TW201944292A - Face recognition method including a depth image capturing unit, an image processing unit and a calculation and comparison method - Google Patents

Abstract

The invention relates to a face recognition method, which is characterized in that after a face recognition system detects a face of a person to be tested, a face recognition operation is performed. As such, the face recognition method of the present invention effectively completes a safe recognition of the facial image features mainly by a hardware design that uses a depth image capturing unit to capture a three-dimensional image of a user's face, in cooperation with an image processing unit that selects a plurality of feature points from the captured facial image, as well as by a method that calculates and compares the length and depth of the connecting line segments between any two feature points. The invention can reliably achieve the main advantage of safer and more comprehensive facial safe recognition by further adopting the operations of calculating and comparing the triangular area enclosed by three line segments.

Description

   Face recognition method   

The present invention relates to a method for face recognition, and more particularly to a security monitoring method for performing face recognition by comparing image length of a face with a depth camera and comparing the connection length and depth of a plurality of feature points.

According to the rapid development of science and technology, the formation of smart cities can not only deploy dense networks and powerful control centers, but also fully grasp the crowd distribution lines to provide rapid and correct social prevention monitoring of the situation For example, in the monitoring of traffic flow, a monitoring system is installed in street lights or traffic signs, or even information exchange between vehicles. Through a single platform for real-time monitoring and management, it can target scenes such as traffic jams, accidents or crowd crimes. Control, which effectively assists in evacuation or tracking of criminals ’vehicle movements; the face recognition system is an emerging part of smart cities, especially for people who do n’t like to go out with their keys, face recognition is a big gospel, This is because more and more people's residences are using automatic induction access control systems to replace the existing keyhole access control equipment, which has indeed improved convenience and security, but the current automatic induction access control systems are mostly It adopts radio frequency identification (RFID) method for this purpose. It is carried out in the form of an RFID reader. The method is to provide the user with an object containing an RDID tag. When the user brings the RFID tag close to the RFID reader, the radio frequency identification The reader can verify whether the RFID tag is aligned to determine whether to let the user enter. However, the main disadvantage of RFID technology is that the card is not recognized, and there are still many security concerns.

Face recognition is currently the most secure way of access control systems, which can effectively solve the shortcomings of the above-mentioned radio frequency identification technology; however, the current face recognition is mostly a 2D recognition method, which mainly captures three-dimensional human faces with a 2D camera. Plane information, the face recognition system only looks for identification data that can be compared in 2D information. In this way, as long as the interested person captures a photo or a plan view with relevant face data, it can effectively deceive 2D face recognition. The system also achieves the goal of easy entry and exit; therefore, how to effectively combine the plane and three-dimensional information of the face through innovative hardware design to achieve a safer and more comprehensive face security recognition is still the face Identification and other related industry developers and related researchers need to continue their efforts to overcome and solve problems.

Today, the inventor is in view of the many shortcomings in the traditional face recognition method when it is actually implemented, so it is a tireless spirit, supplemented by its rich professional knowledge and years of practical experience to improve it Based on this, the invention was developed.

The main purpose of the present invention is to provide a face recognition method, in particular to a security monitoring method for performing face recognition by using a depth camera for image capture of a face and comparing the connection length and depth of a plurality of feature points, It is mainly designed to capture the three-dimensional image of the user's face by the depth image capture unit, and the image processing unit is used to select the length and depth of the line segments between the plurality of feature points and the two feature points in the face image using the image processing unit. The calculation and comparison methods can effectively complete the security recognition of facial image features, and can further combine the calculation and comparison of the triangle area surrounded by the three line segments, and indeed achieve the main advantages of safer and more comprehensive face security recognition By.

