Hair extraction system, method, and computer readable storage medium

Abstract

The application provides a hair extraction system, method and computer readable storage medium, and relates to the field of hair extraction. The hair extraction system comprises an initialization module, a high-frequency data processing module and a low-frequency hair extraction module; the initialization module is used for obtaining a target hair image from an image pool and performing regional division on the target hair image to obtain a plurality of hair extraction sub-regions; the high-frequency data processing module is used for obtaining the target hair image from the image pool and performing rough extraction on the target hair image to extract a hair image in the target hair image; and the low-frequency hair extraction module is used for obtaining the hair extraction sub-region and performing fine extraction on the target hair according to the hair extraction sub-region and the hair image. The hair extraction system provided by the embodiment of the application can realize rough extraction and fine extraction of the hair through the high-frequency module and the low-frequency module respectively, and can quickly and efficiently extract the hair.

Description

Technical Field

[0001] This application relates to the field of hair extraction, and more specifically, to a hair extraction system, method, and computer-readable storage medium. Background Technology

[0002] Hair transplantation typically involves extracting hair follicles from a specific area and then transplanting them to the target area using specialized needles. Therefore, hair extraction is a crucial part of the procedure; currently, the most common extraction method is to control the movement of a robotic arm to extract the target hair.

[0003] For hair transplant robots, the overall precision of multi-joint robotic arms usually cannot meet the precision requirements of hair extraction. In the field of medical devices, human-machine collaborative operation is generally used to improve the precision of hair extraction. However, human-machine collaboration is prone to introducing errors, which leads to a decrease in the precision of hair extraction. Furthermore, the current human-machine collaboration method has low hair extraction efficiency and the user experience needs to be improved. Summary of the Invention

[0004] The purpose of this application is to provide a hair extraction system, method, and computer-readable storage medium, which achieves coarse and fine extraction of hair through a high-frequency module and a low-frequency module respectively, enabling rapid and efficient hair extraction.

[0005] In a first aspect, embodiments of this application provide a hair extraction system, comprising: an initialization module, a high-frequency data processing module, and a low-frequency hair extraction module. The initialization module is used to acquire a target hair image from an image pool and divide the target hair image into regions to obtain multiple hair extraction sub-regions. The high-frequency data processing module is used to acquire the target hair image from the image pool and perform coarse extraction on the target hair image to extract the hair images within the target hair image. The low-frequency hair extraction module is used to acquire the hair extraction sub-regions and perform fine extraction of the target hair based on the hair extraction sub-regions and the hair images. With the cooperation of the high-frequency data processing module and the low-frequency hair extraction module, the computing power for local and global positioning is rationally allocated. The high-frequency data processing module handles local hair positioning, while the low-frequency hair extraction module handles global hair positioning, improving the processing capability of visually guided real-time video stream image data.

[0006] In the above implementation process, the hair extraction system provided in this application embodiment retrieves the target hair image from the image pool through the initialization module and divides the target hair image into regions; furthermore, the coarse extraction and fine extraction of hair are achieved through the cooperation of the high-frequency data processing module and the low-frequency hair extraction module. Using the hair extraction system provided in this application embodiment can greatly improve the accuracy and precision of hair extraction and enhance the user experience.

[0007] Optionally, in this embodiment, the low-frequency hair extraction module includes a matching submodule and a task creation submodule. During the process of refining the target hair based on the hair extraction sub-region and the hair image, the low-frequency extraction module is used to acquire images captured by at least two different cameras corresponding to the target hair image; the matching submodule is used to filter out the target hair corresponding to each hair extraction sub-region based on the hair extraction sub-region, the hair image, and the images captured by at least two different cameras, and calculate the number of hairs extracted from each hair sub-region based on the target hair; the task creation submodule is used to create a hair extraction task based on the target hair and the number of hairs extracted; wherein the length of the linear list of the hair extraction task is consistent with the number of hairs extracted.

[0008] In the above implementation process, the low-frequency hair extraction module in the hair extraction system provided in this application embodiment includes a matching submodule and a task creation submodule; during the fine extraction process, the matching submodule obtains the matching relationship, and the task creation module creates the corresponding hair extraction task. With the cooperation of the matching submodule and the task creation submodule, hair extraction tasks corresponding to sub-regions can be created quickly.

[0009] Optionally, in this embodiment, the low-frequency hair extraction module further includes a pose acquisition submodule. After creating a hair extraction task based on the target hair and the number of hairs to be extracted, the pose acquisition submodule is used to acquire images captured by at least two different shooting devices corresponding to each target hair from the image pool in the linear list order of the hair extraction task, and to acquire the hair coordinates of each target hair based on the images captured by the at least two different shooting devices; wherein, the hair coordinates include the root coordinates and tip coordinates of the target hair.

