 23 This is a schematic diagram of a blood vessel feature recognition device provided in an embodiment of this application. Figure 23 As shown, the blood vessel feature recognition device includes:

[0115] The blood vessel image extraction module 2301 is used to process the obtained sclera region image based on the blood vessel segmentation algorithm to obtain the first blood vessel mask image of the sclera region.

[0116] The blood vessel image thinning module 2302 is used to thin the blood vessels in the first blood vessel mask image to obtain the second blood vessel mask image.

[0117] The feature point determination module 2303 is used to identify blood vessel pixels in the second blood vessel mask image based on the neighborhood method and feature point recognition rules to obtain blood vessel feature points.

[0118] The feature information extraction module 2304 is used to determine the feature information of the blood vessel contour based on the coordinate information of each blood vessel feature point in the second blood vessel mask image.

[0119] In one possible implementation, it also includes: a sclera region recognition module, used before processing the acquired sclera region image based on the blood vessel segmentation algorithm to obtain the first blood vessel mask map of the sclera region:

[0120] The acquired eye image is masked to obtain an eye mask image;

[0121] Based on the shape of the sclera region in the eye mask image, the sclera region image is separated from the eye image.

[0122] In one possible implementation, the feature points include: the terminal points and nodes of the blood vessels. The feature point determination module 2303 performs recognition processing on the blood vessel pixels in the second blood vessel mask image based on the neighborhood method and feature point recognition rules to obtain the blood vessel feature points, including:

[0123] Based on the eight-neighbor method, the blood vein pixels in the second blood vein mask image are identified to obtain the identification result data of the end point and the identification result data of the node.

[0124] The identification result data of the nodes is filtered based on the two-domain method, the four-domain method, and the feature point identification rules.

[0125] In one possible implementation, the node includes a branching point and an intersection point. The feature point determination module 2303 filters the identification result data of the node based on the two-neighborhood method, the four-neighborhood method, and the feature point identification rules, including:

[0126] Y-shaped bifurcation points are filtered out from the node identification result data based on the two-neighborhood method.

[0127] Based on the four-domain method, T-shaped bifurcation points and cross-shaped intersection points are filtered out from the node identification result data.

[0128] In one possible implementation, the node includes a branching point and an intersection point. The process by which the feature point determination module 2303 filters the identification result data of the node based on the two-neighborhood method, the four-neighborhood method, and the feature point identification rules also includes:

[0129] If a target node exists in the node identification result data and the nodes adjacent to the target node are not on the same side, then the target node is determined as an intersection point. The target node is a node with no less than 4 adjacent nodes.

[0130] In one possible implementation, the feature point determination module 2303 is further configured to, when filtering out T-shaped bifurcation points from the node identification result data based on the four-neighborhood method, if all adjacent pixels are identified as T-shaped bifurcation points, then the pixel with the smallest Harmanton distance to the adjacent pixels is determined as the T-shaped bifurcation point.

[0131] In one possible implementation, the blood vessel feature points include: end points and nodes. The feature information extraction module 2304 determines the feature information of the blood vessel contour based on the coordinate information of each of the blood vessel feature points in the second blood vessel mask image, including:

[0132] The distance from each terminal point to the nearest connected node is determined based on the search algorithm, and the length of each blood vessel branch is obtained.

[0133] The number of blood vessel bifurcations is determined based on the length threshold, the length of each blood vessel bifurcation, and the number of nodes.

[0134] Based on the minimum bounding rectangle of the blood vessel bifurcation, the angle between adjacent blood vessel bifurcations at the same node is determined.

[0135] This application also provides an electronic device in its embodiments. (See reference...) Figure 24 The diagram illustrates a structural schematic suitable for implementing the electronic device in the embodiments of this application. The electronic device in the embodiments of this application may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 24 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0136] like Figure 24 As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processor, etc.) 2401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 2402 or a program loaded from a storage device 2408 into a random access memory (RAM) 2403. When the electronic device is powered on, the RAM 2403 also stores various programs and data required for the operation of the electronic device. The processing unit 2401, ROM 2402, and RAM 2403 are interconnected via a bus 2404. An input / output (I / O) interface 2405 is also connected to the bus 2404.

[0137] Typically, the following devices can be connected to I / O interface 2405: input devices 2406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 2407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 2408 including, for example, memory cards, hard drives, etc.; and communication devices 2409. Communication device 2409 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 24 Electronic devices with various devices have been demonstrated; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0138] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the blood vessel feature recognition methods provided in this application.