In order to achieve the above-mentioned implementation purpose, the present inventor has developed the following implementation technology, wherein the face recognition method of the present invention is to perform a face recognition action after a face recognition system detects a person's face ; First, use a depth image capture unit for image capture of an original face; then, use a selection module built into an image processing unit to select a plurality of first feature points in the image of the original face, and separately Calculate the first distance value between the first feature point and the depth image capture unit; then, use the length calculation module built in the image processing unit to connect the pair of first feature points to obtain a plurality of first line segments, and respectively Calculate the length of the first line segment to obtain a plurality of first length values, and calculate a first depth difference between the first distance values of the first feature points connected in pairs; then, the first feature points, The image of the original face of the first line segment, the first length value, and the first depth difference value is stored in a storage unit; then, the above steps are repeated to use the depth image capture unit to capture a face to be measured Image, and obtain a plurality of second feature points corresponding to the position of the first feature point on the face to be measured, a plurality of second line segments and a second length value connected by the second feature point, and a plurality of second distance values A difference from the second depth and stored in the storage unit; thereafter, a comparison unit is used to compare the first length value and the corresponding second length value, and the first depth difference and the corresponding second depth value; Finally, when the difference between the first length value and the corresponding second length value, and the difference between the first depth difference value and the corresponding second depth difference value are within an error range, the face to be measured is Same as the original face.

The face recognition method as described above, wherein the depth image capturing unit is a device such as a TOF camera or a dual-lens camera.

As described above, when the depth image capturing unit is a TOF camera, the depth image capturing unit includes at least a light emitting module, a receiving module, and an image capturing module.

The face recognition method described above, wherein the light emitting module emits a plurality of light spots on the original face or the face to be measured.

The face recognition method as described above, wherein the receiving module receives a plurality of reflected light spots reflected by the original face or the face to be measured, and transmits the reflected light spots to the image processing unit.

The face recognition method as described above, wherein the image capturing module includes a first optical lens and a first photosensitive element connected to the first optical lens, and the first optical lens captures an original face or a test object. An image of the face is formed on the first photosensitive element.

In the face recognition method as described above, the first optical lens is a device such as a fisheye lens, a wide-angle lens, or a standard lens.

The face recognition method described above, wherein the first photosensitive element is one of a device such as a Photo Coupled Device (CCD) or a Complementary Metal-Oxide-Semiconductor (CMOS).

The face recognition method as described above, when the depth image capturing unit is a dual-lens camera, the depth image capturing unit includes two second optical lenses and a second photoreceptor respectively connected to the second optical lens. Element, the second optical lens simultaneously captures the image of the original face or the face to be measured and forms an image on the second photosensitive element.

In the face recognition method as described above, the second optical lens is a device such as a fisheye lens, a wide-angle lens, or a standard lens.

In the face recognition method as described above, the second photosensitive element is a device such as a photo-coupled element (CCD) or a complementary metal oxide semiconductor (CMOS).

The face recognition method described above, wherein the error range is between 98% and 100%.

The face recognition method as described above, wherein before the original face image is stored, an area calculation module built in the image processing unit can be further used to calculate the first of the first triangle surrounded by the three first line segments. The area value, and the first area value added up to the first total area value.

As described above, after comparing the first length value with the corresponding second length value, the area calculation module can be further used to calculate the second area of the second triangle surrounded by the three second line segments. Value, and the second area value added up to a second total area value.

The face recognition method as described above, wherein the area calculation module calculates the first area value or the second area value using a sea dragon formula.

The face recognition method described above, wherein after the last step is completed, the comparison unit can be further used to compare the first total area value and the second total area value. When the difference is within the error range, the face to be measured is the same as the original face.

