A symmetry detection method and intelligent device

Abstract

The present invention discloses a symmetry detection method and intelligent device. By performing key point detection on a reference image, key point information of symmetrical parts of facial features can be accurately located and identified. A detection line for auxiliary detection of whether the symmetrical parts are symmetrical is determined through the key point information. Afterwards, the detection line and facial key point information are used to determine whether the symmetrical parts of the face are symmetrical, and the symmetry can be displayed on a display with a mirror display function, thereby providing auxiliary information and guidance for users to put on makeup.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent devices, and in particular to a symmetry detection method and an intelligent device. Background Art

[0002] In daily life, for users who need to put on makeup, when they put on makeup in front of a mirror, especially when they put on makeup or trim their eyebrows, due to people's makeup habits, they usually put the side that needs to be made up close to the mirror, which will cause problems such as different heights and lengths of the eyebrows drawn or trimmed, thereby making the eyebrow makeup asymmetrical, or the makeup drawn cannot meet the user's requirements due to the asymmetry of other parts.

[0003] Based on this, how to help users perform symmetry detection when applying makeup so as to achieve the makeup look required by the users is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the invention

[0004] The present invention provides a symmetry detection method and an intelligent device, which are used to solve the problem of how to help a user perform symmetry detection when putting on makeup so as to achieve a makeup look required by the user.

[0005] According to a first aspect of an embodiment of the present application, there is provided a smart device, including:

[0006] A display configured to display a picture, wherein the display has a mirror display function;

[0007] The image collector is configured to: collect the user's facial information, obtain a reference image and transmit it to the processor;

[0008] The processor is configured to:

[0009] Receive a reference image sent by the image collector, perform key point detection on the reference image to obtain facial key point information, wherein the facial key point information includes key point information of at least one pair of symmetrical parts of facial features, and the symmetrical parts satisfy at least one geometric symmetry feature;

[0010] Determining, according to the facial key point information, a detection line for assisting in detecting whether the symmetrical parts are symmetrical, and displaying the detection line on the display;

[0011] Based on the detection line and the facial key point information, it is determined whether the symmetrical part is symmetrical and the result is output.

[0012] Optionally, the facial key point information includes nose bridge key point information, and the processor is configured to:

[0013] Determine the central vertical auxiliary line of the face according to the key point information of the bridge of the nose, and draw a vertical line from the key point of any symmetrical part to the central vertical auxiliary line according to the key point information of the symmetrical part to obtain at least one horizontal auxiliary line;

[0014] Using the central vertical auxiliary line and at least one horizontal auxiliary line as the detection line, and displaying correction prompt information on the display when it is determined that the face needs to be corrected according to the detection line;

[0015] The processor is specifically configured to perform key point detection on the corrected reference image captured again by the image collector to determine the facial key point information.

[0016] Optionally, the processor is configured to:

[0017] When it is determined that the at least one horizontal auxiliary line is not parallel to the horizontal axis of the reference image or the vertical distances between the same key points of any pair of symmetrical parts and the central vertical auxiliary line are not equal, it is determined that correction is required.

[0018] Optionally, the processor is configured to:

[0019] If it is determined to output the result of whether the symmetrical part is symmetrical, the result of whether the symmetrical part is symmetrical is output on the display through the change information of the detection line and / or through text information;

[0020] If it is determined to output the correction prompt information, the correction prompt information is output and displayed on the display through the change information of the detection line and / or through text information.

[0021] Optionally, it also includes:

[0022] A player is configured to play voice prompt information;

[0023] The processor is configured to:

[0024] If it is determined to output the result of whether the symmetrical part is symmetrical, output corresponding voice prompt information through the player according to the result of whether the symmetrical part is symmetrical;

[0025] If it is determined to output the correction prompt information, corresponding voice prompt information is output through the player according to the correction prompt information.

[0026] Optionally, the symmetrical parts include eyes and / or eyebrows, and the processor is configured to:

[0027] According to the eye key point information, a vertical line is drawn from the key point where the inner corner of any eye is located to the central vertical auxiliary line to obtain a first horizontal auxiliary line; and / or

[0028] According to the eyebrow key point information, a vertical line is drawn from the key point where the beginning of any eyebrow is located to the central vertical auxiliary line to obtain a second horizontal auxiliary line.

[0029] Optionally, the processor is configured to:

[0030] Based on the detection line and facial key point information, calculate geometric feature parameters and determine satisfied geometric symmetry features;

[0031] When at least one geometric symmetry feature satisfied by any pair of symmetrical parts is determined, and all geometric symmetry features satisfied by the pair of symmetrical parts are determined based on the geometric feature parameters, the symmetrical parts are determined to be symmetrical, otherwise the unsatisfied geometric symmetry features are displayed on the display.

[0032] Optionally, the geometric feature parameters include a first distance from a key point at a specified position of the eyebrow to a central vertical auxiliary line, a second distance between key points at the eyebrow start and eyebrow end, a line between two highest key points of the eyebrow, a line between two lowest key points of the eyebrow, and a third distance from a key point at an upper and / or lower position of the eyebrow to a first horizontal auxiliary line. The processor is configured to perform at least one of the following steps:

[0033] If the difference between the first distances corresponding to the same designated positions of the two eyebrows does not exceed the first preset threshold, it is determined that the geometric symmetry feature of the left and right positions of the eyebrows is satisfied;

[0034] If the second distances corresponding to the two eyebrows are not greater than the second preset threshold, it is determined that the geometric symmetry feature of the left and right lengths of the eyebrows is symmetrical;

[0035] If the line between the highest key points of the two eyebrows and the line between the lowest key points are parallel to the horizontal axis of the reference image, a geometric symmetry feature that satisfies the symmetry of the height of the eyebrows is determined;

[0036] If the difference between the third distances corresponding to the same position on the upper and / or lower sides of the two eyebrows does not exceed the third preset threshold, it is determined that the geometric symmetry feature of the eyebrow height symmetry is satisfied.