[0010] In the above implementation process, the low-frequency hair extraction module in the hair extraction system provided in this application embodiment also includes a pose acquisition submodule; the pose acquisition module performs coordinate transformation on the target hair, thereby obtaining the root coordinates and tip coordinates of the target hair, realizing accurate acquisition of the target hair pose and improving the accuracy of target hair extraction.

[0011] Optionally, in this embodiment, the low-frequency hair extraction module further includes a safety coordinate acquisition module and a hair extraction submodule. After acquiring the hair coordinates of each target hair based on images captured by at least two different imaging devices, the safety coordinate acquisition module is used to acquire the hair vector in three-dimensional coordinates based on the hair coordinates. The direction of the hair vector is from the root of the target hair to the tip. The safety coordinate acquisition module is used to convert the hair vector into a safety coordinate point in the robotic arm's base coordinate system. The robotic arm is used to perform the hair extraction operation. The hair extraction submodule is used to control the robotic arm to move to the safety coordinate point and control the robotic arm to perform the hair extraction operation on the target hair.

[0012] In the above implementation process, the safety coordinate acquisition module and the hair extraction submodule of the hair extraction system respectively calculate the safety coordinate points and control the robotic arm to perform hair extraction operations; due to the existence of the safety coordinate acquisition module, the robotic arm stops at a safe position every time, ensuring the consistency and safety of each hair extraction operation.

[0013] Optionally, in this embodiment, the hair extraction submodule includes a correction unit; during the process of controlling the robotic arm to move to a safe coordinate point and controlling the robotic arm to perform hair extraction on the target hair, the correction unit is used to obtain the pin coordinates of the hair extraction needle tip controlled by the robotic arm in images captured by imaging devices at at least two different positions after the hair extraction submodule controls the robotic arm to move to the safe coordinate point; the correction unit is used to calculate the pixel distance between the pin coordinates and the hair root coordinates, and determine whether the pixel distance meets the preset requirements; the hair extraction submodule is used to control the robotic arm to perform hair extraction on the target hair when the pixel distance meets the preset requirements.

[0014] In the above implementation process, after the robotic arm moves to the safe coordinate point, the correction unit acquires the image of the needle tip in the left and right cameras, and determines whether the distance between the needle tip coordinate and the hair root coordinate meets the preset requirements based on the needle tip coordinate in the left and right cameras. If the preset requirements are met, the robotic arm can be controlled to perform hair extraction operation on the target hair. In other words, the hair extraction system in this embodiment determines whether the robotic arm meets the requirements for hair extraction through the correction unit of the hair extraction submodule; by judging the distance between the needle tip coordinate and the hair root coordinate, it accurately controls whether the robotic arm performs hair extraction operation, ensuring accurate needle placement of the robotic arm. This not only improves the efficiency of hair extraction and ensures the yield of hair extraction, but also greatly enhances the user experience.

[0015] Optionally, in this embodiment, the correction unit is further configured to acquire the needle tip coordinates in images captured by imaging devices at at least two different positions when the pixel distance does not meet the preset requirements; the correction unit is further configured to acquire the correction distance of the correction robot arm based on the needle tip coordinates and the lower needle coordinates; the correction unit is further configured to correct the pose of the robot arm based on the correction distance; the correction unit is further configured to reacquire the lower needle coordinates in images captured by imaging devices at at least two different positions, and determine again whether the pixel distance between the lower needle coordinates and the hair root coordinates meets the preset requirements; the hair extraction submodule is further configured to abandon the extraction of target hair when the pixel distance between the lower needle coordinates and the hair root coordinates still does not meet the preset requirements.

[0016] In the above implementation process, when the pixel distance does not meet the preset requirements, the correction unit is also used to correct the pose of the robotic arm based on the needle tip coordinates and the needle placement coordinates; after correction, it is determined again whether the pixel distance meets the requirements. If it meets the preset requirements, the hair extraction operation is performed on the target hair; if it does not meet the preset requirements, the hair extraction operation on the target hair is abandoned. Using the hair extraction system provided in this application embodiment, the pose of the robotic arm can be corrected before the hair extraction operation is performed to ensure accurate needle placement.

[0017] Optionally, in this embodiment, after the target hair is finely extracted based on the hair extraction sub-region and the hair image, the high-frequency data processing module is further used to cover the position corresponding to the target hair after the hair extraction operation is performed on the hair image and update the target hair image.

