A method and device for constructing a three-dimensional model of a face difference mask

Abstract

The present invention discloses a method and device for constructing a three-dimensional face difference mask model. The method comprises: obtaining a target face model and a recipient face model; modifying the normals of the target face model and the recipient face model; aligning the target face model and the recipient face model according to the normals; performing a Boolean merge operation on the target face model and the recipient face model to obtain a three-dimensional face difference mask model; filling the non-bridging areas of the three-dimensional face difference mask model to form an overall closed surface; and processing the joints of the three-dimensional face difference mask model to generate a target face difference mask model. The present invention can ensure that the mask fits perfectly when worn by the recipient, improving comfort and concealment. If the model is made of a soft structure such as silicone, it can also facilitate expression transmission when worn. The method has broad application prospects in the fields of security protection, counter-terrorism, counter-espionage, and security system testing.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional modeling, and in particular to a method and device for constructing a three-dimensional model of a face difference mask. Background Art

[0002] In recent years, with the development of facial recognition technology, facial masks have attracted the attention of research institutions worldwide in the fields of security, counterterrorism, counterespionage, and security system testing. By obtaining a 3D model of a target's face, researchers can create a similar facial mask and use it to crack the target's facial recognition authentication systems (such as access control systems and mobile phones).

[0003] However, existing models used to manufacture target face masks are generally single-face 3D patch models, which are stretched to a certain thickness and then 3D printed or remolded. Although the external shape of the traditional 3D face model produced in this way is consistent with the target face, the internal shape does not fit the recipient face. This not only makes it uncomfortable to wear, but also makes the mask appear abrupt and less concealed due to the poor fit. In addition, if a soft silicone mask is made from a traditional face model, the incorrect internal shape will cause the overall face shape to be deformed when worn, greatly reducing the external face shape's ability to crack the face recognition system, and further making it impossible to achieve the expression transmission effect. Summary of the Invention

[0004] The technical problem solved by the present invention is to overcome the deficiencies of the prior art and provide a method and device for constructing a three-dimensional model of a face difference mask.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for constructing a three-dimensional model of a face difference mask, comprising:

[0006] Obtaining a target face model and a recipient face model;

[0007] Modifying the normals of the target face model and the recipient face model;

[0008] aligning the target face model and the recipient face model according to the normal;

[0009] Performing a Boolean merge operation on the target face model and the receptor face model to obtain a face difference mask three-dimensional model;

[0010] Filling the non-bridging area of ​​the three-dimensional model of the face difference mask to form an overall closed surface;

[0011] The spliced ​​parts of the face difference mask three-dimensional model are processed to generate a target face difference mask model.

[0012] Optionally, modifying the normals of the target face model and the recipient face model includes:

[0013] The normal of the target face model is modified to face outward, and the normal of the recipient face model is modified to face inward.

[0014] Optionally, aligning the target face model and the recipient face model according to the normal direction includes:

[0015] The distance between the receptor face model and the target face model is adjusted to 0.5-10 mm, and the overall directions of the target face model and the receptor face model are adjusted to 180°.

[0016] Optionally, performing a Boolean merging operation on the target face model and the recipient face model to obtain a face difference mask three-dimensional model includes:

[0017] Adjacent face patches of the curved surface of the target face model and the curved surface of the receptor face model are bridged so that the target face model and the receptor face model are connected as an overall curved surface to form the face difference mask three-dimensional model.

[0018] Optionally, processing the spliced ​​portion of the face difference mask three-dimensional model to generate a target face difference mask model includes:

[0019] The joints of the three-dimensional face difference mask model are smoothed, cropped, and trimmed to form a smooth and uniform target difference mask model.

[0020] In order to solve the above technical problems, an embodiment of the present invention provides a device for constructing a three-dimensional model of a face difference mask, comprising:

[0021] A face model acquisition module is used to acquire a target face model and a receptor face model;

[0022] A model normal modification module, used to modify the normals of the target face model and the recipient face model;

[0023] a model alignment module, configured to align the target face model and the recipient face model according to the normal direction;

[0024] A three-dimensional model acquisition module is used to perform a Boolean merge operation on the target face model and the receptor face model to obtain a three-dimensional face difference mask model;

[0025] A closed surface forming module, configured to fill the non-bridging area of ​​the three-dimensional model of the face difference mask to form an overall closed surface;

[0026] The target mask model generation module is used to process the splicing parts of the face difference mask three-dimensional model to generate a target face difference mask model.