[0037] Optionally, the geometric feature parameters include a fourth distance from a key point at a specified eye position to a central vertical auxiliary line, and a line between two highest key points of the eyes and a line between two lowest key points. The processor is configured to perform at least one of the following steps:

[0038] If the difference between the fourth distances corresponding to the same designated positions of the two eyes does not exceed a fourth preset threshold, determining that the geometric symmetry feature that satisfies the symmetry of the left and right positions of the eyes is satisfied;

[0039] If the line between the highest key points of the two eyes and the line between the lowest key points are parallel to the horizontal axis of the reference image, a geometric symmetry feature that satisfies the symmetry of the high and low positions of the eyes is determined.

[0040] According to a second aspect of an embodiment of the present application, a symmetry detection method is provided, the device comprising:

[0041] Receive a reference image sent by the image collector, perform key point detection on the reference image to obtain facial key point information, wherein the facial key point information includes key point information of at least one pair of symmetrical parts of facial features, and the symmetrical parts satisfy at least one geometric symmetry feature;

[0042] Determining, according to the facial key point information, a detection line for assisting in detecting whether the symmetrical parts are symmetrical, and displaying the detection line on the display;

[0043] Based on the detection line and the facial key point information, it is determined whether the symmetrical part is symmetrical and the result is output.

[0044] According to the third aspect of an embodiment of the present application, a chip is provided, which is coupled to a storage unit in a user device so that the chip calls program instructions stored in the storage unit during operation to implement the above-mentioned various aspects of the embodiment of the present application and any possible method involved in each aspect.

[0045] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores program instructions. When the computer-readable storage medium is run on a computer, the computer executes the above-mentioned various aspects of the embodiment of the present application and any possible method involved in each aspect.

[0046] According to a fifth aspect of an embodiment of the present application, a computer program product is provided. When the computer program product is run on an electronic device, the electronic device executes and implements the above-mentioned various aspects of the embodiment of the present application and any possible method involved in each aspect.

[0047] In addition, the technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by different implementation methods in the first aspect, and will not be repeated here.

[0048] The symmetry detection method and intelligent device provided by the present invention have the following beneficial effects:

[0049] A symmetry detection method and intelligent device provided by the present invention can accurately locate and identify the key point information of symmetrical parts of facial features by performing key point detection on a reference image, determine the detection line for auxiliary detection of whether the symmetrical parts are symmetrical through the above key point information, and then use the detection line and facial key point information to determine whether the symmetrical parts of the face are symmetrical, and can display it on a display with a mirror display function, so as to provide auxiliary information and guidance for users to put on makeup. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0051] Figure 1 A schematic diagram of an asymmetric eyebrow provided by an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of the structure of an intelligent device provided by an embodiment of the present invention;

[0053] Figure 3 A schematic diagram of the structure of an intelligent device provided by an embodiment of the present invention;

[0054] Figure 4 A schematic diagram of a method for performing key point detection on a reference image to obtain facial key point information provided by an embodiment of the present invention;

[0055] Figure 5 A schematic diagram of the effect of using the PFLD key point detection algorithm to detect 98 key points of a face provided by an embodiment of the present invention;

[0056] Figure 6 A schematic diagram of the structure of an intelligent device provided by an embodiment of the present invention;

[0057] Figure 7 A schematic diagram of a correction process for a tilted face in a reference image provided by an embodiment of the present invention;

[0058] Figure 8 A schematic diagram of a central vertical line and horizontal auxiliary lines of a reference image provided by an embodiment of the present invention;

[0059] Fig. 9 A schematic diagram of a method for determining eyebrow symmetry provided by an embodiment of the present invention;

[0060] Fig.10 A schematic diagram of a method for determining eyebrow symmetry provided by an embodiment of the present invention;

[0061] Fig.11 A schematic diagram of a method for determining the symmetry of eyes and mouth provided by an embodiment of the present invention;

[0062] Fig.12 A schematic diagram of a symmetry detection method provided by an embodiment of the present invention;

[0063] Fig.13 A schematic diagram of a symmetry detection method provided by an embodiment of the present invention;

[0064] Fig.14 A schematic diagram of a symmetry detection method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0067] The application scenarios described in the embodiments of the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention, and do not constitute a limitation on the technical solutions provided by the embodiments of the present invention. It is known to those skilled in the art that with the emergence of new application scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0068] like Figure 1 As shown, when applying makeup or trimming eyebrows, due to the different shapes of individual eyebrows and makeup habits, it is easy to cause the height of the eyebrows to be asymmetrical or the thickness to be asymmetrical. In view of the above reasons, an embodiment of the present invention provides a smart device, such as Figure 2 As shown, it may include:

[0069] A display 201 is configured to display images, wherein the display has a mirror display function;

[0070] The image collector 202 is configured to: collect the user's facial information, obtain a reference image and transmit it to the processor;

[0071] The processor 203 is configured to:

[0072] Receive a reference image sent by an image collector, perform key point detection on the reference image to obtain facial key point information, where the facial key point information includes key point information of at least one pair of symmetrical parts of facial features, where the symmetrical parts satisfy at least one geometric symmetry feature;

[0073] Determining, according to the facial key point information, a detection line for assisting in detecting whether the symmetrical parts are symmetrical, and displaying the detection line on the display;

[0074] Based on the detection line and the facial key point information, it is determined whether the symmetrical part is symmetrical and the result is output.

[0075] Through the above-mentioned intelligent device, key point detection can be performed on the reference image, and the key point information of the symmetrical parts of the facial features can be accurately located and identified. The detection line used to assist in detecting whether the symmetrical parts are symmetrical is determined through the above-mentioned key point information. Then, the detection line and the facial key point information are used to determine whether the symmetrical parts of the face are symmetrical and the results are output, including displaying on a display with a mirror display function, or playing voice prompt information through a player, to provide auxiliary information and guidance for users to put on makeup, and to assist users to better modify and complete their facial makeup.

[0076] Optionally, in an embodiment of the present application, the display has a mirror function. When the user uses the smart device, it can be used only as an ordinary mirror to meet the need of looking in the mirror, or the user can perform facial symmetry detection through the detection lines displayed by the above-mentioned smart device to provide auxiliary information and guidance for the user to put on makeup.

