Ventilator mask manufacturing parameter determination method and device, computer equipment and readable storage medium

Abstract

The application relates to a respirator mask manufacturing parameter determination method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: obtaining a face image of a target object, performing three-dimensional face reconstruction based on the face image to obtain a three-dimensional face model; performing face region segmentation on the three-dimensional face model to determine a mask region in the three-dimensional face model, and a nasal mask region and a mouth block region in the mask region; determining target size parameters of the mask region, the nasal mask region and the mouth block region respectively based on three-dimensional coordinates of face feature points in respective covered regions of the mask region, the nasal mask region and the mouth block region; and determining manufacturing parameters of a respirator mask according to the target size parameters of the mask region, the nasal mask region and the mouth block region. The respirator mask manufactured by the method can be fitted to the face of the target object, thereby avoiding air leakage of the respirator mask during use and improving the use effect of the respirator.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mask manufacturing, in particular to a breathing machine mask manufacturing parameter determination method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] In the process of using a breathing machine non-invasively, the user needs to wear a breathing machine mask (such as a mouth-nose mask or a nose mask) connected with a breathing pipeline to assist ventilation. The current breathing machine mask generally has several fixed sizes for the user to choose from, such as large, medium and small sizes. However, due to the different shapes of the faces of users, the fixed size of the breathing machine mask is difficult to fit all users, and the breathing machine mask with an inappropriate size may have the risk of air leakage during use, affecting the use effect of the breathing machine. Therefore, there is an urgent need for a breathing machine mask that can fit the face of a user and improve the use effect of the breathing machine. SUMMARY

[0003] Therefore, it is necessary to provide a breathing machine mask manufacturing parameter determination method, device, computer equipment, computer readable storage medium and computer program product, which can make the breathing machine mask fit the face of a user and improve the use effect of the breathing machine.

[0004] In a first aspect, the present application provides a breathing machine mask manufacturing parameter determination method, comprising:

[0005] obtaining a face image of a target object, performing three-dimensional reconstruction of the face based on the face image to obtain a three-dimensional face model; the three-dimensional face model includes three-dimensional coordinates of a plurality of face feature points in the face image;

[0006] performing face region segmentation on the three-dimensional face model to determine a mask region in the three-dimensional face model, and a nose mask region and a mouth block region in the mask region;

[0007] determining target size parameters of the mask region, the nose mask region and the mouth block region respectively based on the three-dimensional coordinates of the face feature points in the respective covered regions of the mask region, the nose mask region and the mouth block region;

[0008] determining manufacturing parameters of a breathing machine mask according to the target size parameters of the mask region, the nose mask region and the mouth block region.

[0009] In one of the embodiments, the face region segmentation on the three-dimensional face model to determine the mask region in the three-dimensional face model, and the nose mask region and the mouth block region in the mask region comprises:

[0010] performing face region segmentation on the three-dimensional face model according to a three-dimensional face structure composed of the face feature points in the three-dimensional face model to obtain a face region segmentation result;

[0011] According to the face region segmentation result, a mask region and a nose cover region in the mask region are determined in the face three-dimensional model;

[0012] Based on the face three-dimensional structure composed of the face feature points in the mask region, mouth cover region detection is performed in the mask region to determine the mouth cover region.

[0013] In one of the embodiments, according to the face three-dimensional structure composed of the face feature points in the face three-dimensional model, face region segmentation is performed on the face three-dimensional model to obtain the face region segmentation result, which includes:

[0014] The face three-dimensional model is input into the face region segmentation model, so that the face region segmentation model performs face region segmentation on the face three-dimensional model according to the face three-dimensional structure composed of the face feature points in the face three-dimensional model, and outputs the face region segmentation result;

[0015] The face region segmentation model is generated by the following method:

[0016] A data set including a plurality of preset face three-dimensional models is obtained; each preset face three-dimensional model has a labeled mask region and a nose cover region;

[0017] Based on the data set, the face region segmentation model is trained and obtained.

[0018] In one of the embodiments, based on the face three-dimensional structure composed of the face feature points in the mask region, mouth cover region detection is performed in the mask region to determine the mouth cover region, which includes:

[0019] An initial contour of the mouth cover region is obtained;

[0020] According to the initial contour of the mouth cover region and the face three-dimensional structure composed of the face feature points in the mask region, contour point detection is performed on the face feature points in the mask region to determine target feature points in the mask region that belong to the edge of the mouth cover region;

[0021] Based on the target feature points, the mouth cover region is determined.

[0022] In one of the embodiments, based on the three-dimensional coordinates of the face feature points in the respective regions covered by the mask region, the nose cover region and the mouth cover region, the target size parameters of the mask region, the nose cover region and the mouth cover region are respectively determined, which includes:

[0023] Based on the three-dimensional coordinates of the face feature points in the respective regions covered by the mask region, the nose cover region and the mouth cover region, the initial size parameters of the mask region, the nose cover region and the mouth cover region are respectively determined;

[0024] A size conversion ratio between the face three-dimensional model and the actual face of the target object is determined.

[0025] According to the size conversion ratio, the initial size parameters of the mask area, the nose cover area and the mouth cover area are converted to obtain the target size parameters of the mask area, the nose cover area and the mouth cover area.

[0026] In one of the embodiments, the manufacturing parameters of the respirator mask are determined according to the target size parameters of the mask area, the nose cover area and the mouth cover area, including:

[0027] The preset material thicknesses of the mask, the nose cover and the mouth cover in the respirator mask are obtained.

[0028] According to the preset material thicknesses of the mask, the nose cover and the mouth cover in the respirator mask, the target size parameters of the mask area, the nose cover area and the mouth cover area are adjusted to obtain the manufacturing parameters of the respirator mask.

[0029] In one of the embodiments, the respirator mask manufacturing parameter determination method further includes:

[0030] The mask manufacturing parameter determination model is trained based on the plurality of face images whose total number exceeds the threshold value;

[0031] The face image of the target object is input into the mask manufacturing parameter determination model to obtain the manufacturing parameters output by the mask manufacturing parameter determination model; the manufacturing parameters are used to manufacture the respirator mask matched with the face of the target object.

[0032] In a second aspect, the present application further provides a respirator mask manufacturing parameter determination device, including:

[0033] The face three-dimensional reconstruction module is configured to obtain a face image of a target object, perform face three-dimensional reconstruction based on the face image, and obtain a face three-dimensional model; the face three-dimensional model includes three-dimensional coordinates of a plurality of face feature points in the face image;

[0034] The face area segmentation module is configured to perform face area segmentation on the face three-dimensional model, and determine a mask area in the face three-dimensional model, and a nose cover area and a mouth cover area in the mask area;

[0035] The size parameter determination module is configured to determine target size parameters of the mask area, the nose cover area and the mouth cover area respectively based on the three-dimensional coordinates of the face feature points in the areas covered by the mask area, the nose cover area and the mouth cover area respectively.