[0027] Optionally, the model normal modification module includes:

[0028] The model normal modification unit is used to modify the normal of the target face model to face outward, and to modify the normal of the recipient face model to face inward.

[0029] Optionally, the model alignment module includes:

[0030] The model alignment unit is used to adjust the distance between the receptor face model and the target face model to 0.5-10 mm, and adjust the overall direction of the target face model and the receptor face model to 180 degrees.

[0031] Optionally, the three-dimensional model acquisition module includes:

[0032] The three-dimensional model forming unit is used to bridge the adjacent surface patches of the target face model and the recipient face model so that the target face model and the recipient face model are connected as an overall surface to form the face difference mask three-dimensional model.

[0033] Optionally, the target mask model generation module includes:

[0034] The target mask model forming unit is used to smooth, crop and trim the joints of the face difference mask three-dimensional model to form a smooth and uniform target difference mask model.

[0035] The advantages of the present invention compared with the prior art are:

[0036] The embodiments of the present invention can ensure a perfect fit when worn by the recipient, improving comfort and concealment. If the model is made of a soft structure such as silicone, it can also help convey facial expressions when worn. It has broad application prospects in security protection, counter-terrorism, counter-espionage, and security system testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flowchart of the steps of a method for constructing a three-dimensional model of a face difference mask provided by an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of a recipient face model and a target face model provided by an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of the normal directions of a receptor face model and a target face model provided by an embodiment of the present invention;

[0040] Figure 4 A schematic diagram of modifying the normal direction of a model provided by an embodiment of the present invention;

[0041] Figure 5 A schematic diagram of a three-dimensional face difference mask model provided by an embodiment of the present invention;

[0042] Figure 6 A schematic diagram of filling a non-bridging area of ​​a model provided by an embodiment of the present invention;

[0043] Figure 7 A schematic diagram of a target difference mask model provided by an embodiment of the present invention;

[0044] Figure 8 A schematic structural diagram of a device for constructing a three-dimensional model of a face difference mask provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] Example 1

[0046] Reference Figure 1 , shows a flowchart of the steps of a method for constructing a three-dimensional model of a face difference mask provided by an embodiment of the present invention, such as Figure 1 As shown, the method may include:

[0047] Step 101: Obtain a target face model and a recipient face model.

[0048] In this embodiment, the target face model and the recipient face model are both STL format patch models, such as Figure 2 As shown, the ratio of the target face model to the recipient face model is 1:1.

[0049] In a specific implementation, when designing a face difference mask model, a target face model and a receptor face model can be obtained.

[0050] After the target face model and the recipient face model are acquired, step 102 is executed.

[0051] Step 102: Modify the normals of the target face model and the recipient face model.

[0052] After obtaining the target face model and the receptor face model, the normals of the target face model and the receptor face model can be modified. Specifically, the normals of the target face model and the receptor face model are modified so that the normal of the target face model is super-outward and the normal of the receptor face model is inward, and the overall normals of the two models are 180°, such as Figure 3 and Figure 4 As mentioned above, the model normal before modification is as follows Figure 3 As shown, the modified model normal is as follows Figure 4In this example, the distance between the recipient face model and the target face model is 0.5 to 5 mm. Since the two face models are of similar size, the target face model does not need to be scaled.

[0053] After the normals of the target face model and the recipient face model are modified, step 103 is performed.

[0054] Step 103: Align the target face model and the recipient face model according to the normal direction.

[0055] After modifying the normals of the target face model and the recipient face model, the target face model and the recipient face model can be aligned according to the modified normals. Specifically, the target face model and the recipient face model are aligned so that the overall normals are 180 degrees. The distance between the recipient face model and the target face model is set to 0.5 to 10 mm. If necessary, the scaling ratio of the target face model can be adjusted within the range of 0.9 to 1.1 times.