[0077] The smart device in the embodiment of the present application may be a mirror with a display function, such as Figure 3 As shown (the display is not shown in the figure), or a display device with a mirror function, and the display device can be a mobile terminal or a TV and other devices with a display function, which is not limited here.

[0078] Optionally, the user can set whether to turn on the detection line function according to actual needs. In the embodiment of the present application, a detection line switch can be set. When the user only needs to look in the mirror, the user can choose to turn off the detection line switch. At this time, the detection line will not be displayed on the display. When the user has makeup or other needs, the user can choose to turn on the detection line switch. At this time, the detection line will be displayed on the display. Through the setting of the detection line switch, different functions can be realized under different user needs, thereby improving the user experience.

[0079] In addition, the image collector can be an image acquisition structure such as a camera, as long as it can achieve image acquisition, and the specific implementation structure is not specifically limited here.

[0080] Optionally, the processor receives a reference image sent by the image collector, which may be a reference image collected in real time by the image collector through an image collection structure such as a camera. Specifically, the image collector may send the reference image to the processor at a set time interval, or send the reference image to the processor whenever the reference image changes. As another optional implementation method, the image collector may collect static photos, pictures, etc. as reference images, and send the reference image to the processor.

[0081] Optionally, performing key point detection on the reference image to obtain facial key point information may include the following methods, such as Figure 4 As shown:

[0082] Step S401, detecting the reference image through MTCNN (Multi-task convolutional neural network) to complete the detection and positioning of the face in the reference image;

[0083] Step S402, using PFLD (A Practical Facial Landmark Detector, face key point detection algorithm) to detect key points of the face located in the reference image to obtain facial key point information, wherein the algorithm has high accuracy in complex conditions of unconstrained posture, expression, lighting and occlusion, and can effectively solve the problems of geometric constraints and data imbalance; and can expand the receptive field and better capture the global structure of the face, and accurately locate the key points in the image;

[0084] Specifically, MTCNN face detection is used in combination with the PFLD facial key point detection algorithm to locate facial key points based on face detection. PFLD integrates the imbalance of various types of data in the data set and the three different dimensions of the face into the loss function by designing a reasonable loss function, so that a simple small model can also have sufficiently good detection accuracy. A method combining the main network to predict the position of key points and the auxiliary network to calculate the facial posture angle is adopted, and multi-scale full connection is used to obtain richer facial features for key point positioning, which greatly improves the detection accuracy of key points. At the same time, MobileNetV2 is used to simplify the model. The addition of MobileNetV2 reduces model parameters and improves the calculation speed of the model, which makes PFLD more accurate and faster when performing key point detection. The effect of using the PFLD key point detection algorithm to detect 98 key points of the face is as follows: Figure 5 shown.

[0085] Optionally, before using MTCNN to detect and locate faces in a reference image, the embodiment of the present application first needs to pre-train the MTCNN model. Specifically, the reference image and the face coordinate frame annotated in the reference image are used as training samples and input into the above-mentioned MTCNN model. The parameters of the MTCNN model are adjusted to complete the pre-training process.

[0086] Optionally, before using PFLD to perform key point detection on the face located in the reference image, the embodiment of the present application first needs to pre-train the PFLD model. Specifically, the face image and the key point position coordinates in the face image are used as training samples and input into the above-mentioned PFLD model to adjust the parameters of the PFLD model.

[0087] Of course, in actual situations, when determining the key point information of the face based on the reference image, it is not limited to the above-mentioned PFLD algorithm, and other algorithms that can determine the key point information of the face can also be used, which is not limited here.

[0088] Optionally, the facial key point information includes key point information of at least one pair of symmetrical parts of the facial features, and the symmetrical parts satisfy at least one geometric symmetry feature. Specifically, the facial features may be but are not limited to eyes, eyebrows and the like. Optionally, for the mouth, symmetry detection may also be performed using the symmetry detection method of the present application.

[0089] Optionally, when the embodiment of the present application obtains the result of whether the above-mentioned symmetrical part is symmetrical, the result of whether the symmetrical part is symmetrical can be output on the display through the change information of the detection line. Specifically, when the above-mentioned symmetrical part is determined to be symmetrical, the detection line does not change. When the above-mentioned part is determined to be asymmetrical, the color of the detection line corresponding to the asymmetrical part can be changed, or the display mode can be changed, such as changing the display mode of the corresponding detection line to a flashing display, or other modes, which are not limited here. Optionally, the data detected by the detection line can also be displayed on the above-mentioned detection line. For example, when it is detected that the lengths of the eyebrows on both sides are not equal, their respective lengths can be marked on the corresponding detection line, or the difference in the lengths of the two sides can be marked on the corresponding detection line, which is not limited here.

[0090] Optionally, the result of whether the symmetrical part is symmetrical can be output on the display through corresponding text information. For example, the text information can mark the symmetrical part as "symmetrical" or "asymmetrical", which is not limited here.

[0091] Optionally, after obtaining the facial key point information, a detection line for assisting in detecting whether the symmetrical parts are symmetrical is determined according to the facial key point information, specifically by the following method:

[0092] 1) determining the central vertical auxiliary line of the face according to the key point information of the bridge of the nose, and drawing a vertical line from the key point of any symmetrical part to the central vertical auxiliary line according to the key point information of the symmetrical part to obtain at least one horizontal auxiliary line;

[0093] The facial key point information includes the nose bridge key point information. According to the nose bridge key point information, the central vertical auxiliary line of the face is determined. Specifically, according to the coordinates corresponding to the mean of the horizontal coordinates of the key points of the nose bridge, an auxiliary line perpendicular to the horizontal axis of the reference image is made as the central vertical auxiliary line of the face.

[0094] After obtaining the central vertical auxiliary line of the face, a vertical line is drawn from the key point of any symmetrical part to the central vertical auxiliary line to obtain at least one horizontal auxiliary line. Specifically, the key point of any of the above-mentioned symmetrical parts can be the eyebrow head, eyebrow tail, inner corner of the eye or outer corner of the eye and other key points. During specific implementation, technical personnel in this field can set the position of the key point according to actual needs, and then draw a vertical line from the key point to the central vertical auxiliary line to obtain at least one horizontal auxiliary line. For example, when performing symmetry detection on the eyebrows, the eyebrow head and the inner corner of the eye can be set as key points to obtain two horizontal auxiliary lines.