[0036] The manufacturing parameter determination module is configured to determine the manufacturing parameters of the respirator mask according to the target size parameters of the mask area, the nose cover area and the mouth cover area.

[0037] In a third aspect, the present application also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0038] obtaining a facial image of a target object, performing three-dimensional reconstruction of the face based on the facial image to obtain a three-dimensional face model, wherein the three-dimensional face model comprises three-dimensional coordinates of a plurality of facial feature points in the facial image;

[0039] performing facial region segmentation on the three-dimensional face model to determine a mask region in the three-dimensional face model, and a nose cover region and a mouth cover region in the mask region;

[0040] determining target size parameters of the mask region, the nose cover region and the mouth cover region respectively based on the three-dimensional coordinates of the facial feature points in the regions covered by the mask region, the nose cover region and the mouth cover region respectively;

[0041] determining manufacturing parameters of a respirator mask according to the target size parameters of the mask region, the nose cover region and the mouth cover region respectively.

[0042] In a fourth aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the following steps:

[0043] obtaining a facial image of a target object, performing three-dimensional reconstruction of the face based on the facial image to obtain a three-dimensional face model, wherein the three-dimensional face model comprises three-dimensional coordinates of a plurality of facial feature points in the facial image;

[0044] performing facial region segmentation on the three-dimensional face model to determine a mask region in the three-dimensional face model, and a nose cover region and a mouth cover region in the mask region;

[0045] determining target size parameters of the mask region, the nose cover region and the mouth cover region respectively based on the three-dimensional coordinates of the facial feature points in the regions covered by the mask region, the nose cover region and the mouth cover region respectively;

[0046] determining manufacturing parameters of a respirator mask according to the target size parameters of the mask region, the nose cover region and the mouth cover region respectively.

[0047] In a fifth aspect, the present application also provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the following steps:

[0048] obtaining a facial image of a target object, performing three-dimensional reconstruction of the face based on the facial image to obtain a three-dimensional face model, wherein the three-dimensional face model comprises three-dimensional coordinates of a plurality of facial feature points in the facial image;

[0049] The face region segmentation is performed on the face three-dimensional model to determine a mask region in the face three-dimensional model, and a nose cover region and a mouth cover region in the mask region;

[0050] Based on the three-dimensional coordinates of the face feature points in the regions covered by the mask region, the nose cover region and the mouth cover region, target size parameters of the mask region, the nose cover region and the mouth cover region are respectively determined;

[0051] According to the target size parameters of the mask region, the nose cover region and the mouth cover region, the production parameters of the respirator mask are determined.

[0052] The respirator mask production parameter determination method, device, computer equipment, computer readable storage medium and computer program product, first obtain a face image of a target object, and then perform face three-dimensional reconstruction based on the face image to obtain a face three-dimensional model, wherein the face three-dimensional model includes three-dimensional coordinates of a plurality of face feature points in the face image. Further, the face region segmentation is performed on the face three-dimensional model to determine a mask region in the face three-dimensional model, and a nose cover region and a mouth cover region in the mask region. Then, based on the three-dimensional coordinates of the face feature points in the regions covered by the mask region, the nose cover region and the mouth cover region, target size parameters of the mask region, the nose cover region and the mouth cover region are respectively determined. Finally, according to the target size parameters of the mask region, the nose cover region and the mouth cover region, the production parameters of the respirator mask are determined. In the whole process, the production parameters of the respirator mask can be determined based on the face three-dimensional model of the target object, so that the finally produced respirator mask fits the face of the target object, thereby avoiding air leakage of the respirator mask in use, and further improving the use effect of the respirator. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technical solutions, the drawings needed to be used in the description of the embodiments of the present application or the related technical solutions will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without creative labor.

[0054] Figure 1 An application environment diagram of the respirator mask production parameter determination method in an embodiment;

[0055] Figure 2 A flowchart of the respirator mask production parameter determination method in an embodiment;

[0056] Figure 3 A flowchart of the face region segmentation performed on the face three-dimensional model in an embodiment;

[0057] Figure 4 a flowchart of a process of obtaining a face region segmentation model in an embodiment;

[0058] Figure 5 a flowchart of a process of detecting a mouth blocking region in an embodiment;

[0059] Figure 6 a flowchart of a process of determining target size parameters of a mouth-nose mask in an embodiment;

[0060] Figure 7 a flowchart of a process of determining target size parameters of a nose mask in an embodiment;

[0061] Figure 8 a flowchart of a process of determining a model and a face image of a target object based on mask manufacturing parameters, and obtaining manufacturing parameters in an embodiment;

[0062] Figure 9 a flowchart of a process of a respirator mask manufacturing parameter determination method in another embodiment;

[0063] Figure 10 a structural block diagram of a respirator mask manufacturing parameter determination device in an embodiment;

[0064] Figure 11 an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0065] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0066] The respirator mask manufacturing parameter determination method provided by the embodiments of the present application can be applied in an application environment as shown in the figure. Figure 1 The terminal 102 installed with an image acquisition device can communicate with the server 104 through a network, and the image acquisition device can be a camera. The data storage system can store data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on a cloud or other network server. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices, etc. The server 104 can be a stand-alone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0067] Specifically, the server 104 can obtain the face image of the target object collected by the terminal 102 through communication with the terminal 102, and perform face three-dimensional reconstruction based on the face image to obtain a face three-dimensional model of the target object, wherein the face three-dimensional model includes the three-dimensional coordinates of a plurality of facial feature points in the face image of the target object. Further, the server 104 can perform face region segmentation on the face three-dimensional model to determine a mask region in the face three-dimensional model, and a nose cover region and a mouth cover region in the mask region. Further, the server 104 can determine target size parameters of the mask region, the nose cover region and the mouth cover region respectively based on the three-dimensional coordinates of the facial feature points in the respective covered regions of the mask region, the nose cover region and the mouth cover region, to determine the production parameters of the respirator mask according to the target size parameters of the mask region, the nose cover region and the mouth cover region.

[0068] In one exemplary embodiment, as shown in Figure 2 , a respirator mask production parameter determination method is provided, which is applied to the server 104 in Figure 1 for example, and includes the following steps 202 to 208. Among them:

[0069] Step 202, obtaining a face image of a target object, performing face three-dimensional reconstruction based on the face image to obtain a face three-dimensional model; the face three-dimensional model includes the three-dimensional coordinates of a plurality of facial feature points in the face image.

