Three-dimensional face imaging method, device, equipment and storage medium

Abstract

The present invention belongs to the technical field of image processing, and discloses a three-dimensional face imaging method, device, equipment and storage medium. The method includes: acquiring original three-dimensional volume data of a tissue to be measured; determining the face position and amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold; determining a target positioning point profile according to the face position and the amniotic membrane position; performing transparency clearing on the original three-dimensional volume data according to the target positioning point profile to obtain three-dimensional face data of the tissue to be measured; and completing three-dimensional face imaging display of the tissue to be measured according to the three-dimensional face data. By the above method, a target positioning point profile is determined based on the amniotic membrane position and the face position, so as to identify the tissue information before the face of the tissue to be measured. Finally, transparency clearing is performed on the original three-dimensional volume data according to the target positioning point profile to complete three-dimensional face imaging display of the tissue to be measured, thereby automatically obtaining a clear, comprehensive and complete face image of the object to be measured, and improving the image rendering effect.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a three-dimensional face imaging method, apparatus, device and storage medium. Background Art

[0002] The existing ultrasonic three-dimensional imaging method is based on the principle of ray casting imaging. It uses ray projection imaging for three-dimensional volume rendering and fuses and displays the rendered images. However, the image data collected by the ultrasonic probe not only contains the face information of the tissue to be measured, but also other tissue information such as amniotic fluid, amnion, and abdominal skin of the environment where the tissue to be measured is located. Usually, in order to directly obtain the face information of the tissue to be measured, before three-dimensional imaging of the volume data, the obtained three-dimensional volume data is cropped (under the guidance of a two-dimensional ultrasonic image, the data of the target area is selected through an ROI (Region Of Interest) box for three-dimensional imaging). However, this cropping is manual and regular cropping. In the actual application process, the relationship between the amnion, amniotic fluid, abdominal skin of the environment where the tissue to be measured is located and the tissue to be measured is not regular, which easily leads to missing cropping or overcropping during the cropping process, and finally results in an incomplete three-dimensional face image of the tissue to be measured or a face image of the tissue to be measured covered by other tissues.

[0003] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of the present invention is to provide a three-dimensional face imaging method, apparatus, device and storage medium, aiming to solve the technical problem that the prior art cannot automatically obtain the complete face information of the object to be measured.

[0005] To achieve the above purpose, the present invention provides a three-dimensional face imaging method, and the method includes the following steps:

[0006] Obtain the original three-dimensional volume data of the tissue to be measured;

[0007] Determine the face position and amnion position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold;

[0008] Determine the target positioning point profile according to the face position and the amnion position;

[0009] Clear the transparency of the original three-dimensional volume data according to the target positioning point profile to obtain the three-dimensional face data of the tissue to be measured;

[0010] Complete the three-dimensional face imaging display of the tissue to be measured according to the three-dimensional face data.

[0011] Optionally, determining the facial position and amniotic position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold value includes:

[0012] Obtaining a preset facial threshold value, a preset amniotic threshold value, and a preset bone threshold value;

[0013] Determining the maximum value of the target volume data according to the original three-dimensional volume data;

[0014] Determining a target facial threshold value, a target amniotic threshold value, and a target bone threshold value according to the maximum value of the target volume data, the preset facial threshold value, the preset amniotic threshold value, and the preset bone threshold value;

[0015] Determining the facial position and amniotic position of the tissue to be measured according to the original three-dimensional volume data, the target facial threshold value, the target amniotic threshold value, and the target bone threshold value.

[0016] Optionally, determining the facial position and amniotic position of the tissue to be measured according to the original three-dimensional volume data, the target facial threshold value, the target amniotic threshold value, and the target bone threshold value includes:

[0017] Determining the bone position of the tissue to be measured according to the original three-dimensional volume data and the target bone threshold value;

[0018] Determining the facial position of the tissue to be measured in the reverse direction of the ultrasonic beam based on the bone position and the target facial threshold value;

[0019] Determining the amniotic position of the tissue to be measured in the reverse direction of the ultrasonic beam according to the facial position and the target amniotic threshold value.

[0020] Optionally, determining the target positioning point profile according to the facial position and the amniotic position includes:

[0021] Obtaining a preset positioning parameter;

[0022] Determining an initial positioning point and a target marker value corresponding to the initial positioning point according to the preset positioning parameter, the amniotic position, and the facial position;

[0023] Obtaining the target length and target width of the original three-dimensional volume data;

[0024] Determining the target positioning point profile according to the target length, the target width, the initial positioning point, and the target marker value corresponding to the initial positioning point.

[0025] Optionally, determining the target positioning point profile according to the target length, the target width, the initial positioning point, and the target marker value corresponding to the initial positioning point includes:

[0026] Determine the first positioning point profile according to the target length, target width, and initial positioning point;

[0027] Determine the invalid positioning points in the first positioning point profile according to the initial positioning point;

[0028] Fill the invalid positioning points in the first positioning point profile to obtain the target positioning point profile.