[0095] 2) using the central vertical auxiliary line and at least one horizontal auxiliary line as the detection line, and displaying correction prompt information on the display when it is determined that the face needs to be corrected according to the detection line;

[0096] Specifically, the central vertical auxiliary line and any one of the above-mentioned horizontal auxiliary lines can be used as detection lines, or the central vertical auxiliary line and any or all of the above-mentioned horizontal auxiliary lines can be used as detection lines. Those skilled in the art can set them according to actual conditions.

[0097] Optionally, the embodiment of the present application determines whether the face needs to be corrected in the following manner:

[0098] When it is determined that the at least one horizontal auxiliary line is not parallel to the horizontal axis of the reference image or the vertical distances between the same key points of any pair of symmetrical parts and the central vertical auxiliary line are not equal, it is determined that correction is required.

[0099] Optionally, when the embodiment of the present application determines to output the correction prompt information, the correction prompt information can be output on the display through the change information of the detection line. Specifically, when it is determined that the face needs to be corrected, the color of the detection line corresponding to the asymmetric part detected can be changed, or the display method can be changed, such as changing the display method of the corresponding detection line to a flashing display, or other methods, which are not limited here. Optionally, the data detected by the detection line can also be displayed on the above-mentioned detection line, such as the angle of facial inclination can be marked on the corresponding detection line, which is not limited here.

[0100] Optionally, the correction prompt information may be output on the display through corresponding text information. For example, the text information may mark the symmetrical part with the word "tilted", which is not limited here.

[0101] Optionally, in an embodiment of the present invention, if Figure 6 As shown, the smart device may also include:

[0102] A player 604 is configured to play voice information;

[0103] A player is configured to play voice prompt information;

[0104] At this point, the processor is configured as:

[0105] If it is determined to output the result of whether the symmetrical part is symmetrical, output corresponding voice prompt information through the player according to the result of whether the symmetrical part is symmetrical;

[0106] If it is determined to output the correction prompt information, corresponding voice prompt information is output through the player according to the correction prompt information.

[0107] That is to say, in addition to displaying auxiliary lines and corresponding text on the display, auxiliary functions can also be provided through voice, so as to provide users with all-round and comprehensive assistance and guidance, and improve the user experience.

[0108] like Figure 7 As shown, when the face in the reference image is tilted, the horizontal auxiliary line obtained according to the reference image is not parallel to the horizontal axis of the reference image, and the central vertical auxiliary line obtained according to the reference image is not parallel to the vertical axis of the reference image. As another optional implementation (not shown in the figure), the vertical distance between the same key point of any pair of symmetrical parts and the central vertical auxiliary line can also be calculated. Figure 7 In the example, if the vertical distances are not equal, then when it is determined that the face needs to be corrected, correction prompt information is displayed on the display screen so that the user can adjust the face angle, position, etc. according to the correction prompt information.

[0109] The processor is specifically configured to perform key point detection on the corrected reference image captured again by the image collector to determine the facial key point information.

[0110] The detection line of the embodiment of the present application can, on the one hand, determine whether the face needs to be corrected. After the correction, key point detection is performed on the corrected reference image captured again by the image collector to determine the facial key point information for key point detection. On the other hand, when performing key point detection, based on the detection line and the facial key point information, geometric feature parameters are calculated and the satisfied geometric symmetry features are determined. According to the determination result, whether the symmetrical part is symmetrical is obtained and displayed on the display.

[0111] Optionally, the facial symmetry detection in the embodiment of the present application includes eye symmetry detection, eyebrow symmetry detection, or symmetry detection of both eyes and eyebrows. Specifically, the corresponding horizontal auxiliary lines are determined in the following manner:

[0112] 1) According to the eye key point information, a vertical line is drawn from the key point where the inner corner of any eye is located to the central vertical auxiliary line to obtain a first horizontal auxiliary line;

[0113] 2) according to the eyebrow key point information, a vertical line is drawn from the key point where the eyebrow of any eyebrow is located to the central vertical auxiliary line to obtain a second horizontal auxiliary line;

[0114] 3) According to the eye key point information, a vertical line is drawn from the key point where the inner corner of any eye is located to the central vertical auxiliary line to obtain a first horizontal auxiliary line, and according to the eyebrow key point information, a vertical line is drawn from the key point where the eyebrow is located to the central vertical auxiliary line to obtain a second horizontal auxiliary line.

[0115] Optionally, based on the detection line and facial key point information, geometric feature parameters are calculated and satisfied geometric symmetry features are determined;

[0116] When at least one geometric symmetry feature satisfied by any pair of symmetrical parts is determined, and all geometric symmetry features satisfied by the pair of symmetrical parts are determined based on the geometric feature parameters, the symmetrical parts are determined to be symmetrical, otherwise the unsatisfied geometric symmetry features are displayed on the display.

[0117] According to the above central vertical auxiliary line and horizontal auxiliary line, the geometric feature parameters are calculated through the facial key point information, and the satisfied geometric symmetry features are determined.

[0118] like Figure 8 , which is a schematic diagram of the central vertical line and horizontal auxiliary lines of the reference image provided in an embodiment of the present application.