[0070] Wherein, the number of face images of the target object is at least one. If it is one, the face image needs to be an image of the front face of the target object, and if it is multiple, it can be a face image of the target object collected from multiple angles, so as to accurately establish the face three-dimensional model of the target object subsequently.

[0071] Optionally, after obtaining the face image of the target object through the terminal, the server can pre-process the face image of the target object, and then input the processed face image into a pre-constructed face three-dimensional reconstruction model to obtain the face three-dimensional model of the target object output by the face three-dimensional reconstruction model. Wherein, the pre-processing can include image denoising, image denoising, image size adjustment, image rotation and flipping, etc.

[0072] In a specific application scenario, the face three-dimensional reconstruction model in the embodiment can automatically detect the face region of the input face image, so as to locate the key facial feature points in the detected face region using a feature point detection algorithm, and automatically map the key facial feature points to a three-dimensional space to construct the face three-dimensional model of the target object.

[0073] The key facial feature points include, but are not limited to, the middle point and contour point of the eyebrow, the contour point of the tip of the nose, the bridge of the nose and the ala of the nose, the convex point on the bridge of the nose, the pupil center point, the corner of the eye, the contour point of the upper and lower eyelids of the eye, the corner of the mouth, the contour point of the upper and lower lips, the edge point of the face, and the preset sampling point in other areas of the face. The face region detection can be realized based on a face detection algorithm, and the face detection algorithm that can be used includes, but is not limited to, a Haar feature classifier (a machine learning algorithm for target detection, especially face detection), MTCNN (Multi-task Cascaded Convolutional Networks, a face detection method based on cascaded convolutional neural networks), SSD (Single Shot MultiBox Detector, a single detection multi-target method), and CNN (convolutional neural network). The feature point detection algorithm includes, but is not limited to, SIFT (Scale Invariant Feature Transform, a feature point detection algorithm based on scale invariance), FAST (Features from Accelerated Segment Test, a fast feature point detection method), and Harris corner point detection algorithm. As to how to map the key facial feature points to the three-dimensional space, any one of 3DMM (3D Morphable Model, three-dimensional morphable model), deep learning (DL), and epipolar geometry can be used. The 3DMM is a generative model for face appearance and shape, the 3D generative adversarial network and 3D convolutional neural network in the deep learning technology can be used for 3D face reconstruction, and the epipolar geometry can generate a single 3D image using multiple non-synthetic perspective images of the same subject.

[0074] In step 204, the face region segmentation is performed on the face three-dimensional model to determine the mask region in the face three-dimensional model, and the nose mask region and the mouth block region in the mask region.

[0075] The respirator mask can include a mouth-nose mask covering the nose and the mouth, and a nose mask covering only the nose. The mouth-nose mask is provided with a mouth block region, and the mouth block region can be provided with a silica gel mouth block. The silica gel mouth block can closely fit the face of the user of the respirator mask, especially in the mouth-nose region, to form an effective seal. Such sealing performance helps to prevent air leakage and ensures the use effect of the respirator.

[0076] Optionally, the server can perform facial region segmentation on the three-dimensional face model of the target object based on a pre-trained facial region segmentation model, according to a three-dimensional structure of the facial feature points in the three-dimensional face model (such as a facial median axis, shapes of facial organs, etc.), to determine a mask region in the three-dimensional face model, and a nose mask region and a mouth cover region in the mask region, so that a mouth-nose mask (with a silica gel mouth cover) suitable for the target object can be manufactured according to the mask region and the mouth cover region in the three-dimensional face model, and a nose mask suitable for the target object can be manufactured according to the nose mask region in the three-dimensional face model.

[0077] In step 206, target size parameters of the mask region, the nose mask region, and the mouth cover region are determined respectively based on the three-dimensional coordinates of the facial feature points in the respective covered regions.

[0078] Optionally, the server can perform spatial geometric calculation based on the three-dimensional coordinates of the facial feature points in the respective covered regions of the mask region, the nose mask region, and the mouth cover region, to determine the width, length, and depth of the mask region, the nose mask region, and the mouth cover region in the three-dimensional face model respectively, and further convert the width, length, and depth of the mask region, the nose mask region, and the mouth cover region in the three-dimensional face model into actual sizes, so as to determine the target size parameters of the mask region, the nose mask region, and the mouth cover region.

[0079] In step 208, manufacturing parameters of the respirator mask are determined according to the target size parameters of the mask region, the nose mask region, and the mouth cover region.

[0080] The target size parameters of the mask region can be used to determine the manufacturing parameters of the mouth-nose mask as a whole, and the target size parameters of the mouth cover region can be used to determine the manufacturing parameters of the silica gel mouth cover in the mouth-nose mask, so as to manufacture a mouth-nose mask that can fit the face of the target object and has good sealing performance. The target size parameters of the nose mask region can be used to determine the manufacturing parameters of the nose mask.

[0081] Optionally, to ensure that the final respirator mask prepared can fit the face of the target object, for the preparable oral-nasal mask, the server can adjust the target size parameters of the mask region and the mouthpiece region according to the respective preset thicknesses of the required (oral-nasal) mask and the mouthpiece (in the oral-nasal mask), for example, appropriately increase the sizes of the mask region and the mouthpiece region, respectively, to determine the final preparation parameters of the oral-nasal mask in the respirator mask; for the preparable nasal mask, the server can adjust the target size parameter of the nasal mask region according to the preset thickness of the required nasal mask, for example, appropriately increase the size of the nasal mask region, to determine the final preparation parameters of the nasal mask in the respirator mask. The respective preset materials of the (oral-nasal) mask, the nasal mask, and the mouthpiece (in the oral-nasal mask) in the respirator mask need to provide sufficient comfort and sealing, and the preset material thickness can be configured according to actual needs and stored in a data storage system connected to the server, so that the server can obtain it.

[0082] Illustratively, if the server detects that the target object has selected to collect and upload a face image and agrees to customize the respirator mask, the server can quickly determine the preparation parameters of the respirator mask (oral-nasal mask and / or nasal mask) based on the above respirator mask preparation parameter determination method according to the face image of the target object, and feed back the preparation parameters to the preparer of the respirator mask in real time, so that the preparer can timely and accurately prepare the respirator mask suitable for the target object, ensuring that the respirator mask will not leak air and will not affect the wearing comfort due to improper size when the target object uses the respirator non-invasively later.