[0056] After the target face model and the recipient face model are aligned according to the normal direction, step 104 is performed.

[0057] Step 104: performing a Boolean merge operation on the target face model and the receptor face model to obtain a face difference mask three-dimensional model.

[0058] After aligning the target face model and the receptor face model according to the normal, the target face model and the receptor face model can be subjected to a Boolean merge operation to obtain a face difference mask three-dimensional model. Specifically, the target face model and the receptor face model are subjected to a Boolean merge operation, that is, the two models are merged into one model. At this time, an overall three-dimensional model including the two surfaces of the target face and the receptor face is formed. The target face surface and the receptor face surface are bridged at the forehead and the chin respectively, so that the target face model and the receptor face model are connected as an overall surface to form a face difference mask three-dimensional model, as shown in the attached figure. Figure 5 shown.

[0059] After the target face model and the recipient face model are subjected to a Boolean merge operation to obtain a face difference mask three-dimensional model, step 105 is executed.

[0060] Step 105: Fill the non-bridging area of ​​the face difference mask three-dimensional model to form an overall closed surface.

[0061] After the target face model and the receptor face model are subjected to a Boolean merge operation to obtain a face difference mask 3D model, the non-bridging area of ​​the face difference mask 3D model can be filled to form an overall closed surface. Specifically, the holes (non-bridging area) of the face difference mask 3D model are filled to form an overall closed surface, as shown in the attached figure. Figure 6 shown.

[0062] Of course, in the process of bridging the target face model and the recipient face model patches, the location and number of the bridges are not limited, and it is only necessary to connect the two models into an overall surface.

[0063] After the non-bridging area of ​​the face difference mask three-dimensional model is filled to form an overall closed surface, step 106 is performed.

[0064] Step 106: Process the joints of the face difference mask three-dimensional model to generate a target face difference mask model.

[0065] After filling the non-bridging area of ​​the face difference mask 3D model to form an overall closed surface, the joints of the face difference mask 3D model can be processed to generate a target face difference mask model. Specifically, the joints of the face difference mask 3D model are smoothed and trimmed to form a smooth and uniform difference mask model, as shown in the attached figure. Figure 7 shown.

[0066] The above-mentioned solution provided by the embodiment of the present invention is simple to operate. It only requires two facial patch models, the subject and the target, to form a wearable difference mask model. The facial difference mask model formed by this method is a complete and closed three-dimensional surface model, suitable for various 3D printing processes and convenient and practical to manufacture.

[0067] The method for constructing a three-dimensional face difference mask model provided by the present invention ensures a perfect fit when worn by the recipient, improving comfort and concealment. If the model is made of a soft structure such as silicone, it also facilitates the transmission of facial expressions when worn. It has broad application prospects in security protection, counterterrorism, counterespionage, and security system testing.

[0068] Example 2

[0069] Reference Figure 8 , shows a schematic structural diagram of a device for constructing a three-dimensional face difference mask model according to an embodiment of the present invention, such as Figure 8 As shown, the device may include:

[0070] The face model acquisition module 810 is used to acquire the target face model and the recipient face model;

[0071] A model normal modification module 820 is used to modify the normals of the target face model and the recipient face model;

[0072] A model alignment module 830 is configured to align the target face model and the recipient face model according to the normal direction;

[0073] A three-dimensional model acquisition module 840 is configured to perform a Boolean merge operation on the target face model and the recipient face model to obtain a face difference mask three-dimensional model;

[0074] A closed surface forming module 850 is configured to fill the non-bridging area of ​​the face difference mask three-dimensional model to form an overall closed surface;

[0075] The target mask model generating module 860 is used to process the splicing parts of the face difference mask three-dimensional model to generate a target face difference mask model.

[0076] Optionally, the model normal modification module includes:

[0077] The model normal modification unit is used to modify the normal of the target face model to face outward, and to modify the normal of the recipient face model to face inward.

[0078] Optionally, the model alignment module includes:

[0079] The model alignment unit is used to adjust the distance between the receptor face model and the target face model to 0.5-10 mm, and adjust the overall direction of the target face model and the receptor face model to 180 degrees.