Therefore, the face recognition method of the present invention is mainly designed to capture a three-dimensional image of a user's face by a depth image capture unit, and the image processing unit is used to select a plurality of feature points and two or two features in the face image. The method of calculating and comparing the length and depth of the line segment between the points effectively completes the safe identification of the facial image features, and can further combine the calculation and comparison of the triangle area surrounded by the three line segments, which is indeed more secure and The main advantages of more comprehensive face security recognition; In addition, the face recognition method of the present invention mainly uses a TOF camera to capture the depth differences between the feature points and other feature points of the face as a face One of the important basis of identification can effectively solve the shortcomings of interested people using a photo or plan with the same face to deceive the two-dimensional face recognition system, and indeed achieve the main advantages of a more secure and difficult to crack face recognition system and method; Furthermore, the face recognition method of the present invention mainly involves comparing the depth value of feature points on the face, the length of the connecting line, and the connection. A plurality of comparison targets such as the area of a triangle surrounded by lines, in order to increase the accuracy of face recognition, and indeed achieve the main purpose of accurate recognition and attention to safety considerations; finally, the face recognition method of the present invention mainly uses depth images The capture unit captures the three-dimensional features of the human face, allowing users to face the facial image capture of the depth image capture unit at different angles. The face recognition system can accurately give the depth difference of the feature points of the face. It can effectively solve the shortcomings of traditional facial recognition systems that have incorrect judgment due to incorrect angles, and indeed achieve the main advantage of significantly reducing the time required for facial recognition.

(1) ‧‧‧Face recognition system

(11) ‧‧‧Depth image acquisition unit

(111) ‧‧‧Lighting Module

(112) ‧‧‧Receiving module

(113) ‧‧‧Image capture module

(1131) ‧‧‧First Optical Lens

(12) ‧‧‧Image processing unit

(121) ‧‧‧Select Module

(122) ‧‧‧Length Calculation Module

(123) ‧‧‧Area Calculation Module

(13) ‧‧‧Storage unit

(14) ‧‧‧Comparison unit

(2) ‧‧‧ROI range

(3) ‧‧‧ Testee

(A) ‧‧‧Original face

(A1) ‧‧‧The first feature point

(A2) ‧‧‧First line segment

(Ae1) ‧‧‧First area value

(Ae2) ‧‧‧Second Area Value

(B) ‧‧‧Face to be tested

(B1) ‧‧‧Second feature point

(B2) ‧‧‧Second Line Segment

(L1) ‧‧‧First length value

(L2) ‧‧‧Second length value

(T1) ‧‧‧First Triangle

(T2) ‧‧‧Second Triangle

(S1) ‧‧‧Step 1

(S2) ‧‧‧Step 2

(S3) ‧‧‧Step Three

(S4) ‧‧‧Step 4

(S5) ‧‧‧Step 5

(S6) ‧‧‧Step 6

(S7) ‧‧‧Step 7

FIG. 1: Flow chart of steps of the face recognition method of the present invention

Fig. 2: Schematic diagram of the hardware architecture of the face recognition system used in the face recognition method of the present invention

Figure 3: Feature point selection of a preferred embodiment of the face recognition method of the present invention

Fig. 4: Schematic diagram of connecting line segments in a preferred embodiment of the face recognition method of the present invention

Fig. 5: Schematic diagram of the face recognition to be tested in a preferred embodiment of the face recognition method of the present invention

In order for the reviewing committee members to understand the technical features, contents, advantages of the present invention, and the effects that can be achieved, the present invention is described in detail with the accompanying drawings in the form of embodiments, and the diagrams used therein, Its main purpose is only for the purpose of illustration and supplementary description. It may not be the actual proportion and precise configuration after the implementation of the invention. Therefore, the attached drawings should not be interpreted and limited to the scope of rights of the present invention in actual implementation. , He Xianxian.