[0083] The above respirator mask preparation parameter determination method first obtains the face image of the target object, thereby performing face three-dimensional reconstruction based on the face image to obtain a face three-dimensional model, wherein the face three-dimensional model includes the three-dimensional coordinates of a plurality of face feature points in the face image. Further, the face three-dimensional model is segmented to determine the mask region in the face three-dimensional model, and the nasal mask region and the mouthpiece region in the mask region, thereby determining the target size parameters of the mask region, the nasal mask region, and the mouthpiece region, respectively, based on the three-dimensional coordinates of the face feature points in the respective covered regions of the mask region, the nasal mask region, and the mouthpiece region, to determine the preparation parameters of the respirator mask according to the target size parameters of the mask region, the nasal mask region, and the mouthpiece region. In the whole process, the preparation parameters of the respirator mask can be determined based on the face three-dimensional model of the target object, so that the final respirator mask fits the face of the target object, thereby avoiding air leakage of the respirator mask in use, and further improving the use effect of the respirator.

[0084] In one exemplary embodiment, the face three-dimensional model is segmented to determine the mask region in the face three-dimensional model, and the nasal mask region and the mouthpiece region in the mask region, including:

[0085] According to the face three-dimensional structure composed of the face feature points in the face three-dimensional model, the face three-dimensional model is segmented to obtain a face region segmentation result;

[0086] According to the face region segmentation result, a mask region and a nose mask region in the mask region are determined in the face three-dimensional model;

[0087] Based on the face three-dimensional structure composed of the face feature points in the mask region, mouth block region detection is performed in the mask region to determine the mouth block region.

[0088] Optionally, the server can segment the face region according to the face three-dimensional structure composed of the face feature points in the face three-dimensional model by using a pre-trained face region segmentation model to obtain a face region segmentation result. The face region segmentation model can be used to identify a mask region that should be covered by a mouth-nose mask and a nose mask region that should be covered by a nose mask in the face three-dimensional model. The face region segmentation model can automatically label the face feature points in the mask region and the nose mask region, respectively, and output a face region segmentation result carrying the labels. The server can determine the mask region and the nose mask region in the mask region in the face three-dimensional model according to the face region segmentation result output by the face three-dimensional model. Further, the server can also perform mouth block region detection in the mask region based on the face three-dimensional structure composed of the face feature points in the mask region to determine the mouth block region in the mask region.

[0089] For example, as shown in Figure 3 , a flowchart for face region segmentation of a face three-dimensional model is provided. After obtaining at least one face image of a target object, the server can input the face image of the target object into a face three-dimensional reconstruction model to obtain a face three-dimensional model output by the face three-dimensional reconstruction model. Further, the server can input the face three-dimensional model of the target object into a pre-trained face region segmentation model to obtain a face region segmentation result labeled with a mask region (as shown in Figure 3 covering the nose and mouth), and a nose mask region (as shown in Figure 3 covering the nose). Further, the server can further detect the mask region to determine a mouth block region suitable for the target object. It should be noted that Figure 3 the face three-dimensional model, the nose mask region, the mask region, and the mouth block region in are only examples. In actual production of a breathing mask, the shape of the mouth-nose mask (with a silicone mouth block inside) and the nose mask can be flexibly adjusted to ensure that the finally produced breathing mask fits the face of the target object and meets the use requirements.

[0090] In the embodiment, the mask region, the nose cover region and the mouth cover region suitable for the target object can be determined to make the breathing machine mask for the target object individually, so that the target object will not leak air when using the made breathing machine mask, and the comfort will not be affected due to improper size.

[0091] In one of the embodiments, the face region segmentation of the face three-dimensional model is performed according to the face three-dimensional structure composed of the face feature points in the face three-dimensional model, and the face region segmentation result is obtained, which includes:

[0092] The face three-dimensional model is input into the face region segmentation model, so that the face region segmentation model performs the face region segmentation of the face three-dimensional model according to the face three-dimensional structure composed of the face feature points in the face three-dimensional model, and outputs the face region segmentation result;

[0093] The face region segmentation model is generated by the following method:

[0094] A data set including a plurality of preset face three-dimensional models is obtained; each preset face three-dimensional model is labeled with a mask region and a nose cover region;

[0095] The face region segmentation model is trained based on the data set.

[0096] Optionally, the server can first obtain the facial images of a plurality of historical objects, and clean and preprocess the facial images of the plurality of historical objects. Then, for each historical object, the server can input at least one facial image of the historical object after preprocessing into a pre-constructed face three-dimensional reconstruction model to obtain a face three-dimensional model of each historical object. Further, a mask region covering the mouth and nose and a nose mask region covering the nose can be respectively labeled for the face three-dimensional model of each historical object by a human. Based on this, the server can obtain a dataset of a plurality of preset face three-dimensional models, each of which has labeled mask region and nose mask region. Further, the server can perform dataset division on the dataset according to a preset ratio to obtain a training set including a plurality of preset face three-dimensional models, a validation set including a plurality of preset face three-dimensional models, and a test set including a plurality of preset face three-dimensional models. The server can perform iterative optimization on the initial face region segmentation model based on the training set until a model iterative optimization stop condition (which can be flexibly configured according to actual training requirements) is reached to obtain at least one trained model, perform model evaluation on the at least one trained model based on the validation set to select at least one test model from the at least one trained model, and perform model testing on the at least one test model based on the test set to determine a final face region segmentation model from the at least one test model. The validation set can be used to select at least one best model from the at least one trained model, and the test set is used to test the performance of the selected best model. After obtaining the face three-dimensional model of the target object, the server can input the face three-dimensional model into the face region segmentation model that has passed the model performance test, so that the face region segmentation model performs face region segmentation on the face three-dimensional model according to the face three-dimensional structure formed by the face feature points in the face three-dimensional model, and outputs the face region segmentation result.

[0097] For example, the initial face region segmentation model can be built based on a deep learning architecture, including but not limited to: U-Net (Convolutional Networks for Biomedical Image Segmentation, a semantic segmentation model widely used in the field of deep learning for image segmentation tasks), FCN (Fully Convolutional Networks, a convolutional neural network mainly used for image semantic segmentation), and SegNet (a deep learning-based image semantic segmentation model that innovatively uses an encoder-decoder structure and introduces a pooling index transfer mechanism, which can effectively improve the accuracy of the segmentation result and the calculation efficiency of the model).