[0029] Optionally, the filling the invalid positioning points in the first positioning point profile to obtain the target positioning point profile includes:

[0030] Obtain the first wire bundle corresponding to the invalid positioning points;

[0031] Determine the filling module with a preset area according to the first wire bundle;

[0032] Perform profile filling on the first positioning point profile according to a preset interpolation template, the first wire bundle, and the filling module to obtain a second positioning point profile;

[0033] Perform smoothing processing on the second positioning point profile according to a preset smoothing module to obtain the target positioning point profile.

[0034] Optionally, the clearing the transparency of the original three-dimensional volume data according to the target positioning point profile to obtain the three-dimensional face data of the tissue to be measured includes:

[0035] Determine the depth of the target ultrasonic beam according to the target positioning point profile;

[0036] Search for the clearing area in the original three-dimensional volume data where the depth of the ultrasonic beam is less than the depth of the target ultrasonic beam;

[0037] Clear the transparency of the clearing area to obtain the three-dimensional face data of the tissue to be measured.

[0038] In addition, to achieve the above object, the present invention also provides a three-dimensional face imaging device, and the three-dimensional face imaging device includes:

[0039] An acquisition module, configured to acquire the original three-dimensional volume data of the tissue to be measured;

[0040] A determination module, configured to determine the face position and amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold;

[0041] The determination module is further configured to determine the target positioning point profile according to the face position and the amniotic membrane position;

[0042] A clearing module, configured to clear the transparency of the original three-dimensional volume data according to the target positioning point section to obtain the three-dimensional face data of the tissue to be measured;

[0043] A display module, configured to complete the three-dimensional face imaging display of the tissue to be measured according to the three-dimensional face data.

[0044] In addition, to achieve the above object, the present invention also provides a three-dimensional face imaging device, which includes: a memory, a processor, and a three-dimensional face imaging program stored on the memory and executable on the processor. The three-dimensional face imaging program is configured to implement the three-dimensional face imaging method as described above.

[0045] In addition, to achieve the above object, the present invention also provides a storage medium, on which a three-dimensional face imaging program is stored. When the three-dimensional face imaging program is executed by a processor, it implements the three-dimensional face imaging method as described above.

[0046] The present invention obtains the original three-dimensional volume data of the tissue to be measured; determines the face position and amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold; determines the target positioning point section according to the face position and the amniotic membrane position; clears the transparency of the original three-dimensional volume data according to the target positioning point section to obtain the three-dimensional face data of the tissue to be measured; and completes the three-dimensional face imaging display of the tissue to be measured according to the three-dimensional face data. By analyzing the original three-dimensional volume data to determine the face position of the tissue to be measured and the amniotic membrane position in the original three-dimensional volume data, and determining the target positioning point section based on the amniotic membrane position and the face position, the tissue information before the face of the tissue to be measured can be identified. Finally, the transparency of the original three-dimensional volume data is cleared according to the target positioning point section to complete the three-dimensional face imaging display of the tissue to be measured, so as to automatically obtain a clear, comprehensive and complete face image of the object to be measured, improving the image rendering effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a schematic structural diagram of a three-dimensional face imaging device in a hardware operating environment related to the embodiment solution of the present invention;

[0048] Figure 2 is a schematic flowchart of the first embodiment of the three-dimensional face imaging method of the present invention;

[0049] Figure 3 is a flowchart of position determination of an embodiment of the three-dimensional face imaging method of the present invention;

[0050] Figure 4 is a schematic flowchart of the second embodiment of the three-dimensional face imaging method of the present invention;

[0051] Figure 5Schematic diagram of the overall process of an embodiment of the three-dimensional face imaging method of the present invention;

[0052] Figure 6 Block diagram of the structure of the first embodiment of the three-dimensional face imaging device of the present invention.

[0053] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0054] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] Referring to Figure 1 , Figure 1 Schematic diagram of the structure of the three-dimensional face imaging device in the hardware operating environment related to the embodiment solution of the present invention.

[0056] As Figure 1 shown, the three-dimensional face imaging device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed Random Access Memory (RAM) memory or a stable Non-Volatile Memory (NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0057] Those skilled in the art can understand that Figure 1 the structure shown in

[0058] does not constitute a limitation on the three-dimensional face imaging device, and may include more or fewer components than shown in the figure, or combine some components, or different component arrangements. Figure 1 As

[0059] shown, the memory 1005, as a storage medium, may include an operating system, a network communication module, a user interface module, and a three-dimensional face imaging program. Figure 1In the face three-dimensional imaging device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the face three-dimensional imaging device of the present invention can be arranged in the face three-dimensional imaging device. The face three-dimensional imaging device calls the face three-dimensional imaging program stored in the memory 1005 through the processor 1001 and executes the face three-dimensional imaging method provided by the embodiments of the present invention.