[0018] In the above implementation process, the high-frequency data processing module in the hair extraction system provided in this application embodiment can refresh the data in real time, cover the area where hair extraction operation has been performed, and perform hair extraction operation in the updated target area; and the high-frequency data processing module can also discard data that has not been used for a long time, which can not only improve the system's response speed, but also improve the accuracy of hair extraction.

[0019] Optionally, in this embodiment, the high-frequency data processing module is further configured to acquire in real time the order in which each target hair in each hair image is subjected to hair extraction operation, and update the current target hair according to the order.

[0020] In the above implementation process, the hair extraction system provided in this application embodiment continuously updates the tracked target and the target hair on the processed target image through the high-frequency data processing module; it can organize the data in a timely manner, and the hair extraction system provided in this application embodiment can maintain the system response efficiency, thereby achieving efficient hair extraction operation.

[0021] Optionally, in this embodiment of the application, the system further includes an image acquisition module; the image acquisition module is used to acquire multiple hair images and store the multiple hair images in an image pool; wherein, the image pool is a shared resource storage pool.

[0022] In the above implementation process, the embodiments of this application use an image pool to store shared resources. The initialization module, the high-frequency data processing module, and the low-frequency data retrieval module can all directly retrieve images from the image pool. By setting up the image pool, each module can share image resources, thereby improving the efficiency of hair extraction.

[0023] Optionally, in this embodiment of the application, the high-frequency data processing module and the low-frequency hair extraction module are specifically used to simultaneously extract hair from multiple hair images.

[0024] In the above implementation process, the high-frequency data processing module and the low-frequency extraction module of this application embodiment work synchronously, and there is data interaction between the two as described above; by using the high-frequency data processing module and the low-frequency extraction module to realize coarse and fine hair extraction respectively, and the real-time data interaction between the two can improve the overall efficiency of hair extraction.

[0025] Secondly, embodiments of this application provide a hair extraction method, which is applied to a hair extraction system including an initialization module, a high-frequency data processing module, and a low-frequency hair extraction module. The hair extraction method includes: the initialization module acquiring a target hair image from an image pool and dividing the target hair image into regions to obtain multiple hair extraction sub-regions; the high-frequency data processing module acquiring the target hair image from the image pool and performing coarse extraction on the target hair image to extract hair images from the target hair image; and the low-frequency hair extraction module acquiring the hair extraction sub-regions and performing fine extraction on the target hair based on the hair extraction sub-regions and the hair image.

[0026] Thirdly, embodiments of this application provide an electronic device, which includes a memory and a processor. The memory stores program instructions, and when the processor reads and runs the program instructions, it executes the steps in the implementation of the second aspect described above.

[0027] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer program instructions, which, when read and executed by a processor, perform the steps in the second aspect of the implementation described above. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a schematic diagram of the first module of the hair extraction system provided in an embodiment of this application;

[0030] Figure 2 This is a schematic diagram of the second module of the hair extraction system provided in the embodiments of this application;

[0031] Figure 3 A flowchart for hair extraction provided in an embodiment of this application;

[0032] Figure 4This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0033] Icons: Hair Extraction System - 100; Initialization Module - 110; High-Frequency Data Processing Module - 120; Low-Frequency Hair Extraction Module - 130; Matching Submodule - 131; Task Creation Submodule - 132; Pose Acquisition Submodule - 133; Safe Coordinate Acquisition Module - 134; Hair Extraction Submodule - 135; Correction Unit - 1351; Image Acquisition Module - 140. Detailed Implementation

[0034] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings. For example, the flowcharts and block diagrams in the drawings illustrate the architecture, functions, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or part of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions. In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0035] During the research process, the applicant discovered that for hair extraction robots, the overall precision of the multi-joint robotic arm could not reach 0.1mm, resulting in insufficient accuracy in hair extraction. Therefore, it is necessary to use other closed-loop methods to enable the multi-joint robotic arm to continuously move to different targets with a precision of 0.1mm.

[0036] In the field of medical devices, human-machine collaborative operation is generally used to improve the accuracy of hair extraction; however, human-machine collaboration is prone to introducing errors, which leads to a decrease in the accuracy of hair extraction.

[0037] Based on this, the hair extraction system provided in this application compensates for the motion error of the robotic arm through a visual method. This not only lowers the threshold for medical treatment but also allows the device to operate freely for hair extraction through visual processing, thereby achieving an extraction accuracy of 0.1mm or less. The 0.1mm accuracy effectively limits the diameter of the extraction needle, improving both the efficiency and accuracy of hair extraction while minimizing wounds on the patient and greatly aiding postoperative recovery.

[0038] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the first module of the hair extraction system 100 provided in the embodiments of this application; the hair extraction system 100 includes an initialization module 110, a high-frequency data processing module 120 and a low-frequency hair extraction module 130.