[0098] For example, as shown in Figure 4 , a flowchart for obtaining a face region segmentation model is provided, which mainly includes the following steps:

[0099] Step 402, collect the facial images of a plurality of historical objects, and clean and pretreat the facial images of each historical object;

[0100] Step 404, input the pretreated facial image of each historical object into a face three-dimensional reconstruction model to obtain a face three-dimensional model of each historical object;

[0101] Step 406, after marking the mask area and the nose cover area of the face three-dimensional model of each historical object respectively, a data set is obtained;

[0102] Step 408, divide the data set to obtain a training set, a verification set and a test set;

[0103] Step 410, train an initial face area segmentation model based on the training set to obtain at least one trained model;

[0104] Step 412, select the best model from the at least one trained model based on the verification set, and test the performance of the selected best model based on the test set;

[0105] If the model performance test is passed, step 414 is performed, and the model passing the model performance test is used as the face area segmentation model; otherwise, step 410 is returned.

[0106] In the embodiment, the initial face area segmentation model can be trained, selected and tested by the training set, the verification set and the test set to obtain the final face area segmentation model, so that the face area segmentation model can accurately segment the face area of the face three-dimensional model, thereby facilitating accurate determination of the mask area and the nose cover area suitable for the target object.

[0107] In one of the embodiments, based on the face three-dimensional structure composed of the facial feature points in the mask area, the mouth cover area detection is performed in the mask area to determine the mouth cover area, comprising:

[0108] Obtaining a mouth cover area basic contour;

[0109] According to the mouth cover area basic contour and the face three-dimensional structure composed of the facial feature points in the mask area, contour point detection is performed on the facial feature points in the mask area to determine the target feature points belonging to the edge of the mouth cover area in the mask area;

[0110] Based on the target feature points, the mouth cover area is determined.

[0111] The mouth cover area can be provided with a silicone mouth, which can improve the mouth and nose dryness and bitterness caused by mouth breathing when the target object uses the respirator mask, thereby improving the operation effect of the respirator and the use experience of the target object.

[0112] Optionally, the server can first obtain the basic outline of the mouth guard area, and then based on the basic outline of the mouth guard area and the three-dimensional structure of the face formed by the facial feature points in the mask area, perform contour point detection on the facial feature points in the mask area based on an edge detection algorithm or a shape-based algorithm, determine the target feature points in the mask area that belong to the edge of the mouth guard area, and then determine the mouth guard area in the mask area based on the target feature points. The edge detection algorithm can be a Canny edge detection algorithm, and the shape-based algorithm relies more on the overall shape information of the object and extracts the contour by fitting a shape model. In the shape-based algorithm, Hough Transform can be used to detect straight lines, circles and other simple shapes, while more complex shapes can require the use of active contour models (such as Snake model) or Level Set Method and other technologies.

[0113] As shown in Figure 5 , a flowchart for detecting the mouth guard area is provided, and the server can perform contour point detection on the mask area based on the basic outline of the mouth guard area as shown in Figure 5 , so as to determine the mouth guard area in the mask area, so that the production parameters of the silicone mouth guard can be determined based on the facial feature points in the mouth guard area subsequently. It should be noted that Figure 5 , the outline of the mask area and the basic outline of the mouth guard area are only examples, and the mask area and the mouth guard area in the actual production of the respirator mask can be flexibly adjusted according to the shape of the respirator mask, and the final produced oral-nasal mask can be ensured to fit the face of the target object and meet the use requirements.

[0114] In this embodiment, the mask area suitable for the target object can be determined based on the mask area suitable for the target object, which is beneficial to subsequent production of the silicone mouth guard customized for the target object based on the production parameters of the mask area and the production parameters of the mouth guard area, so as to obtain the oral-nasal mask suitable for the target object.

[0115] In one of the embodiments, based on the three-dimensional coordinates of the facial feature points in the areas covered by the mask area, the nose cover area and the mouth guard area, the target size parameters of the mask area, the nose cover area and the mouth guard area are determined respectively, including:

[0116] Based on the three-dimensional coordinates of the facial feature points in the areas covered by the mask area, the nose cover area and the mouth guard area, the initial size parameters of the mask area, the nose cover area and the mouth guard area are determined respectively;

[0117] Determine the size conversion ratio between the three-dimensional model of the face and the actual face of the target object;

[0118] The initial size parameters of the mask area, the nose cover area and the mouth cover area are converted according to the size conversion ratio to obtain the target size parameters of the mask area, the nose cover area and the mouth cover area.

[0119] In the process of pre-constructing the face three-dimensional reconstruction model, the size of the face three-dimensional model of each historical object output by the face three-dimensional reconstruction model can be recorded, and the size of the face three-dimensional model of each historical object is compared with the actual face size to calculate a unified size conversion ratio, and the size conversion ratio is stored in the data storage system.

[0120] Optionally, the server can determine the width (which can be calculated by the difference of x-axis coordinates), the length (which can be calculated by the difference of y-axis coordinates) and the depth (which can be calculated by the difference of z-axis coordinates) of the mask area, the nose cover area and the mouth cover area in the face three-dimensional model with reference to the central axis of the face three-dimensional model based on the three-dimensional coordinates of the face feature points in the covered area of the mask area, the nose cover area and the mouth cover area, so as to determine the initial size parameters of the mask area, the nose cover area and the mouth cover area in the face three-dimensional model. Further, the server can obtain the pre-calculated size conversion ratio between the face three-dimensional model and the actual face of the target object, and then convert the initial size parameters of the mask area, the nose cover area and the mouth cover area according to the size conversion ratio to obtain the target size parameters of the mask area, the nose cover area and the mouth cover area in the real use scenario.

[0121] As shown in the flowchart of determining the target size parameters of the oral-nasal mask, the initial size parameters of the mask area can include the width, the length and the depth of multiple places in the mask area, and the initial size parameters of the mouth cover area can include the width, the length and the depth of multiple places in the mouth cover area. Figure 6 As shown in the flowchart of determining the target size parameters of the oral-nasal mask, the initial size parameters of the mask area can include the width, the length and the depth of multiple places in the mask area, and the initial size parameters of the mouth cover area can include the width, the length and the depth of multiple places in the mouth cover area. Figure 6 As shown in the flowchart of determining the target size parameters of the oral-nasal mask, the initial size parameters of the mask area can include the width, the length and the depth of multiple places in the mask area, and the initial size parameters of the mouth cover area can include the width, the length and the depth of multiple places in the mouth cover area. Figure 6 Further, the server can aggregate all the length data, the width data and the depth data of the mask area and the mouth cover area to determine the initial size parameters of the mask area and the mouth cover area, and then determine the target size parameters of the mask area and the mouth cover area, i.e. the target size parameters of the oral-nasal mask, after size conversion, so as to subsequently manufacture the oral-nasal mask (with the mouth cover silicone) that can fit the face of the target object.