[0139] This application also provides a computer-readable storage medium carrying one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the blood vessel feature recognition methods provided in this application.

[0140] It should also be noted that the device embodiments described above are merely illustrative. The units described 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 the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0141] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0142] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0143] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

Claims

1. A blood vessel feature recognition method characterized by comprising: include: The obtained scleral region image is processed based on the blood vessel segmentation algorithm to obtain the first blood vessel mask image of the scleral region. The blood vessels in the first blood vessel mask image are refined to obtain the second blood vessel mask image; Based on the domain method and feature point recognition rules, the blood vein pixels in the second blood vein mask are identified to obtain blood vein feature points. Based on the coordinate information of each blood vessel feature point in the second blood vessel mask image, the feature information of the blood vessel contour is determined.

2. The blood vessel feature recognition method according to claim 1, characterized by, Before processing the obtained scleral region image based on the blood vessel segmentation algorithm to obtain the first blood vessel mask map of the scleral region, the following steps are also included: The acquired eye image is masked to obtain an eye mask image; Based on the shape of the sclera region in the eye mask image, the sclera region image is separated from the eye image.

3. The blood vessel feature recognition method according to claim 1, characterized by, The feature points include: the terminal points and nodes of blood vessels. The blood vessel pixels in the second blood vessel mask image are identified based on the neighborhood method and feature point recognition rules to obtain blood vessel feature points, including: Based on the eight-neighbor method, the blood vein pixels in the second blood vein mask image are identified to obtain the identification result data of the end point and the identification result data of the node. The identification result data of the nodes is filtered based on the two-domain method, the four-domain method, and the feature point identification rules.

4. The blood vessel feature recognition method according to claim 3, characterized in that, The nodes include branching points and intersection points. The filtering process for the node identification result data based on the two-neighborhood method, the four-neighborhood method, and the feature point identification rules includes: Y-shaped bifurcation points are filtered out from the node identification result data based on the two-neighborhood method. Based on the four-domain method, T-shaped bifurcation points and cross-shaped intersection points are filtered out from the node identification result data.

5. The blood vessel feature recognition method according to claim 4, characterized in that, The nodes include branching points and intersection points. The filtering of the node identification result data based on the two-neighborhood method, the four-neighborhood method, and the feature point identification rules further includes: If a target node exists in the node identification result data and the nodes adjacent to the target node are not on the same side, then the target node is determined as an intersection point. The target node is a node with no less than 4 adjacent nodes.

6. The blood vessel feature recognition method according to claim 4, characterized in that, When filtering out T-shaped bifurcation points from the node identification result data based on the four-neighborhood method, if all adjacent pixels are identified as T-shaped bifurcation points, then the pixel with the smallest Harmanton distance to its adjacent pixels is determined as the T-shaped bifurcation point.

7. The blood vessel feature recognition method according to any one of claims 1 to 6, characterized in that, The blood vessel feature points include: end points and nodes. Based on the coordinate information of each blood vessel feature point in the second blood vessel mask image, the feature information of the blood vessel contour is determined, including: The distance from each terminal point to the nearest connected node is determined based on the search algorithm, and the length of each blood vessel branch is obtained. The number of blood vessel bifurcations is determined based on the length threshold, the length of each blood vessel bifurcation, and the number of nodes. Based on the minimum bounding rectangle of the blood vessel bifurcation, the angle between adjacent blood vessel bifurcations at the same node is determined.

8. A blood vessel feature recognition apparatus characterized by comprising: include: The blood vessel image extraction module is used to process the acquired sclera region image based on the blood vessel segmentation algorithm to obtain the first blood vessel mask image of the sclera region. The blood vessel image thinning module is used to thin the blood vessels in the first blood vessel mask image to obtain a second blood vessel mask image. The feature point determination module is used to identify blood vein pixels in the second blood vein mask image based on the neighborhood method and feature point recognition rules to obtain blood vein feature points; The feature information extraction module is used to determine the feature information of the blood vessel contour based on the coordinate information of each blood vessel feature point in the second blood vessel mask image.

9. An electronic device, comprising: It includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program to enable the electronic device to implement the blood vessel feature recognition method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that The storage medium carries one or more computer programs that, when executed by an electronic device, enable the electronic device to implement the blood vessel feature recognition method as described in any one of claims 1 to 7.

Images