[0039] The initialization module 110 is used to obtain the target hair image from the image pool and to divide the target hair image into regions to obtain multiple hair extraction sub-regions.

[0040] In the above implementation process, the initialization module 110 is used to acquire the target hair image from the image pool, and to divide the target hair image into regions to obtain multiple hair extraction sub-regions. It should be noted that the target hair image can be understood as the target region for which hair extraction is desired. Dividing this region into several sub-regions allows for the initial division of the large area for hair extraction. Dividing it into several sub-regions and then further extracting from them improves the accuracy of hair extraction. For example, the region division can be achieved through methods such as rasterization or meshing, which can divide the overall region into several sub-regions.

[0041] The high-frequency data processing module 120 is used to acquire the target hair image from the image pool and perform coarse extraction on the target hair image to extract the hair image from the target hair image. The low-frequency hair extraction module 130 is used to acquire the hair extraction sub-region and perform fine extraction on the target hair based on the hair extraction sub-region and the hair image.

[0042] In the above implementation process, the hair extraction system 100 has two main execution modules: a high-frequency data processing module 120 and a low-frequency hair extraction module 130. The high-frequency data processing module 120 primarily performs coarse extraction of the target hair image, while the low-frequency hair extraction module 130 primarily performs fine extraction of the hair. The coarse extraction system of the hair extraction system 100 provided in this embodiment achieves both coarse and fine hair extraction through the cooperation of the high-frequency data processing module 120 and the low-frequency hair extraction module 130. With the cooperation of the high-frequency data processing module and the low-frequency hair extraction module, the computing power for local and global positioning is rationally allocated. The high-frequency data processing module handles local hair positioning, while the low-frequency hair extraction module handles global hair positioning, improving the processing capability of real-time video stream image data for visual guidance. Under the same sampling frequency conditions, the real-time performance of the video stream is improved.

[0043] pass Figure 1 As can be seen, the hair extraction system 100 provided in this application embodiment retrieves the target hair image from the image pool through the initialization module 110 and divides the target hair image into regions; furthermore, the high-frequency data processing module 120 and the low-frequency hair extraction module 130 work together to achieve coarse and fine extraction of hair. Using the hair extraction system 100 provided in this application embodiment can greatly improve the accuracy and precision of hair extraction and enhance the user experience.

[0044] Please refer to Figure 2 , Figure 2 This is a schematic diagram of the second module of the hair extraction system 100 provided in the embodiments of this application; wherein, the low-frequency hair extraction module 130 includes a matching submodule 131 and a task creation submodule 132.

[0045] Following on from the previous text, during the process of refining the target hair based on the hair extraction sub-region and the hair image, the low-frequency extraction module is used to acquire images captured by at least two different imaging devices corresponding to the target hair image.

[0046] It should be noted that, typically, a hair extraction machine includes two or more image capturing devices. The number of capturing devices greatly affects the accuracy of hair extraction. This application embodiment uses the processing of images acquired by the left and right capturing devices as an example to introduce the system function. In practical applications, the number of target images processed by the hair extraction system 100 can be adaptively adjusted, and the number of images processed by the system should not be a limitation on the protection scope of the hair extraction system 100 provided in this application embodiment.

[0047] The matching submodule 131 is used to filter out the target hair corresponding to each hair extraction subregion based on the hair extraction subregion, the hair image, and images captured by at least two different imaging devices, and to calculate the number of hairs extracted from the hair subregion based on the target hair.

[0048] In the above implementation process, the matching submodule 131 filters out the target hair corresponding to each hair extraction sub-region, calculates the total amount of target hair in the sub-region, and uses it as the hair extraction quantity for the hair sub-region.

[0049] The task creation submodule 132 is used to create a hair extraction task based on the target hair and the number of hairs to be extracted; wherein the length of the linear list of the hair extraction task is the same as the number of hairs to be extracted.

[0050] In the above implementation process, the task creation submodule 132 in the low-frequency hair extraction module 130 creates a hair extraction task based on the target hair and the number of target hairs to be extracted. It should be noted that the length of the linear list of the hair extraction task is the same as the number of hairs to be extracted; the linear list can be a stack or a queue; those skilled in the art can implement corresponding processing methods according to different types of linear lists, which will not be elaborated here.

[0051] After a hair extraction task is established, each target hair becomes the target for hair extraction. When the task is executed, the target number can be incremented to update the target hair for which hair extraction is to be performed.

[0052] pass Figure 2 As can be seen, the low-frequency hair extraction module 130 in the hair extraction system 100 provided in this application embodiment includes a matching submodule 131 and a task creation submodule 132; during the fine extraction process, the matching submodule 131 obtains the matching relationship, and the task creation module creates the corresponding hair extraction task. With the cooperation of the matching submodule 131 and the task creation submodule 132, hair extraction tasks corresponding to sub-regions can be created quickly.