[0060] An embodiment of the present invention provides a face three-dimensional imaging method. Refer to Figure 2 , Figure 2 which is a schematic flowchart of the first embodiment of a face three-dimensional imaging method of the present invention.

[0061] In this embodiment, the face three-dimensional imaging method includes the following steps:

[0062] Step S10: Obtain the original three-dimensional volume data of the tissue to be measured.

[0063] It should be noted that the execution subject of this embodiment is an ultrasonic detection device. The ultrasonic detection device emits an ultrasonic beam, obtains the original three-dimensional volume data of the tissue to be measured, determines the face position and amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold, determines a target positioning point profile based on the face position and the amniotic membrane position, clears the transparency of the original three-dimensional volume data based on the target positioning point profile, so as to obtain clear face three-dimensional data of the tissue to be measured without other tissue information, and completes the face three-dimensional imaging display of the tissue to be measured according to the face three-dimensional data.

[0064] It can be understood that the ultrasonic detection device emits an ultrasonic beam to collect multiple two-dimensional images of the tissue to be measured, and performs interpolation reconstruction on the two-dimensional images, so as to obtain the original three-dimensional volume data of the tissue to be measured. The original three-dimensional volume data is consistent with the spatial structure of the tissue to be measured. The original three-dimensional volume data is composed of a voxel ag[i][j][k] and a transparency parameter aw[i][j][k]. Each voxel corresponds to a transparency parameter, and aw is determined by an empirical function faw(ag). For example, the ultrasonic detection device emits an ultrasonic beam to collect 188 two-dimensional images of 255*399, where 255 is the horizontal resolution and 399 is the axial resolution. Interpolation reconstruction is performed on the two-dimensional images, and the two-dimensional images are converted into a volume data ag of 600*600*400 through three-dimensional reconstruction in the GPU of the ultrasonic detection device. Each voxel value ag[i][j][k] in the volume data has a corresponding transparency value aw[i][j][k], where both ag and aw are normalized to values between 0 and 1.

[0065] Step S20: Determine the face position and amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold.

[0066] It should be noted that after obtaining the original three-dimensional volume data, the original three-dimensional volume data is traversed, and the face position and amniotic membrane position of the tissue to be measured are determined based on the result obtained from the traversal and a preset threshold. The preset threshold refers to a preset threshold coefficient used to locate the face position, amniotic membrane position, and bone position in the direction of the ultrasonic beam.

[0067] It can be understood that in order to accurately locate the face position and amniotic membrane position of the tissue to be measured, further, determining the face position and amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data and the preset threshold includes: obtaining a preset face threshold, a preset amniotic membrane threshold, and a preset bone threshold; determining the maximum value of the target volume data according to the original three-dimensional volume data; determining a target face threshold, a target amniotic membrane threshold, and a target bone threshold according to the maximum value of the target volume data, the preset face threshold, the preset amniotic membrane threshold, and the preset bone threshold; and determining the face position and amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data, the target face threshold, the target amniotic membrane threshold, and the target bone threshold.

[0068] In a specific implementation, the preset face threshold, the preset amniotic membrane threshold, and the preset bone threshold refer to preset threshold coefficients used to locate the face position, amniotic membrane position, and bone position in the direction of the ultrasonic beam respectively, and the values corresponding to the preset face threshold, the preset amniotic membrane threshold, and the preset bone threshold are TFa, TFb, and TBf respectively. In this embodiment, TBf is set to 0.75, and it can also be other values. This embodiment does not limit this, but this embodiment takes TBf being set to 0.75 as an example for illustration.

[0069] It should be noted that by traversing the original three-dimensional volume data, the maximum value VOIMaxGray of the volume data in the original three-dimensional volume data is obtained, and the maximum value VOIMaxGray of the volume data in the original three-dimensional volume data is the maximum value of the target volume data. The target face threshold, the target amniotic membrane threshold, and the target bone threshold are determined according to the maximum value of the target volume data, the preset face threshold, the preset amniotic membrane threshold, and the preset bone threshold. The target face threshold, the target amniotic membrane threshold, and the target bone threshold are used to locate the face position, amniotic membrane position, and bone position in the direction of the ultrasonic beam respectively. According to the maximum value of the target volume data and the preset face threshold, the target face threshold from the bone of the tissue to be measured to the face of the tissue to be measured can be determined as VOIMaxGray*TFa. According to the maximum value of the target volume data and the preset amniotic membrane threshold, the target amniotic membrane threshold from the face of the tissue to be measured through the amniotic fluid to the amniotic membrane can be determined as VOIMaxGray*TFb. According to the maximum value of the target volume data and the preset bone threshold, the target bone threshold can be determined as VOIMaxGray*TBf.