[0122] As shown in the flowchart of determining the target size parameters of the oral-nasal mask, the initial size parameters of the mask area can include the width, the length and the depth of multiple places in the mask area, and the initial size parameters of the mouth cover area can include the width, the length and the depth of multiple places in the mouth cover area.Figure 7 As shown, a flowchart for determining the target size parameters of the nasal mask is provided. Taking the nasal mask in the respirator mask as an example, the initial size parameters of the nasal mask region can include the width, length, and depth at multiple locations within the nasal mask region. Figure 7 In this embodiment, the longest length of the nasal mask region, the width at a certain location, and the depth at a certain location (i.e., the height of a point on the nasal bridge at the center axis of the three-dimensional face model) are shown, but the size parameters that can be obtained in this embodiment are not limited to Figure 7 the several locations shown. Further, the server can aggregate all length data, width data, and depth data of the nasal mask region to determine the initial size parameters of the nasal mask region, and after size conversion, determine the target size parameters of the nasal mask region, i.e., the target size parameters of the nasal mask, so as to subsequently manufacture a nasal mask that can fit the face of the target object.

[0123] In this embodiment, size conversion can be performed based on the initial size parameters in the three-dimensional face model of the target object to accurately determine the target size parameters for manufacturing the respirator mask of the target object, thereby facilitating subsequent individualized customization of the respirator mask (nasal mask and / or oral-nasal mask with a silicone mouthpiece) for the target object.

[0124] In one of the embodiments, the manufacturing parameters of the respirator mask are determined based on the target size parameters of the mask region, the nasal mask region, and the mouthpiece region, including:

[0125] obtaining the preset material thicknesses of the mask, the nasal mask, and the mouthpiece in the respirator mask, respectively;

[0126] adjusting the target size parameters of the mask region, the nasal mask region, and the mouthpiece region based on the preset material thicknesses of the mask, the nasal mask, and the mouthpiece in the respirator mask, respectively, to obtain the manufacturing parameters of the respirator mask.

[0127] The preset materials of the mask, the nasal mask, and the mouthpiece in the respirator mask need to provide sufficient comfort and sealing, and the preset material thicknesses can be configured according to actual needs. The specific preset material thicknesses can vary due to different manufacturers and material selections.

[0128] Optionally, for the oral-nasal mask that can be manufactured, the server can adjust the target size parameters of the mask region and the mouthpiece region based on the preset thicknesses of the mask (oral-nasal mask) and the mouthpiece (silicone mouthpiece in the oral-nasal mask), respectively. For example, the sizes of the mask region and the mouthpiece region are appropriately increased to determine the final manufacturing parameters of the oral-nasal mask in the respirator mask. For the nasal mask that can be manufactured, the server can adjust the target size parameters of the nasal mask region based on the preset thickness of the nasal mask, for example, appropriately increase the size of the nasal mask region to determine the final manufacturing parameters of the nasal mask in the respirator mask.

[0129] Exemplarily, when adjusting the production parameters of the respirator mask, the preset material thickness of the mask, the nose cover and the mouth block need to be considered, and the target size parameters are adjusted accordingly to ensure the comfort and sealing of the produced respirator mask. Taking the silicone mouth block in the nose and mouth mask as an example, if the material thickness of the silicone mouth block is about 2mm, the width, length and depth of the target size parameters in the mouth block area can be uniformly increased by 2mm.

[0130] In this embodiment, considering the influence of material thickness on the size of the respirator mask, the comfort of the finally produced respirator mask can be improved by adjusting the target size parameters of the mask area, the nose cover area and the mouth block area, and it is also ensured that the finally produced respirator mask can fit the face of the target object, avoiding air leakage of the respirator mask during use.

[0131] In one possible implementation, as shown in Figure 8 A flowchart for determining the mask production parameters based on the mask production parameter determination model and the face image of the target object is provided, mainly including the following steps:

[0132] Step 802, based on the plurality of face images whose total number exceeds the threshold value, a mask production parameter determination model is trained.

[0133] The threshold value can be flexibly configured according to the actual application scenario.

[0134] In this embodiment, in the case that the collected face images are sufficient, a regression model that can directly output the production parameters of the respirator mask based on the face image can also be trained based on a large number of face images, i.e. the mask production parameter determination model. The regression model can predict the dependent variable based on the independent variable, and the types of regression model include but are not limited to: convolutional neural network regression, visual Transformer regression, limited regression, polynomial regression, ridge regression, decision tree regression, random forest regression, and support vector machine regression.

[0135] Step 804, inputting the face image of the target object into the mask production parameter determination model to obtain the production parameters output by the mask production parameter determination model; the production parameters are used to produce the respirator mask matched with the face of the target object.

[0136] Optionally, after obtaining the face image of the target object, the server can input the face image of the target object into the mask production parameter determination model to obtain the production parameters of the respirator mask suitable for the target object output by the mask production parameter determination model, thereby improving the efficiency of obtaining the production parameters.

[0137] In this embodiment, based on a large number of face image samples, a model that can accurately output production parameters based on face images can be trained, thereby improving the efficiency of obtaining production parameters.

[0138] In one detailed embodiment, as shown in Figure 9 FIG. 1 is a schematic diagram of a flowchart of a method for determining a mask making parameter of a respirator mask, mainly comprising the following steps:

[0139] Step 902, obtaining a face image of a target object, performing three-dimensional reconstruction of the face based on the face image, and obtaining a three-dimensional face model;

[0140] Step 904, inputting the three-dimensional face model into a face region segmentation model to obtain a face region segmentation result output by the three-dimensional face model;

[0141] Step 906, determining a mask region and a nasal mask region within the mask region in the three-dimensional face model according to the face region segmentation result;

[0142] Step 908, performing contour point detection on the face feature points within the mask region according to a three-dimensional structure of the face composed of the mask region base contour and the face feature points within the mask region, and determining target feature points belonging to the edge of the mouthpiece region within the mask region;

[0143] Step 910, determining the mouthpiece region based on the target feature points;

[0144] Step 912, determining initial size parameters of the mask region, the nasal mask region and the mouthpiece region respectively based on the three-dimensional coordinates of the face feature points within the respective covered regions of the mask region, the nasal mask region and the mouthpiece region;

[0145] Step 914, determining a size conversion ratio between the three-dimensional face model and the actual face of the target object;

[0146] Step 916, performing size conversion on the initial size parameters of the mask region, the nasal mask region and the mouthpiece region according to the size conversion ratio to obtain target size parameters of the mask region, the nasal mask region and the mouthpiece region respectively;

[0147] Step 918, obtaining preset material thicknesses of the mask, the nasal mask and the mouthpiece in the respirator mask respectively;

[0148] Step 920, adjusting the target size parameters of the mask region, the nasal mask region and the mouthpiece region respectively according to the preset material thicknesses of the mask, the nasal mask and the mouthpiece in the respirator mask respectively to obtain the mask making parameter of the respirator mask.