[0119] Optionally, the embodiment of the present application determines the symmetry of the eyebrows and eyes as follows:

[0120] 1. Based on the above detection lines and eyebrow key point information, calculate the geometric feature parameters and determine the satisfied geometric symmetry features;

[0121] Optionally, the geometric feature parameters corresponding to the eyebrow include at least one of the following:

[0122] 1) A first distance from a key point at a designated position of the eyebrow to the central vertical auxiliary line. Preferably, the designated position of the eyebrow may be any position on the eyebrow contour line. The symmetry of the eyebrow contour may be determined by comparing the positions of the key points on the eyebrow contour line;

[0123] 2) The second distance between the key points of the eyebrow start and eyebrow end;

[0124] 3) The line between the two highest key points of the eyebrow, the line between the two lowest key points, and optionally, the line between the second highest key points and the line between the second lowest key points of the eyebrow, or the lines between the above key points are selected for symmetry detection at the same time. As another optional implementation method, the lines between key points at different positions are selected, because the thickness of different parts of the eyebrow is different, the more lines between key points that are not connected are selected, the more accurate the result of the symmetry detection is;

[0125] 4) a third distance from the key point at the upper and / or lower side of the eyebrow to the first horizontal auxiliary line;

[0126] Optionally, the eyebrow geometric feature parameters are calculated and the satisfied geometric symmetry features are determined by at least one of the following methods:

[0127] 1) If the difference between the first distances corresponding to the same designated positions of the two eyebrows does not exceed the first preset threshold, it is determined that the geometric symmetry feature of the left-right symmetry of the eyebrows is satisfied. Specifically, by detecting the difference between the distances of the same designated positions of the two eyebrows and the central vertical line, it is determined whether the two eyebrows are left-right symmetric;

[0128] 2) If the second distances corresponding to the two eyebrows are not greater than the second preset threshold, determining that the geometric symmetry feature of the left and right lengths of the eyebrows is symmetrical;

[0129] 3) If the line between the highest key points of the two eyebrows and the line between the lowest key points are parallel to the horizontal axis of the reference image, the geometric symmetry feature that satisfies the symmetry of the height of the eyebrows is determined. At the same time, by determining that the line between the highest key points of the two eyebrows and the line between the lowest key points are parallel to the horizontal axis of the reference image, it can also be determined whether the thickness of the eyebrows is symmetrical;

[0130] Optionally, an auxiliary line perpendicular to the central vertical line may be made based on any highest key point of the eyebrow, and it is determined whether the vertical distance between the auxiliary line and the highest key point of the eyebrow on the other side is less than a first preset value; an auxiliary line perpendicular to the central vertical line may be made based on any lowest key point, and it is determined whether the numerical distance between the auxiliary line and the lowest key point on the other side is less than a second preset value. If the above conditions are met, it is determined that the geometric symmetry feature of the symmetry of the high and low positions of the eyebrow is met;

[0131] 4) If the difference between the third distances corresponding to the same position on the upper and / or lower sides of the two eyebrows does not exceed the third preset threshold, it is determined that the geometric symmetry feature of the eyebrow height symmetry is satisfied.

[0132] like Fig. 9 and Fig.10 FIG. 4 is a schematic diagram showing how to determine the symmetry of the eyebrow using the above method.

[0133] 2. Based on the above detection lines and eye key point information, calculate the geometric feature parameters and determine the satisfied geometric symmetry features;

[0134] Optionally, the geometric feature parameters corresponding to the eye include at least one of the following:

[0135] 1) A fourth distance from a key point at a designated eye position to a central vertical auxiliary line. Preferably, the key point at the designated eye position is a key point on an eye contour line, and the symmetry of the eye is determined by the fourth distance from the key point on the eye contour to the central vertical auxiliary line;

[0136] 2) The line between the two highest key points of the eyes and the line between the lowest key points. Optionally, the line between the second highest key points of the eyes and the line between the second lowest key points can also be selected, or the lines between the above key points can be selected at the same time for symmetry detection. As another optional implementation method, the lines between key points at different positions are selected. Because the thickness of different parts of the eyes is not the same, the more lines between key points at different positions are selected, the more accurate the result of the symmetry detection is.

[0137] Optionally, the eye geometric feature parameters are calculated and the satisfied geometric symmetry features are determined by at least one of the following methods:

[0138] 1) If the difference between the fourth distances corresponding to the same designated positions of the two eyes does not exceed a fourth preset threshold, it is determined that the geometric symmetry feature satisfies the symmetry of the left and right eye positions;

[0139] 2) If the line between the highest key points of the two eyes and the line between the lowest key points are parallel to the horizontal axis of the reference image, the geometric symmetry feature that satisfies the symmetry of the high and low positions of the eyes is determined. At the same time, by determining that the line between the highest key points of the two eyes and the line between the lowest key points are parallel to the horizontal axis of the reference image, it can also be determined whether the sizes of the eyes are symmetrical;

[0140] Optionally, based on any highest key point of the eye, an auxiliary line perpendicular to the central vertical line can be made to determine whether the vertical distance between the above auxiliary line and the highest key point of the other side of the eye is less than a third preset value. Based on any lowest key point, an auxiliary line perpendicular to the central vertical line can be made to determine whether the numerical distance between the above auxiliary line and the lowest key point on the other side is less than a fourth preset value. If all the above conditions are met, the geometric symmetry feature that satisfies the symmetry of the high and low positions of the eyes is determined.

[0141] like Fig.11 FIG. 4 is a schematic diagram showing the method for determining the symmetry of the eye.

[0142] Optionally, although the mouth is not a paired symmetrical part, the symmetry of the mouth can still be detected by the symmetry detection method proposed in the embodiment of the present application;

[0143] Optionally, the geometric feature parameters corresponding to the mouth in the embodiment of the present application include:

[0144] 1) The fifth distance from the key point at the specified position of the mouth to the central vertical auxiliary line. Preferably, the fifth distance from the key points corresponding to the corners of the mouth on both sides to the central vertical auxiliary line is selected to determine the left-right symmetry of the mouth;

[0145] 2) The lines between the highest key points and the lowest key points of the mouth. Optionally, the lines between the second highest key points and the second lowest key points of the mouth and eyes can also be selected, or the lines between the above key points can be selected at the same time for symmetry detection. As another optional implementation method, the lines between key points at different positions are selected. Because the heights of different parts of the mouth are different, the more lines between key points at different positions are selected, the more accurate the symmetry detection result is;

[0146] Optionally, the geometric feature parameters of the mouth are calculated and the satisfied geometric symmetry features are determined by at least one of the following methods:

[0147] 1) If the difference between the fourth distances corresponding to the same designated positions of the two mouths does not exceed a fourth preset threshold, it is determined that the geometric symmetry feature satisfies the symmetry of the left and right positions of the mouths;

[0148] 2) If the line between the highest key points of the two mouths and the line between the lowest key points are parallel to the horizontal axis of the reference image, the geometric symmetry feature that satisfies the symmetry of the height of the mouth is determined. At the same time, by determining that the line between the highest key points of the two mouths and the line between the lowest key points are parallel to the horizontal axis of the reference image, it can also be determined whether the height of the mouth is symmetrical;

[0149] Optionally, based on any highest key point of the mouth, an auxiliary line perpendicular to the central vertical line is made to determine whether the vertical distance between the auxiliary line and the highest key point of the eyebrow on the other side is less than a fifth preset value; based on any lowest key point, an auxiliary line perpendicular to the central vertical line is made to determine whether the numerical distance between the auxiliary line and the lowest key point on the other side is less than a sixth preset value. If all the above conditions are met, it is determined that the geometric symmetry feature that satisfies the symmetry of the high and low positions of the mouth is met. Specifically, Fig.11 A schematic diagram of determining the mouth symmetry by the above method is also shown in FIG.