[0070] It can be understood that after obtaining the target face threshold, the target amniotic membrane threshold, and the target bone threshold, the face position PF2 and the amniotic membrane position PF1 of the tissue to be measured can be determined in the original three-dimensional volume data according to the target face threshold, the target amniotic membrane threshold, and the target bone threshold.

[0071] In a specific implementation, in order to accurately locate the face position and the amniotic membrane position, further, determining the face position and the amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data, the target face threshold, the target amniotic membrane threshold, and the target bone threshold includes: determining the bone position of the tissue to be measured according to the original three-dimensional volume data and the target bone threshold; determining the face position of the tissue to be measured in the reverse direction of the ultrasonic beam based on the bone position and the target face threshold; and determining the amniotic membrane position of the tissue to be measured in the reverse direction of the ultrasonic beam according to the face position and the target amniotic membrane threshold.

[0072] It should be noted that in the original three-dimensional volume data, traversing is performed in the ultrasonic beam direction with the target bone threshold VOIMaxGray*TBf to locate the bone position PF of the tissue to be measured. Starting from the bone position PF, traversing and retrieving is performed in the reverse direction of the ultrasonic beam with the target face threshold VOIMaxGray*TFa. The retrieval rule is decreasing. A point smaller than the target face threshold VOIMaxGray*TFa is found, and this point is used as the face position PF2 of the tissue to be measured. Starting from the face position PF2, traversing and retrieving is performed in the reverse direction of the ultrasonic beam with the target amniotic membrane threshold VOIMaxGray*TFb. The retrieval rule is increasing. A point larger than the target amniotic membrane threshold VOIMaxGray*TFb is found, and this point is used as the amniotic membrane position PF1. As Figure 3 shown, there is a 600*600*400 volume data ag in the original three-dimensional volume data. Each volume data ag has a voxel value ag[i][j][k] and a transparency value aw[i][j][k]. k, m, and n are the third dimension of the original three-dimensional volume data, and mm, nn, and ss are the second dimension (ultrasonic beam direction) of the original three-dimensional volume data. The bone position PF of the tissue to be measured is determined in the ultrasonic beam direction according to the target bone threshold. Based on the bone position and the target face threshold VOIMaxGray*TFa, a decreasing retrieval is performed to obtain the face position. Based on the face position and the target amniotic membrane threshold VOIMaxGray*TFb, an increasing detection is performed to obtain the amniotic membrane position.

[0073] Step S30: Determine the target positioning point profile according to the face position and the amniotic membrane position.

[0074] It should be noted that after obtaining the facial position and amniotic membrane position of the tissue to be measured, the target positioning point profile between the facial position and the amniotic membrane position on all ultrasonic beams in the original three-dimensional volume data can be determined. The target positioning point profile AutoFace_D is the critical interface for clearing the transparency of the original three-dimensional volume data.

[0075] Step S40: Clear the transparency of the original three-dimensional volume data according to the target positioning point profile to obtain the facial three-dimensional data of the tissue to be measured.

[0076] It should be noted that after obtaining the target positioning point profile, the transparency of the original three-dimensional volume data is cleared based on the target positioning point profile, so as to obtain the cleared original three-dimensional volume data. The cleared original three-dimensional volume data is the facial three-dimensional data of the tissue to be measured.

[0077] It can be understood that in order to obtain clear facial three-dimensional data and improve the clarity and comprehensiveness of facial imaging, further, the step of clearing the transparency of the original three-dimensional volume data according to the target positioning point profile to obtain the facial three-dimensional data of the tissue to be measured includes: determining the target ultrasonic beam depth according to the target positioning point profile; searching for the clearing area in the original three-dimensional volume data where the ultrasonic beam depth is less than the target ultrasonic beam depth; and clearing the transparency of the clearing area to obtain the facial three-dimensional data of the tissue to be measured.

[0078] In a specific implementation, after obtaining multiple target positioning point profiles AutoFace_D, the target ultrasonic beam depth AutoFace_D[i][j] corresponding to the target positioning point profile is determined. The ultrasonic beam depth in the original three-dimensional volume data that is less than the target ultrasonic beam depth AutoFace_D[i][j] is used as the clearing area, and the transparency of the volume data corresponding to the clearing area is cleared, so as to obtain the cleared original three-dimensional volume data. The irregular tissue information other than in front of the face of the tissue to be measured is identified and cleared to obtain the cleared original three-dimensional volume data.

[0079] Step S50: Complete the three-dimensional imaging display of the face of the tissue to be measured according to the facial three-dimensional data.

[0080] It should be noted that after obtaining the facial three-dimensional data, the facial three-dimensional data is rendered by a ray casting algorithm to obtain the final facial three-dimensional image, and the three-dimensional image of the face is displayed.