[0149] It should be understood that although the steps in the flowcharts involved in the embodiments described above are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0150] Based on the same inventive concept, the embodiments of the present application also provide a breathing mask manufacturing parameter determination device for implementing the breathing mask manufacturing parameter determination method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more breathing mask manufacturing parameter determination device embodiments provided below can refer to the limitations of the breathing mask manufacturing parameter determination method described above, which will not be repeated here.

[0151] In one exemplary embodiment, as shown in Figure 10 A breathing mask manufacturing parameter determination device is provided, comprising: a face three-dimensional reconstruction module 1002, a face region segmentation module 1004, a size parameter determination module 1006, and a manufacturing parameter determination module 1008, wherein:

[0152] The face three-dimensional reconstruction module is configured to acquire a face image of a target object, perform face three-dimensional reconstruction based on the face image, and obtain a face three-dimensional model; the face three-dimensional model includes three-dimensional coordinates of a plurality of face feature points in the face image.

[0153] The face region segmentation module is configured to perform face region segmentation on the face three-dimensional model, and determine a mask region, a nasal mask region, and a mouth block region in the mask region in the face three-dimensional model.

[0154] The size parameter determination module is configured to determine target size parameters of the mask region, the nasal mask region, and the mouth block region, respectively, based on the three-dimensional coordinates of the face feature points in the regions covered by the mask region, the nasal mask region, and the mouth block region.

[0155] The manufacturing parameter determination module is configured to determine the manufacturing parameters of the breathing mask according to the target size parameters of the mask region, the nasal mask region, and the mouth block region.

[0156] The respirator mask manufacturing parameter determination apparatus obtains a face image of a target object, performs face three-dimensional reconstruction based on the face image, and obtains a face three-dimensional model, wherein the face three-dimensional model includes three-dimensional coordinates of a plurality of face feature points in the face image. Further, the face three-dimensional model is subjected to face region segmentation, and a mask region in the face three-dimensional model and a nose cover region and a mouth block region in the mask region are determined. Then, based on the three-dimensional coordinates of the face feature points in the respective regions covered by the mask region, the nose cover region and the mouth block region, target size parameters of the mask region, the nose cover region and the mouth block region are respectively determined. Finally, the manufacturing parameters of the respirator mask are determined according to the target size parameters of the mask region, the nose cover region and the mouth block region. In the whole process, the manufacturing parameters of the respirator mask are determined based on the face three-dimensional model of the target object, so that the respirator mask finally manufactured can fit the face of the target object, thereby avoiding air leakage of the respirator mask in use and improving the use effect of the respirator.

[0157] In one of the embodiments, the face region segmentation module is further configured to: segment the face three-dimensional model according to a face three-dimensional structure formed by the face feature points in the face three-dimensional model to obtain a face region segmentation result; determine the mask region and the nose cover region in the mask region in the face three-dimensional model according to the face region segmentation result; and detect the mouth block region in the mask region based on the face three-dimensional structure formed by the face feature points in the mask region to determine the mouth block region.

[0158] In one of the embodiments, the face region segmentation module is further configured to: input the face three-dimensional model into a face region segmentation model, so that the face region segmentation model segments the face three-dimensional model according to a face three-dimensional structure formed by the face feature points in the face three-dimensional model, and outputs a face region segmentation result.

[0159] In one of the embodiments, the respirator mask manufacturing parameter determination apparatus further comprises a face region segmentation model generation module, which is configured to: obtain a data set comprising a plurality of preset face three-dimensional models, wherein each preset face three-dimensional model has a labeled mask region and a labeled nose cover region; and train a face region segmentation model based on the data set.

[0160] In one of the embodiments, the face region segmentation module is further configured to: obtain a mouth block region basic contour; detect contour points of the face feature points in the mask region according to the mouth block region basic contour and a face three-dimensional structure formed by the face feature points in the mask region, and determine target feature points belonging to the edge of the mouth block region in the mask region; and determine the mouth block region based on the target feature points.

[0161] In one of the embodiments, the size parameter determination module is further configured to: determine initial size parameters of the mask area, the nose cover area and the mouth cover area respectively based on the three-dimensional coordinates of the facial feature points in the respective covered areas of the mask area, the nose cover area and the mouth cover area; determine a size conversion ratio between the three-dimensional face model and the actual face of the target object; and perform size conversion on the initial size parameters of the mask area, the nose cover area and the mouth cover area respectively according to the size conversion ratio to obtain the target size parameters of the mask area, the nose cover area and the mouth cover area.

[0162] In one of the embodiments, the production parameter determination module is further configured to: obtain preset material thicknesses of the mask, the nose cover and the mouth cover in the respirator mask respectively; and adjust the target size parameters of the mask area, the nose cover area and the mouth cover area respectively according to the preset material thicknesses of the mask, the nose cover and the mouth cover in the respirator mask respectively to obtain the production parameters of the respirator mask.

[0163] In one of the embodiments, the respirator mask production parameter determination apparatus further comprises a mask production parameter determination model training module, which is configured to: train the mask production parameter determination model based on the plurality of face images whose total number exceeds the threshold value; input the face image of the target object into the mask production parameter determination model to obtain the production parameters output by the mask production parameter determination model; and use the production parameters to produce the respirator mask matched with the face of the target object.

[0164] The above-mentioned various modules in the respirator mask production parameter determination apparatus can be realized by software, hardware and combinations thereof in whole or in part. The above-mentioned various modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form so as to be called and executed by the processor to perform the operations corresponding to the above-mentioned various modules.

[0165] In one exemplary embodiment, a computer device, which can be a server, is provided, and an internal structure diagram of the computer device can be as shown in FIG. 1. Figure 11As shown in the figure. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store ventilator mask manufacturing parameter determination data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to realize a ventilator mask manufacturing parameter determination method.

[0166] Those skilled in the art can understand that, Figure 11 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0167] In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in each of the method embodiments described above.

[0168] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps in each of the method embodiments described above.

[0169] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps in each of the method embodiments described above.