[0053] Please continue reading. Figure 2 The low-frequency hair extraction module 130 in the hair extraction system 100 provided in this application embodiment also includes a pose acquisition submodule 133.

[0054] After creating a hair extraction task based on the target hair and the number of hairs to be extracted, the pose acquisition submodule 133 is used to acquire images captured by at least two different shooting devices corresponding to each target hair from the image pool in the order of the linear list of the hair extraction task, and to acquire the hair coordinates of each target hair based on the images captured by at least two different shooting devices; wherein, the hair coordinates include the root coordinates and tip coordinates of the target hair.

[0055] In the above implementation process, after creating the hair extraction task, the pose acquisition submodule acquires images of the same target hair from the left camera device and the right camera device according to the order of the linear list. The root coordinates and tip coordinates of each target hair are calculated from the two images acquired by the first camera device and the second camera device symmetrically set with the first camera device (e.g., the left camera device and the right camera device, or the top camera device and the bottom camera device).

[0056] For example, after calibrating the image acquisition device, the three-dimensional coordinates of the hair root and hair tip in the camera coordinate system can be obtained, and then the three-dimensional coordinates of the hair root and hair tip in the robot arm base coordinate system can be obtained based on the hand-eye calibration results.

[0057] Therefore, it can be seen that the low-frequency hair extraction module 130 in the hair extraction system 100 provided in this application embodiment also includes a pose acquisition submodule 133; by performing coordinate transformation on the target hair through the pose acquisition module, the root coordinates and tip coordinates of the target hair are obtained, thereby realizing the accurate acquisition of the pose of the target hair and improving the accuracy of target hair extraction.

[0058] Please continue reading. Figure 2 In an optional embodiment of this application, the low-frequency hair extraction module 130 further includes a safety coordinate acquisition module 134 and a hair extraction submodule 135.

[0059] After acquiring the hair coordinates of each target hair based on images captured by imaging devices at at least two different locations, the safety coordinate acquisition module 134 is used to acquire a hair vector in three-dimensional coordinates based on the hair coordinates; wherein the direction of the hair vector is from the root of the target hair to the tip. The safety coordinate acquisition module 134 is used to convert the hair vector into a safety coordinate point in the robotic arm's base coordinate system; wherein the robotic arm is used to perform the hair extraction operation. The hair extraction submodule 135 is used to control the robotic arm to move to the safety coordinate point and control the robotic arm to perform the hair extraction operation on the target hair.

[0060] In the above implementation process, the safety coordinate acquisition module 134 converts the hair vector of the target hair in the three-dimensional coordinate system into a safety coordinate point in the base coordinate system of the robotic arm; this point is the safety coordinate point of the robotic arm, and the robotic arm stops at this safety coordinate point before each hair extraction; further, the hair extraction submodule 135 controls the robotic arm to perform hair extraction operation with the safety coordinate point as the starting point.

[0061] Therefore, the safety coordinate acquisition module 134 and the hair extraction submodule 135 of the hair extraction system 100 respectively calculate the safety coordinate points and control the robotic arm to perform the hair extraction operation. Due to the existence of the safety coordinate acquisition module 134, the robotic arm stops at a safe position every time, ensuring the consistency and safety of each hair extraction operation.

[0062] Please continue reading. Figure 2 The hair extraction submodule 135 includes a correction unit 1351.

[0063] During the process of controlling the robotic arm to move to a safe coordinate point and performing hair extraction, the correction unit 1351 is used to acquire the pin coordinates of the hair extraction needle tip controlled by the robotic arm in images captured by imaging devices at at least two different positions after the hair extraction submodule 135 controls the robotic arm to move to the safe coordinate point. The correction unit 1351 is used to calculate the pixel distance between the pin coordinates and the hair root coordinates, and determine whether the pixel distance meets the preset requirements. The hair extraction submodule 135 is used to control the robotic arm to perform hair extraction on the target hair when the pixel distance meets the preset requirements.

[0064] For example, after inserting the needle, the needle tip is positioned at point P2 in the left and right diagrams, and at point P0 at the hair root. The distance between P0 and P2 is calculated. If the distance between P0 and P2 meets a preset requirement, a hair-picking operation can be performed, for example, D. P0-P2 The distance between P0 and P2 is less than a preset number of pixel units; wherein, the preset number of pixel units can range from 4 to 6 pixel units (4-6 pixels); if D P0-P2 Within a preset number of pixels, the robotic arm can be controlled to perform hair extraction operations.