[0081] In this embodiment, the original three-dimensional volume data of the tissue to be measured is obtained; the face position and amniotic membrane position of the tissue to be measured are determined according to the original three-dimensional volume data and a preset threshold; a target positioning point section is determined according to the face position and the amniotic membrane position; the transparency of the original three-dimensional volume data is cleared according to the target positioning point section to obtain the three-dimensional face data of the tissue to be measured; and the three-dimensional face imaging display of the tissue to be measured is completed according to the three-dimensional face data. By analyzing the original three-dimensional volume data, the face position of the tissue to be measured and the amniotic membrane position in the original three-dimensional volume data are determined, and a target positioning point section is determined based on the amniotic membrane position and the face position, so as to identify the tissue information before the face of the tissue to be measured. Finally, the transparency of the original three-dimensional volume data is cleared according to the target positioning point section to complete the three-dimensional face imaging display of the tissue to be measured, thereby automatically obtaining a clear, comprehensive and complete face image of the object to be measured, and improving the image rendering effect.

[0082] Reference Figure 4 , Figure 4 is a schematic flowchart of the second embodiment of a three-dimensional face imaging method of the present invention.

[0083] Based on the above first embodiment, in the three-dimensional face imaging method of this embodiment, the step S30 includes:

[0084] Step S31: Obtain preset positioning parameters.

[0085] It should be noted that the preset positioning parameter refers to a coefficient preset for obtaining the target positioning point section. The preset positioning parameter a_TF1TF0 is any value between 0 and 1. In this embodiment, the preset positioning parameter a_TF1TF0 is taken as an example of 0.9 for illustration.

[0086] Step S32: Determine an initial positioning point and a target marker value corresponding to the initial positioning point according to the preset positioning parameter, the amniotic membrane position, and the face position.

[0087] It should be noted that after obtaining the preset positioning parameter, the amniotic membrane position, and the face position, the initial positioning point and the target marker value corresponding to the initial positioning point can be determined according to the preset positioning parameter, the amniotic membrane position, and the face position. There are multiple initial positioning points AutoFace_D, and each initial positioning point corresponds to a target marker value AutoFace_Bflag. The target marker value AutoFace_Bflag is used to determine whether the initial positioning point is valid.

[0088] It can be understood that the amniotic membrane position and the face position are input into the function F to obtain multiple initial positioning points AutoFace_D, where F(PF2, PF1)=PF1+(PF2 - PF1)*a_TF1TF0, and the corresponding target marker value AutoFace_Bflag is obtained according to the positions of the initial positioning points.

[0089] Step S33: Obtain the target length and target width of the original three-dimensional volume data.

[0090] It should be noted that since the original three-dimensional volume data is constructed from multiple two-dimensional images, the target length and target width in the original three-dimensional volume data are obtained.

[0091] Step S34: Determine the target positioning point profile according to the target length, target width, initial positioning points, and the target marker values corresponding to the initial positioning points.

[0092] It should be noted that the target positioning point profile can be determined according to the target length, target width, initial positioning points, and the target marker values corresponding to the initial positioning points, and the length and width of the target positioning point profile are both the target length and target width.

[0093] It can be understood that in order to obtain an accurate target positioning point profile, further, the determining the target positioning point profile according to the target length, target width, initial positioning points, and the target marker values corresponding to the initial positioning points includes: determining a first positioning point profile according to the target length, target width, and initial positioning points; determining the invalid positioning points in the first positioning point profile according to the initial positioning points; and filling the invalid positioning points in the first positioning point profile to obtain the target positioning point profile.

[0094] In a specific implementation, the first positioning point profile is determined according to the target length, target width, and initial positioning points. Since the initial positioning points correspond to the positioning points under each ultrasonic beam, there are states that do not meet the positioning point retrieval. Therefore, the invalid positioning points in the first positioning point profile can be determined according to the initial positioning points. When the corresponding beam in the target marker value AutoFace_Bflag is 1, it indicates valid, and when it is 0, it indicates invalid.

[0095] It should be noted that after obtaining the invalid positioning points, it is necessary to use the values in the area near the invalid positioning points to fill and perfect the invalid positioning points, so as to obtain the target positioning point profile.

[0096] It can be understood that, in order to accurately fill the invalid positioning points to obtain a target positioning point profile that meets the requirements. Further, filling the invalid positioning points in the first positioning point profile to obtain a target positioning point profile includes: obtaining the first wire bundle corresponding to the invalid positioning points; determining a filling module with a preset area according to the first wire bundle; performing profile filling on the first positioning point profile according to a preset interpolation template, the first wire bundle, and the filling module to obtain a second positioning point profile; and performing smoothing processing on the second positioning point profile according to a preset smoothing module to obtain a target positioning point profile.