[0150] Based on the same inventive concept, an embodiment of the present invention provides a symmetry detection method, which is implemented by the above-mentioned smart device provided by the embodiment of the present invention, such as Fig.12 As shown, the method may include:

[0151] S1201, receiving a reference image sent by the image collector, performing key point detection on the reference image to obtain facial key point information, wherein the facial key point information includes key point information of at least one pair of symmetrical parts of facial features, and the symmetrical parts satisfy at least one geometric symmetry feature;

[0152] S1202, determining a detection line for assisting in detecting whether a symmetrical part is symmetrical according to the facial key point information, and displaying the detection line on the display;

[0153] S1203: Determine whether the symmetrical parts are symmetrical based on the detection lines and the facial key point information, and output the result.

[0154] Optionally, the facial key point information includes nose bridge key point information, and determining a detection line for assisting in detecting whether the symmetrical parts are symmetrical according to the facial key point information includes:

[0155] Determine the central vertical auxiliary line of the face according to the key point information of the bridge of the nose, and draw a vertical line from the key point of any symmetrical part to the central vertical auxiliary line according to the key point information of the symmetrical part to obtain at least one horizontal auxiliary line;

[0156] Using the central vertical auxiliary line and at least one horizontal auxiliary line as the detection line, and displaying correction prompt information on the display when it is determined that the face needs to be corrected according to the detection line;

[0157] The processor is specifically configured to perform key point detection on the corrected reference image captured again by the image collector to determine the facial key point information.

[0158] Optionally, determine whether correction of the face is needed, including:

[0159] When it is determined that the at least one horizontal auxiliary line is not parallel to the horizontal axis of the reference image or the vertical distances between the same key points of any pair of symmetrical parts and the central vertical auxiliary line are not equal, it is determined that correction is required.

[0160] Optionally, outputting the result of determining whether the symmetrical part is symmetrical includes:

[0161] If it is determined to output the result of whether the symmetrical part is symmetrical, the result of whether the symmetrical part is symmetrical is output on the display through the change information of the detection line and / or through text information;

[0162] If it is determined to output the correction prompt information, the correction prompt information is output and displayed on the display through the change information of the detection line and / or through text information.

[0163] Optionally, it also includes:

[0164] If it is determined to output the result of whether the symmetrical part is symmetrical, output corresponding voice prompt information through the player according to the result of whether the symmetrical part is symmetrical;

[0165] If it is determined to output the correction prompt information, corresponding voice prompt information is output through the player according to the correction prompt information.

[0166] Optionally, the symmetrical parts include eyes and / or eyebrows, and determining a detection line for assisting in detecting whether the symmetrical parts are symmetrical includes:

[0167] According to the eye key point information, a vertical line is drawn from the key point where the inner corner of any eye is located to the central vertical auxiliary line to obtain a first horizontal auxiliary line; and / or

[0168] According to the eyebrow key point information, a vertical line is drawn from the key point where the beginning of any eyebrow is located to the central vertical auxiliary line to obtain a second horizontal auxiliary line.

[0169] Optionally, determining whether the symmetrical parts are symmetrical based on the detection line and the facial key point information includes:

[0170] Based on the detection line and facial key point information, calculate geometric feature parameters and determine satisfied geometric symmetry features;

[0171] When at least one geometric symmetry feature satisfied by any pair of symmetrical parts is determined, and all geometric symmetry features satisfied by the pair of symmetrical parts are determined based on the geometric feature parameters, the symmetrical parts are determined to be symmetrical, otherwise the unsatisfied geometric symmetry features are displayed on the display.

[0172] Optionally, the geometric feature parameters include a first distance from a key point at a designated position of the eyebrow to a central vertical auxiliary line, a second distance between key points at the eyebrow head and eyebrow tail, a line between two highest key points of the eyebrow, a line between two lowest key points of the eyebrow, and a third distance from a key point at an upper and / or lower position of the eyebrow to a first horizontal auxiliary line, comprising at least one of the following steps:

[0173] If the difference between the first distances corresponding to the same designated positions of the two eyebrows does not exceed the first preset threshold, it is determined that the geometric symmetry feature of the left and right positions of the eyebrows is satisfied;

[0174] If the second distances corresponding to the two eyebrows are not greater than the second preset threshold, it is determined that the geometric symmetry feature of the left and right lengths of the eyebrows is symmetrical;

[0175] If the line between the highest key points of the two eyebrows and the line between the lowest key points are parallel to the horizontal axis of the reference image, a geometric symmetry feature that satisfies the symmetry of the height of the eyebrows is determined;

[0176] If the difference between the third distances corresponding to the same position on the upper and / or lower sides of the two eyebrows does not exceed the third preset threshold, it is determined that the geometric symmetry feature of the eyebrow height symmetry is satisfied.

[0177] Optionally, the geometric feature parameters include a fourth distance from a key point at a designated eye position to a central vertical auxiliary line, and a line between two highest key points of the eyes and a line between two lowest key points, comprising at least one of the following steps:

[0178] If the difference between the fourth distances corresponding to the same designated positions of the two eyes does not exceed a fourth preset threshold, determining that the geometric symmetry feature that satisfies the symmetry of the left and right positions of the eyes is satisfied;

[0179] If the line between the highest key points of the two eyes and the line between the lowest key points are parallel to the horizontal axis of the reference image, a geometric symmetry feature that satisfies the symmetry of the high and low positions of the eyes is determined.