[0065] Therefore, after the robotic arm moves to the safe coordinate point, the correction unit 1351 acquires the image of the needle tip in the left and right cameras, and determines whether the distance between the needle tip coordinate and the hair root coordinate meets the preset requirements based on the needle tip coordinate in the left and right cameras. If the preset requirements are met, the robotic arm can be controlled to perform hair extraction operation on the target hair. In other words, the hair extraction system 100 in this embodiment determines whether the robotic arm meets the requirements for hair extraction through the correction unit 1351 of the hair extraction submodule 135; by judging the distance between the needle tip coordinate and the hair root coordinate, it accurately controls whether the robotic arm performs hair extraction operation, ensuring accurate needle placement of the robotic arm, which not only improves the efficiency of hair extraction, but also greatly enhances the user experience.

[0066] In an optional embodiment, the correction unit 1351 is further configured to acquire the needle tip coordinates in images captured by imaging devices at at least two different positions when the pixel distance does not meet the preset requirements; the correction unit 1351 is further configured to acquire the correction distance of the correction robot arm based on the needle tip coordinates and the down needle coordinates; the correction unit 1351 is further configured to correct the pose of the robot arm based on the correction distance; the correction unit 1351 is further configured to reacquire the down needle coordinates in images captured by imaging devices at at least two different positions, and determine again whether the pixel distance between the down needle coordinates and the hair root coordinates meets the preset requirements; the hair extraction submodule 135 is further configured to abandon the extraction of target hair when the pixel distance between the down needle coordinates and the hair root coordinates still does not meet the preset requirements.

[0067] For example, after inserting the needle, the needle tip is positioned at point P2 in the left and right diagrams, and at point P0 at the hair root. The distance between P0 and P2 is calculated. If the distance between P0 and P2 meets a preset requirement, a hair-picking operation can be performed, for example, D. P0-P2 If the distance is greater than 4-6 pixels, the position of the needle tip at the safe coordinate point P1 is obtained, and the distance between P1 and P2 is calculated, which is the correction distance. The pose of the robotic arm is corrected using the distance between P1 and P2. After pose correction, the distance between P0 and P2 is obtained again, and D is judged again. P0-P2 The relationship between the target hair and the preset requirements is such that if the preset requirements are met, the robotic arm can be controlled to perform hair extraction; if the preset requirements are not met, the extraction of hair from the target hair is abandoned, and the extraction of hair from the next target hair is performed.

[0068] Therefore, when the pixel distance does not meet the preset requirements, the correction unit 1351 is also used to correct the pose of the robotic arm based on the needle tip coordinates and the needle placement coordinates. After correction, it is determined again whether the pixel distance meets the requirements. If it meets the preset requirements, the hair extraction operation is performed on the target hair. If it does not meet the preset requirements, the hair extraction operation on the target hair is abandoned. Using the hair extraction system 100 provided in this application embodiment, the pose of the robotic arm can be corrected before the hair extraction operation is performed to ensure accurate needle placement.

[0069] In an optional embodiment, after refining the target hair based on the hair extraction sub-region and the hair image, the high-frequency data processing module 120 is further configured to mask the position corresponding to the target hair after the hair extraction operation is performed on the hair image and update the target hair image.

[0070] It should be understood that after fine extraction of a specific target hair, high-frequency data processing will mask the position of the target hair that has already undergone hair extraction, and then update the target hair image after masking; the masking operation can be performed by setting a mask.

[0071] The high-frequency data processing module 120 can promptly clean up data that has not been used for a long time, thereby improving the system's response efficiency.

[0072] Therefore, it can be seen that the high-frequency data processing module 120 in the hair extraction system 100 provided in this application embodiment can refresh the data in real time, cover the area where the hair extraction operation has been performed, and perform the hair extraction operation in the updated target area; and the high-frequency data processing module 120 can also discard data that has not been used for a long time, which can not only improve the system's response speed, but also improve the accuracy of hair extraction.

[0073] In an optional embodiment, the high-frequency data processing module 120 is further configured to acquire in real time the order in which hair extraction operations are performed on each target hair in each hair image, and update the current target hair according to the order. That is, the high-frequency data processing module 120 can acquire in real time the order in which hair extraction operations are performed on each target hair in each hair image, and continuously update the target hair that is about to undergo hair extraction operations.

[0074] Therefore, it can be seen that the hair extraction system 100 provided in this application embodiment realizes continuous updating of the tracked target and the target hair on the processed target image by the high-frequency data processing module 120; it can organize the data in a timely manner, and the hair extraction system 100 provided in this application embodiment can maintain the system response efficiency, thereby realizing the efficient performance of hair extraction operation.