[0097] In a specific implementation, obtain the wire bundle where the invalid positioning point is located, and use the wire bundle where the invalid positioning point is located as the first wire bundle. Determine a filling module with a preset area with the first wire bundle as the core. The preset area refers to that the length and width of the filling module are both Kernel_width1. In this embodiment, the value of Kernel_width1 is taken as 7, and it can also be other values, but this embodiment takes 7 as an example for illustration. The preset interpolation template refers to a 7*7 matrix AutoFaceKernel1. In this embodiment, the values of the matrix are AutoFaceKernel1

[49] = {1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 0.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f, 1.0f}. Interpolate the position of the invalid positioning point. With the first wire bundle as the center, AutoFaceKernel1 as the template, and the peripheral wire bundles with a preset area of Kernel_width1 as the filling module, the weighted mean of the peripheral wire bundles and the template fills the value corresponding to the invalid positioning point. The specific formula is

[0098] where AutoFace_D[i][j] is the value of the invalid positioning point, Kernel_width1 is the length and width of the filling module, and AutoFaceKernel1 is the preset interpolation template for interpolation. In this embodiment, the values of the elements of the preset interpolation template are all 1.

[0099] It should be noted that after filling the invalid positioning points in the first positioning point profile, an unsmoothed second positioning point profile is obtained. After smoothing the second positioning point profile according to a preset smoothing module, a target positioning point profile is obtained.

[0100] It can be understood that the preset smoothing module refers to the module AutofaceKernel2 with both length and width of Kernel_width2, and the smoothing formula is specifically

[0101] AutoFace_D refers to the filled 600*600 positioning points in the second positioning point profile. In the preset smoothing module, AutoFaceKernel2

[49] = {0.25f, 0.25f, 0.25f, 0.25f, 0.25f, 0.25f, 0.25f, 0.25f, 0.75f, 0.75f, 0.75f, 0.75f, 0.75f, 0.25f, 0.25f, 0.75f, 1.0f, 1.0f, 1.0f, 0.75f, 0.25f, 0.25f, 0.75f, 1.0f, 1.0f, 1.0f, 0.75f, 0.25f, 0.25f, 0.75f, 1.0f, 1.0f, 1.0f, 0.75f, 0.25f, 0.25f, 0.75f, 0.75f, 0.75f, 0.75f, 0.75f, 0.25f, 0.25f, 0.25f, 0.25f, 0.25f, 0.25f, 0.25f, 0.25f}. Finally, the smoothing process of the second positioning point profile is completed to obtain the target positioning point profile.

[0102] In specific implementation, as Figure 5 shown, through ultrasonic three-dimensional volume data acquisition, multiple two-dimensional images of the tissue to be measured are obtained. The two-dimensional images are interpolated and reconstructed to obtain the original three-dimensional volume data of the tissue to be measured. Under the original three-dimensional volume data, the facial position and the anterior amniotic position of the tissue to be measured under the ultrasonic beam are obtained, and the positioning point profiles of the tissue to be measured on all ultrasonic beams in the original three-dimensional volume data are obtained, the positioning point profiles are filled and perfected, and the filled and perfected positioning point profiles are smoothed. Finally, three-dimensional imaging and display are performed on the obtained facial three-dimensional data according to the ray casting algorithm.

[0103] In this embodiment, preset positioning parameters are obtained; an initial positioning point and a target marker value corresponding to the initial positioning point are determined according to the preset positioning parameters, the amniotic membrane position, and the face position; a target length and a target width of the original three-dimensional volume data are obtained; and a target positioning point profile is determined according to the target length, the target width, the initial positioning point, and the target marker value corresponding to the initial positioning point. By using the preset positioning parameters, the amniotic membrane position, and the face position to determine the initial positioning point and the target marker value corresponding to the initial positioning point, an accurate target positioning point profile is obtained based on the target length, the target width, the initial positioning point, and the target marker value corresponding to the initial positioning point, improving the accuracy during subsequent transparency clearing.

[0104] In addition, referring to Figure 6 , this embodiment also provides a facial three-dimensional imaging device, which includes:

[0105] An acquisition module 10, configured to acquire the original three-dimensional volume data of the tissue to be measured.

[0106] A determination module 20, configured to determine the face position and the amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold.

[0107] The determination module 20 is further configured to determine a target positioning point profile according to the face position and the amniotic membrane position.

[0108] A clearing module 30, configured to clear the transparency of the original three-dimensional volume data according to the target positioning point profile to obtain the facial three-dimensional data of the tissue to be measured.

[0109] A display module 40, configured to complete the facial three-dimensional imaging display of the tissue to be measured according to the facial three-dimensional data.