First, please refer to FIG. 1 and FIG. 2 for a flowchart of the steps of the face recognition method of the present invention, and a schematic diagram of the hardware architecture of the face recognition system used. Among the fields of application of the face recognition method of the present invention It can be used for example but not limited to face recognition for entrance and exit. The method is to first use a face recognition system (1) to establish a recognition model for face recognition in a storage unit (13); then, when After the face recognition system (1) detects the face of a person to be tested (3) in a ROI range (2), the ratio between the face of the person to be tested (3) and the pre-stored recognition model is activated. For the action, if the comparison success rate is within an error range, the entrance is opened for the person to be tested (3). The face recognition method of the present invention mainly includes the following steps: Step 1 (S1): Use a The depth image capture unit (11) captures an image of an original face (A); in addition, the depth image capture unit (11) is a device such as a TOF camera or a dual-lens camera, and when the depth image capture When the acquisition unit (11) is a TOF camera, the depth image acquisition unit (1 1) It includes at least a light emitting module (111), a receiving module (112), and an image capturing module (113). The light emitting module (111) emits a plurality of light spots on the original face (A ), And the receiving module (112) receives a plurality of reflected light spots reflected by the original face (A) and transmits them to the image processing unit (12), and the image capturing module (113) includes a first An optical lens (1131) and a first photosensitive element (1132) connected to the first optical lens (1131), and the first optical lens (1131) captures an image of the original face (A) on the first photosensitive element (1132) imaging, where the first optical lens (1131) is a device such as a fisheye lens, a wide-angle lens, or a standard lens, and the first photosensitive element (1132) is a photocoupler (CCD) or complementary metal oxide Semiconductor device (CMOS) and other devices; in a preferred embodiment of the present invention, since face recognition must first establish a model for recognition, the present invention uses a depth image capture presented in the form of a TOF camera The fetching unit (11) captures a facial image of the subject (3), and this facial image is called The image of the original face (A) is mainly captured by the first optical lens (1131) built in the TOF camera and presented in the form of a fisheye lens. The image of the original face (A) is captured by a photoelectric coupling element (CCD). ) Form the image on the first photosensitive element (1132); Step 2 (S2): Use a selection module (121) built in an image processing unit (12) to select a plurality of images from the original face (A) First feature points (A1), and calculate the first distance value between the first feature point (A1) and the depth image capture unit (11) respectively; please refer to FIG. 2 and FIG. 3 together A schematic diagram of feature point selection of a preferred embodiment of the face recognition method of the present invention, wherein the image processing unit (12) is electrically connected to the deep image capture unit (11), and the built-in image processing unit (12) is selected. The module (121) is based on the first feature points (A1) of 11 positions including the facial features of the original face (A), and calculates the 11 first feature points (A1) and the depth image acquisition unit (11). The first distance value between the two, this first distance value is the depth value of the first feature point (A1); Step three (S3): use the built-in length meter of the image processing unit (12) The module (122) connects a pair of first feature points (A1) to obtain a plurality of first line segments (A2), and calculates the length of the first line segment (A2) to obtain a plurality of first length values (L1) , And calculate the first depth difference (De1) between the first length value (L1) of the first feature point (A1) connected by two by two; please refer to FIG. 2 and FIG. 4 together A schematic diagram of line segment connection of a preferred embodiment of the face recognition method of the present invention, wherein a length calculation module (122) built in the image processing unit (12) is used to convert the pair of first feature points (A1) to the first line segment. (A2) are connected to each other. The 11 first feature points (A1) are connected to each other to obtain 20 first line segments (A2), and the length calculation module (122) calculates the 20 first line segments ( The first length value (L1) of A2) is calculated based on the depth value of the first feature point (A1) connected to each other. This is the first depth difference; however, it must be noted that It is to be noted that the number of the first feature points (A1) and the number of the first line segments (A2) connecting the first feature points (A1) to each other are for convenience of description, and are not based on the present invention. Limited and cooked Knowing this artist should know the number of different first feature points (A1) and the number of first line segments (A2) connected to each other, as long as the face recognition system (1) can perform The calculation of the difference between the length of the first line segment (A2) and the first depth (De1) can be regarded as an extension of the technical features of the present invention, and will not image the actual implementation of the present invention. Step four (S4): An image of the original face (A) of the first feature point (A1), the first line segment (A2), the first length value (L1), and the first depth difference value is stored in a storage unit (13); In a preferred embodiment of the present invention, the storage unit (13) is electrically connected to the image processing unit (12), the original face (A) image obtained by the above steps, and the original face (A) included in the original face (A). The information of the first feature point (A1), the first line segment (A2), the first length value (L1), and the first depth difference are all stored in the storage unit (13), which can be used as the entrance and exit face Step 5 (S5): Repeat step 1 (S1) to step 3 (S3), use the depth image acquisition unit (11) to capture an image of the face (B) to be tested, And obtain a plurality of second feature points (B1) on the face (B) corresponding to the positions of the first feature points (A1), and a plurality of second line segments (B2) connected by the second feature points (B1) And the second length value (L2), and the plurality of second distance values and the second depth difference are stored in the storage unit (13); please refer to the face of the present invention shown in FIG. 2 and FIG. 5 together. Schematic diagram of facial recognition of a preferred embodiment of the facial recognition method. After the establishment of the original facial (A) image recognition model in steps 1 (S1) to 3 (S3), when the subject (3 ) When face recognition is required to enter and exit the entrance, the depth image capture unit (11) captures its face image, this face image is called the face to be tested (B) image; then, select the module (121) The five features of the face (B) to be tested are set to the second feature points (B1) at 11 positions corresponding to the first feature points (A1), and the 11 second feature points (B1) and The second distance value between the depth image capturing units (11), this second distance value is the depth value of the second feature point (B1); continued, the length calculation module (122) is about to pair the second feature points (B1) The second line segments (B2) are connected to each other. With the interconnection between 11 second feature points (B1), 20 second line segments (B2) can be obtained, and the length calculation module (122) calculates these 20 lines respectively. The second length value (L2) of the second line segment (B2); then, based on the depth values of the second feature points (B1) connected to each other, calculate the difference in depth between the two, which is the second depth difference Finally, an image of the face to be measured (B) having the second feature point (B1), the second line segment (B2), the second length value (L2), and the second depth difference is stored in the storage unit ( 13); step six (S6): using a comparison unit (14) to compare the first length value (L1) and the corresponding second length value (L2), and the first depth difference and the corresponding first Two depth differences; in a preferred embodiment of the present invention, the comparison unit (14) electrically connected to the image processing unit (12) performs a first length value (L1) and a corresponding second length value (L2) ), And the comparison action between the first depth difference and the corresponding second depth difference, please refer to FIG. 4 and FIG. 5 again, the first characteristic point of point C in FIG. 4 (A1) with point D The first length value (L1) of the first line segment (A2) connected between a feature point (A1) can be the same as the second feature point (B1) to point D of point C in FIG. 5 The second length value (L2) of the second line segment (B2) connected between the second feature points (B1) is compared with each other; and step 7 (S7): when the first length value (L1) and the corresponding second length When the difference between the values (L2) and the difference between the first depth difference and the corresponding second depth difference are within an error range, the face to be measured (B) is the original face (A) Same; in addition, the error range is between 98% and 100%; in a preferred embodiment of the present invention, when the comparison unit (14) compares the first length value (L1) with the corresponding second value The difference between the length value (L2) and the difference between the first depth difference and the corresponding second depth difference is between 98% and 100%, which means that the face to be measured (B) and the original face (A ) Are the same person's face, the face recognition is successful and the test subject (3) is allowed to enter and exit the entrance.