[0180] Among them, regarding the implementation method of the above steps, please refer to the specific embodiment of the above-mentioned smart device, and the repeated parts will not be repeated here.

[0181] By performing key point detection on the reference image, the key point information of the symmetrical parts of the facial features can be accurately located and identified, and the detection line used to assist in detecting whether the symmetrical parts are symmetrical is determined through the above key point information. Then, the detection line and the facial key point information are used to determine whether the symmetrical parts of the face are symmetrical, and it can be displayed on a display with a mirror display function, providing auxiliary information and guidance for users when applying makeup.

[0182] Optionally, the above-mentioned symmetry detection method can also be applied to the scenario of performing facial symmetry detection on pictures. For example, after obtaining the photo, if it is necessary to adjust the position of the facial features to make the facial features symmetrical, the adjustment can be made through the detection line proposed in the embodiment of the present application.

[0183] Taking the symmetry detection of eyebrows as an example, a symmetry detection method provided by an embodiment of the present application is specifically introduced below. Fig.13 As shown, including:

[0184] Step S1301, collecting the user's facial information to obtain a reference image;

[0185] Step S1302, performing key point detection on the reference image to obtain facial key point information, where the facial key point information includes nose bridge key point information;

[0186] Step S1303, determining a central vertical auxiliary line of the face according to the key point information of the bridge of the nose, and drawing a vertical line from the key point where the inner corner of any eye is located to the central vertical auxiliary line according to the key point information of the eyebrow and the eye to obtain a first horizontal auxiliary line;

[0187] Step S1304, when it is determined that the first horizontal auxiliary line is not parallel to the horizontal axis of the reference image or the vertical distances between the same key point of the eyebrow and the central vertical auxiliary line are not equal, it is determined that correction is required;

[0188] Step S1305, when it is determined that the face needs to be corrected, correction prompt information is displayed on the display screen;

[0189] Step S1306, performing key point detection on the corrected reference image collected again to determine facial key point information;

[0190] Step S1307, determining a first distance from a key point at a designated position of the eyebrow to a central vertical auxiliary line, and if the difference between the first distances corresponding to the same designated positions of the two eyebrows does not exceed a first preset threshold, determining that the geometric symmetry feature of the left-right position symmetry of the eyebrow is satisfied; otherwise, determining that the geometric symmetry feature of the left-right position symmetry of the eyebrow is not satisfied;

[0191] Step S1308, determining the second distance between the key points where the eyebrow head and eyebrow tail are located, if the corresponding second distances of the two eyebrows are not greater than the second preset threshold, determining that the geometric symmetry feature of the left and right lengths of the eyebrows is satisfied, otherwise, determining that the geometric symmetry feature of the left and right lengths of the eyebrows is not satisfied;

[0192] Step S1309, determining a line between two highest key points of the eyebrows and a line between two lowest key points of the eyebrows. If the line between the two highest key points and the line between the two lowest key points of the eyebrows are parallel to the horizontal axis of the reference image, it is determined that the geometric symmetry feature of the symmetry of the height of the eyebrows is satisfied; otherwise, it is determined that the geometric symmetry feature of the symmetry of the height of the eyebrows is not satisfied.

[0193] Step S1310, determining a third distance from a key point at the upper and / or lower side of the eyebrow to the first horizontal auxiliary line, if the difference between the third distances corresponding to the same positions at the upper and / or lower sides of the two eyebrows does not exceed a third preset threshold, it is determined that the geometric symmetry feature of eyebrow height symmetry is satisfied; otherwise, it is determined that the geometric symmetry feature of eyebrow height symmetry is not satisfied;

[0194] Step S1311, when it is determined that all the above geometric symmetry features are met, the symmetry is satisfied.

[0195] Taking the symmetry detection of the eye as an example, a symmetry detection method provided by an embodiment of the present application is specifically introduced below. Fig.14 As shown, including:

[0196] Step S1401, collecting the user's facial information to obtain a reference image;

[0197] Step S1402, performing key point detection on the reference image to obtain facial key point information, where the facial key point information includes nose bridge key point information;

[0198] Step S1403, determining a central vertical auxiliary line of the face according to the key point information of the bridge of the nose, and drawing a vertical line from the key point where the inner corner of any eye is located to the central vertical auxiliary line according to the key point information of the eyes to obtain a first horizontal auxiliary line;

[0199] Step S1404, when it is determined that the first horizontal auxiliary line is not parallel to the horizontal axis of the reference image or the vertical distances between the same key point of the eye and the central vertical auxiliary line are not equal, it is determined that correction is required;

[0200] Step S1405, when it is determined that the face needs to be corrected, correction prompt information is displayed on the display screen;

[0201] Step S1406, performing key point detection on the re-collected corrected reference image to determine facial key point information;

[0202] Step S1407, determining a fourth distance from the key point of the designated eye position to the central vertical auxiliary line, if the difference between the fourth distances corresponding to the same designated eye positions of the two eyes does not exceed a fourth preset threshold, determining that the geometric symmetry feature of the left and right eye positions is satisfied, otherwise, determining that the geometric symmetry feature of the left and right eye positions is not satisfied;

[0203] Step S1408, determining a line connecting the highest key points of the two eyes and a line connecting the lowest key points. If the line connecting the highest key points of the two eyes and a line connecting the lowest key points are parallel to the horizontal axis of the reference image, it is determined that the geometric symmetry feature of the eye height symmetry is satisfied. Otherwise, it is determined that the geometric symmetry feature of the eye height symmetry is not satisfied.

[0204] Step S1409: When all the above geometric symmetry features are met, the symmetry is satisfied.

[0205] An embodiment of the present invention further provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enables the computer to execute the symmetry detection method provided in the above embodiment.

[0206] An embodiment of the present application further provides a computer program product, including a computer program, wherein the computer program includes program instructions. When the program instructions are executed by an electronic device, the electronic device executes the symmetry detection method provided in the above embodiment.