[0110] In this embodiment, the original three-dimensional volume data of the tissue to be measured is acquired; the face position and the amniotic membrane position of the tissue to be measured are determined according to the original three-dimensional volume data and a preset threshold; a target positioning point profile is determined according to the face position and the amniotic membrane position; the transparency of the original three-dimensional volume data is cleared according to the target positioning point profile to obtain the facial three-dimensional data of the tissue to be measured; and the facial three-dimensional imaging display of the tissue to be measured is completed according to the facial three-dimensional data. By analyzing the original three-dimensional volume data to determine the face position of the tissue to be measured and the amniotic membrane position in the original three-dimensional volume data, and determining the target positioning point profile based on the amniotic membrane position and the face position, the tissue information before the face of the tissue to be measured is identified. Finally, the transparency of the original three-dimensional volume data is cleared according to the target positioning point profile to complete the facial three-dimensional imaging display of the tissue to be measured, thereby obtaining a clear and comprehensive facial image of the object to be measured, improving the image rendering effect, and automatically obtaining a clear, comprehensive, and complete facial image of the object to be measured, improving the image rendering effect.

[0111] In one embodiment, the determining module 20 is further configured to obtain a preset face threshold, a preset amniotic membrane threshold, and a preset bone threshold;

[0112] Determine the maximum value of the target volume data according to the original three-dimensional volume data;

[0113] Determine a target face threshold, a target amniotic membrane threshold, and a target bone threshold according to the maximum value of the target volume data, the preset face threshold, the preset amniotic membrane threshold, and the preset bone threshold;

[0114] Determine the face position and the amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data, the target face threshold, the target amniotic membrane threshold, and the target bone threshold.

[0115] In one embodiment, the determining module 20 is further configured to determine the bone position of the tissue to be measured according to the original three-dimensional volume data and the target bone threshold;

[0116] Determine the face position of the tissue to be measured in the reverse direction of the ultrasonic beam based on the bone position and the target face threshold;

[0117] Determine the amniotic membrane position of the tissue to be measured in the reverse direction of the ultrasonic beam according to the face position and the target amniotic membrane threshold.

[0118] In one embodiment, the determining module 20 is further configured to obtain a preset positioning parameter;

[0119] Determine an initial positioning point and a target marker value corresponding to the initial positioning point according to the preset positioning parameter, the amniotic membrane position, and the face position;

[0120] Obtain the target length and target width of the original three-dimensional volume data;

[0121] Determine a target positioning point profile according to the target length, the target width, the initial positioning point, and the target marker value corresponding to the initial positioning point.

[0122] In one embodiment, the determining module 20 is further configured to determine a first positioning point profile according to the target length, the target width, and the initial positioning point;

[0123] Determine invalid positioning points in the first positioning point profile according to the initial positioning point;

[0124] Fill the invalid positioning points in the first positioning point profile to obtain a target positioning point profile.

[0125] In one embodiment, the determining module 20 is further configured to obtain a first beam corresponding to the invalid positioning point;

[0126] Determine a filling module with a preset area according to the first wire harness;

[0127] Perform profile filling on the first positioning point profile according to a preset interpolation template, the first wire harness, and the filling module to obtain a second positioning point profile;

[0128] Perform smoothing processing on the second positioning point profile according to a preset smoothing module to obtain a target positioning point profile.

[0129] In an embodiment, the clearing module 30 is further configured to determine a target ultrasonic beam depth according to the target positioning point profile;

[0130] Search for a clearing area in the original three-dimensional volume data where the ultrasonic beam depth is less than the target ultrasonic beam depth;

[0131] Perform transparency clearing on the clearing area to obtain the three-dimensional face data of the tissue to be measured.

[0132] Since this device adopts all the technical solutions of the above-mentioned all embodiments, it has at least all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be elaborated here one by one.

[0133] In addition, an embodiment of the present invention further provides a storage medium, on which a three-dimensional face imaging program is stored. When the three-dimensional face imaging program is executed by a processor, the steps of the three-dimensional face imaging method as described above are implemented.

[0134] Since this storage medium adopts all the technical solutions of the above-mentioned all embodiments, it has at least all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be elaborated here one by one.

[0135] It should be noted that the above-described work process is only illustrative and does not limit the protection scope of the present invention. In actual applications, those skilled in the art can select some or all of them according to actual needs to achieve the purpose of the solution of this embodiment, and no limitation is made here.

[0136] In addition, for the technical details not described in detail in this embodiment, reference can be made to the three-dimensional face imaging method provided in any embodiment of the present invention, which will not be elaborated here.

[0137] In addition, it should be noted that in this text, the terms "including", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or system including such element.