[0080] Optionally, the three-dimensional model acquisition module includes:

[0081] The three-dimensional model forming unit is used to bridge the adjacent surface patches of the target face model and the recipient face model so that the target face model and the recipient face model are connected as an overall surface to form the face difference mask three-dimensional model.

[0082] Optionally, the target mask model generation module includes:

[0083] The target mask model forming unit is used to smooth, crop and trim the joints of the face difference mask three-dimensional model to form a smooth and uniform target difference mask model.

[0084] The device for constructing a three-dimensional face mask model using difference values, provided by the present invention, ensures a perfect fit when worn by the wearer, improving comfort and concealment. If the model is made of a soft structure such as silicone, it also facilitates the transmission of facial expressions when worn. It has broad application prospects in security protection, counterterrorism, counterespionage, and security system testing.

[0085] The specific embodiments described in this application can help those skilled in the art to more fully understand this application, but do not limit this application in any way. Therefore, those skilled in the art should understand that this application can still be modified or replaced by equivalents; and all technical solutions and improvements that do not deviate from the spirit and technical essence of this application should be included in the scope of protection of the patent application.

[0086] The contents not described in detail in the specification of the present invention belong to the common knowledge of those skilled in the art.

Claims

1. A method for constructing a three-dimensional face difference mask model, characterized in that: include: Obtaining a target face model and a recipient face model; Modifying the normals of the target face model and the recipient face model; aligning the target face model and the recipient face model according to the normal; Performing a Boolean merge operation on the target face model and the receptor face model to obtain a face difference mask three-dimensional model; Filling the non-bridging area of ​​the three-dimensional model of the face difference mask to form an overall closed surface; Processing the splicing parts of the face difference mask three-dimensional model to generate a target face difference mask model; The modifying of the normals of the target face model and the recipient face model comprises: Modifying the normal of the target face model to face outward, and modifying the normal of the recipient face model to face inward; The aligning the target face model and the recipient face model according to the normal direction includes: Adjusting the distance between the receptor face model and the target face model to 0.5-10 mm, and adjusting the overall direction of the target face model and the receptor face model to 180°; The step of performing a Boolean merging operation on the target face model and the receptor face model to obtain a face difference mask three-dimensional model comprises: Bridging adjacent patches of the curved surface of the target face model and the curved surface of the recipient face model, so that the target face model and the recipient face model are connected into an integral curved surface, thereby forming the face difference mask three-dimensional model; The processing of the splicing portion of the face difference mask three-dimensional model to generate a target face difference mask model includes: The joints of the three-dimensional face difference mask model are smoothed, cropped, and trimmed to form a smooth and uniform target difference mask model.

2. A device for constructing a three-dimensional model of a face difference mask, characterized in that: include: A face model acquisition module is used to acquire a target face model and a receptor face model; A model normal modification module, used to modify the normals of the target face model and the recipient face model; a model alignment module, configured to align the target face model and the recipient face model according to the normal direction; A three-dimensional model acquisition module is used to perform a Boolean merge operation on the target face model and the receptor face model to obtain a three-dimensional face difference mask model; A closed surface forming module, configured to fill the non-bridging area of ​​the three-dimensional model of the face difference mask to form an overall closed surface; A target mask model generation module is used to process the splicing portion of the face difference mask three-dimensional model to generate a target face difference mask model; The modifying of the normals of the target face model and the recipient face model comprises: Modifying the normal of the target face model to face outward, and modifying the normal of the recipient face model to face inward; The aligning the target face model and the recipient face model according to the normal direction includes: Adjusting the distance between the receptor face model and the target face model to 0.5-10 mm, and adjusting the overall direction of the target face model and the receptor face model to 180°; The step of performing a Boolean merging operation on the target face model and the receptor face model to obtain a face difference mask three-dimensional model comprises: Bridging adjacent patches of the curved surface of the target face model and the curved surface of the recipient face model, so that the target face model and the recipient face model are connected into an integral curved surface, thereby forming the face difference mask three-dimensional model; The processing of the splicing portion of the face difference mask three-dimensional model to generate a target face difference mask model includes: The joints of the three-dimensional face difference mask model are smoothed, cropped, and trimmed to form a smooth and uniform target difference mask model.

Images