[0170] It should be noted that the user information (including but not limited to user face information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0171] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. In the embodiments provided in the present application, any reference to memory, database or other medium can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0172] Any technical features in the above embodiments can be combined, and for the sake of brevity, not all possible combinations are described, however, any combination of the technical features is considered to be within the scope of the present application. The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be pointed out that, for those skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for determining manufacturing parameters of a ventilator mask, characterized in that: The method comprises: Acquire a facial image of a target object, and perform three-dimensional facial reconstruction based on the facial image to obtain a three-dimensional facial model; the three-dimensional facial model includes three-dimensional coordinates of a plurality of facial feature points in the facial image; Performing facial region segmentation on the three-dimensional facial model to determine a mask region, a nose mask region, and a mouth guard region within the mask region in the three-dimensional facial model; Determining initial size parameters of the face mask area, the nose mask area, and the mouth stop area based on the three-dimensional coordinates of facial feature points within the areas covered by the face mask area, the nose mask area, and the mouth stop area respectively; Determining a size conversion ratio between the three-dimensional facial model and the actual face of the target subject; wherein, in the process of pre-building the three-dimensional facial reconstruction model, the size of the three-dimensional facial model of each historical subject output by the three-dimensional facial reconstruction model is recorded, and the size of the three-dimensional facial model of each historical subject is compared with the actual facial size to calculate a unified size conversion ratio; Performing size conversion on the initial size parameters of the face mask area, the nasal mask area, and the mouth stop area according to the size conversion ratio to obtain target size parameters of the face mask area, the nasal mask area, and the mouth stop area; Get the preset material thickness of the face mask, nose mask and mouth guard of the ventilator mask; According to the preset material thicknesses of the face mask, nasal mask and mouth stop in the ventilator mask, the target size parameters of the face mask area, the nasal mask area and the mouth stop area are adjusted to obtain the manufacturing parameters of the ventilator mask.

2. The method according to claim 1, characterized in that The step of performing facial region segmentation on the three-dimensional facial model to determine a mask region, a nose mask region, and a mouth guard region within the mask region includes: performing facial region segmentation on the three-dimensional facial model according to the three-dimensional facial structure formed by facial feature points in the three-dimensional facial model to obtain a facial region segmentation result; Determining a face mask region and a nose mask region within the face mask region in the three-dimensional facial model according to the facial region segmentation result; Based on the three-dimensional facial structure formed by the facial feature points in the mask area, the mouth stop area is detected in the mask area to determine the mouth stop area.

3. The method according to claim 2, characterized in that The step of performing facial region segmentation on the three-dimensional facial model according to the three-dimensional facial structure formed by facial feature points in the three-dimensional facial model to obtain a facial region segmentation result includes: Inputting the three-dimensional facial model into a facial region segmentation model, so that the facial region segmentation model performs facial region segmentation on the three-dimensional facial model according to the three-dimensional facial structure formed by facial feature points in the three-dimensional facial model, and outputs a facial region segmentation result; The facial region segmentation model is generated by: Acquire a data set including a plurality of preset three-dimensional facial models; each of the preset three-dimensional facial models has a mask area and a nose mask area marked; The facial region segmentation model is trained based on the data set.

4. The method according to claim 2, characterized in that The method of detecting the mouth stop region in the mask region based on the three-dimensional facial structure formed by facial feature points in the mask region to determine the mouth stop region includes: Get the basic outline of the mouth block area; Performing contour point detection on the facial feature points in the mask area according to the three-dimensional facial structure formed by the basic contour of the mouth stop area and the facial feature points in the mask area, and determining target feature points in the mask area that belong to the edge of the mouth stop area; Based on the target feature points, a mouth-blocking area is determined.

5. The method according to claim 1, wherein The determining of initial size parameters of the face mask area, the nose mask area, and the mouth stop area based on the three-dimensional coordinates of facial feature points within the areas covered by the face mask area, the nose mask area, and the mouth stop area respectively includes: Based on the three-dimensional coordinates of the facial feature points in the areas covered by the mask area, the nasal mask area and the mouth stop area, and with reference to the central axis of the facial three-dimensional model, the width, length and depth of the mask area, the nasal mask area and the mouth stop area in the facial three-dimensional model are determined, thereby determining the initial size parameters of the mask area, the nasal mask area and the mouth stop area in the facial three-dimensional model respectively.

6. The method according to claim 5, characterized in that The initial size parameters of the nasal mask area include: widths, lengths, and depths at multiple locations within the nasal mask area; Determining the initial size parameters of the nasal mask area in the three-dimensional facial model includes: summarizing all lengths, widths, and depths of the nasal mask area, thereby determining the initial size parameters of the nasal mask area in the three-dimensional facial model.

7. The method according to claim 1, characterized in that The method further comprises: Based on multiple facial images whose total number exceeds a threshold, a mask production parameter determination model is trained; The facial image of the target object is input into the mask production parameter determination model to obtain production parameters output by the mask production parameter determination model; the production parameters are used to produce a ventilator mask that matches the face of the target object.

8. A device for determining manufacturing parameters of a ventilator mask, characterized in that: The device comprises: A facial 3D reconstruction module is configured to obtain a facial image of a target object and perform 3D facial reconstruction based on the facial image to obtain a 3D facial model; the 3D facial model includes 3D coordinates of a plurality of facial feature points in the facial image; A facial region segmentation module is used to perform facial region segmentation on the three-dimensional facial model to determine the mask region, and the nose mask region and the mouth guard region within the mask region in the three-dimensional facial model; a size parameter determination module for determining initial size parameters of the face mask area, the nose mask area, and the mouth stop area based on the three-dimensional coordinates of facial feature points within the areas covered by the face mask area, the nose mask area, and the mouth stop area, and determining a size conversion ratio between the three-dimensional facial model and the actual face of the target object; wherein, in the process of pre-constructing the three-dimensional facial reconstruction model, the size of the three-dimensional facial model of each historical object output by the three-dimensional facial reconstruction model is recorded, and the size of the three-dimensional facial model of each historical object is compared with the actual facial size to calculate a unified size conversion ratio; according to the size conversion ratio, the initial size parameters of the face mask area, the nose mask area, and the mouth stop area are converted to obtain target size parameters of the face mask area, the nose mask area, and the mouth stop area; The manufacturing parameter determination module is used to obtain the preset material thickness of the face mask, nasal mask and mouth stop in the ventilator mask, and adjust the target size parameters of the face mask area, the nasal mask area and the mouth stop area according to the preset material thickness of the face mask, the nasal mask and the mouth stop in the ventilator mask to obtain the manufacturing parameters of the ventilator mask.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images