[0138] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0139] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as Read Only Memory (ROM) / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0140] The above are only the preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or equivalent process transformation made by using the description of the present invention and the drawings, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A three-dimensional facial imaging method, characterized in that, the three-dimensional facial imaging method includes: obtaining original three-dimensional volume data of a tissue to be measured; determining the facial position and amniotic position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold; determining a target positioning point profile according to the facial position and the amniotic position; performing transparency clearing on the original three-dimensional volume data according to the target positioning point profile to obtain three-dimensional facial data of the tissue to be measured; completing three-dimensional facial imaging display of the tissue to be measured according to the three-dimensional facial data; wherein, the determining a target positioning point profile according to the facial position and the amniotic position includes: obtaining preset positioning parameters; determining an initial positioning point and a target marker value corresponding to the initial positioning point according to the preset positioning parameters, the amniotic position, and the facial position; obtaining a target length and a target width of the original three-dimensional volume data; determining a target positioning point profile according to the target length, the target width, the initial positioning point, and the target marker value corresponding to the initial positioning point.

2. The three-dimensional facial imaging method according to claim 1, characterized in that, the determining the facial position and the amniotic position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold includes: obtaining a preset facial threshold, a preset amniotic threshold, and a preset bone threshold; determining a maximum value of target volume data according to the original three-dimensional volume data; determining a target facial threshold, a target amniotic threshold, and a target bone threshold according to the maximum value of the target volume data, the preset facial threshold, the preset amniotic threshold, and the preset bone threshold; determining the facial position and the amniotic position of the tissue to be measured according to the original three-dimensional volume data, the target facial threshold, the target amniotic threshold, and the target bone threshold.

3. The three-dimensional facial imaging method according to claim 2, characterized in that, the determining the facial position and the amniotic position of the tissue to be measured according to the original three-dimensional volume data, the target facial threshold, the target amniotic threshold, and the target bone threshold includes: determining the bone position of the tissue to be measured according to the original three-dimensional volume data and the target bone threshold; determining the facial position of the tissue to be measured in the reverse direction of the ultrasonic beam based on the bone position and the target facial threshold; determining the amniotic position of the tissue to be measured in the reverse direction of the ultrasonic beam according to the facial position and the target amniotic threshold.

4. The three-dimensional facial imaging method according to claim 1, characterized in that, the determining a target positioning point profile according to the target length, the target width, the initial positioning point, and the target marker value corresponding to the initial positioning point includes: determining a first positioning point profile according to the target length, the target width, and the initial positioning point; determining invalid positioning points in the first positioning point profile according to the initial positioning point; filling the invalid positioning points in the first positioning point profile to obtain a target positioning point profile.

5. The three-dimensional facial imaging method according to claim 4, characterized in that, the filling the invalid positioning points in the first positioning point profile to obtain a target positioning point profile includes: Obtain the first wire harness corresponding to the invalid positioning point; Determine a filling module with a preset area according to the first wire harness; Perform profile filling on the first positioning point profile according to a preset interpolation template, the first wire harness, and the filling module to obtain a second positioning point profile; Perform smoothing processing on the second positioning point profile according to a preset smoothing module to obtain a target positioning point profile.

6. The three-dimensional face imaging method according to any one of claims 1 to 5, characterized in that the step of clearing the transparency of the original three-dimensional volume data according to the target positioning point profile to obtain the three-dimensional face data of the tissue to be measured includes: Determine the depth of the target ultrasonic beam according to the target positioning point profile; Search for a clearing area in the original three-dimensional volume data where the depth of the ultrasonic beam is less than the depth of the target ultrasonic beam; Clear the transparency of the clearing area to obtain the three-dimensional face data of the tissue to be measured.

7. A three-dimensional face imaging device, characterized in that the three-dimensional face imaging device includes: An acquisition module for acquiring the original three-dimensional volume data of the tissue to be measured; A determination module for determining the face position and the amniotic membrane position of the tissue to be measured according to the original three-dimensional volume data and a preset threshold; The determination module is further configured to determine a target positioning point profile according to the face position and the amniotic membrane position; A clearing module for clearing the transparency of the original three-dimensional volume data according to the target positioning point profile to obtain the three-dimensional face data of the tissue to be measured; A display module for completing the three-dimensional face imaging display of the tissue to be measured according to the three-dimensional face data; The determination module is further configured to obtain preset positioning parameters; Determine an initial positioning point and a target marker value corresponding to the initial positioning point according to the preset positioning parameters, the amniotic membrane position, and the face position; Obtain the target length and target width of the original three-dimensional volume data; Determine a target positioning point profile according to the target length, target width, initial positioning point, and the target marker value corresponding to the initial positioning point.

8. A three-dimensional face imaging device, characterized in that the device includes: a memory, a processor, and a three-dimensional face imaging program stored on the memory and executable on the processor, and the three-dimensional face imaging program is configured to implement the three-dimensional face imaging method according to any one of claims 1 to 6.

9. A storage medium, characterized in that a three-dimensional face imaging program is stored on the storage medium, and when the three-dimensional face imaging program is executed by a processor, it implements the three-dimensional face imaging method according to any one of claims 1 to 6.

Images