In addition, before the original face (A) image is stored in step four (S4), an area calculation module (123) built in the image processing unit (12) can be further used to calculate the area calculated by the three first line segments (A2). The first area value (Ae1) of the enclosed first triangle (T1), and the first area value (Ae1) combined with the first total area value; further, the area can be further used after step 6 (S6) is completed The calculation module (123) calculates a second area value (Ae2) of a second triangle (T2) surrounded by three second line segments (B2), and a second total area value summed up by the second area value (Ae2); In addition, the area calculation module (123) uses a Hailong formula to calculate the first area value (Ae1) and the second area value (Ae2); further, after step 7 (S7) is completed, a comparison unit ( 14) Compare the first total area value and the second total area value. If the difference between the first total area value and the second total area value is within the error range, the face to be measured (B) is the original face Part (A) is the same; please refer to Figure 4 and Figure 5 again. The first triangle (T1) surrounded by three first line segments (A2) is calculated by the Hailong formula. The first area value (Ae1), and the sum of the first area values (Ae1) of the ten first triangles (T1) formed by the 20 first line segments (A2) is the first total area value; the same, The second area value (Ae2) and the second total area value can also be calculated in the image of the face (B) to be measured, and then continue to compare the first total area value and the second total area value after step 7 (S7). If the error of the comparison is within the error range of 98% ~ 100%, it means that the face (B) to be tested is the same face as the original face (A) to allow the person (3) to enter and exit the entrance .