[0207] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0208] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0209] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0210] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0211] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0212] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0213] The technical solution provided by the present application is introduced in detail above. The principles and implementation methods of the present application are explained by using specific examples in the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A smart device, characterized in that: include: A display configured to display a picture, wherein the display has a mirror display function; The image collector is configured to: collect the user's facial information, obtain a reference image and transmit it to the processor; The processor is configured to: Receive a reference image sent by the image collector, perform key point detection on the reference image to obtain facial key point information, wherein the facial key point information includes key point information of at least one pair of symmetrical parts of facial features, and the symmetrical parts satisfy at least one geometric symmetry feature; Determining, according to the facial key point information, a detection line for assisting in detecting whether the symmetrical parts are symmetrical, and displaying the detection line on the display; Based on the detection line and facial key point information, calculate geometric feature parameters and determine satisfied geometric symmetry features; Determine at least one geometric symmetry feature satisfied by any pair of symmetrical parts, and when all geometric symmetry features satisfied by the pair of symmetrical parts are determined according to the geometric feature parameters, determine that the symmetrical parts are symmetrical, otherwise the unsatisfied geometric symmetry features are displayed on the display; Based on the detection line and the facial key point information, it is determined whether the symmetrical part is symmetrical and the result is output.

2. The smart device according to claim 1, characterized in that: The facial key point information includes nose bridge key point information, and the processor is configured to: Determine the central vertical auxiliary line of the face according to the key point information of the bridge of the nose, and draw a vertical line from the key point of any symmetrical part to the central vertical auxiliary line according to the key point information of the symmetrical part to obtain at least one horizontal auxiliary line; Using the central vertical auxiliary line and at least one horizontal auxiliary line as the detection line, and displaying correction prompt information on the display when it is determined that the face needs to be corrected according to the detection line; The processor is specifically configured to perform key point detection on the corrected reference image captured again by the image collector to determine the facial key point information.

3. The smart device according to claim 2, characterized in that: The processor is configured to: When it is determined that the at least one horizontal auxiliary line is not parallel to the horizontal axis of the reference image or the vertical distances between the same key points of any pair of symmetrical parts and the central vertical auxiliary line are not equal, it is determined that correction is required.

4. The smart device according to claim 1 or 2, characterized in that: The processor is configured to: If it is determined to output the result of whether the symmetrical part is symmetrical, the result of whether the symmetrical part is symmetrical is output on the display through the change information of the detection line and / or through text information; If it is determined to output the correction prompt information, the correction prompt information is output and displayed on the display through the change information of the detection line and / or through text information.

5. The smart device according to claim 1 or 2, characterized in that: Also includes: A player is configured to play voice prompt information; The processor is configured to: If it is determined to output the result of whether the symmetrical part is symmetrical, output corresponding voice prompt information through the player according to the result of whether the symmetrical part is symmetrical; If it is determined to output the correction prompt information, the corresponding voice prompt information is output through the player according to the correction prompt information.

6. The smart device according to claim 2, characterized in that: The symmetrical parts include eyes and / or eyebrows, and the processor is configured to: According to the eye key point information, a vertical line is drawn from the key point where the inner corner of any eye is located to the central vertical auxiliary line to obtain a first horizontal auxiliary line; and / or According to the eyebrow key point information, a vertical line is drawn from the key point where the beginning of any eyebrow is located to the central vertical auxiliary line to obtain a second horizontal auxiliary line.

7. The smart device according to claim 1, characterized in that: The geometric feature parameters include a first distance from a key point at a designated position of the eyebrow to a central vertical auxiliary line, a second distance between key points at the beginning and end of the eyebrow, a line between two highest key points of the eyebrow, a line between two lowest key points of the eyebrow, and a third distance from a key point at an upper and / or lower position of the eyebrow to a first horizontal auxiliary line. The processor is configured to perform at least one of the following steps: If the difference between the first distances corresponding to the same designated positions of the two eyebrows does not exceed the first preset threshold, it is determined that the geometric symmetry feature of the left and right positions of the eyebrows is satisfied; If the second distances corresponding to the two eyebrows are not greater than the second preset threshold, it is determined that the geometric symmetry feature of the left and right lengths of the eyebrows is symmetrical; If the line between the highest key points of the two eyebrows and the line between the lowest key points are parallel to the horizontal axis of the reference image, a geometric symmetry feature that satisfies the symmetry of the height of the eyebrows is determined; If the difference between the third distances corresponding to the same position on the upper and / or lower sides of the two eyebrows does not exceed the third preset threshold, it is determined that the geometric symmetry feature of eyebrow height symmetry is satisfied.

8. The smart device according to claim 1, characterized in that: The geometric feature parameters include a fourth distance from a key point at a designated eye position to a central vertical auxiliary line, and a line between two highest key points of the eyes and a line between two lowest key points. The processor is configured to perform at least one of the following steps: If the difference between the fourth distances corresponding to the same designated positions of the two eyes does not exceed a fourth preset threshold, determining that the geometric symmetry feature that satisfies the symmetry of the left and right positions of the eyes is satisfied; If the line between the highest key points of the two eyes and the line between the lowest key points are parallel to the horizontal axis of the reference image, a geometric symmetry feature that satisfies the symmetry of the high and low positions of the eyes is determined.

9. A symmetry detection method, characterized in that: The method includes: Receive a reference image sent by an image collector, perform key point detection on the reference image to obtain facial key point information, wherein the facial key point information includes key point information of at least one pair of symmetrical parts of facial features, and the symmetrical parts satisfy at least one geometric symmetry feature; Determine, according to the facial key point information, a detection line for assisting in detecting whether the symmetrical parts are symmetrical, and display the detection line on a display; Based on the detection line and facial key point information, calculate geometric feature parameters and determine satisfied geometric symmetry features; Determine at least one geometric symmetry feature satisfied by any pair of symmetrical parts, and when all geometric symmetry features satisfied by the pair of symmetrical parts are determined according to the geometric feature parameters, determine that the symmetrical parts are symmetrical, otherwise the unsatisfied geometric symmetry features are displayed on the display; Based on the detection line and the facial key point information, it is determined whether the symmetrical part is symmetrical and the result is output.

Images