[0075] Please continue reading. Figure 2 In an optional embodiment of this application, the hair extraction system 100 further includes an image acquisition module 140. The image acquisition module 140 is used to acquire multiple hair images and store the multiple hair images in an image pool; wherein, the image pool is a shared resource storage pool.

[0076] Therefore, it can be seen that the embodiments of this application use an image pool to store shared resources, and the initialization module 110, the high-frequency data processing module 120 and the low-frequency data retrieval module 130 can all directly retrieve images from the image pool; by setting up the image pool, each module can share image resources, thereby improving the efficiency of hair extraction.

[0077] In an optional embodiment, the high-frequency data processing module 120 and the low-frequency hair extraction module 130 are specifically used to simultaneously extract hair from multiple hair images.

[0078] Therefore, it can be seen that the high-frequency data processing module 120 and the low-frequency extraction module in this embodiment of the application work synchronously, and there is data interaction between the two as described above; the high-frequency data processing module 120 and the low-frequency extraction module 130 respectively realize coarse and fine hair extraction, and the real-time data interaction between the two can improve the overall efficiency of hair extraction.

[0079] Please refer to Figure 3 , Figure 3 A flowchart for hair extraction provided in this application embodiment; this application embodiment also provides a hair extraction method, which is applied to a hair extraction system including an initialization module, a high-frequency data processing module, and a low-frequency hair extraction module. The hair extraction method includes the following steps:

[0080] Step S100: The initialization module obtains the target hair image from the image pool and divides the target hair image into regions to obtain multiple hair extraction sub-regions.

[0081] In step S100 above, the initialization module acquires the target hair image from the image pool, divides the target hair image into regions, and obtains multiple hair extraction sub-regions. It should be noted that the target hair image can be considered as the target region for which hair extraction is desired. Dividing this region into several sub-regions allows for the initial division of the large region to be extracted; further extraction from these sub-regions improves the accuracy of hair extraction.

[0082] Step S101: The high-frequency data processing module obtains the target hair image from the image pool and performs coarse extraction on the target hair image to extract the hair image in the target hair image.

[0083] Step S102: The low-frequency hair extraction module obtains the hair extraction sub-region, and performs fine extraction of the target hair based on the hair extraction sub-region and the hair image.

[0084] In the above steps S101-S102, the hair extraction system uses two main execution modules: a high-frequency data processing module and a low-frequency hair extraction module. The high-frequency data processing module mainly performs coarse extraction of the target hair image, while the low-frequency hair extraction module mainly performs fine extraction of the hair. The hair extraction method provided in this application embodiment achieves coarse and fine extraction of hair through the cooperation of the high-frequency data processing module and the low-frequency hair extraction module.

[0085] Please see Figure 4 , Figure 4This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. An electronic device 300 provided in this application includes: a processor 301 and a memory 302. The memory 302 stores machine-readable instructions executable by the processor 301. When the machine-readable instructions are executed by the processor 301, the method described above is performed.

[0086] Based on the same inventive concept, embodiments of this application also provide a computer-readable storage medium storing computer program instructions, which, when read and executed by a processor, perform the steps in any of the above implementations.

[0087] The computer-readable storage medium can be any medium capable of storing program code, such as Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM). The storage medium stores the program, and the processor executes the program after receiving an execution instruction. The method executed by the electronic terminal as defined in any embodiment of this invention can be applied to the processor or implemented by the processor.

[0088] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0089] Furthermore, the units described as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0091] It can be replaced and can be implemented, wholly or partially, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, wholly or partially, in the form of a computer program product. 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 the present invention are generated.

[0092] 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, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0093] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0094] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A hair extraction system, characterized in that, The hair extraction system includes: an initialization module, a high-frequency data processing module, and a low-frequency hair extraction module; The initialization module is used to obtain a target hair image from the image pool and to divide the target hair image into regions to obtain multiple hair extraction sub-regions. The high-frequency data processing module is used to obtain the target hair image from the image pool and perform coarse extraction on the target hair image to extract the hair image in the target hair image; The low-frequency hair extraction module is used to acquire the hair extraction sub-region and perform fine extraction of the target hair based on the hair extraction sub-region and the hair image; the high-frequency data processing module and the low-frequency hair extraction module are specifically used to simultaneously extract hair from multiple hair images; The low-frequency hair extraction module also includes a safety coordinate acquisition module and a hair extraction submodule; After obtaining the hair coordinates of each target hair based on images captured by cameras at at least two different locations, The safety coordinate acquisition module is used to acquire a hair vector in three-dimensional coordinates based on the hair coordinates; wherein the direction of the hair vector is from the root of the target hair to the tip of the hair; The safety coordinate acquisition module is used to convert the hair vector into a safety coordinate point in the robot arm's base coordinate system; wherein, the robot arm is used to perform the hair extraction operation; The hair extraction submodule is used to control the robotic arm to move to the safe coordinate point and to control the robotic arm to perform hair extraction operation on the target hair. The high-frequency data processing module is also used to cover the position corresponding to the target hair after the hair extraction operation is performed on the hair image, and update the target hair image.