Furthermore, when the depth image capturing unit (11) is a dual-lens camera, the depth image capturing unit (11) includes two second optical lenses (not shown in the figure), and one and two optical lenses respectively. The connected second photosensitive element (not shown in the figure), the second optical lens simultaneously captures the image of the original face (A) or the face to be tested (B) for imaging on the second photosensitive element; a preferred implementation thereof In the same example, the dual-lens camera can also obtain the depth value of the first feature point (A1) and the second feature point (B1), and can also achieve the function of face recognition.

As can be seen from the above implementation description, compared with the prior art, the face recognition method of the present invention has the following advantages:

1. The face recognition method of the present invention is mainly designed by capturing a three-dimensional image of a user's face through a depth image capturing unit, and selecting an image processing unit to select a plurality of feature points and two or more feature points in the face image. The method of calculating and comparing the length and depth of the connecting line segments effectively completes the safe identification of facial image features, and can further combine the calculation and comparison of the triangle area surrounded by the three line segments, which indeed achieves a safer and more secure The main advantage of comprehensive face safety recognition.

2. The face recognition method of the present invention mainly uses a TOF camera to capture the depth difference between a plurality of feature points such as facial features and the feature points, as an important basis for face recognition, which can effectively solve the problem of interested people Disadvantages of two-dimensional face recognition systems are deceived by photos or floor plans with the same faces, and it does achieve the main advantages of a more secure and difficult-to-decipher system and method of face recognition.

3. The face recognition method of the present invention is mainly to compare the depth value of feature points on the face, the length of the connecting line, and the area of the triangle surrounded by the connecting line to increase the number of face recognition methods. Accuracy, indeed, achieves the main purpose of accurate identification and attention to safety considerations.

4. The face recognition method of the present invention mainly uses the depth image capture unit to capture the three-dimensional features of the human face, allowing the user to face the face image of the depth image capture unit at different angles when the face image is captured. The recognition system can accurately give the depth difference of the feature points of the face, which effectively solves the shortcomings of the traditional face recognition system due to the incorrect angle and the wrong judgment, and indeed achieves the major advantage of significantly reducing the time of face recognition.

In summary, the face recognition method of the present invention can indeed achieve the expected use effect through the embodiments disclosed above, and the present invention has not been disclosed before the application. It has fully complied with the provisions of the Patent Law and Claim. I filed an application for an invention patent in accordance with the law, and I urge you to examine it and grant the patent.

However, the illustrations and descriptions disclosed above are only preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Anyone who is familiar with the technology, according to the characteristic scope of the present invention, makes other Equivalent changes or modifications should be regarded as not departing from the design scope of the present invention.