2. The system according to claim 1, characterized in that, The low-frequency acquisition and transmission module includes: a matching submodule and a task creation submodule; During the process of refining the target hair based on the hair extraction sub-region and the hair image The low-frequency extraction module is used to acquire images captured by at least two different cameras at the target hair image. The matching submodule is used to filter out the target hair corresponding to each hair extraction subregion based on the hair extraction subregion, the hair image, and the images captured by the imaging devices at at least two different locations, and to calculate the number of hairs extracted from the hair subregion based on the target hairs. The task creation submodule is used to create a hair extraction task based on the target hair and the number of hairs extracted; wherein the length of the linear list of the hair extraction task is the same as the number of hairs extracted.

3. The system according to claim 2, characterized in that, The low-frequency acquisition module also includes a pose acquisition submodule; After creating the hair extraction task based on the target hair and the number of hairs to be extracted, The pose acquisition submodule is used to acquire images captured by at least two different shooting devices corresponding to each target hair from the image pool in the linear order of the hair extraction task, and to acquire the hair coordinates of each target hair based on the images captured by the at least two different shooting devices; wherein, the hair coordinates include the root coordinates and tip coordinates of the target hair.

4. The system according to claim 1, characterized in that, The hair extraction submodule includes a correction unit; During the process of controlling the robotic arm to move to the safe coordinate point and controlling the robotic arm to perform hair extraction on the target hair, The correction unit is used to obtain the down-needle coordinates of the hair extraction needle tip controlled by the robotic arm in the images captured by the imaging devices at at least two different positions after the hair extraction submodule controls the robotic arm to move to the safe coordinate point. The correction unit is used to calculate the pixel distance between the lower needle coordinate and the hair root coordinate, and to determine whether the pixel distance meets the preset requirements; The hair extraction submodule is used to control the robotic arm to perform hair extraction on the target hair when the pixel distance meets the preset requirements.

5. The system according to claim 4, characterized in that, The correction unit is also used to obtain the needle tip coordinates in the images captured by the imaging devices at at least two different positions when the pixel distance does not meet the preset requirements. The correction unit is also used to obtain the correction distance for correcting the robotic arm based on the needle tip coordinates and the down needle coordinates; The correction unit is also used to correct the pose of the robotic arm based on the correction distance; The correction unit is also used to reacquire the lower pin coordinates in the images captured by the at least two different shooting devices, and to determine again whether the pixel distance between the lower pin coordinates and the hair root coordinates meets the preset requirements; The hair extraction submodule is also used to abandon the extraction of the target hair when the pixel distance between the needle coordinate and the hair root coordinate still does not meet the preset requirements.

6. The system according to claim 1, characterized in that, The high-frequency data processing module is also used to acquire in real time the order in which each target hair in each hair image is subjected to hair extraction operation, and to update the current target hair according to the order.

7. The system according to claim 1, characterized in that, The system also includes an image acquisition module; The image acquisition module is used to acquire multiple hair images and store the multiple hair images in an image pool; wherein, the image pool is a shared resource storage pool.

8. A method for hair extraction, characterized in that, The hair extraction method is applied to a hair extraction system that includes an initialization module, a high-frequency data processing module, and a low-frequency hair extraction module. The hair extraction method includes: The initialization module obtains a target hair image from the image pool and divides the target hair image into regions to obtain multiple hair extraction sub-regions. The high-frequency data processing module obtains the target hair image from the image pool and performs coarse extraction on the target hair image to extract the hair image from the target hair image; The low-frequency hair extraction module acquires the hair extraction sub-region and performs fine extraction of the target hair based on the hair extraction sub-region and the hair image, including: after acquiring the hair coordinates of each target hair based on images captured by at least two different imaging devices, acquiring a hair vector in three-dimensional coordinates based on the hair coordinates; wherein the direction of the hair vector is from the root to the tip of the target hair; converting the hair vector into a safe coordinate point in the robotic arm's base coordinate system; wherein the robotic arm is used to perform the hair extraction operation; controlling the robotic arm to move to the safe coordinate point, and controlling the robotic arm to perform the hair extraction operation on the target hair; The location corresponding to the target hair after the hair extraction operation is performed is masked on the hair image, and the target hair image is updated.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, perform the steps of the method of claim 8.

Images