Claims (16)

    A face recognition method is performed after a face recognition system detects a face of a test subject, and performs a face recognition action. The face recognition method includes the following steps: Step 1: Use a depth image The capture unit captures an image of an original face. Step 2: Use a selection module built into an image processing unit to select a plurality of first feature points in the image of the original face and calculate the first features separately. The first distance value between the point and the depth image capturing unit; step three: using the length calculation module built in the image processing unit to connect the two first feature points to obtain a plurality of first line segments, and Calculate the lengths of the first line segments to obtain a plurality of first length values, and calculate a first depth difference between the first distance values of the first feature points connected in pairs; Step 4: Images of the original face such as the first feature point, the first line segment, the first length value, and the first depth difference value are stored in a storage unit; Step 5: Repeat this step 1 to this step Third, use that deep The image capturing unit captures an image of a face to be measured, and obtains a plurality of second feature points corresponding to the positions of the first feature points on the face to be measured, and the plurality of second feature points are connected by the second feature points. The second line segment and the second length value, and the plurality of second distance values and the second depth difference are stored in the storage unit; Step 6: Use a comparison unit to compare the corresponding first length values with the corresponding ones. The second length value, the first depth difference value and the corresponding second depth value; and step 7: when the difference between the first length value and the corresponding second length value, and the first depth When the difference between the difference and the corresponding second depth difference is within an error range, the face to be measured is the same as the original face.         The face recognition method as described in the first item of the patent application scope, wherein the depth image capturing unit is one of a TOF camera or a dual-lens camera.         The face recognition method according to item 2 of the scope of patent application, wherein when the depth image capturing unit is a TOF camera, the depth image capturing unit includes at least a light emitting module, a receiving module, and a Image capture module.         The face recognition method according to item 3 of the scope of patent application, wherein the light emitting module emits a plurality of light spots on the original face or the face to be tested.         The face recognition method according to item 3 of the scope of patent application, wherein the receiving module receives a plurality of reflected light spots reflected by the original face or the face to be measured, and transmits them to the image processing unit.         The face recognition method according to item 3 of the scope of patent application, wherein the image capturing module includes a first optical lens, and a first photosensitive element connected to the first optical lens, the first optical lens The image of the original face or the face to be measured is captured on the first photosensitive element.         The face recognition method as described in item 6 of the patent application scope, wherein the first optical lens is one of a fisheye lens, a wide-angle lens, or a standard lens.         The facial recognition method as described in item 6 of the patent application scope, wherein the first photosensitive element is one of a photo-coupled element (CCD) or a complementary metal oxide semiconductor (CMOS).         The face recognition method according to item 2 of the scope of the patent application, wherein when the depth image capturing unit is a dual-lens camera, the depth image capturing unit includes two second optical lenses, and a second lens and a second lens respectively. The second optical lens is connected to a second photosensitive element. The second optical lens simultaneously captures an image of the original face or the face to be measured and forms an image on the second photosensitive element.         The facial recognition method according to item 9 of the scope of patent application, wherein the second optical lens is one of a fisheye lens, a wide-angle lens, or a standard lens.         The facial recognition method according to item 9 of the scope of the patent application, wherein the second photosensitive element is one of a photoelectric coupling element (CCD) or a complementary metal oxide semiconductor (CMOS).         The facial recognition method described in item 1 of the patent application range, wherein the error range is between 98% and 100%.         According to the facial recognition method described in item 1 of the scope of patent application, before the fourth step, an area calculation module built in the image processing unit is further used to calculate the third area surrounded by the three first line segments. The first area value of a triangle and the first total area value summed up by the first area values.         The facial recognition method according to item 13 of the scope of patent application, wherein after the step 6 is completed, the area calculation module is further used to calculate the second area value of the second triangle surrounded by the three line segments. And the second total area value summed up by the second area values.         The face recognition method according to item 13 or 14 of the scope of patent application, wherein the area calculation module calculates the first area value or the second area value using a sea dragon formula.         The face recognition method according to item 1 or 13 or 14 of the scope of patent application, wherein after the completion of step 7, the comparison unit is further used to compare the first total area value with the second total area value. When the difference between the first total area value and the second total area value is within the error range, the face to be measured is the same as the original face.